midgard/youtube-dl
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity
youtube-dl/youtube_dl/utils.py

6194 lines
182 KiB
Python
Raw Normal View History

Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
#!/usr/bin/env python
Unify coding cookie
2016-10-02 13:39:18 +02:00
# coding: utf-8
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
[utils] Modernize
2014-11-02 11:37:49 +01:00
from __future__ import unicode_literals
[letv] Fix extraction Using data URIs for passing the decrypted M3U8 manifest, which is supported by ffmpeg only.
2015-07-22 14:03:05 +02:00
import base64
[utils] Add OHDave's RSA encryption function
2016-02-16 23:01:44 +01:00
import binascii
[instagram] Fix info_dict key name
2014-03-24 01:40:09 +01:00
import calendar
Fix unicode_escape (Fixes #2695)
2014-04-04 23:00:51 +02:00
import codecs
[utils] Improve cookie files support + Add support for UTF-8 in cookie files * Skip malformed cookie file entries instead of crashing (invalid entry len, invalid expires at)
2020-05-04 23:19:33 +02:00
import collections
Ignore BOM in batch files (Fixes #2450)
2014-02-25 01:43:17 +01:00
import contextlib
Set process title to youtube-dl This allows killing all youtube-dl processes with killall youtube-dl, and shows up nicer in some programs.
2013-12-16 05:04:12 +01:00
import ctypes
Fix platform name in Python 2 with --verbose (Closes #1228)
2013-08-28 12:57:10 +02:00
import datetime
import email.utils
[cda] Implement birthday verification (closes #12789)
2017-05-01 17:09:18 +02:00
import email.header
Do not re-encode / to # if / is a platform separator, and correctly handle permission errors (Fixes #831)
2013-05-13 09:20:08 +02:00
import errno
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
import functools
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
import gzip
Use io.BytesIO instead of StringIO
2012-11-28 00:09:17 +01:00
import io
Instead of replacing accented characters with an underscore when sanitizing file names in restricted mode, replace them with their non-accented equivalents fixes #9347
2016-05-02 05:21:39 +02:00
import itertools
Correct JSON writing (Closes #596)
2012-12-20 13:13:24 +01:00
import json
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
import locale
[zdf/common] Use API in ZDF extractor. This also comes with a lot of extra format fields Fixes #1518
2013-11-25 03:12:26 +01:00
import math
[YoutubeDL] Add generic video filtering (Fixes #4916) This functionality is intended to eventually encompass the current format filtering.
2015-02-10 03:32:21 +01:00
import operator
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
import os
Fix platform name in Python 2 with --verbose (Closes #1228)
2013-08-28 12:57:10 +02:00
import platform
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
import random
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
import re
Fix platform name in Python 2 with --verbose (Closes #1228)
2013-08-28 12:57:10 +02:00
import socket
Instead of replacing accented characters with an underscore when sanitizing file names in restricted mode, replace them with their non-accented equivalents fixes #9347
2016-05-02 05:21:39 +02:00
import ssl
Improve --bidi-workaround support
2013-12-09 18:29:07 +01:00
import subprocess
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
import sys
[utils] Make JSON file writes atomic (Fixes #3549)
2014-08-21 13:01:13 +02:00
import tempfile
[utils] Improve cookie files support + Add support for UTF-8 in cookie files * Skip malformed cookie file entries instead of crashing (invalid entry len, invalid expires at)
2020-05-04 23:19:33 +02:00
import time
Make ExtractorError usable for other causes
2013-01-03 15:39:55 +01:00
import traceback
[utils] Sanitize look-alike Unicode glyphs in non-ID filename fields when --restrict-filenames Implements https://github.com/ytdl-org/youtube-dl/issues/31216#issuecomment-1236102822, which has a test.
2022-10-11 14:18:12 +02:00
import unicodedata
[generic] Suppress warning about doctypes in RSS parser
2014-03-10 17:31:32 +01:00
import xml.etree.ElementTree
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
import zlib
[util] Move compatibility functions out of util utils is large enough without these compatibility functions. Everything that is present in newer versions of Python (i.e. with dev Python it's just an import) goes into compat.py . Everything else (i.e. youtube-dl-specific helpers) goes into utils.py .
2014-11-02 11:23:40 +01:00
from .compat import (
[utils] Handle HTMLParseError in extract_attributes (closes #13349)
2017-06-11 20:52:24 +02:00
compat_HTMLParseError,
[utils] Add extract_attributes for extracting html tag attributes This is much more robust than just using regexps, and handles all the common scenarios, such as empty/no values, repeated attributes, entity decoding, mixed case names, and the different possible value quoting schemes.
2016-01-02 20:49:59 +01:00
compat_HTMLParser,
[utils] Add support for support for experimental HTTP response status code 308 Permanent Redirect (refs #27877, refs #28768)
2021-04-16 22:22:13 +02:00
compat_HTTPError,
Appease pyflakes8-3
2015-02-01 11:30:56 +01:00
compat_basestring,
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
compat_casefold,
[util] Move compatibility functions out of util utils is large enough without these compatibility functions. Everything that is present in newer versions of Python (i.e. with dev Python it's just an import) goes into compat.py . Everything else (i.e. youtube-dl-specific helpers) goes into utils.py .
2014-11-02 11:23:40 +01:00
compat_chr,
[utils] Backport traverse_obj (etc) from yt-dlp (#31156) * Backport traverse_obj and closely related function from yt-dlp (code by pukkandan) * Backport LazyList, variadic(), try_call (code by pukkandan) * Recast using yt-dlp's newer traverse_obj() implementation and tests (code by grub4k) * Add tests for Unicode case folding support matching Py3.5+ (requires f102e3d) * Improve/add tests for variadic, try_call, join_nonempty Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-11-03 11:09:37 +01:00
compat_collections_abc,
[YoutubeDL] Introduce YoutubeDLCookieJar and clarify the rationale behind session cookies (closes #12929)
2018-12-09 00:00:32 +01:00
compat_cookiejar,
[utils] Fix youtube-dl under PyPy3 on Windows
2014-12-12 04:01:08 +01:00
compat_ctypes_WINFUNCTYPE,
Use a wrapper around xml.etree.ElementTree.fromstring in python 2.x (#7178) Attributes aren't unicode objects, so they couldn't be directly used in info_dict fields (for example '--write-description' doesn't work with bytes).
2015-10-25 20:04:55 +01:00
compat_etree_fromstring,
[utils] Introduce expand_path
2017-03-25 20:30:10 +01:00
compat_expanduser,
[util] Move compatibility functions out of util utils is large enough without these compatibility functions. Everything that is present in newer versions of Python (i.e. with dev Python it's just an import) goes into compat.py . Everything else (i.e. youtube-dl-specific helpers) goes into utils.py .
2014-11-02 11:23:40 +01:00
compat_html_entities,
[utils] Decode HTML5 entities Used in test_Vporn_1. Also related to #9270
2016-06-10 09:11:55 +02:00
compat_html_entities_html5,
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
compat_http_client,
[utils] Improve str_to_int
2019-12-15 17:15:24 +01:00
compat_integer_types,
[utils] Fix another old python 2.6 kwargs issue (Closes #5539)
2015-04-27 16:00:18 +02:00
compat_kwargs,
Move write_xattr to utils.py There are some other places that use xattr functions. It's better to move it to a common place so that others can use it.
2016-09-29 18:28:32 +02:00
compat_os_name,
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
compat_re_Match,
[compat] Rename shlex_quote and remove unused subprocess_check_output
2016-05-10 09:58:25 +02:00
compat_shlex_quote,
[util] Move compatibility functions out of util utils is large enough without these compatibility functions. Everything that is present in newer versions of Python (i.e. with dev Python it's just an import) goes into compat.py . Everything else (i.e. youtube-dl-specific helpers) goes into utils.py .
2014-11-02 11:23:40 +01:00
compat_str,
[compat] Rename struct_(un)pack to compat_struct_(un)pack
2016-05-03 10:50:16 +02:00
compat_struct_pack,
[utils] Add decode_png for openload (#9706)
2016-08-06 20:42:58 +02:00
compat_struct_unpack,
[util] Move compatibility functions out of util utils is large enough without these compatibility functions. Everything that is present in newer versions of Python (i.e. with dev Python it's just an import) goes into compat.py . Everything else (i.e. youtube-dl-specific helpers) goes into utils.py .
2014-11-02 11:23:40 +01:00
compat_urllib_error,
compat_urllib_parse,
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
compat_urllib_parse_parse_qs as compat_parse_qs,
[compat] Add compat_urllib_parse_urlencode and eliminate encode_dict encode_dict functionality has been improved and moved directly into compat_urllib_parse_urlencode All occurrences of compat_urllib_parse.urlencode throughout the codebase have been replaced by compat_urllib_parse_urlencode Closes #8974
2016-03-25 20:46:57 +01:00
compat_urllib_parse_urlencode,
[util] Move compatibility functions out of util utils is large enough without these compatibility functions. Everything that is present in newer versions of Python (i.e. with dev Python it's just an import) goes into compat.py . Everything else (i.e. youtube-dl-specific helpers) goes into utils.py .
2014-11-02 11:23:40 +01:00
compat_urllib_parse_urlparse,
[utils] Unquote crendentials passed to SOCKS proxies Fixes #9450
2016-05-12 12:57:53 +02:00
compat_urllib_parse_unquote_plus,
[util] Move compatibility functions out of util utils is large enough without these compatibility functions. Everything that is present in newer versions of Python (i.e. with dev Python it's just an import) goes into compat.py . Everything else (i.e. youtube-dl-specific helpers) goes into utils.py .
2014-11-02 11:23:40 +01:00
compat_urllib_request,
[utils] Use compat_xpath
2016-03-17 21:52:23 +01:00
compat_xpath,
[util] Move compatibility functions out of util utils is large enough without these compatibility functions. Everything that is present in newer versions of Python (i.e. with dev Python it's just an import) goes into compat.py . Everything else (i.e. youtube-dl-specific helpers) goes into utils.py .
2014-11-02 11:23:40 +01:00
)
[core] Decode environment variables with filesystem encoding (Fixes #3854, Fixes #3217, Fixes #2918) Introduces compat versions of os.getenv and os.path.expanduser
2014-09-30 17:27:53 +02:00
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
from .socks import (
ProxyType,
sockssocket,
)
[core] Decode environment variables with filesystem encoding (Fixes #3854, Fixes #3217, Fixes #2918) Introduces compat versions of os.getenv and os.path.expanduser
2014-09-30 17:27:53 +02:00
[utils] Register SOCKS protocols in urllib and support SOCKS4A
2016-05-03 09:15:32 +02:00
def register_socks_protocols():
# "Register" SOCKS protocols
[utils] Add rationale for register_socks_protocols
2016-05-03 09:37:30 +02:00
# In Python < 2.6.5, urlsplit() suffers from bug https://bugs.python.org/issue7904
# URLs with protocols not in urlparse.uses_netloc are not handled correctly
[utils] Register SOCKS protocols in urllib and support SOCKS4A
2016-05-03 09:15:32 +02:00
for scheme in ('socks', 'socks4', 'socks4a', 'socks5'):
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
if scheme not in compat_urllib_parse.uses_netloc:
compat_urllib_parse.uses_netloc.append(scheme)
[utils] Register SOCKS protocols in urllib and support SOCKS4A
2016-05-03 09:15:32 +02:00
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
# Unfavoured alias
compiled_regex_type = compat_re_Match
implement fallbacks and defaults in _search_regex
2013-06-06 14:35:08 +02:00
[utils] Introduce random_user_agent and use as default User-Agent (closes #21546)
2019-06-28 19:32:43 +02:00
def random_user_agent():
_USER_AGENT_TPL = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/%s Safari/537.36'
_CHROME_VERSIONS = (
'74.0.3729.129',
'76.0.3780.3',
'76.0.3780.2',
'74.0.3729.128',
'76.0.3780.1',
'76.0.3780.0',
'75.0.3770.15',
'74.0.3729.127',
'74.0.3729.126',
'76.0.3779.1',
'76.0.3779.0',
'75.0.3770.14',
'74.0.3729.125',
'76.0.3778.1',
'76.0.3778.0',
'75.0.3770.13',
'74.0.3729.124',
'74.0.3729.123',
'73.0.3683.121',
'76.0.3777.1',
'76.0.3777.0',
'75.0.3770.12',
'74.0.3729.122',
'76.0.3776.4',
'75.0.3770.11',
'74.0.3729.121',
'76.0.3776.3',
'76.0.3776.2',
'73.0.3683.120',
'74.0.3729.120',
'74.0.3729.119',
'74.0.3729.118',
'76.0.3776.1',
'76.0.3776.0',
'76.0.3775.5',
'75.0.3770.10',
'74.0.3729.117',
'76.0.3775.4',
'76.0.3775.3',
'74.0.3729.116',
'75.0.3770.9',
'76.0.3775.2',
'76.0.3775.1',
'76.0.3775.0',
'75.0.3770.8',
'74.0.3729.115',
'74.0.3729.114',
'76.0.3774.1',
'76.0.3774.0',
'75.0.3770.7',
'74.0.3729.113',
'74.0.3729.112',
'74.0.3729.111',
'76.0.3773.1',
'76.0.3773.0',
'75.0.3770.6',
'74.0.3729.110',
'74.0.3729.109',
'76.0.3772.1',
'76.0.3772.0',
'75.0.3770.5',
'74.0.3729.108',
'74.0.3729.107',
'76.0.3771.1',
'76.0.3771.0',
'75.0.3770.4',
'74.0.3729.106',
'74.0.3729.105',
'75.0.3770.3',
'74.0.3729.104',
'74.0.3729.103',
'74.0.3729.102',
'75.0.3770.2',
'74.0.3729.101',
'75.0.3770.1',
'75.0.3770.0',
'74.0.3729.100',
'75.0.3769.5',
'75.0.3769.4',
'74.0.3729.99',
'75.0.3769.3',
'75.0.3769.2',
'75.0.3768.6',
'74.0.3729.98',
'75.0.3769.1',
'75.0.3769.0',
'74.0.3729.97',
'73.0.3683.119',
'73.0.3683.118',
'74.0.3729.96',
'75.0.3768.5',
'75.0.3768.4',
'75.0.3768.3',
'75.0.3768.2',
'74.0.3729.95',
'74.0.3729.94',
'75.0.3768.1',
'75.0.3768.0',
'74.0.3729.93',
'74.0.3729.92',
'73.0.3683.117',
'74.0.3729.91',
'75.0.3766.3',
'74.0.3729.90',
'75.0.3767.2',
'75.0.3767.1',
'75.0.3767.0',
'74.0.3729.89',
'73.0.3683.116',
'75.0.3766.2',
'74.0.3729.88',
'75.0.3766.1',
'75.0.3766.0',
'74.0.3729.87',
'73.0.3683.115',
'74.0.3729.86',
'75.0.3765.1',
'75.0.3765.0',
'74.0.3729.85',
'73.0.3683.114',
'74.0.3729.84',
'75.0.3764.1',
'75.0.3764.0',
'74.0.3729.83',
'73.0.3683.113',
'75.0.3763.2',
'75.0.3761.4',
'74.0.3729.82',
'75.0.3763.1',
'75.0.3763.0',
'74.0.3729.81',
'73.0.3683.112',
'75.0.3762.1',
'75.0.3762.0',
'74.0.3729.80',
'75.0.3761.3',
'74.0.3729.79',
'73.0.3683.111',
'75.0.3761.2',
'74.0.3729.78',
'74.0.3729.77',
'75.0.3761.1',
'75.0.3761.0',
'73.0.3683.110',
'74.0.3729.76',
'74.0.3729.75',
'75.0.3760.0',
'74.0.3729.74',
'75.0.3759.8',
'75.0.3759.7',
'75.0.3759.6',
'74.0.3729.73',
'75.0.3759.5',
'74.0.3729.72',
'73.0.3683.109',
'75.0.3759.4',
'75.0.3759.3',
'74.0.3729.71',
'75.0.3759.2',
'74.0.3729.70',
'73.0.3683.108',
'74.0.3729.69',
'75.0.3759.1',
'75.0.3759.0',
'74.0.3729.68',
'73.0.3683.107',
'74.0.3729.67',
'75.0.3758.1',
'75.0.3758.0',
'74.0.3729.66',
'73.0.3683.106',
'74.0.3729.65',
'75.0.3757.1',
'75.0.3757.0',
'74.0.3729.64',
'73.0.3683.105',
'74.0.3729.63',
'75.0.3756.1',
'75.0.3756.0',
'74.0.3729.62',
'73.0.3683.104',
'75.0.3755.3',
'75.0.3755.2',
'73.0.3683.103',
'75.0.3755.1',
'75.0.3755.0',
'74.0.3729.61',
'73.0.3683.102',
'74.0.3729.60',
'75.0.3754.2',
'74.0.3729.59',
'75.0.3753.4',
'74.0.3729.58',
'75.0.3754.1',
'75.0.3754.0',
'74.0.3729.57',
'73.0.3683.101',
'75.0.3753.3',
'75.0.3752.2',
'75.0.3753.2',
'74.0.3729.56',
'75.0.3753.1',
'75.0.3753.0',
'74.0.3729.55',
'73.0.3683.100',
'74.0.3729.54',
'75.0.3752.1',
'75.0.3752.0',
'74.0.3729.53',
'73.0.3683.99',
'74.0.3729.52',
'75.0.3751.1',
'75.0.3751.0',
'74.0.3729.51',
'73.0.3683.98',
'74.0.3729.50',
'75.0.3750.0',
'74.0.3729.49',
'74.0.3729.48',
'74.0.3729.47',
'75.0.3749.3',
'74.0.3729.46',
'73.0.3683.97',
'75.0.3749.2',
'74.0.3729.45',
'75.0.3749.1',
'75.0.3749.0',
'74.0.3729.44',
'73.0.3683.96',
'74.0.3729.43',
'74.0.3729.42',
'75.0.3748.1',
'75.0.3748.0',
'74.0.3729.41',
'75.0.3747.1',
'73.0.3683.95',
'75.0.3746.4',
'74.0.3729.40',
'74.0.3729.39',
'75.0.3747.0',
'75.0.3746.3',
'75.0.3746.2',
'74.0.3729.38',
'75.0.3746.1',
'75.0.3746.0',
'74.0.3729.37',
'73.0.3683.94',
'75.0.3745.5',
'75.0.3745.4',
'75.0.3745.3',
'75.0.3745.2',
'74.0.3729.36',
'75.0.3745.1',
'75.0.3745.0',
'75.0.3744.2',
'74.0.3729.35',
'73.0.3683.93',
'74.0.3729.34',
'75.0.3744.1',
'75.0.3744.0',
'74.0.3729.33',
'73.0.3683.92',
'74.0.3729.32',
'74.0.3729.31',
'73.0.3683.91',
'75.0.3741.2',
'75.0.3740.5',
'74.0.3729.30',
'75.0.3741.1',
'75.0.3741.0',
'74.0.3729.29',
'75.0.3740.4',
'73.0.3683.90',
'74.0.3729.28',
'75.0.3740.3',
'73.0.3683.89',
'75.0.3740.2',
'74.0.3729.27',
'75.0.3740.1',
'75.0.3740.0',
'74.0.3729.26',
'73.0.3683.88',
'73.0.3683.87',
'74.0.3729.25',
'75.0.3739.1',
'75.0.3739.0',
'73.0.3683.86',
'74.0.3729.24',
'73.0.3683.85',
'75.0.3738.4',
'75.0.3738.3',
'75.0.3738.2',
'75.0.3738.1',
'75.0.3738.0',
'74.0.3729.23',
'73.0.3683.84',
'74.0.3729.22',
'74.0.3729.21',
'75.0.3737.1',
'75.0.3737.0',
'74.0.3729.20',
'73.0.3683.83',
'74.0.3729.19',
'75.0.3736.1',
'75.0.3736.0',
'74.0.3729.18',
'73.0.3683.82',
'74.0.3729.17',
'75.0.3735.1',
'75.0.3735.0',
'74.0.3729.16',
'73.0.3683.81',
'75.0.3734.1',
'75.0.3734.0',
'74.0.3729.15',
'73.0.3683.80',
'74.0.3729.14',
'75.0.3733.1',
'75.0.3733.0',
'75.0.3732.1',
'74.0.3729.13',
'74.0.3729.12',
'73.0.3683.79',
'74.0.3729.11',
'75.0.3732.0',
'74.0.3729.10',
'73.0.3683.78',
'74.0.3729.9',
'74.0.3729.8',
'74.0.3729.7',
'75.0.3731.3',
'75.0.3731.2',
'75.0.3731.0',
'74.0.3729.6',
'73.0.3683.77',
'73.0.3683.76',
'75.0.3730.5',
'75.0.3730.4',
'73.0.3683.75',
'74.0.3729.5',
'73.0.3683.74',
'75.0.3730.3',
'75.0.3730.2',
'74.0.3729.4',
'73.0.3683.73',
'73.0.3683.72',
'75.0.3730.1',
'75.0.3730.0',
'74.0.3729.3',
'73.0.3683.71',
'74.0.3729.2',
'73.0.3683.70',
'74.0.3729.1',
'74.0.3729.0',
'74.0.3726.4',
'73.0.3683.69',
'74.0.3726.3',
'74.0.3728.0',
'74.0.3726.2',
'73.0.3683.68',
'74.0.3726.1',
'74.0.3726.0',
'74.0.3725.4',
'73.0.3683.67',
'73.0.3683.66',
'74.0.3725.3',
'74.0.3725.2',
'74.0.3725.1',
'74.0.3724.8',
'74.0.3725.0',
'73.0.3683.65',
'74.0.3724.7',
'74.0.3724.6',
'74.0.3724.5',
'74.0.3724.4',
'74.0.3724.3',
'74.0.3724.2',
'74.0.3724.1',
'74.0.3724.0',
'73.0.3683.64',
'74.0.3723.1',
'74.0.3723.0',
'73.0.3683.63',
'74.0.3722.1',
'74.0.3722.0',
'73.0.3683.62',
'74.0.3718.9',
'74.0.3702.3',
'74.0.3721.3',
'74.0.3721.2',
'74.0.3721.1',
'74.0.3721.0',
'74.0.3720.6',
'73.0.3683.61',
'72.0.3626.122',
'73.0.3683.60',
'74.0.3720.5',
'72.0.3626.121',
'74.0.3718.8',
'74.0.3720.4',
'74.0.3720.3',
'74.0.3718.7',
'74.0.3720.2',
'74.0.3720.1',
'74.0.3720.0',
'74.0.3718.6',
'74.0.3719.5',
'73.0.3683.59',
'74.0.3718.5',
'74.0.3718.4',
'74.0.3719.4',
'74.0.3719.3',
'74.0.3719.2',
'74.0.3719.1',
'73.0.3683.58',
'74.0.3719.0',
'73.0.3683.57',
'73.0.3683.56',
'74.0.3718.3',
'73.0.3683.55',
'74.0.3718.2',
'74.0.3718.1',
'74.0.3718.0',
'73.0.3683.54',
'74.0.3717.2',
'73.0.3683.53',
'74.0.3717.1',
'74.0.3717.0',
'73.0.3683.52',
'74.0.3716.1',
'74.0.3716.0',
'73.0.3683.51',
'74.0.3715.1',
'74.0.3715.0',
'73.0.3683.50',
'74.0.3711.2',
'74.0.3714.2',
'74.0.3713.3',
'74.0.3714.1',
'74.0.3714.0',
'73.0.3683.49',
'74.0.3713.1',
'74.0.3713.0',
'72.0.3626.120',
'73.0.3683.48',
'74.0.3712.2',
'74.0.3712.1',
'74.0.3712.0',
'73.0.3683.47',
'72.0.3626.119',
'73.0.3683.46',
'74.0.3710.2',
'72.0.3626.118',
'74.0.3711.1',
'74.0.3711.0',
'73.0.3683.45',
'72.0.3626.117',
'74.0.3710.1',
'74.0.3710.0',
'73.0.3683.44',
'72.0.3626.116',
'74.0.3709.1',
'74.0.3709.0',
'74.0.3704.9',
'73.0.3683.43',
'72.0.3626.115',
'74.0.3704.8',
'74.0.3704.7',
'74.0.3708.0',
'74.0.3706.7',
'74.0.3704.6',
'73.0.3683.42',
'72.0.3626.114',
'74.0.3706.6',
'72.0.3626.113',
'74.0.3704.5',
'74.0.3706.5',
'74.0.3706.4',
'74.0.3706.3',
'74.0.3706.2',
'74.0.3706.1',
'74.0.3706.0',
'73.0.3683.41',
'72.0.3626.112',
'74.0.3705.1',
'74.0.3705.0',
'73.0.3683.40',
'72.0.3626.111',
'73.0.3683.39',
'74.0.3704.4',
'73.0.3683.38',
'74.0.3704.3',
'74.0.3704.2',
'74.0.3704.1',
'74.0.3704.0',
'73.0.3683.37',
'72.0.3626.110',
'72.0.3626.109',
'74.0.3703.3',
'74.0.3703.2',
'73.0.3683.36',
'74.0.3703.1',
'74.0.3703.0',
'73.0.3683.35',
'72.0.3626.108',
'74.0.3702.2',
'74.0.3699.3',
'74.0.3702.1',
'74.0.3702.0',
'73.0.3683.34',
'72.0.3626.107',
'73.0.3683.33',
'74.0.3701.1',
'74.0.3701.0',
'73.0.3683.32',
'73.0.3683.31',
'72.0.3626.105',
'74.0.3700.1',
'74.0.3700.0',
'73.0.3683.29',
'72.0.3626.103',
'74.0.3699.2',
'74.0.3699.1',
'74.0.3699.0',
'73.0.3683.28',
'72.0.3626.102',
'73.0.3683.27',
'73.0.3683.26',
'74.0.3698.0',
'74.0.3696.2',
'72.0.3626.101',
'73.0.3683.25',
'74.0.3696.1',
'74.0.3696.0',
'74.0.3694.8',
'72.0.3626.100',
'74.0.3694.7',
'74.0.3694.6',
'74.0.3694.5',
'74.0.3694.4',
'72.0.3626.99',
'72.0.3626.98',
'74.0.3694.3',
'73.0.3683.24',
'72.0.3626.97',
'72.0.3626.96',
'72.0.3626.95',
'73.0.3683.23',
'72.0.3626.94',
'73.0.3683.22',
'73.0.3683.21',
'72.0.3626.93',
'74.0.3694.2',
'72.0.3626.92',
'74.0.3694.1',
'74.0.3694.0',
'74.0.3693.6',
'73.0.3683.20',
'72.0.3626.91',
'74.0.3693.5',
'74.0.3693.4',
'74.0.3693.3',
'74.0.3693.2',
'73.0.3683.19',
'74.0.3693.1',
'74.0.3693.0',
'73.0.3683.18',
'72.0.3626.90',
'74.0.3692.1',
'74.0.3692.0',
'73.0.3683.17',
'72.0.3626.89',
'74.0.3687.3',
'74.0.3691.1',
'74.0.3691.0',
'73.0.3683.16',
'72.0.3626.88',
'72.0.3626.87',
'73.0.3683.15',
'74.0.3690.1',
'74.0.3690.0',
'73.0.3683.14',
'72.0.3626.86',
'73.0.3683.13',
'73.0.3683.12',
'74.0.3689.1',
'74.0.3689.0',
'73.0.3683.11',
'72.0.3626.85',
'73.0.3683.10',
'72.0.3626.84',
'73.0.3683.9',
'74.0.3688.1',
'74.0.3688.0',
'73.0.3683.8',
'72.0.3626.83',
'74.0.3687.2',
'74.0.3687.1',
'74.0.3687.0',
'73.0.3683.7',
'72.0.3626.82',
'74.0.3686.4',
'72.0.3626.81',
'74.0.3686.3',
'74.0.3686.2',
'74.0.3686.1',
'74.0.3686.0',
'73.0.3683.6',
'72.0.3626.80',
'74.0.3685.1',
'74.0.3685.0',
'73.0.3683.5',
'72.0.3626.79',
'74.0.3684.1',
'74.0.3684.0',
'73.0.3683.4',
'72.0.3626.78',
'72.0.3626.77',
'73.0.3683.3',
'73.0.3683.2',
'72.0.3626.76',
'73.0.3683.1',
'73.0.3683.0',
'72.0.3626.75',
'71.0.3578.141',
'73.0.3682.1',
'73.0.3682.0',
'72.0.3626.74',
'71.0.3578.140',
'73.0.3681.4',
'73.0.3681.3',
'73.0.3681.2',
'73.0.3681.1',
'73.0.3681.0',
'72.0.3626.73',
'71.0.3578.139',
'72.0.3626.72',
'72.0.3626.71',
'73.0.3680.1',
'73.0.3680.0',
'72.0.3626.70',
'71.0.3578.138',
'73.0.3678.2',
'73.0.3679.1',
'73.0.3679.0',
'72.0.3626.69',
'71.0.3578.137',
'73.0.3678.1',
'73.0.3678.0',
'71.0.3578.136',
'73.0.3677.1',
'73.0.3677.0',
'72.0.3626.68',
'72.0.3626.67',
'71.0.3578.135',
'73.0.3676.1',
'73.0.3676.0',
'73.0.3674.2',
'72.0.3626.66',
'71.0.3578.134',
'73.0.3674.1',
'73.0.3674.0',
'72.0.3626.65',
'71.0.3578.133',
'73.0.3673.2',
'73.0.3673.1',
'73.0.3673.0',
'72.0.3626.64',
'71.0.3578.132',
'72.0.3626.63',
'72.0.3626.62',
'72.0.3626.61',
'72.0.3626.60',
'73.0.3672.1',
'73.0.3672.0',
'72.0.3626.59',
'71.0.3578.131',
'73.0.3671.3',
'73.0.3671.2',
'73.0.3671.1',
'73.0.3671.0',
'72.0.3626.58',
'71.0.3578.130',
'73.0.3670.1',
'73.0.3670.0',
'72.0.3626.57',
'71.0.3578.129',
'73.0.3669.1',
'73.0.3669.0',
'72.0.3626.56',
'71.0.3578.128',
'73.0.3668.2',
'73.0.3668.1',
'73.0.3668.0',
'72.0.3626.55',
'71.0.3578.127',
'73.0.3667.2',
'73.0.3667.1',
'73.0.3667.0',
'72.0.3626.54',
'71.0.3578.126',
'73.0.3666.1',
'73.0.3666.0',
'72.0.3626.53',
'71.0.3578.125',
'73.0.3665.4',
'73.0.3665.3',
'72.0.3626.52',
'73.0.3665.2',
'73.0.3664.4',
'73.0.3665.1',
'73.0.3665.0',
'72.0.3626.51',
'71.0.3578.124',
'72.0.3626.50',
'73.0.3664.3',
'73.0.3664.2',
'73.0.3664.1',
'73.0.3664.0',
'73.0.3663.2',
'72.0.3626.49',
'71.0.3578.123',
'73.0.3663.1',
'73.0.3663.0',
'72.0.3626.48',
'71.0.3578.122',
'73.0.3662.1',
'73.0.3662.0',
'72.0.3626.47',
'71.0.3578.121',
'73.0.3661.1',
'72.0.3626.46',
'73.0.3661.0',
'72.0.3626.45',
'71.0.3578.120',
'73.0.3660.2',
'73.0.3660.1',
'73.0.3660.0',
'72.0.3626.44',
'71.0.3578.119',
'73.0.3659.1',
'73.0.3659.0',
'72.0.3626.43',
'71.0.3578.118',
'73.0.3658.1',
'73.0.3658.0',
'72.0.3626.42',
'71.0.3578.117',
'73.0.3657.1',
'73.0.3657.0',
'72.0.3626.41',
'71.0.3578.116',
'73.0.3656.1',
'73.0.3656.0',
'72.0.3626.40',
'71.0.3578.115',
'73.0.3655.1',
'73.0.3655.0',
'72.0.3626.39',
'71.0.3578.114',
'73.0.3654.1',
'73.0.3654.0',
'72.0.3626.38',
'71.0.3578.113',
'73.0.3653.1',
'73.0.3653.0',
'72.0.3626.37',
'71.0.3578.112',
'73.0.3652.1',
'73.0.3652.0',
'72.0.3626.36',
'71.0.3578.111',
'73.0.3651.1',
'73.0.3651.0',
'72.0.3626.35',
'71.0.3578.110',
'73.0.3650.1',
'73.0.3650.0',
'72.0.3626.34',
'71.0.3578.109',
'73.0.3649.1',
'73.0.3649.0',
'72.0.3626.33',
'71.0.3578.108',
'73.0.3648.2',
'73.0.3648.1',
'73.0.3648.0',
'72.0.3626.32',
'71.0.3578.107',
'73.0.3647.2',
'73.0.3647.1',
'73.0.3647.0',
'72.0.3626.31',
'71.0.3578.106',
'73.0.3635.3',
'73.0.3646.2',
'73.0.3646.1',
'73.0.3646.0',
'72.0.3626.30',
'71.0.3578.105',
'72.0.3626.29',
'73.0.3645.2',
'73.0.3645.1',
'73.0.3645.0',
'72.0.3626.28',
'71.0.3578.104',
'72.0.3626.27',
'72.0.3626.26',
'72.0.3626.25',
'72.0.3626.24',
'73.0.3644.0',
'73.0.3643.2',
'72.0.3626.23',
'71.0.3578.103',
'73.0.3643.1',
'73.0.3643.0',
'72.0.3626.22',
'71.0.3578.102',
'73.0.3642.1',
'73.0.3642.0',
'72.0.3626.21',
'71.0.3578.101',
'73.0.3641.1',
'73.0.3641.0',
'72.0.3626.20',
'71.0.3578.100',
'72.0.3626.19',
'73.0.3640.1',
'73.0.3640.0',
'72.0.3626.18',
'73.0.3639.1',
'71.0.3578.99',
'73.0.3639.0',
'72.0.3626.17',
'73.0.3638.2',
'72.0.3626.16',
'73.0.3638.1',
'73.0.3638.0',
'72.0.3626.15',
'71.0.3578.98',
'73.0.3635.2',
'71.0.3578.97',
'73.0.3637.1',
'73.0.3637.0',
'72.0.3626.14',
'71.0.3578.96',
'71.0.3578.95',
'72.0.3626.13',
'71.0.3578.94',
'73.0.3636.2',
'71.0.3578.93',
'73.0.3636.1',
'73.0.3636.0',
'72.0.3626.12',
'71.0.3578.92',
'73.0.3635.1',
'73.0.3635.0',
'72.0.3626.11',
'71.0.3578.91',
'73.0.3634.2',
'73.0.3634.1',
'73.0.3634.0',
'72.0.3626.10',
'71.0.3578.90',
'71.0.3578.89',
'73.0.3633.2',
'73.0.3633.1',
'73.0.3633.0',
'72.0.3610.4',
'72.0.3626.9',
'71.0.3578.88',
'73.0.3632.5',
'73.0.3632.4',
'73.0.3632.3',
'73.0.3632.2',
'73.0.3632.1',
'73.0.3632.0',
'72.0.3626.8',
'71.0.3578.87',
'73.0.3631.2',
'73.0.3631.1',
'73.0.3631.0',
'72.0.3626.7',
'71.0.3578.86',
'72.0.3626.6',
'73.0.3630.1',
'73.0.3630.0',
'72.0.3626.5',
'71.0.3578.85',
'72.0.3626.4',
'73.0.3628.3',
'73.0.3628.2',
'73.0.3629.1',
'73.0.3629.0',
'72.0.3626.3',
'71.0.3578.84',
'73.0.3628.1',
'73.0.3628.0',
'71.0.3578.83',
'73.0.3627.1',
'73.0.3627.0',
'72.0.3626.2',
'71.0.3578.82',
'71.0.3578.81',
'71.0.3578.80',
'72.0.3626.1',
'72.0.3626.0',
'71.0.3578.79',
'70.0.3538.124',
'71.0.3578.78',
'72.0.3623.4',
'72.0.3625.2',
'72.0.3625.1',
'72.0.3625.0',
'71.0.3578.77',
'70.0.3538.123',
'72.0.3624.4',
'72.0.3624.3',
'72.0.3624.2',
'71.0.3578.76',
'72.0.3624.1',
'72.0.3624.0',
'72.0.3623.3',
'71.0.3578.75',
'70.0.3538.122',
'71.0.3578.74',
'72.0.3623.2',
'72.0.3610.3',
'72.0.3623.1',
'72.0.3623.0',
'72.0.3622.3',
'72.0.3622.2',
'71.0.3578.73',
'70.0.3538.121',
'72.0.3622.1',
'72.0.3622.0',
'71.0.3578.72',
'70.0.3538.120',
'72.0.3621.1',
'72.0.3621.0',
'71.0.3578.71',
'70.0.3538.119',
'72.0.3620.1',
'72.0.3620.0',
'71.0.3578.70',
'70.0.3538.118',
'71.0.3578.69',
'72.0.3619.1',
'72.0.3619.0',
'71.0.3578.68',
'70.0.3538.117',
'71.0.3578.67',
'72.0.3618.1',
'72.0.3618.0',
'71.0.3578.66',
'70.0.3538.116',
'72.0.3617.1',
'72.0.3617.0',
'71.0.3578.65',
'70.0.3538.115',
'72.0.3602.3',
'71.0.3578.64',
'72.0.3616.1',
'72.0.3616.0',
'71.0.3578.63',
'70.0.3538.114',
'71.0.3578.62',
'72.0.3615.1',
'72.0.3615.0',
'71.0.3578.61',
'70.0.3538.113',
'72.0.3614.1',
'72.0.3614.0',
'71.0.3578.60',
'70.0.3538.112',
'72.0.3613.1',
'72.0.3613.0',
'71.0.3578.59',
'70.0.3538.111',
'72.0.3612.2',
'72.0.3612.1',
'72.0.3612.0',
'70.0.3538.110',
'71.0.3578.58',
'70.0.3538.109',
'72.0.3611.2',
'72.0.3611.1',
'72.0.3611.0',
'71.0.3578.57',
'70.0.3538.108',
'72.0.3610.2',
'71.0.3578.56',
'71.0.3578.55',
'72.0.3610.1',
'72.0.3610.0',
'71.0.3578.54',
'70.0.3538.107',
'71.0.3578.53',
'72.0.3609.3',
'71.0.3578.52',
'72.0.3609.2',
'71.0.3578.51',
'72.0.3608.5',
'72.0.3609.1',
'72.0.3609.0',
'71.0.3578.50',
'70.0.3538.106',
'72.0.3608.4',
'72.0.3608.3',
'72.0.3608.2',
'71.0.3578.49',
'72.0.3608.1',
'72.0.3608.0',
'70.0.3538.105',
'71.0.3578.48',
'72.0.3607.1',
'72.0.3607.0',
'71.0.3578.47',
'70.0.3538.104',
'72.0.3606.2',
'72.0.3606.1',
'72.0.3606.0',
'71.0.3578.46',
'70.0.3538.103',
'70.0.3538.102',
'72.0.3605.3',
'72.0.3605.2',
'72.0.3605.1',
'72.0.3605.0',
'71.0.3578.45',
'70.0.3538.101',
'71.0.3578.44',
'71.0.3578.43',
'70.0.3538.100',
'70.0.3538.99',
'71.0.3578.42',
'72.0.3604.1',
'72.0.3604.0',
'71.0.3578.41',
'70.0.3538.98',
'71.0.3578.40',
'72.0.3603.2',
'72.0.3603.1',
'72.0.3603.0',
'71.0.3578.39',
'70.0.3538.97',
'72.0.3602.2',
'71.0.3578.38',
'71.0.3578.37',
'72.0.3602.1',
'72.0.3602.0',
'71.0.3578.36',
'70.0.3538.96',
'72.0.3601.1',
'72.0.3601.0',
'71.0.3578.35',
'70.0.3538.95',
'72.0.3600.1',
'72.0.3600.0',
'71.0.3578.34',
'70.0.3538.94',
'72.0.3599.3',
'72.0.3599.2',
'72.0.3599.1',
'72.0.3599.0',
'71.0.3578.33',
'70.0.3538.93',
'72.0.3598.1',
'72.0.3598.0',
'71.0.3578.32',
'70.0.3538.87',
'72.0.3597.1',
'72.0.3597.0',
'72.0.3596.2',
'71.0.3578.31',
'70.0.3538.86',
'71.0.3578.30',
'71.0.3578.29',
'72.0.3596.1',
'72.0.3596.0',
'71.0.3578.28',
'70.0.3538.85',
'72.0.3595.2',
'72.0.3591.3',
'72.0.3595.1',
'72.0.3595.0',
'71.0.3578.27',
'70.0.3538.84',
'72.0.3594.1',
'72.0.3594.0',
'71.0.3578.26',
'70.0.3538.83',
'72.0.3593.2',
'72.0.3593.1',
'72.0.3593.0',
'71.0.3578.25',
'70.0.3538.82',
'72.0.3589.3',
'72.0.3592.2',
'72.0.3592.1',
'72.0.3592.0',
'71.0.3578.24',
'72.0.3589.2',
'70.0.3538.81',
'70.0.3538.80',
'72.0.3591.2',
'72.0.3591.1',
'72.0.3591.0',
'71.0.3578.23',
'70.0.3538.79',
'71.0.3578.22',
'72.0.3590.1',
'72.0.3590.0',
'71.0.3578.21',
'70.0.3538.78',
'70.0.3538.77',
'72.0.3589.1',
'72.0.3589.0',
'71.0.3578.20',
'70.0.3538.76',
'71.0.3578.19',
'70.0.3538.75',
'72.0.3588.1',
'72.0.3588.0',
'71.0.3578.18',
'70.0.3538.74',
'72.0.3586.2',
'72.0.3587.0',
'71.0.3578.17',
'70.0.3538.73',
'72.0.3586.1',
'72.0.3586.0',
'71.0.3578.16',
'70.0.3538.72',
'72.0.3585.1',
'72.0.3585.0',
'71.0.3578.15',
'70.0.3538.71',
'71.0.3578.14',
'72.0.3584.1',
'72.0.3584.0',
'71.0.3578.13',
'70.0.3538.70',
'72.0.3583.2',
'71.0.3578.12',
'72.0.3583.1',
'72.0.3583.0',
'71.0.3578.11',
'70.0.3538.69',
'71.0.3578.10',
'72.0.3582.0',
'72.0.3581.4',
'71.0.3578.9',
'70.0.3538.67',
'72.0.3581.3',
'72.0.3581.2',
'72.0.3581.1',
'72.0.3581.0',
'71.0.3578.8',
'70.0.3538.66',
'72.0.3580.1',
'72.0.3580.0',
'71.0.3578.7',
'70.0.3538.65',
'71.0.3578.6',
'72.0.3579.1',
'72.0.3579.0',
'71.0.3578.5',
'70.0.3538.64',
'71.0.3578.4',
'71.0.3578.3',
'71.0.3578.2',
'71.0.3578.1',
'71.0.3578.0',
'70.0.3538.63',
'69.0.3497.128',
'70.0.3538.62',
'70.0.3538.61',
'70.0.3538.60',
'70.0.3538.59',
'71.0.3577.1',
'71.0.3577.0',
'70.0.3538.58',
'69.0.3497.127',
'71.0.3576.2',
'71.0.3576.1',
'71.0.3576.0',
'70.0.3538.57',
'70.0.3538.56',
'71.0.3575.2',
'70.0.3538.55',
'69.0.3497.126',
'70.0.3538.54',
'71.0.3575.1',
'71.0.3575.0',
'71.0.3574.1',
'71.0.3574.0',
'70.0.3538.53',
'69.0.3497.125',
'70.0.3538.52',
'71.0.3573.1',
'71.0.3573.0',
'70.0.3538.51',
'69.0.3497.124',
'71.0.3572.1',
'71.0.3572.0',
'70.0.3538.50',
'69.0.3497.123',
'71.0.3571.2',
'70.0.3538.49',
'69.0.3497.122',
'71.0.3571.1',
'71.0.3571.0',
'70.0.3538.48',
'69.0.3497.121',
'71.0.3570.1',
'71.0.3570.0',
'70.0.3538.47',
'69.0.3497.120',
'71.0.3568.2',
'71.0.3569.1',
'71.0.3569.0',
'70.0.3538.46',
'69.0.3497.119',
'70.0.3538.45',
'71.0.3568.1',
'71.0.3568.0',
'70.0.3538.44',
'69.0.3497.118',
'70.0.3538.43',
'70.0.3538.42',
'71.0.3567.1',
'71.0.3567.0',
'70.0.3538.41',
'69.0.3497.117',
'71.0.3566.1',
'71.0.3566.0',
'70.0.3538.40',
'69.0.3497.116',
'71.0.3565.1',
'71.0.3565.0',
'70.0.3538.39',
'69.0.3497.115',
'71.0.3564.1',
'71.0.3564.0',
'70.0.3538.38',
'69.0.3497.114',
'71.0.3563.0',
'71.0.3562.2',
'70.0.3538.37',
'69.0.3497.113',
'70.0.3538.36',
'70.0.3538.35',
'71.0.3562.1',
'71.0.3562.0',
'70.0.3538.34',
'69.0.3497.112',
'70.0.3538.33',
'71.0.3561.1',
'71.0.3561.0',
'70.0.3538.32',
'69.0.3497.111',
'71.0.3559.6',
'71.0.3560.1',
'71.0.3560.0',
'71.0.3559.5',
'71.0.3559.4',
'70.0.3538.31',
'69.0.3497.110',
'71.0.3559.3',
'70.0.3538.30',
'69.0.3497.109',
'71.0.3559.2',
'71.0.3559.1',
'71.0.3559.0',
'70.0.3538.29',
'69.0.3497.108',
'71.0.3558.2',
'71.0.3558.1',
'71.0.3558.0',
'70.0.3538.28',
'69.0.3497.107',
'71.0.3557.2',
'71.0.3557.1',
'71.0.3557.0',
'70.0.3538.27',
'69.0.3497.106',
'71.0.3554.4',
'70.0.3538.26',
'71.0.3556.1',
'71.0.3556.0',
'70.0.3538.25',
'71.0.3554.3',
'69.0.3497.105',
'71.0.3554.2',
'70.0.3538.24',
'69.0.3497.104',
'71.0.3555.2',
'70.0.3538.23',
'71.0.3555.1',
'71.0.3555.0',
'70.0.3538.22',
'69.0.3497.103',
'71.0.3554.1',
'71.0.3554.0',
'70.0.3538.21',
'69.0.3497.102',
'71.0.3553.3',
'70.0.3538.20',
'69.0.3497.101',
'71.0.3553.2',
'69.0.3497.100',
'71.0.3553.1',
'71.0.3553.0',
'70.0.3538.19',
'69.0.3497.99',
'69.0.3497.98',
'69.0.3497.97',
'71.0.3552.6',
'71.0.3552.5',
'71.0.3552.4',
'71.0.3552.3',
'71.0.3552.2',
'71.0.3552.1',
'71.0.3552.0',
'70.0.3538.18',
'69.0.3497.96',
'71.0.3551.3',
'71.0.3551.2',
'71.0.3551.1',
'71.0.3551.0',
'70.0.3538.17',
'69.0.3497.95',
'71.0.3550.3',
'71.0.3550.2',
'71.0.3550.1',
'71.0.3550.0',
'70.0.3538.16',
'69.0.3497.94',
'71.0.3549.1',
'71.0.3549.0',
'70.0.3538.15',
'69.0.3497.93',
'69.0.3497.92',
'71.0.3548.1',
'71.0.3548.0',
'70.0.3538.14',
'69.0.3497.91',
'71.0.3547.1',
'71.0.3547.0',
'70.0.3538.13',
'69.0.3497.90',
'71.0.3546.2',
'69.0.3497.89',
'71.0.3546.1',
'71.0.3546.0',
'70.0.3538.12',
'69.0.3497.88',
'71.0.3545.4',
'71.0.3545.3',
'71.0.3545.2',
'71.0.3545.1',
'71.0.3545.0',
'70.0.3538.11',
'69.0.3497.87',
'71.0.3544.5',
'71.0.3544.4',
'71.0.3544.3',
'71.0.3544.2',
'71.0.3544.1',
'71.0.3544.0',
'69.0.3497.86',
'70.0.3538.10',
'69.0.3497.85',
'70.0.3538.9',
'69.0.3497.84',
'71.0.3543.4',
'70.0.3538.8',
'71.0.3543.3',
'71.0.3543.2',
'71.0.3543.1',
'71.0.3543.0',
'70.0.3538.7',
'69.0.3497.83',
'71.0.3542.2',
'71.0.3542.1',
'71.0.3542.0',
'70.0.3538.6',
'69.0.3497.82',
'69.0.3497.81',
'71.0.3541.1',
'71.0.3541.0',
'70.0.3538.5',
'69.0.3497.80',
'71.0.3540.1',
'71.0.3540.0',
'70.0.3538.4',
'69.0.3497.79',
'70.0.3538.3',
'71.0.3539.1',
'71.0.3539.0',
'69.0.3497.78',
'68.0.3440.134',
'69.0.3497.77',
'70.0.3538.2',
'70.0.3538.1',
'70.0.3538.0',
'69.0.3497.76',
'68.0.3440.133',
'69.0.3497.75',
'70.0.3537.2',
'70.0.3537.1',
'70.0.3537.0',
'69.0.3497.74',
'68.0.3440.132',
'70.0.3536.0',
'70.0.3535.5',
'70.0.3535.4',
'70.0.3535.3',
'69.0.3497.73',
'68.0.3440.131',
'70.0.3532.8',
'70.0.3532.7',
'69.0.3497.72',
'69.0.3497.71',
'70.0.3535.2',
'70.0.3535.1',
'70.0.3535.0',
'69.0.3497.70',
'68.0.3440.130',
'69.0.3497.69',
'68.0.3440.129',
'70.0.3534.4',
'70.0.3534.3',
'70.0.3534.2',
'70.0.3534.1',
'70.0.3534.0',
'69.0.3497.68',
'68.0.3440.128',
'70.0.3533.2',
'70.0.3533.1',
'70.0.3533.0',
'69.0.3497.67',
'68.0.3440.127',
'70.0.3532.6',
'70.0.3532.5',
'70.0.3532.4',
'69.0.3497.66',
'68.0.3440.126',
'70.0.3532.3',
'70.0.3532.2',
'70.0.3532.1',
'69.0.3497.60',
'69.0.3497.65',
'69.0.3497.64',
'70.0.3532.0',
'70.0.3531.0',
'70.0.3530.4',
'70.0.3530.3',
'70.0.3530.2',
'69.0.3497.58',
'68.0.3440.125',
'69.0.3497.57',
'69.0.3497.56',
'69.0.3497.55',
'69.0.3497.54',
'70.0.3530.1',
'70.0.3530.0',
'69.0.3497.53',
'68.0.3440.124',
'69.0.3497.52',
'70.0.3529.3',
'70.0.3529.2',
'70.0.3529.1',
'70.0.3529.0',
'69.0.3497.51',
'70.0.3528.4',
'68.0.3440.123',
'70.0.3528.3',
'70.0.3528.2',
'70.0.3528.1',
'70.0.3528.0',
'69.0.3497.50',
'68.0.3440.122',
'70.0.3527.1',
'70.0.3527.0',
'69.0.3497.49',
'68.0.3440.121',
'70.0.3526.1',
'70.0.3526.0',
'68.0.3440.120',
'69.0.3497.48',
'69.0.3497.47',
'68.0.3440.119',
'68.0.3440.118',
'70.0.3525.5',
'70.0.3525.4',
'70.0.3525.3',
'68.0.3440.117',
'69.0.3497.46',
'70.0.3525.2',
'70.0.3525.1',
'70.0.3525.0',
'69.0.3497.45',
'68.0.3440.116',
'70.0.3524.4',
'70.0.3524.3',
'69.0.3497.44',
'70.0.3524.2',
'70.0.3524.1',
'70.0.3524.0',
'70.0.3523.2',
'69.0.3497.43',
'68.0.3440.115',
'70.0.3505.9',
'69.0.3497.42',
'70.0.3505.8',
'70.0.3523.1',
'70.0.3523.0',
'69.0.3497.41',
'68.0.3440.114',
'70.0.3505.7',
'69.0.3497.40',
'70.0.3522.1',
'70.0.3522.0',
'70.0.3521.2',
'69.0.3497.39',
'68.0.3440.113',
'70.0.3505.6',
'70.0.3521.1',
'70.0.3521.0',
'69.0.3497.38',
'68.0.3440.112',
'70.0.3520.1',
'70.0.3520.0',
'69.0.3497.37',
'68.0.3440.111',
'70.0.3519.3',
'70.0.3519.2',
'70.0.3519.1',
'70.0.3519.0',
'69.0.3497.36',
'68.0.3440.110',
'70.0.3518.1',
'70.0.3518.0',
'69.0.3497.35',
'69.0.3497.34',
'68.0.3440.109',
'70.0.3517.1',
'70.0.3517.0',
'69.0.3497.33',
'68.0.3440.108',
'69.0.3497.32',
'70.0.3516.3',
'70.0.3516.2',
'70.0.3516.1',
'70.0.3516.0',
'69.0.3497.31',
'68.0.3440.107',
'70.0.3515.4',
'68.0.3440.106',
'70.0.3515.3',
'70.0.3515.2',
'70.0.3515.1',
'70.0.3515.0',
'69.0.3497.30',
'68.0.3440.105',
'68.0.3440.104',
'70.0.3514.2',
'70.0.3514.1',
'70.0.3514.0',
'69.0.3497.29',
'68.0.3440.103',
'70.0.3513.1',
'70.0.3513.0',
'69.0.3497.28',
)
return _USER_AGENT_TPL % random.choice(_CHROME_VERSIONS)
Py3 compat for unichr and htmlentitydefs
2012-11-28 00:02:55 +01:00
std_headers = {
[utils] Introduce random_user_agent and use as default User-Agent (closes #21546)
2019-06-28 19:32:43 +02:00
'User-Agent': random_user_agent(),
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.7',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
'Accept-Encoding': 'gzip, deflate',
'Accept-Language': 'en-us,en;q=0.5',
Py3 compat for unichr and htmlentitydefs
2012-11-28 00:02:55 +01:00
}
some fixes, pulled the codename from the code
2012-12-30 18:22:36 +01:00
PEP8 applied
2014-11-23 20:41:03 +01:00
[utils] Add common user agents map
2016-12-11 18:49:07 +01:00
USER_AGENTS = {
'Safari': 'Mozilla/5.0 (X11; Linux x86_64; rv:10.0) AppleWebKit/533.20.25 (KHTML, like Gecko) Version/5.0.4 Safari/533.20.27',
}
[utils] Add default value for xpath_text
2015-06-28 18:56:07 +02:00
NO_DEFAULT = object()
[utils] Backport traverse_obj (etc) from yt-dlp (#31156) * Backport traverse_obj and closely related function from yt-dlp (code by pukkandan) * Backport LazyList, variadic(), try_call (code by pukkandan) * Recast using yt-dlp's newer traverse_obj() implementation and tests (code by grub4k) * Add tests for Unicode case folding support matching Py3.5+ (requires f102e3d) * Improve/add tests for variadic, try_call, join_nonempty Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-11-03 11:09:37 +01:00
IDENTITY = lambda x: x
[utils] Add default value for xpath_text
2015-06-28 18:56:07 +02:00
[Yam] Add new extractor
2015-02-13 08:14:23 +01:00
ENGLISH_MONTH_NAMES = [
'January', 'February', 'March', 'April', 'May', 'June',
'July', 'August', 'September', 'October', 'November', 'December']
[utils] Improve month_by_name and add tests
2016-09-14 18:13:55 +02:00
MONTH_NAMES = {
'en': ENGLISH_MONTH_NAMES,
'fr': [
[utils] Use native french month names
2016-09-14 18:57:01 +02:00
'janvier', 'février', 'mars', 'avril', 'mai', 'juin',
'juillet', 'août', 'septembre', 'octobre', 'novembre', 'décembre'],
[utils] Improve month_by_name and add tests
2016-09-14 18:13:55 +02:00
}
[utils,franceinter] Add french months' names and fix extraction Update of the "FranceInter" radio extractor : webpages HTML structure had changed, the extractor didn't work. So I updated this extractor to get the mp3 URL and all details.
2016-09-02 18:31:52 +02:00
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
# Timezone names for RFC2822 obs-zone
# From https://github.com/python/cpython/blob/3.11/Lib/email/_parseaddr.py#L36-L42
TIMEZONE_NAMES = {
'UT': 0, 'UTC': 0, 'GMT': 0, 'Z': 0,
'AST': -4, 'ADT': -3, # Atlantic (used in Canada)
'EST': -5, 'EDT': -4, # Eastern
'CST': -6, 'CDT': -5, # Central
'MST': -7, 'MDT': -6, # Mountain
'PST': -8, 'PDT': -7 # Pacific
}
[utils] Extract known extensions for reuse
2016-01-03 20:08:34 +01:00
KNOWN_EXTENSIONS = (
'mp4', 'm4a', 'm4p', 'm4b', 'm4r', 'm4v', 'aac',
'flv', 'f4v', 'f4a', 'f4b',
'webm', 'ogg', 'ogv', 'oga', 'ogx', 'spx', 'opus',
'mkv', 'mka', 'mk3d',
'avi', 'divx',
'mov',
'asf', 'wmv', 'wma',
'3gp', '3g2',
'mp3',
'flac',
'ape',
'wav',
'f4f', 'f4m', 'm3u8', 'smil')
improved performance by extracting accented chars to top level
2016-05-03 02:40:30 +02:00
# needed for sanitizing filenames in restricted mode
Added sanitization support for Hungarian letters Ő and Ű
2016-06-02 11:51:48 +02:00
ACCENT_CHARS = dict(zip('ÂÃÄÀÁÅÆÇÈÉÊËÌÍÎÏÐÑÒÓÔÕÖŐØŒÙÚÛÜŰÝÞßàáâãäåæçèéêëìíîïðñòóôõöőøœùúûüűýþÿ',
[utils] Transliterate "þ" as "th" (#20897) Despite visual similarity "þ" is unrelated to "p". It is normally transliterated as "th": $ echo þ-Þ | iconv -t ASCII//TRANSLIT th-TH
2019-05-10 20:42:32 +02:00
itertools.chain('AAAAAA', ['AE'], 'CEEEEIIIIDNOOOOOOO', ['OE'], 'UUUUUY', ['TH', 'ss'],
'aaaaaa', ['ae'], 'ceeeeiiiionooooooo', ['oe'], 'uuuuuy', ['th'], 'y')))
improved performance by extracting accented chars to top level
2016-05-03 02:40:30 +02:00
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
DATE_FORMATS = (
'%d %B %Y',
'%d %b %Y',
'%B %d %Y',
[utils] Add more date formats
2017-01-12 16:39:45 +01:00
'%B %dst %Y',
'%B %dnd %Y',
[utils] Handle rd-suffixed day parts in unified_strdate (#23199)
2019-11-26 18:08:37 +01:00
'%B %drd %Y',
[utils] Add more date formats
2017-01-12 16:39:45 +01:00
'%B %dth %Y',
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
'%b %d %Y',
[utils] Add more date formats
2017-01-12 16:39:45 +01:00
'%b %dst %Y',
'%b %dnd %Y',
[utils] Handle rd-suffixed day parts in unified_strdate (#23199)
2019-11-26 18:08:37 +01:00
'%b %drd %Y',
[utils] Add more date formats
2017-01-12 16:39:45 +01:00
'%b %dth %Y',
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
'%b %dst %Y %I:%M',
'%b %dnd %Y %I:%M',
[utils] Handle rd-suffixed day parts in unified_strdate (#23199)
2019-11-26 18:08:37 +01:00
'%b %drd %Y %I:%M',
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
'%b %dth %Y %I:%M',
'%Y %m %d',
'%Y-%m-%d',
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
'%Y.%m.%d.',
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
'%Y/%m/%d',
[utils] Recognize more formats in unified_timestamp Used in CtsNews
2016-08-10 05:36:49 +02:00
'%Y/%m/%d %H:%M',
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
'%Y/%m/%d %H:%M:%S',
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
'%Y%m%d%H%M',
'%Y%m%d%H%M%S',
'%Y%m%d',
[utils] Add another date format seen in NextTV
2017-01-23 16:31:43 +01:00
'%Y-%m-%d %H:%M',
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
'%Y-%m-%d %H:%M:%S',
'%Y-%m-%d %H:%M:%S.%f',
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
'%Y-%m-%d %H:%M:%S:%f',
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
'%d.%m.%Y %H:%M',
'%d.%m.%Y %H.%M',
'%Y-%m-%dT%H:%M:%SZ',
'%Y-%m-%dT%H:%M:%S.%fZ',
'%Y-%m-%dT%H:%M:%S.%f0Z',
'%Y-%m-%dT%H:%M:%S',
'%Y-%m-%dT%H:%M:%S.%f',
'%Y-%m-%dT%H:%M',
[utils] Lower priority for rare date formats and add tests
2016-09-29 18:47:25 +02:00
'%b %d %Y at %H:%M',
'%b %d %Y at %H:%M:%S',
[utils] Add another date format pattern (#14999)
2017-12-16 15:56:16 +01:00
'%B %d %Y at %H:%M',
'%B %d %Y at %H:%M:%S',
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
'%H:%M %d-%b-%Y',
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
)
DATE_FORMATS_DAY_FIRST = list(DATE_FORMATS)
DATE_FORMATS_DAY_FIRST.extend([
'%d-%m-%Y',
'%d.%m.%Y',
'%d.%m.%y',
'%d/%m/%Y',
'%d/%m/%y',
'%d/%m/%Y %H:%M:%S',
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
'%d-%m-%Y %H:%M',
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
])
DATE_FORMATS_MONTH_FIRST = list(DATE_FORMATS)
DATE_FORMATS_MONTH_FIRST.extend([
'%m-%d-%Y',
'%m.%d.%Y',
'%m/%d/%Y',
'%m/%d/%y',
'%m/%d/%Y %H:%M:%S',
])
[utils] Expose PACKED_CODES_RE
2016-10-19 18:28:49 +02:00
PACKED_CODES_RE = r"}\('(.+)',(\d+),(\d+),'([^']+)'\.split\('\|'\)"
[malltv] Add extractor (closes #18058)
2018-10-10 23:47:21 +02:00
JSON_LD_RE = r'(?is)<script[^>]+type=(["\']?)application/ld\+json\1[^>]*>(?P<json_ld>.+?)</script>'
[utils] Expose PACKED_CODES_RE
2016-10-19 18:28:49 +02:00
[Yam] Add new extractor
2015-02-13 08:14:23 +01:00
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
def preferredencoding():
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Get preferred encoding.
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
Returns the best encoding scheme for the system, based on
locale.getpreferredencoding() and some further tweaks.
"""
try:
pref = locale.getpreferredencoding()
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
'TEST'.encode(pref)
Don't use bare 'except:' They catch any exception, including KeyboardInterrupt, we don't want to catch it.
2015-03-27 13:02:20 +01:00
except Exception:
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
pref = 'UTF-8'
Simplified preferredencoding() Not sure what is the point to use yield to return encoding, thus it will simplify the whole function. Signed-off-by: Arvydas Sidorenko <asido4@gmail.com>
2012-07-01 18:21:27 +02:00
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
return pref
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Correct JSON writing (Closes #596)
2012-12-20 13:13:24 +01:00
[utils] Make JSON file writes atomic (Fixes #3549)
2014-08-21 13:01:13 +02:00
def write_json_file(obj, fn):
Fix "ERROR: Cannot write metadata to JSON file" on Windows Fixes #4246
2014-11-20 07:05:39 +01:00
""" Encode obj as JSON and write it to fn, atomically if possible """
[utils] Make JSON file writes atomic (Fixes #3549)
2014-08-21 13:01:13 +02:00
[cache] Fix writing to paths with unicode characters * Use "compat_getenv" * "write_json_file" now expects the filename to be a string
2014-11-18 23:28:42 +01:00
fn = encodeFilename(fn)
Fix UnicodeEncodeError with --write-info-json on Python 2.7 + Windows Fixes #4244
2014-11-20 07:04:04 +01:00
if sys.version_info < (3, 0) and sys.platform != 'win32':
[utils] Fix "write_json_file" for unicode names in python 2.x (fixes #4125)
2014-11-15 22:00:32 +01:00
encoding = get_filesystem_encoding()
# os.path.basename returns a bytes object, but NamedTemporaryFile
# will fail if the filename contains non ascii characters unless we
# use a unicode object
path_basename = lambda f: os.path.basename(fn).decode(encoding)
# the same for os.path.dirname
path_dirname = lambda f: os.path.dirname(fn).decode(encoding)
else:
path_basename = os.path.basename
path_dirname = os.path.dirname
[utils] Add missing mode and encoding arguments
2014-08-21 17:03:00 +02:00
args = {
'suffix': '.tmp',
[utils] Fix "write_json_file" for unicode names in python 2.x (fixes #4125)
2014-11-15 22:00:32 +01:00
'prefix': path_basename(fn) + '.',
'dir': path_dirname(fn),
[utils] Add missing mode and encoding arguments
2014-08-21 17:03:00 +02:00
'delete': False,
}
[utils] Make JSON file writes atomic (Fixes #3549)
2014-08-21 13:01:13 +02:00
# In Python 2.x, json.dump expects a bytestream.
# In Python 3.x, it writes to a character stream
if sys.version_info < (3, 0):
[utils] Add missing mode and encoding arguments
2014-08-21 17:03:00 +02:00
args['mode'] = 'wb'
[utils] Make JSON file writes atomic (Fixes #3549)
2014-08-21 13:01:13 +02:00
else:
[utils] Add missing mode and encoding arguments
2014-08-21 17:03:00 +02:00
args.update({
'mode': 'w',
'encoding': 'utf-8',
})
[utils] Fix another old python 2.6 kwargs issue (Closes #5539)
2015-04-27 16:00:18 +02:00
tf = tempfile.NamedTemporaryFile(**compat_kwargs(args))
[utils] Make JSON file writes atomic (Fixes #3549)
2014-08-21 13:01:13 +02:00
try:
with tf:
json.dump(obj, tf)
Fix "ERROR: Cannot write metadata to JSON file" on Windows Fixes #4246
2014-11-20 07:05:39 +01:00
if sys.platform == 'win32':
# Need to remove existing file on Windows, else os.rename raises
# WindowsError or FileExistsError.
try:
os.unlink(fn)
except OSError:
pass
[utils] Fix file permissions in write_json_file (closes #12471) (#25122)
2020-05-19 22:21:52 +02:00
try:
mask = os.umask(0)
os.umask(mask)
os.chmod(tf.name, 0o666 & ~mask)
except OSError:
pass
[utils] Make JSON file writes atomic (Fixes #3549)
2014-08-21 13:01:13 +02:00
os.rename(tf.name, fn)
Don't use bare 'except:' They catch any exception, including KeyboardInterrupt, we don't want to catch it.
2015-03-27 13:02:20 +01:00
except Exception:
[utils] Make JSON file writes atomic (Fixes #3549)
2014-08-21 13:01:13 +02:00
try:
os.remove(tf.name)
except OSError:
pass
raise
if sys.version_info >= (2, 7):
[utils] Make value optional for find_xpath_attr This allows selecting particular attributes by name but without specifying the value and similar to xpath syntax `[@attrib]`
2015-08-01 16:22:13 +02:00
def find_xpath_attr(node, xpath, key, val=None):
Add helper function find_path_attr
2013-07-11 16:12:08 +02:00
""" Find the xpath xpath[@key=val] """
[utils] Relax attribute key assert
2015-09-04 19:57:27 +02:00
assert re.match(r'^[a-zA-Z_-]+$', key)
[utils] Make value optional for find_xpath_attr This allows selecting particular attributes by name but without specifying the value and similar to xpath syntax `[@attrib]`
2015-08-01 16:22:13 +02:00
expr = xpath + ('[@%s]' % key if val is None else "[@%s='%s']" % (key, val))
Add helper function find_path_attr
2013-07-11 16:12:08 +02:00
return node.find(expr)
else:
[utils] Make value optional for find_xpath_attr This allows selecting particular attributes by name but without specifying the value and similar to xpath syntax `[@attrib]`
2015-08-01 16:22:13 +02:00
def find_xpath_attr(node, xpath, key, val=None):
[utils] Use compat_xpath
2016-03-17 21:52:23 +01:00
for f in node.findall(compat_xpath(xpath)):
[utils] Make value optional for find_xpath_attr This allows selecting particular attributes by name but without specifying the value and similar to xpath syntax `[@attrib]`
2015-08-01 16:22:13 +02:00
if key not in f.attrib:
continue
if val is None or f.attrib.get(key) == val:
Add helper function find_path_attr
2013-07-11 16:12:08 +02:00
return f
return None
Add an extractor for internetvideoarchive.com videos It's used by videodetective.com
2013-10-12 21:34:04 +02:00
# On python2.6 the xml.etree.ElementTree.Element methods don't support
# the namespace parameter
PEP8 applied
2014-11-23 20:41:03 +01:00
Add an extractor for internetvideoarchive.com videos It's used by videodetective.com
2013-10-12 21:34:04 +02:00
def xpath_with_ns(path, ns_map):
components = [c.split(':') for c in path.split('/')]
replaced = []
for c in components:
if len(c) == 1:
replaced.append(c[0])
else:
ns, tag = c
replaced.append('{%s}%s' % (ns_map[ns], tag))
return '/'.join(replaced)
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
[utils] Add xpath_element and xpath_attr
2015-09-04 19:56:45 +02:00
def xpath_element(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
[utils] Support list of xpath in xpath_element
2015-10-31 17:39:44 +01:00
def _find_xpath(xpath):
[utils] Use compat_xpath
2016-03-17 21:52:23 +01:00
return node.find(compat_xpath(xpath))
[utils] Support list of xpath in xpath_element
2015-10-31 17:39:44 +01:00
if isinstance(xpath, (str, compat_str)):
n = _find_xpath(xpath)
else:
for xp in xpath:
n = _find_xpath(xp)
if n is not None:
break
[utils] Apply 2.6 xpath craziness This fixes ARD on 2.6
2014-09-13 09:11:14 +02:00
[utils] Improve xpath_text
2015-09-04 20:34:49 +02:00
if n is None:
[utils] Add default value for xpath_text
2015-06-28 18:56:07 +02:00
if default is not NO_DEFAULT:
return default
elif fatal:
[ard] Make more robust against missing thumbnails I cannot reproduce this error, it's from travis.
2014-09-13 09:09:55 +02:00
name = xpath if name is None else name
raise ExtractorError('Could not find XML element %s' % name)
else:
return None
[utils] Add xpath_element and xpath_attr
2015-09-04 19:56:45 +02:00
return n
def xpath_text(node, xpath, name=None, fatal=False, default=NO_DEFAULT):
[utils] Improve xpath_text
2015-09-04 20:34:49 +02:00
n = xpath_element(node, xpath, name, fatal=fatal, default=default)
if n is None or n == default:
return n
if n.text is None:
if default is not NO_DEFAULT:
return default
elif fatal:
name = xpath if name is None else name
raise ExtractorError('Could not find XML element\'s text %s' % name)
else:
return None
return n.text
[utils] Add xpath_element and xpath_attr
2015-09-04 19:56:45 +02:00
def xpath_attr(node, xpath, key, name=None, fatal=False, default=NO_DEFAULT):
n = find_xpath_attr(node, xpath, key)
if n is None:
if default is not NO_DEFAULT:
return default
elif fatal:
name = '%s[@%s]' % (xpath, key) if name is None else name
raise ExtractorError('Could not find XML attribute %s' % name)
else:
return None
return n.attrib[key]
[ard] Make more robust against missing thumbnails I cannot reproduce this error, it's from travis.
2014-09-13 09:09:55 +02:00
merged unescapeHTML branch; removed lxml dependency
2012-04-11 00:22:51 +02:00
def get_element_by_id(id, html):
Refactor IDParser to search for elements by any attribute not just ID
2012-12-19 15:21:14 +01:00
"""Return the content of the tag with the specified ID in the passed HTML document"""
[refactor] Single quotes consistency
2016-02-14 10:37:17 +01:00
return get_element_by_attribute('id', id, html)
Refactor IDParser to search for elements by any attribute not just ID
2012-12-19 15:21:14 +01:00
[utils] Remove unused get_meta_content function
2014-11-04 23:20:39 +01:00
[utils] Add get_element_by_class For #9950
2016-07-06 14:02:52 +02:00
def get_element_by_class(class_name, html):
Introduce get_elements_by_class and get_elements_by_attribute utility functions
2017-02-11 10:16:54 +01:00
"""Return the content of the first tag with the specified class in the passed HTML document"""
retval = get_elements_by_class(class_name, html)
return retval[0] if retval else None
def get_element_by_attribute(attribute, value, html, escape_value=True):
retval = get_elements_by_attribute(attribute, value, html, escape_value)
return retval[0] if retval else None
def get_elements_by_class(class_name, html):
"""Return the content of all tags with the specified class in the passed HTML document as a list"""
return get_elements_by_attribute(
[utils] Add get_element_by_class For #9950
2016-07-06 14:02:52 +02:00
'class', r'[^\'"]*\b%s\b[^\'"]*' % re.escape(class_name),
html, escape_value=False)
Introduce get_elements_by_class and get_elements_by_attribute utility functions
2017-02-11 10:16:54 +01:00
def get_elements_by_attribute(attribute, value, html, escape_value=True):
Refactor IDParser to search for elements by any attribute not just ID
2012-12-19 15:21:14 +01:00
"""Return the content of the tag with the specified attribute in the passed HTML document"""
merged unescapeHTML branch; removed lxml dependency
2012-04-11 00:22:51 +02:00
[utils] Add get_element_by_class For #9950
2016-07-06 14:02:52 +02:00
value = re.escape(value) if escape_value else value
Introduce get_elements_by_class and get_elements_by_attribute utility functions
2017-02-11 10:16:54 +01:00
retlist = []
for m in re.finditer(r'''(?xs)
[utils] Use a regexp instead of HTMLParser for get_element_by_attribute
2014-11-04 23:33:43 +01:00
<([a-zA-Z0-9:._-]+)
[utils] Support attributes with no values in get_elements_by_attribute()
2017-07-05 17:23:35 +02:00
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
[utils] Use a regexp instead of HTMLParser for get_element_by_attribute
2014-11-04 23:33:43 +01:00
\s+%s=['"]?%s['"]?
[utils] Support attributes with no values in get_elements_by_attribute()
2017-07-05 17:23:35 +02:00
(?:\s+[a-zA-Z0-9:._-]+(?:=[a-zA-Z0-9:._-]*|="[^"]*"|='[^']*'|))*?
[utils] Use a regexp instead of HTMLParser for get_element_by_attribute
2014-11-04 23:33:43 +01:00
\s*>
(?P<content>.*?)
</\1>
Introduce get_elements_by_class and get_elements_by_attribute utility functions
2017-02-11 10:16:54 +01:00
''' % (re.escape(attribute), value), html):
res = m.group('content')
[utils] Use a regexp instead of HTMLParser for get_element_by_attribute
2014-11-04 23:33:43 +01:00
Introduce get_elements_by_class and get_elements_by_attribute utility functions
2017-02-11 10:16:54 +01:00
if res.startswith('"') or res.startswith("'"):
res = res[1:-1]
[utils] Use a regexp instead of HTMLParser for get_element_by_attribute
2014-11-04 23:33:43 +01:00
Introduce get_elements_by_class and get_elements_by_attribute utility functions
2017-02-11 10:16:54 +01:00
retlist.append(unescapeHTML(res))
[ustream] Simplify channel extraction the ChannelParser has been moved to a new function in utils get_meta_content Instead of the SocialStreamParser now it uses a regex
2013-09-13 22:05:29 +02:00
Introduce get_elements_by_class and get_elements_by_attribute utility functions
2017-02-11 10:16:54 +01:00
return retlist
[ustream] Simplify channel extraction the ChannelParser has been moved to a new function in utils get_meta_content Instead of the SocialStreamParser now it uses a regex
2013-09-13 22:05:29 +02:00
[utils] PEP 8
2016-03-16 16:50:04 +01:00
[utils] Add extract_attributes for extracting html tag attributes This is much more robust than just using regexps, and handles all the common scenarios, such as empty/no values, repeated attributes, entity decoding, mixed case names, and the different possible value quoting schemes.
2016-01-02 20:49:59 +01:00
class HTMLAttributeParser(compat_HTMLParser):
"""Trivial HTML parser to gather the attributes for a single element"""
def __init__(self):
[utils] PEP 8
2016-03-16 16:50:04 +01:00
self.attrs = {}
[utils] Add extract_attributes for extracting html tag attributes This is much more robust than just using regexps, and handles all the common scenarios, such as empty/no values, repeated attributes, entity decoding, mixed case names, and the different possible value quoting schemes.
2016-01-02 20:49:59 +01:00
compat_HTMLParser.__init__(self)
def handle_starttag(self, tag, attrs):
self.attrs = dict(attrs)
[utils] PEP 8
2016-03-16 16:50:04 +01:00
[utils] Add extract_attributes for extracting html tag attributes This is much more robust than just using regexps, and handles all the common scenarios, such as empty/no values, repeated attributes, entity decoding, mixed case names, and the different possible value quoting schemes.
2016-01-02 20:49:59 +01:00
def extract_attributes(html_element):
"""Given a string for an HTML element such as
<el
a="foo" B="bar" c="&98;az" d=boz
empty= noval entity="&amp;"
sq='"' dq="'"
>
Decode and return a dictionary of attributes.
{
'a': 'foo', 'b': 'bar', c: 'baz', d: 'boz',
'empty': '', 'noval': None, 'entity': '&',
'sq': '"', 'dq': '\''
}.
NB HTMLParser is stricter in Python 2.6 & 3.2 than in later versions,
but the cases in the unit test will work for all of 2.6, 2.7, 3.2-3.5.
"""
parser = HTMLAttributeParser()
[utils] Handle HTMLParseError in extract_attributes (closes #13349)
2017-06-11 20:52:24 +02:00
try:
parser.feed(html_element)
parser.close()
# Older Python may throw HTMLParseError in case of malformed HTML
except compat_HTMLParseError:
pass
[utils] Add extract_attributes for extracting html tag attributes This is much more robust than just using regexps, and handles all the common scenarios, such as empty/no values, repeated attributes, entity decoding, mixed case names, and the different possible value quoting schemes.
2016-01-02 20:49:59 +01:00
return parser.attrs
merged unescapeHTML branch; removed lxml dependency
2012-04-11 00:22:51 +02:00
[utils] PEP 8
2016-03-16 16:50:04 +01:00
merged unescapeHTML branch; removed lxml dependency
2012-04-11 00:22:51 +02:00
def clean_html(html):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Clean an HTML snippet into a readable string"""
[netzkino] Add new extractor (Fixes #4669)
2015-01-09 23:59:18 +01:00
if html is None: # Convenience for sanitizing descriptions etc.
return html
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
# Newline vs <br />
html = html.replace('\n', ' ')
[utils] Fix inconsistent output of clean_html `\s` in Python 2.x doesn't match unicode whitespace characters by default
2017-04-28 17:34:27 +02:00
html = re.sub(r'(?u)\s*<\s*br\s*/?\s*>\s*', '\n', html)
html = re.sub(r'(?u)<\s*/\s*p\s*>\s*<\s*p[^>]*>', '\n', html)
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
# Strip html tags
html = re.sub('<.*?>', '', html)
# Replace html entities
html = unescapeHTML(html)
fix FunnyOrDieIE, MyVideoIE, TEDIE
2013-03-29 15:59:13 +01:00
return html.strip()
merged unescapeHTML branch; removed lxml dependency
2012-04-11 00:22:51 +02:00
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
def sanitize_open(filename, open_mode):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Try to open the given filename, and slightly tweak it if this fails.
Attempts to open the given filename. If this fails, it tries to change
the filename slightly, step by step, until it's either able to open it
or it fails and raises a final exception, like the standard open()
function.
It returns the tuple (stream, definitive_file_name).
"""
try:
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
if filename == '-':
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
if sys.platform == 'win32':
import msvcrt
msvcrt.setmode(sys.stdout.fileno(), os.O_BINARY)
use sys.stdout.buffer only on Python3
2013-03-28 13:13:03 +01:00
return (sys.stdout.buffer if hasattr(sys.stdout, 'buffer') else sys.stdout, filename)
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
stream = open(encodeFilename(filename), open_mode)
return (stream, filename)
except (IOError, OSError) as err:
Do not re-encode / to # if / is a platform separator, and correctly handle permission errors (Fixes #831)
2013-05-13 09:20:08 +02:00
if err.errno in (errno.EACCES,):
raise
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
Do not re-encode / to # if / is a platform separator, and correctly handle permission errors (Fixes #831)
2013-05-13 09:20:08 +02:00
# In case of error, try to remove win32 forbidden chars
[utils] Fix sanitize_open
2015-03-08 15:56:28 +01:00
alt_filename = sanitize_path(filename)
Do not re-encode / to # if / is a platform separator, and correctly handle permission errors (Fixes #831)
2013-05-13 09:20:08 +02:00
if alt_filename == filename:
raise
else:
# An exception here should be caught in the caller
[utils] Fix sanitize_open
2015-03-08 15:56:28 +01:00
stream = open(encodeFilename(alt_filename), open_mode)
Do not re-encode / to # if / is a platform separator, and correctly handle permission errors (Fixes #831)
2013-05-13 09:20:08 +02:00
return (stream, alt_filename)
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
def timeconvert(timestr):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Convert RFC 2822 defined time string into system timestamp"""
timestamp = None
timetuple = email.utils.parsedate_tz(timestr)
if timetuple is not None:
timestamp = email.utils.mktime_tz(timetuple)
return timestamp
New optoin --restrict-filenames
2012-11-26 23:58:46 +01:00
PEP8 applied
2014-11-23 20:41:03 +01:00
Keep video IDs verbatim if possible (Closes #571)
2012-12-03 15:36:24 +01:00
def sanitize_filename(s, restricted=False, is_id=False):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Sanitizes a string so it could be used as part of a filename.
If restricted is set, use a stricter subset of allowed characters.
[utils] Carry long doc string
2017-03-01 17:04:02 +01:00
Set is_id if this is not an arbitrary string, but an ID that should be kept
if possible.
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""
def replace_insane(char):
improved performance by extracting accented chars to top level
2016-05-03 02:40:30 +02:00
if restricted and char in ACCENT_CHARS:
return ACCENT_CHARS[char]
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
if char == '?' or ord(char) < 32 or ord(char) == 127:
return ''
elif char == '"':
return '' if restricted else '\''
elif char == ':':
return '_-' if restricted else ' -'
elif char in '\\/|*<>':
return '_'
Restrict more characters (Closes #566)
2012-11-28 12:59:27 +01:00
if restricted and (char in '!&\'()[]{}$;`^,#' or char.isspace()):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
return '_'
if restricted and ord(char) > 127:
return '_'
return char
[utils] Sanitize look-alike Unicode glyphs in non-ID filename fields when --restrict-filenames Implements https://github.com/ytdl-org/youtube-dl/issues/31216#issuecomment-1236102822, which has a test.
2022-10-11 14:18:12 +02:00
# Replace look-alike Unicode glyphs
if restricted and not is_id:
s = unicodedata.normalize('NFKC', s)
[utils] Improve colon handling (Fixes #4683)
2015-01-11 17:40:45 +01:00
# Handle timestamps
s = re.sub(r'[0-9]+(?::[0-9]+)+', lambda m: m.group(0).replace(':', '_'), s)
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
result = ''.join(map(replace_insane, s))
Keep video IDs verbatim if possible (Closes #571)
2012-12-03 15:36:24 +01:00
if not is_id:
while '__' in result:
result = result.replace('__', '_')
result = result.strip('_')
# Common case of "Foreign band name - English song title"
if restricted and result.startswith('-_'):
result = result[2:]
[utils] Prevent hyphen at beginning of filename (Fixes #5035)
2015-02-24 11:38:01 +01:00
if result.startswith('-'):
result = '_' + result[len('-'):]
[utils] Streap leading dots Fixes #2865, closes #5087
2015-03-02 19:07:17 +01:00
result = result.lstrip('.')
Keep video IDs verbatim if possible (Closes #571)
2012-12-03 15:36:24 +01:00
if not result:
result = '_'
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
return result
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
PEP8 applied
2014-11-23 20:41:03 +01:00
[utils] Add sanitize_path
2015-03-08 15:55:22 +01:00
def sanitize_path(s):
"""Sanitizes and normalizes path on Windows"""
if sys.platform != 'win32':
return s
[utils] Fix splitunc deprecation warning
2015-04-16 18:12:38 +02:00
drive_or_unc, _ = os.path.splitdrive(s)
if sys.version_info < (2, 7) and not drive_or_unc:
drive_or_unc, _ = os.path.splitunc(s)
norm_path = os.path.normpath(remove_start(s, drive_or_unc)).split(os.path.sep)
if drive_or_unc:
[utils] Add sanitize_path
2015-03-08 15:55:22 +01:00
norm_path.pop(0)
sanitized_path = [
Fix "invalid escape sequences" error on Python 3.6
2017-01-02 13:08:07 +01:00
path_part if path_part in ['.', '..'] else re.sub(r'(?:[/<>:"\|\\?\*]|[\s.]$)', '#', path_part)
[utils] Add sanitize_path
2015-03-08 15:55:22 +01:00
for path_part in norm_path]
[utils] Fix splitunc deprecation warning
2015-04-16 18:12:38 +02:00
if drive_or_unc:
sanitized_path.insert(0, drive_or_unc + os.path.sep)
[utils] Add sanitize_path
2015-03-08 15:55:22 +01:00
return os.path.join(*sanitized_path)
[utils] Extract sanitize_url routine
2016-03-26 14:33:57 +01:00
def sanitize_url(url):
[utils] Fixup some common URL's typos in sanitize_url (closes #15649)
2018-02-19 16:50:23 +01:00
# Prepend protocol-less URLs with `http:` scheme in order to mitigate
# the number of unwanted failures due to missing protocol
if url.startswith('//'):
return 'http:%s' % url
# Fix some common typos seen so far
COMMON_TYPOS = (
Start moving to ytdl-org
2019-03-09 13:14:41 +01:00
# https://github.com/ytdl-org/youtube-dl/issues/15649
[utils] Fixup some common URL's typos in sanitize_url (closes #15649)
2018-02-19 16:50:23 +01:00
(r'^httpss://', r'https://'),
# https://bx1.be/lives/direct-tv/
(r'^rmtp([es]?)://', r'rtmp\1://'),
)
for mistake, fixup in COMMON_TYPOS:
if re.match(mistake, url):
return re.sub(mistake, fixup, url)
Escape URLs in `sanitized_Request`, not `sanitize_url` d2558234cf5dd12d6896eed5427b7dcdb3ab7b5a added escaping of URLs while sanitizing. However, `sanitize_url` may not always receive an actual URL. Eg: When using `youtube-dl "search query" --default-search ytsearch`, `search query` gets escaped to `search%20query` before being prefixed with `ytsearch:` which is not the intended behavior. So the escaping is moved to `sanitized_Request` instead.
2021-06-01 14:35:41 +02:00
return url
[utils] Extract sanitize_url routine
2016-03-26 14:33:57 +01:00
Rename compat_urllib_request_Request to sanitized_Request and move to utils
2015-11-20 15:33:49 +01:00
def sanitized_Request(url, *args, **kwargs):
Escape URLs in `sanitized_Request`, not `sanitize_url` d2558234cf5dd12d6896eed5427b7dcdb3ab7b5a added escaping of URLs while sanitizing. However, `sanitize_url` may not always receive an actual URL. Eg: When using `youtube-dl "search query" --default-search ytsearch`, `search query` gets escaped to `search%20query` before being prefixed with `ytsearch:` which is not the intended behavior. So the escaping is moved to `sanitized_Request` instead.
2021-06-01 14:35:41 +02:00
return compat_urllib_request.Request(escape_url(sanitize_url(url)), *args, **kwargs)
Rename compat_urllib_request_Request to sanitized_Request and move to utils
2015-11-20 15:33:49 +01:00
[utils] Introduce expand_path
2017-03-25 20:30:10 +01:00
def expand_path(s):
"""Expand shell variables and ~"""
return os.path.expandvars(compat_expanduser(s))
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
def orderedSet(iterable):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
""" Remove all duplicates from the input iterable """
res = []
for el in iterable:
if el not in res:
res.append(el)
return res
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
[instagram] Fix info_dict key name
2014-03-24 01:40:09 +01:00
[utils] Decode HTML5 entities Used in test_Vporn_1. Also related to #9270
2016-06-10 09:11:55 +02:00
def _htmlentity_transform(entity_with_semicolon):
[utils] Modernize tests
2014-08-27 19:11:45 +02:00
"""Transforms an HTML entity to a character."""
[utils] Decode HTML5 entities Used in test_Vporn_1. Also related to #9270
2016-06-10 09:11:55 +02:00
entity = entity_with_semicolon[:-1]
[utils] Modernize tests
2014-08-27 19:11:45 +02:00
# Known non-numeric HTML entity
if entity in compat_html_entities.name2codepoint:
return compat_chr(compat_html_entities.name2codepoint[entity])
[utils] Decode HTML5 entities Used in test_Vporn_1. Also related to #9270
2016-06-10 09:11:55 +02:00
# TODO: HTML5 allows entities without a semicolon. For example,
# '&Eacuteric' should be decoded as 'Éric'.
if entity_with_semicolon in compat_html_entities_html5:
return compat_html_entities_html5[entity_with_semicolon]
[utils] Escape all HTML entities written in hexadecimal form
2015-03-26 16:15:27 +01:00
mobj = re.match(r'#(x[0-9a-fA-F]+|[0-9]+)', entity)
[utils] Modernize tests
2014-08-27 19:11:45 +02:00
if mobj is not None:
numstr = mobj.group(1)
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
if numstr.startswith('x'):
[utils] Modernize tests
2014-08-27 19:11:45 +02:00
base = 16
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
numstr = '0%s' % numstr
[utils] Modernize tests
2014-08-27 19:11:45 +02:00
else:
base = 10
Start moving to ytdl-org
2019-03-09 13:14:41 +01:00
# See https://github.com/ytdl-org/youtube-dl/issues/7518
[utils] Skip invalid/non HTML entities (Closes #7518)
2015-11-16 15:20:16 +01:00
try:
return compat_chr(int(numstr, base))
except ValueError:
pass
[utils] Modernize tests
2014-08-27 19:11:45 +02:00
# Unknown entity in name, return its literal representation
[utils] Style
2015-11-16 15:24:09 +01:00
return '&%s;' % entity
[utils] Modernize tests
2014-08-27 19:11:45 +02:00
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
def unescapeHTML(s):
[instagram] Fix info_dict key name
2014-03-24 01:40:09 +01:00
if s is None:
return None
assert type(s) == compat_str
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
[utils] Modernize tests
2014-08-27 19:11:45 +02:00
return re.sub(
[utils] Fix unescapeHTML for misformed string like "&a&quot;" (#13935)
2017-08-19 15:40:53 +02:00
r'&([^&;]+;)', lambda m: _htmlentity_transform(m.group(1)), s)
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Fix/work around Windows encoding issues (Fixes #2095)
2014-01-05 03:07:55 +01:00
[utils, etc] Kill child processes when yt-dl is killed * derived from PR #26592, closes #26592 Authored by: Unrud
2021-01-09 13:26:12 +01:00
def process_communicate_or_kill(p, *args, **kwargs):
try:
return p.communicate(*args, **kwargs)
except BaseException: # Including KeyboardInterrupt
p.kill()
p.wait()
raise
[utils] Add `get_subprocess_encoding` and filename/argument decode counterparts
2015-04-26 00:29:41 +02:00
def get_subprocess_encoding():
if sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
# For subprocess calls, encode with locale encoding
# Refer to http://stackoverflow.com/a/9951851/35070
encoding = preferredencoding()
else:
encoding = sys.getfilesystemencoding()
if encoding is None:
encoding = 'utf-8'
return encoding
Fix/work around Windows encoding issues (Fixes #2095)
2014-01-05 03:07:55 +01:00
def encodeFilename(s, for_subprocess=False):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""
@param s The name of the file
"""
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Fix/work around Windows encoding issues (Fixes #2095)
2014-01-05 03:07:55 +01:00
assert type(s) == compat_str
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
# Python 3 has a Unicode API
if sys.version_info >= (3, 0):
return s
Woooohooo! python3 youtube_dl BaW_jenozKc -t works!
2012-11-28 00:56:20 +01:00
[utils] Add `get_subprocess_encoding` and filename/argument decode counterparts
2015-04-26 00:29:41 +02:00
# Pass '' directly to use Unicode APIs on Windows 2000 and up
# (Detecting Windows NT 4 is tricky because 'major >= 4' would
# match Windows 9x series as well. Besides, NT 4 is obsolete.)
if not for_subprocess and sys.platform == 'win32' and sys.getwindowsversion()[0] >= 5:
return s
[utils] Jython support - handle filenames correctly Now test:youtube downloads
2016-03-03 11:47:54 +01:00
# Jython assumes filenames are Unicode strings though reported as Python 2.x compatible
if sys.platform.startswith('java'):
return s
[utils] Add `get_subprocess_encoding` and filename/argument decode counterparts
2015-04-26 00:29:41 +02:00
return s.encode(get_subprocess_encoding(), 'ignore')
def decodeFilename(b, for_subprocess=False):
if sys.version_info >= (3, 0):
return b
if not isinstance(b, bytes):
return b
return b.decode(get_subprocess_encoding(), 'ignore')
Fix/work around Windows encoding issues (Fixes #2095)
2014-01-05 03:07:55 +01:00
[ffmpeg] Correct argument encoding on Windows with Python 2.x Fixes #2924
2014-05-16 15:47:54 +02:00
def encodeArgument(s):
if not isinstance(s, compat_str):
# Legacy code that uses byte strings
# Uncomment the following line after fixing all post processors
Improve code style
2014-12-17 00:06:41 +01:00
# assert False, 'Internal error: %r should be of type %r, is %r' % (s, compat_str, type(s))
[ffmpeg] Correct argument encoding on Windows with Python 2.x Fixes #2924
2014-05-16 15:47:54 +02:00
s = s.decode('ascii')
return encodeFilename(s, True)
[utils] Add `get_subprocess_encoding` and filename/argument decode counterparts
2015-04-26 00:29:41 +02:00
def decodeArgument(b):
return decodeFilename(b, True)
Fix --match-title and --reject-title decoding (Closes #690)
2013-02-21 17:09:39 +01:00
def decodeOption(optval):
if optval is None:
return optval
if isinstance(optval, bytes):
optval = optval.decode(preferredencoding())
assert isinstance(optval, compat_str)
return optval
ExtractorError for errors during extraction
2013-01-01 20:27:53 +01:00
PEP8 applied
2014-11-23 20:41:03 +01:00
twitch.tv chapters (#810): print out start and end time
2013-05-04 12:02:18 +02:00
def formatSeconds(secs):
if secs > 3600:
return '%d:%02d:%02d' % (secs // 3600, (secs % 3600) // 60, secs % 60)
elif secs > 60:
return '%d:%02d' % (secs // 60, secs % 60)
else:
return '%d' % secs
Add new --print-traffic option
2013-12-29 15:28:32 +01:00
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
def make_HTTPS_handler(params, **kwargs):
[utils] Enable ALPN in HTTPS to satisfy broken servers See https://github.com/yt-dlp/yt-dlp/issues/3878
2022-05-28 14:52:51 +02:00
# https://www.rfc-editor.org/info/rfc7301
ALPN_PROTOCOLS = ['http/1.1']
def set_alpn_protocols(ctx):
# From https://github.com/yt-dlp/yt-dlp/commit/2c6dcb65fb612fc5bc5c61937bf438d3c473d8d0
# Thanks @coletdjnz
# Some servers may (wrongly) reject requests if ALPN extension is not sent. See:
# https://github.com/python/cpython/issues/85140
# https://github.com/yt-dlp/yt-dlp/issues/3878
try:
ctx.set_alpn_protocols(ALPN_PROTOCOLS)
except (AttributeError, NotImplementedError):
# Python < 2.7.10, not ssl.HAS_ALPN
pass
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
opts_no_check_certificate = params.get('nocheckcertificate', False)
[utils] make_HTTPS_handler: Use ssl.create_default_context in Python 2.7.9 The new features in the ssl module have been backported from 3.4, see https://docs.python.org/dev/whatsnew/2.7.html#pep-466-network-security-enhancements-for-python-2-7
2014-12-12 23:27:25 +01:00
if hasattr(ssl, 'create_default_context'): # Python >= 3.4 or 2.7.9
[ssl] Correct connect creation We want to authenticate the server, see https://docs.python.org/dev/library/ssl.html#ssl.Purpose.SERVER_AUTH .
2015-01-15 02:06:48 +01:00
context = ssl.create_default_context(ssl.Purpose.SERVER_AUTH)
[utils] Enable ALPN in HTTPS to satisfy broken servers See https://github.com/yt-dlp/yt-dlp/issues/3878
2022-05-28 14:52:51 +02:00
set_alpn_protocols(context)
[utils] make_HTTPS_handler: Use ssl.create_default_context in Python 2.7.9 The new features in the ssl module have been backported from 3.4, see https://docs.python.org/dev/whatsnew/2.7.html#pep-466-network-security-enhancements-for-python-2-7
2014-12-12 23:27:25 +01:00
if opts_no_check_certificate:
[ssl] Correct connect creation We want to authenticate the server, see https://docs.python.org/dev/library/ssl.html#ssl.Purpose.SERVER_AUTH .
2015-01-15 02:06:48 +01:00
context.check_hostname = False
[utils] make_HTTPS_handler: Use ssl.create_default_context in Python 2.7.9 The new features in the ssl module have been backported from 3.4, see https://docs.python.org/dev/whatsnew/2.7.html#pep-466-network-security-enhancements-for-python-2-7
2014-12-12 23:27:25 +01:00
context.verify_mode = ssl.CERT_NONE
[utils] Enable ALPN in HTTPS to satisfy broken servers See https://github.com/yt-dlp/yt-dlp/issues/3878
2022-05-28 14:52:51 +02:00
[utils] Make ssl work on Python 2.7.8
2014-12-13 23:27:21 +01:00
try:
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
[utils] Make ssl work on Python 2.7.8
2014-12-13 23:27:21 +01:00
except TypeError:
# Python 2.7.8
# (create_default_context present but HTTPSHandler has no context=)
pass
if sys.version_info < (3, 2):
[utils] Simplify HTTPS socket creation We were duplicating (bad) code and doing crazy things with SSL. Just use TLSv1 across the board, and do with one implementation of HTTPSConnection.connect. Fixes #4696.
2015-01-23 11:15:18 +01:00
return YoutubeDLHTTPSHandler(params, **kwargs)
[utils] Default SSL to TLS. (Fixes #3727) On 2.x, we now try TLS first, and fall back to the compat 23 (basically anything) afterwards. On 3.4+, we now use the proper function so that we get all the latest security configurations. We allow SSLv3 though for the time being, since a lot of older pages use that. On 3.3, we default to SSLv23 (basically "anything, including TLS") because that has the widest compatibility.
2014-09-12 07:50:31 +02:00
else: # Python < 3.4
[utils] Simplify HTTPS socket creation We were duplicating (bad) code and doing crazy things with SSL. Just use TLSv1 across the board, and do with one implementation of HTTPSConnection.connect. Fixes #4696.
2015-01-23 11:15:18 +01:00
context = ssl.SSLContext(ssl.PROTOCOL_TLSv1)
Add --no-check-certificate (#814)
2013-05-04 12:19:02 +02:00
context.verify_mode = (ssl.CERT_NONE
Move the opener to the YoutubeDL object. This is the first step towards being able to just import youtube_dl and start using it. Apart from removing global state, this would fix problems like #1805.
2013-11-22 19:57:52 +01:00
if opts_no_check_certificate
Add --no-check-certificate (#814)
2013-05-04 12:19:02 +02:00
else ssl.CERT_REQUIRED)
Automatically load SSL certs on Windows
2013-12-08 06:54:39 +01:00
context.set_default_verify_paths()
[utils] Enable ALPN in HTTPS to satisfy broken servers See https://github.com/yt-dlp/yt-dlp/issues/3878
2022-05-28 14:52:51 +02:00
set_alpn_protocols(context)
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
return YoutubeDLHTTPSHandler(params, context=context, **kwargs)
Add --no-check-certificate (#814)
2013-05-04 12:19:02 +02:00
[utils] Improve update on error message somewhat We still may want to implement a bulletproof check for the current version, and a better place to add this message so that it works for all kind of other errors too.
2014-11-20 12:14:28 +01:00
InfoExtractor._search_regex: Suggest updating when the regex is not found (suggested in #5442) Reuse the same message from ExtractorError
2015-04-17 14:55:24 +02:00
def bug_reports_message():
if ytdl_is_updateable():
update_cmd = 'type youtube-dl -U to update'
else:
update_cmd = 'see https://yt-dl.org/update on how to update'
msg = '; please report this issue on https://yt-dl.org/bug .'
msg += ' Make sure you are using the latest version; %s.' % update_cmd
msg += ' Be sure to call youtube-dl with the --verbose flag and include its complete output.'
return msg
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
class YoutubeDLError(Exception):
"""Base exception for YoutubeDL errors."""
pass
class ExtractorError(YoutubeDLError):
ExtractorError for errors during extraction
2013-01-01 20:27:53 +01:00
"""Error during info extraction."""
PEP8 applied
2014-11-23 20:41:03 +01:00
[youtube] Include video Id in common error message (Fixes #2786)
2014-04-21 20:34:03 +02:00
def __init__(self, msg, tb=None, expected=False, cause=None, video_id=None):
Do not show bug report for errors that are to be expected (Closes #973)
2013-07-02 08:40:21 +02:00
""" tb, if given, is the original traceback (so that it can be printed out).
If expected is set, this is a normal error message and most likely not a bug in youtube-dl.
"""
if sys.exc_info()[0] in (compat_urllib_error.URLError, socket.timeout, UnavailableVideoError):
expected = True
[youtube] Include video Id in common error message (Fixes #2786)
2014-04-21 20:34:03 +02:00
if video_id is not None:
msg = video_id + ': ' + msg
[utils] Fix js_to_json
2014-09-30 07:56:24 +02:00
if cause:
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
msg += ' (caused by %r)' % cause
Do not show bug report for errors that are to be expected (Closes #973)
2013-07-02 08:40:21 +02:00
if not expected:
InfoExtractor._search_regex: Suggest updating when the regex is not found (suggested in #5442) Reuse the same message from ExtractorError
2015-04-17 14:55:24 +02:00
msg += bug_reports_message()
ExtractorError for errors during extraction
2013-01-01 20:27:53 +01:00
super(ExtractorError, self).__init__(msg)
do not ask the user to report network errors
2013-06-09 11:55:08 +02:00
ExtractorError for errors during extraction
2013-01-01 20:27:53 +01:00
self.traceback = tb
Bubble up all the stack of exceptions and retry download tests on timeout errors
2013-03-09 10:05:43 +01:00
self.exc_info = sys.exc_info() # preserve original exception
[addanime] improve
2013-08-28 04:25:38 +02:00
self.cause = cause
[youtube] Include video Id in common error message (Fixes #2786)
2014-04-21 20:34:03 +02:00
self.video_id = video_id
ExtractorError for errors during extraction
2013-01-01 20:27:53 +01:00
Make ExtractorError usable for other causes
2013-01-03 15:39:55 +01:00
def format_traceback(self):
if self.traceback is None:
return None
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
return ''.join(traceback.format_tb(self.traceback))
Make ExtractorError usable for other causes
2013-01-03 15:39:55 +01:00
ExtractorError for errors during extraction
2013-01-01 20:27:53 +01:00
Add documentation about supported sites (Fixes #4503)
2014-12-30 19:35:35 +01:00
class UnsupportedError(ExtractorError):
def __init__(self, url):
super(UnsupportedError, self).__init__(
'Unsupported URL: %s' % url, expected=True)
self.url = url
[vimeo] Fix pro videos and player.vimeo.com urls The old process can still be used for those videos. Added RegexNotFoundError, which is raised by _search_regex if it can't extract the info.
2013-10-23 14:38:03 +02:00
class RegexNotFoundError(ExtractorError):
"""Error when a regex didn't match"""
pass
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
class GeoRestrictedError(ExtractorError):
"""Geographic restriction Error exception.
This exception may be thrown when a video is not available from your
geographic location due to geographic restrictions imposed by a website.
"""
def __init__(self, msg, countries=None):
super(GeoRestrictedError, self).__init__(msg, expected=True)
self.msg = msg
self.countries = countries
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
class DownloadError(YoutubeDLError):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Download Error exception.
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
This exception may be thrown by FileDownloader objects if they are not
configured to continue on errors. They will contain the appropriate
error message.
"""
PEP8 applied
2014-11-23 20:41:03 +01:00
Bubble up all the stack of exceptions and retry download tests on timeout errors
2013-03-09 10:05:43 +01:00
def __init__(self, msg, exc_info=None):
""" exc_info, if given, is the original exception that caused the trouble (as returned by sys.exc_info()). """
super(DownloadError, self).__init__(msg)
self.exc_info = exc_info
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
class SameFileError(YoutubeDLError):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Same File exception.
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
This exception will be thrown by FileDownloader objects if they detect
multiple files would have to be downloaded to the same file on disk.
"""
pass
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
class PostProcessingError(YoutubeDLError):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Post Processing exception.
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
This exception may be raised by PostProcessor's .run() method to
indicate an error in the postprocessing task.
"""
PEP8 applied
2014-11-23 20:41:03 +01:00
--recode-video option (Closes #18)
2013-01-12 15:07:59 +01:00
def __init__(self, msg):
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
super(PostProcessingError, self).__init__(msg)
--recode-video option (Closes #18)
2013-01-12 15:07:59 +01:00
self.msg = msg
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
PEP8 applied
2014-11-23 20:41:03 +01:00
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
class MaxDownloadsReached(YoutubeDLError):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
""" --max-downloads limit has been reached. """
pass
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
class UnavailableVideoError(YoutubeDLError):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Unavailable Format exception.
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
This exception will be thrown when a video is requested
in a format that is not available for that video.
"""
pass
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
class ContentTooShortError(YoutubeDLError):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Content Too Short exception.
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
This exception may be raised by FileDownloader objects when a file they
download is too small for what the server announced first, indicating
the connection was probably interrupted.
"""
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
def __init__(self, downloaded, expected):
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
super(ContentTooShortError, self).__init__(
'Downloaded {0} bytes, expected {1} bytes'.format(downloaded, expected)
)
Remove redundant (and wrong) class parameters
2015-07-26 16:37:51 +02:00
# Both in bytes
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
self.downloaded = downloaded
self.expected = expected
Split code as a package, compiled into an executable zip
2012-03-25 03:07:37 +02:00
PEP8 applied
2014-11-23 20:41:03 +01:00
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
class XAttrMetadataError(YoutubeDLError):
Move write_xattr to utils.py There are some other places that use xattr functions. It's better to move it to a common place so that others can use it.
2016-09-29 18:28:32 +02:00
def __init__(self, code=None, msg='Unknown error'):
super(XAttrMetadataError, self).__init__(msg)
self.code = code
[utils] Fix xattr error handling
2016-10-01 21:03:41 +02:00
self.msg = msg
Move write_xattr to utils.py There are some other places that use xattr functions. It's better to move it to a common place so that others can use it.
2016-09-29 18:28:32 +02:00
# Parsing code and msg
Fix W504 and disable W503 (closes #20863)
2019-05-10 22:56:22 +02:00
if (self.code in (errno.ENOSPC, errno.EDQUOT)
Fix typos (#27084) * spelling: authorization Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: brightcove Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: creation Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exceeded Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exception Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extension Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extracting Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extraction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: frontline Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: improve Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: length Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: listsubtitles Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: multimedia Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: obfuscated Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: partitioning Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlist Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlists Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: restriction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: services Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: split Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: srmediathek Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: support Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: thumbnail Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: verification Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: whitespaces Signed-off-by: Josh Soref <jsoref@users.noreply.github.com>
2020-11-21 16:00:05 +01:00
or 'No space left' in self.msg or 'Disk quota exceeded' in self.msg):
Move write_xattr to utils.py There are some other places that use xattr functions. It's better to move it to a common place so that others can use it.
2016-09-29 18:28:32 +02:00
self.reason = 'NO_SPACE'
elif self.code == errno.E2BIG or 'Argument list too long' in self.msg:
self.reason = 'VALUE_TOO_LONG'
else:
self.reason = 'NOT_SUPPORTED'
[utils] Introduce YoutubeDLError base class for all youtube-dl exceptions
2016-10-17 13:38:37 +02:00
class XAttrUnavailableError(YoutubeDLError):
Move write_xattr to utils.py There are some other places that use xattr functions. It's better to move it to a common place so that others can use it.
2016-09-29 18:28:32 +02:00
pass
[utils] Fix call to _create_http_connection Avoid confusion over args/kwargs.
2015-01-10 20:05:28 +01:00
def _create_http_connection(ydl_handler, http_class, is_https, *args, **kwargs):
[utils] Strict HTTP responses (Closes #6727)
2015-09-01 22:16:04 +02:00
# Working around python 2 bug (see http://bugs.python.org/issue17849) by limiting
# expected HTTP responses to meet HTTP/1.0 or later (see also
Start moving to ytdl-org
2019-03-09 13:14:41 +01:00
# https://github.com/ytdl-org/youtube-dl/issues/6727)
[utils] Strict HTTP responses (Closes #6727)
2015-09-01 22:16:04 +02:00
if sys.version_info < (3, 0):
Add support for IronPython
2018-01-27 21:04:39 +01:00
kwargs['strict'] = True
hc = http_class(*args, **compat_kwargs(kwargs))
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
source_address = ydl_handler._params.get('source_address')
[utils] Skip remote IP addresses non matching to source address' IP version (closes #13422)
2018-03-17 01:11:47 +01:00
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
if source_address is not None:
[utils] Skip remote IP addresses non matching to source address' IP version (closes #13422)
2018-03-17 01:11:47 +01:00
# This is to workaround _create_connection() from socket where it will try all
# address data from getaddrinfo() including IPv6. This filters the result from
# getaddrinfo() based on the source_address value.
# This is based on the cpython socket.create_connection() function.
# https://github.com/python/cpython/blob/master/Lib/socket.py#L691
def _create_connection(address, timeout=socket._GLOBAL_DEFAULT_TIMEOUT, source_address=None):
host, port = address
err = None
addrs = socket.getaddrinfo(host, port, 0, socket.SOCK_STREAM)
[utils] Improve remote address skipping and add support for python 2.6 (closes #17362)
2018-08-28 20:17:21 +02:00
af = socket.AF_INET if '.' in source_address[0] else socket.AF_INET6
ip_addrs = [addr for addr in addrs if addr[0] == af]
if addrs and not ip_addrs:
ip_version = 'v4' if af == socket.AF_INET else 'v6'
raise socket.error(
"No remote IP%s addresses available for connect, can't use '%s' as source address"
% (ip_version, source_address[0]))
[utils] Skip remote IP addresses non matching to source address' IP version (closes #13422)
2018-03-17 01:11:47 +01:00
for res in ip_addrs:
af, socktype, proto, canonname, sa = res
sock = None
try:
sock = socket.socket(af, socktype, proto)
if timeout is not socket._GLOBAL_DEFAULT_TIMEOUT:
sock.settimeout(timeout)
sock.bind(source_address)
sock.connect(sa)
err = None # Explicitly break reference cycle
return sock
except socket.error as _:
err = _
if sock is not None:
sock.close()
if err is not None:
raise err
else:
[utils] Improve remote address skipping and add support for python 2.6 (closes #17362)
2018-08-28 20:17:21 +02:00
raise socket.error('getaddrinfo returns an empty list')
if hasattr(hc, '_create_connection'):
hc._create_connection = _create_connection
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
sa = (source_address, 0)
if hasattr(hc, 'source_address'): # Python 2.7+
hc.source_address = sa
else: # Python 2.6
def _hc_connect(self, *args, **kwargs):
[utils] Improve remote address skipping and add support for python 2.6 (closes #17362)
2018-08-28 20:17:21 +02:00
sock = _create_connection(
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
(self.host, self.port), self.timeout, sa)
if is_https:
[utils] Simplify HTTPS socket creation We were duplicating (bad) code and doing crazy things with SSL. Just use TLSv1 across the board, and do with one implementation of HTTPSConnection.connect. Fixes #4696.
2015-01-23 11:15:18 +01:00
self.sock = ssl.wrap_socket(
sock, self.key_file, self.cert_file,
ssl_version=ssl.PROTOCOL_TLSv1)
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
else:
self.sock = sock
hc.connect = functools.partial(_hc_connect, hc)
return hc
[utils] Separate codes for handling Youtubedl-* headers
2015-11-29 05:42:50 +01:00
def handle_youtubedl_headers(headers):
[utils] Refactor handle_youtubedl_headers for future extension
2015-11-29 05:58:29 +01:00
filtered_headers = headers
if 'Youtubedl-no-compression' in filtered_headers:
filtered_headers = dict((k, v) for k, v in filtered_headers.items() if k.lower() != 'accept-encoding')
[utils] Separate codes for handling Youtubedl-* headers
2015-11-29 05:42:50 +01:00
del filtered_headers['Youtubedl-no-compression']
[utils] Refactor handle_youtubedl_headers for future extension
2015-11-29 05:58:29 +01:00
return filtered_headers
[utils] Separate codes for handling Youtubedl-* headers
2015-11-29 05:42:50 +01:00
Revert "Install our own HTTPS handler as well (#1309)" This reverts commit 36399e85765a6a04fd84126264af75382fcfd1f6 and fixes #1322.
2013-08-27 23:15:01 +02:00
class YoutubeDLHandler(compat_urllib_request.HTTPHandler):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
"""Handler for HTTP requests and responses.
This class, when installed with an OpenerDirector, automatically adds
the standard headers to every HTTP request and handles gzipped and
deflated responses from web servers. If compression is to be avoided in
a particular request, the original request in the program code only has
[utils] Correct docstring of YoutubeDLHandler
2015-11-29 05:46:04 +01:00
to include the HTTP header "Youtubedl-no-compression", which will be
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
removed before making the real request.
Part of this code was copied from:
http://techknack.net/python-urllib2-handlers/
Andrew Rowls, the author of that code, agreed to release it to the
public domain.
"""
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
def __init__(self, params, *args, **kwargs):
compat_urllib_request.HTTPHandler.__init__(self, *args, **kwargs)
self._params = params
def http_open(self, req):
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
conn_class = compat_http_client.HTTPConnection
socks_proxy = req.headers.get('Ytdl-socks-proxy')
if socks_proxy:
conn_class = make_socks_conn_class(conn_class, socks_proxy)
del req.headers['Ytdl-socks-proxy']
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
return self.do_open(functools.partial(
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
_create_http_connection, self, conn_class, False),
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
req)
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
@staticmethod
def deflate(data):
try:
return zlib.decompress(data, -zlib.MAX_WBITS)
except zlib.error:
return zlib.decompress(data)
Revert "Install our own HTTPS handler as well (#1309)" This reverts commit 36399e85765a6a04fd84126264af75382fcfd1f6 and fixes #1322.
2013-08-27 23:15:01 +02:00
def http_request(self, req):
[YoutubeDL:utils] Move percent encode non-ASCII URLs workaround to http_request and simplify (Closes #6457)
2015-08-06 18:01:01 +02:00
# According to RFC 3986, URLs can not contain non-ASCII characters, however this is not
# always respected by websites, some tend to give out URLs with non percent-encoded
# non-ASCII characters (see telemb.py, ard.py [#3412])
# urllib chokes on URLs with non-ASCII characters (see http://bugs.python.org/issue3991)
# To work around aforementioned issue we will replace request's original URL with
# percent-encoded one
# Since redirects are also affected (e.g. http://www.southpark.de/alle-episoden/s18e09)
# the code of this workaround has been moved here from YoutubeDL.urlopen()
url = req.get_full_url()
url_escaped = escape_url(url)
# Substitute URL if any change after escaping
if url != url_escaped:
[utils] Use update_Request in http_request
2016-03-31 18:55:49 +02:00
req = update_Request(req, url=url_escaped)
[YoutubeDL:utils] Move percent encode non-ASCII URLs workaround to http_request and simplify (Closes #6457)
2015-08-06 18:01:01 +02:00
[utils] Let request headers override standard headers What was I thinking when writing this?
2014-08-26 11:51:48 +02:00
for h, v in std_headers.items():
[utils] Prevent override of custom headers. The dict of headers of request objects in urllib has its keys always capitalized. This causes the lookup to fail and overwrite the header. If for example a Extractor tries to add a "User-Agent" header the internal representation in the request object is "User-agent". The header is therefore clobbered by the "User-Agent" in std_headers, because the strings are not equal.
2015-01-12 22:26:20 +01:00
# Capitalize is needed because of Python bug 2275: http://bugs.python.org/issue2275
# The dict keys are capitalized because of this bug by urllib
if h.capitalize() not in req.headers:
[utils] Let request headers override standard headers What was I thinking when writing this?
2014-08-26 11:51:48 +02:00
req.add_header(h, v)
[utils] Separate codes for handling Youtubedl-* headers
2015-11-29 05:42:50 +01:00
req.headers = handle_youtubedl_headers(req.headers)
[utils:YoutubeDLHandler] Work around brain-dead Python 2.6 httplib In 2.6, the httplib sends fragments! Remove those (fixes generic_26 on 2.6).
2014-09-29 06:15:46 +02:00
if sys.version_info < (2, 7) and '#' in req.get_full_url():
# Python 2.6 is brain-dead when it comes to fragments
req._Request__original = req._Request__original.partition('#')[0]
req._Request__r_type = req._Request__r_type.partition('#')[0]
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
return req
Revert "Install our own HTTPS handler as well (#1309)" This reverts commit 36399e85765a6a04fd84126264af75382fcfd1f6 and fixes #1322.
2013-08-27 23:15:01 +02:00
def http_response(self, req, resp):
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
old_resp = resp
# gzip
if resp.headers.get('Content-encoding', '') == 'gzip':
Tolerate junk at the end of gzip-compressed content (#1268)
2013-08-28 11:57:13 +02:00
content = resp.read()
gz = gzip.GzipFile(fileobj=io.BytesIO(content), mode='rb')
try:
uncompressed = io.BytesIO(gz.read())
except IOError as original_ioerror:
# There may be junk add the end of the file
# See http://stackoverflow.com/q/4928560/35070 for details
for i in range(1, 1024):
try:
gz = gzip.GzipFile(fileobj=io.BytesIO(content[:-i]), mode='rb')
uncompressed = io.BytesIO(gz.read())
except IOError:
continue
break
else:
raise original_ioerror
[utils] Drop an compatibility wrapper for Python < 2.6 addinfourl.getcode is added since Python 2.6a1. As youtube-dl now requires 2.6+, this is no longer necessary. See https://github.com/python/cpython/commit/9b0d46db115c10767b240a0a64286214b50fe6ad
2017-05-27 17:05:02 +02:00
resp = compat_urllib_request.addinfourl(uncompressed, old_resp.headers, old_resp.url, old_resp.code)
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
resp.msg = old_resp.msg
[utils] Remove Content-encoding from headers after decompression With cn_verification_proxy, our http_response() is called twice, one from PerRequestProxyHandler.proxy_open() and another from normal YoutubeDL.urlopen(). As a result, for proxies honoring Accept-Encoding, the following bug occurs: $ youtube-dl -vs --cn-verification-proxy https://secure.uku.im:993 "test:letv" [debug] System config: [] [debug] User config: [] [debug] Command-line args: ['-vs', '--cn-verification-proxy', 'https://secure.uku.im:993', 'test:letv'] [debug] Encodings: locale UTF-8, fs utf-8, out UTF-8, pref UTF-8 [debug] youtube-dl version 2015.12.23 [debug] Git HEAD: 97f18fa [debug] Python version 3.5.1 - Linux-4.3.3-1-ARCH-x86_64-with-arch-Arch-Linux [debug] exe versions: ffmpeg 2.8.4, ffprobe 2.8.4, rtmpdump 2.4 [debug] Proxy map: {} [TestURL] Test URL: http://www.letv.com/ptv/vplay/22005890.html [Letv] 22005890: Downloading webpage [Letv] 22005890: Downloading playJson data ERROR: Unable to download JSON metadata: Not a gzipped file (b'{"') (caused by OSError('Not a gzipped file (b\'{"\')',)); please report this issue on https://yt-dl.org/bug . Make sure you are using the latest version; see https://yt-dl.org/update on how to update. Be sure to call youtube-dl with the --verbose flag and include its complete output. File "/home/yen/Executables/Multimedia/youtube-dl/youtube_dl/extractor/common.py", line 330, in _request_webpage return self._downloader.urlopen(url_or_request) File "/home/yen/Executables/Multimedia/youtube-dl/youtube_dl/YoutubeDL.py", line 1886, in urlopen return self._opener.open(req, timeout=self._socket_timeout) File "/usr/lib/python3.5/urllib/request.py", line 471, in open response = meth(req, response) File "/home/yen/Executables/Multimedia/youtube-dl/youtube_dl/utils.py", line 773, in http_response raise original_ioerror File "/home/yen/Executables/Multimedia/youtube-dl/youtube_dl/utils.py", line 761, in http_response uncompressed = io.BytesIO(gz.read()) File "/usr/lib/python3.5/gzip.py", line 274, in read return self._buffer.read(size) File "/usr/lib/python3.5/gzip.py", line 461, in read if not self._read_gzip_header(): File "/usr/lib/python3.5/gzip.py", line 409, in _read_gzip_header raise OSError('Not a gzipped file (%r)' % magic)
2015-12-27 18:09:18 +01:00
del resp.headers['Content-encoding']
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
# deflate
if resp.headers.get('Content-encoding', '') == 'deflate':
gz = io.BytesIO(self.deflate(resp.read()))
[utils] Drop an compatibility wrapper for Python < 2.6 addinfourl.getcode is added since Python 2.6a1. As youtube-dl now requires 2.6+, this is no longer necessary. See https://github.com/python/cpython/commit/9b0d46db115c10767b240a0a64286214b50fe6ad
2017-05-27 17:05:02 +02:00
resp = compat_urllib_request.addinfourl(gz, old_resp.headers, old_resp.url, old_resp.code)
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
resp.msg = old_resp.msg
[utils] Remove Content-encoding from headers after decompression With cn_verification_proxy, our http_response() is called twice, one from PerRequestProxyHandler.proxy_open() and another from normal YoutubeDL.urlopen(). As a result, for proxies honoring Accept-Encoding, the following bug occurs: $ youtube-dl -vs --cn-verification-proxy https://secure.uku.im:993 "test:letv" [debug] System config: [] [debug] User config: [] [debug] Command-line args: ['-vs', '--cn-verification-proxy', 'https://secure.uku.im:993', 'test:letv'] [debug] Encodings: locale UTF-8, fs utf-8, out UTF-8, pref UTF-8 [debug] youtube-dl version 2015.12.23 [debug] Git HEAD: 97f18fa [debug] Python version 3.5.1 - Linux-4.3.3-1-ARCH-x86_64-with-arch-Arch-Linux [debug] exe versions: ffmpeg 2.8.4, ffprobe 2.8.4, rtmpdump 2.4 [debug] Proxy map: {} [TestURL] Test URL: http://www.letv.com/ptv/vplay/22005890.html [Letv] 22005890: Downloading webpage [Letv] 22005890: Downloading playJson data ERROR: Unable to download JSON metadata: Not a gzipped file (b'{"') (caused by OSError('Not a gzipped file (b\'{"\')',)); please report this issue on https://yt-dl.org/bug . Make sure you are using the latest version; see https://yt-dl.org/update on how to update. Be sure to call youtube-dl with the --verbose flag and include its complete output. File "/home/yen/Executables/Multimedia/youtube-dl/youtube_dl/extractor/common.py", line 330, in _request_webpage return self._downloader.urlopen(url_or_request) File "/home/yen/Executables/Multimedia/youtube-dl/youtube_dl/YoutubeDL.py", line 1886, in urlopen return self._opener.open(req, timeout=self._socket_timeout) File "/usr/lib/python3.5/urllib/request.py", line 471, in open response = meth(req, response) File "/home/yen/Executables/Multimedia/youtube-dl/youtube_dl/utils.py", line 773, in http_response raise original_ioerror File "/home/yen/Executables/Multimedia/youtube-dl/youtube_dl/utils.py", line 761, in http_response uncompressed = io.BytesIO(gz.read()) File "/usr/lib/python3.5/gzip.py", line 274, in read return self._buffer.read(size) File "/usr/lib/python3.5/gzip.py", line 461, in read if not self._read_gzip_header(): File "/usr/lib/python3.5/gzip.py", line 409, in _read_gzip_header raise OSError('Not a gzipped file (%r)' % magic)
2015-12-27 18:09:18 +01:00
del resp.headers['Content-encoding']
[utils] Add issue URL in comment for #6457
2015-09-06 02:23:44 +02:00
# Percent-encode redirect URL of Location HTTP header to satisfy RFC 3986 (see
Start moving to ytdl-org
2019-03-09 13:14:41 +01:00
# https://github.com/ytdl-org/youtube-dl/issues/6457).
[utils] Percent-encode redirect URL of Location header (Closes #6457)
2015-08-06 21:26:40 +02:00
if 300 <= resp.code < 400:
location = resp.headers.get('Location')
if location:
# As of RFC 2616 default charset is iso-8859-1 that is respected by python 3
if sys.version_info >= (3, 0):
location = location.encode('iso-8859-1').decode('utf-8')
[utils] Always decode Location header escape_url is broken for bytes-like objects
2016-05-26 11:22:40 +02:00
else:
location = location.decode('utf-8')
[utils] Percent-encode redirect URL of Location header (Closes #6457)
2015-08-06 21:26:40 +02:00
location_escaped = escape_url(location)
if location != location_escaped:
del resp.headers['Location']
[utils] Use bytes-like objects as header values on Python 2
2016-05-29 13:25:25 +02:00
if sys.version_info < (3, 0):
location_escaped = location_escaped.encode('utf-8')
[utils] Percent-encode redirect URL of Location header (Closes #6457)
2015-08-06 21:26:40 +02:00
resp.headers['Location'] = location_escaped
Convert all tabs to 4 spaces (PEP8)
2012-11-28 02:04:46 +01:00
return resp
Let YoutubeDLHandler (transparent gzip) handle HTTPS URLs as well (Needed for #579)
2012-12-07 00:39:44 +01:00
Revert "Install our own HTTPS handler as well (#1309)" This reverts commit 36399e85765a6a04fd84126264af75382fcfd1f6 and fixes #1322.
2013-08-27 23:15:01 +02:00
https_request = http_request
https_response = http_response
Fix some IEs that didn't return the uploade_date in the YYYYMMDD format Create a function unified_strdate in utils.py to fix these problems
2013-04-27 15:14:20 +02:00
[elpais] Add extractor
2014-02-06 11:29:46 +01:00
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
def make_socks_conn_class(base_class, socks_proxy):
assert issubclass(base_class, (
compat_http_client.HTTPConnection, compat_http_client.HTTPSConnection))
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
url_components = compat_urllib_parse.urlparse(socks_proxy)
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
if url_components.scheme.lower() == 'socks5':
socks_type = ProxyType.SOCKS5
elif url_components.scheme.lower() in ('socks', 'socks4'):
socks_type = ProxyType.SOCKS4
[utils] Register SOCKS protocols in urllib and support SOCKS4A
2016-05-03 09:15:32 +02:00
elif url_components.scheme.lower() == 'socks4a':
socks_type = ProxyType.SOCKS4A
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
[utils] Check for None values in SOCKS proxy Originally reported at https://github.com/rg3/youtube-dl/pull/9287#issuecomment-219617864
2016-05-17 08:38:15 +02:00
def unquote_if_non_empty(s):
if not s:
return s
return compat_urllib_parse_unquote_plus(s)
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
proxy_args = (
socks_type,
url_components.hostname, url_components.port or 1080,
True, # Remote DNS
[utils] Check for None values in SOCKS proxy Originally reported at https://github.com/rg3/youtube-dl/pull/9287#issuecomment-219617864
2016-05-17 08:38:15 +02:00
unquote_if_non_empty(url_components.username),
unquote_if_non_empty(url_components.password),
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
)
class SocksConnection(base_class):
def connect(self):
self.sock = sockssocket()
self.sock.setproxy(*proxy_args)
if type(self.timeout) in (int, float):
self.sock.settimeout(self.timeout)
self.sock.connect((self.host, self.port))
if isinstance(self, compat_http_client.HTTPSConnection):
if hasattr(self, '_context'): # Python > 2.6
self.sock = self._context.wrap_socket(
self.sock, server_hostname=self.host)
else:
self.sock = ssl.wrap_socket(self.sock)
return SocksConnection
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
class YoutubeDLHTTPSHandler(compat_urllib_request.HTTPSHandler):
def __init__(self, params, https_conn_class=None, *args, **kwargs):
compat_urllib_request.HTTPSHandler.__init__(self, *args, **kwargs)
self._https_conn_class = https_conn_class or compat_http_client.HTTPSConnection
self._params = params
def https_open(self, req):
[utils] YoutubeDLHTTPSHandler.https_open: pass all required arguments to do_open With this change the '--no-check-certificate' works again (#4807).
2015-01-29 13:37:17 +01:00
kwargs = {}
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
conn_class = self._https_conn_class
[utils] YoutubeDLHTTPSHandler.https_open: pass all required arguments to do_open With this change the '--no-check-certificate' works again (#4807).
2015-01-29 13:37:17 +01:00
if hasattr(self, '_context'): # python > 2.6
kwargs['context'] = self._context
if hasattr(self, '_check_hostname'): # python 3.x
kwargs['check_hostname'] = self._check_hostname
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
socks_proxy = req.headers.get('Ytdl-socks-proxy')
if socks_proxy:
conn_class = make_socks_conn_class(conn_class, socks_proxy)
del req.headers['Ytdl-socks-proxy']
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
return self.do_open(functools.partial(
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
_create_http_connection, self, conn_class, True),
[utils] YoutubeDLHTTPSHandler.https_open: pass all required arguments to do_open With this change the '--no-check-certificate' works again (#4807).
2015-01-29 13:37:17 +01:00
req, **kwargs)
Add new option --source-address Closes #3618, fixes #721, fixes #2481, fixes #4551, closes #1020.
2015-01-10 19:55:36 +01:00
[YoutubeDL] Introduce YoutubeDLCookieJar and clarify the rationale behind session cookies (closes #12929)
2018-12-09 00:00:32 +01:00
class YoutubeDLCookieJar(compat_cookiejar.MozillaCookieJar):
[utils] Add reference to cookie file format
2020-03-09 22:59:02 +01:00
"""
See [1] for cookie file format.
1. https://curl.haxx.se/docs/http-cookies.html
"""
[utils] strip #HttpOnly_ prefix from cookies files (#20219)
2019-03-03 13:23:59 +01:00
_HTTPONLY_PREFIX = '#HttpOnly_'
[utils] Improve cookie files support + Add support for UTF-8 in cookie files * Skip malformed cookie file entries instead of crashing (invalid entry len, invalid expires at)
2020-05-04 23:19:33 +02:00
_ENTRY_LEN = 7
_HEADER = '''# Netscape HTTP Cookie File
# This file is generated by youtube-dl. Do not edit.
'''
_CookieFileEntry = collections.namedtuple(
'CookieFileEntry',
('domain_name', 'include_subdomains', 'path', 'https_only', 'expires_at', 'name', 'value'))
[utils] strip #HttpOnly_ prefix from cookies files (#20219)
2019-03-03 13:23:59 +01:00
[YoutubeDL] Introduce YoutubeDLCookieJar and clarify the rationale behind session cookies (closes #12929)
2018-12-09 00:00:32 +01:00
def save(self, filename=None, ignore_discard=False, ignore_expires=False):
[utils] Improve cookie files support + Add support for UTF-8 in cookie files * Skip malformed cookie file entries instead of crashing (invalid entry len, invalid expires at)
2020-05-04 23:19:33 +02:00
"""
Save cookies to a file.
Most of the code is taken from CPython 3.8 and slightly adapted
to support cookie files with UTF-8 in both python 2 and 3.
"""
if filename is None:
if self.filename is not None:
filename = self.filename
else:
raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
[YoutubeDL] Introduce YoutubeDLCookieJar and clarify the rationale behind session cookies (closes #12929)
2018-12-09 00:00:32 +01:00
# Store session cookies with `expires` set to 0 instead of an empty
# string
for cookie in self:
if cookie.expires is None:
cookie.expires = 0
[utils] Improve cookie files support + Add support for UTF-8 in cookie files * Skip malformed cookie file entries instead of crashing (invalid entry len, invalid expires at)
2020-05-04 23:19:33 +02:00
with io.open(filename, 'w', encoding='utf-8') as f:
f.write(self._HEADER)
now = time.time()
for cookie in self:
if not ignore_discard and cookie.discard:
continue
if not ignore_expires and cookie.is_expired(now):
continue
if cookie.secure:
secure = 'TRUE'
else:
secure = 'FALSE'
if cookie.domain.startswith('.'):
initial_dot = 'TRUE'
else:
initial_dot = 'FALSE'
if cookie.expires is not None:
expires = compat_str(cookie.expires)
else:
expires = ''
if cookie.value is None:
# cookies.txt regards 'Set-Cookie: foo' as a cookie
# with no name, whereas http.cookiejar regards it as a
# cookie with no value.
name = ''
value = cookie.name
else:
name = cookie.name
value = cookie.value
f.write(
'\t'.join([cookie.domain, initial_dot, cookie.path,
secure, expires, name, value]) + '\n')
[YoutubeDL] Introduce YoutubeDLCookieJar and clarify the rationale behind session cookies (closes #12929)
2018-12-09 00:00:32 +01:00
def load(self, filename=None, ignore_discard=False, ignore_expires=False):
[utils] strip #HttpOnly_ prefix from cookies files (#20219)
2019-03-03 13:23:59 +01:00
"""Load cookies from a file."""
if filename is None:
if self.filename is not None:
filename = self.filename
else:
raise ValueError(compat_cookiejar.MISSING_FILENAME_TEXT)
[utils] Improve cookie files support + Add support for UTF-8 in cookie files * Skip malformed cookie file entries instead of crashing (invalid entry len, invalid expires at)
2020-05-04 23:19:33 +02:00
def prepare_line(line):
if line.startswith(self._HTTPONLY_PREFIX):
line = line[len(self._HTTPONLY_PREFIX):]
# comments and empty lines are fine
if line.startswith('#') or not line.strip():
return line
cookie_list = line.split('\t')
if len(cookie_list) != self._ENTRY_LEN:
raise compat_cookiejar.LoadError('invalid length %d' % len(cookie_list))
cookie = self._CookieFileEntry(*cookie_list)
if cookie.expires_at and not cookie.expires_at.isdigit():
raise compat_cookiejar.LoadError('invalid expires at %s' % cookie.expires_at)
return line
[utils] strip #HttpOnly_ prefix from cookies files (#20219)
2019-03-03 13:23:59 +01:00
cf = io.StringIO()
[utils] Improve cookie files support + Add support for UTF-8 in cookie files * Skip malformed cookie file entries instead of crashing (invalid entry len, invalid expires at)
2020-05-04 23:19:33 +02:00
with io.open(filename, encoding='utf-8') as f:
[utils] strip #HttpOnly_ prefix from cookies files (#20219)
2019-03-03 13:23:59 +01:00
for line in f:
[utils] Improve cookie files support + Add support for UTF-8 in cookie files * Skip malformed cookie file entries instead of crashing (invalid entry len, invalid expires at)
2020-05-04 23:19:33 +02:00
try:
cf.write(prepare_line(line))
except compat_cookiejar.LoadError as e:
write_string(
'WARNING: skipping cookie file entry due to %s: %r\n'
% (e, line), sys.stderr)
continue
[utils] strip #HttpOnly_ prefix from cookies files (#20219)
2019-03-03 13:23:59 +01:00
cf.seek(0)
self._really_load(cf, filename, ignore_discard, ignore_expires)
[YoutubeDL] Introduce YoutubeDLCookieJar and clarify the rationale behind session cookies (closes #12929)
2018-12-09 00:00:32 +01:00
# Session cookies are denoted by either `expires` field set to
# an empty string or 0. MozillaCookieJar only recognizes the former
# (see [1]). So we need force the latter to be recognized as session
# cookies on our own.
# Session cookies may be important for cookies-based authentication,
# e.g. usually, when user does not check 'Remember me' check box while
# logging in on a site, some important cookies are stored as session
# cookies so that not recognizing them will result in failed login.
# 1. https://bugs.python.org/issue17164
for cookie in self:
# Treat `expires=0` cookies as session cookies
if cookie.expires == 0:
cookie.expires = None
cookie.discard = True
[utils] Add cookie processor for cookie correction (Closes #6769)
2015-09-06 02:20:48 +02:00
class YoutubeDLCookieProcessor(compat_urllib_request.HTTPCookieProcessor):
def __init__(self, cookiejar=None):
compat_urllib_request.HTTPCookieProcessor.__init__(self, cookiejar)
def http_response(self, request, response):
# Python 2 will choke on next HTTP request in row if there are non-ASCII
# characters in Set-Cookie HTTP header of last response (see
Start moving to ytdl-org
2019-03-09 13:14:41 +01:00
# https://github.com/ytdl-org/youtube-dl/issues/6769).
[utils] Add cookie processor for cookie correction (Closes #6769)
2015-09-06 02:20:48 +02:00
# In order to at least prevent crashing we will percent encode Set-Cookie
# header before HTTPCookieProcessor starts processing it.
[utils] Comment cookie processing until result from travis and some more testing
2015-09-06 04:16:39 +02:00
# if sys.version_info < (3, 0) and response.headers:
# for set_cookie_header in ('Set-Cookie', 'Set-Cookie2'):
# set_cookie = response.headers.get(set_cookie_header)
# if set_cookie:
# set_cookie_escaped = compat_urllib_parse.quote(set_cookie, b"%/;:@&=+$,!~*'()?#[] ")
# if set_cookie != set_cookie_escaped:
# del response.headers[set_cookie_header]
# response.headers[set_cookie_header] = set_cookie_escaped
[utils] Add cookie processor for cookie correction (Closes #6769)
2015-09-06 02:20:48 +02:00
return compat_urllib_request.HTTPCookieProcessor.http_response(self, request, response)
https_request = compat_urllib_request.HTTPCookieProcessor.http_request
https_response = http_response
[YoutubeDL] Force redirect URL to unicode on python 2
2020-02-29 13:08:44 +01:00
class YoutubeDLRedirectHandler(compat_urllib_request.HTTPRedirectHandler):
[utils] Add support for support for experimental HTTP response status code 308 Permanent Redirect (refs #27877, refs #28768)
2021-04-16 22:22:13 +02:00
"""YoutubeDL redirect handler
The code is based on HTTPRedirectHandler implementation from CPython [1].
This redirect handler solves two issues:
- ensures redirect URL is always unicode under python 2
- introduces support for experimental HTTP response status code
308 Permanent Redirect [2] used by some sites [3]
1. https://github.com/python/cpython/blob/master/Lib/urllib/request.py
2. https://developer.mozilla.org/en-US/docs/Web/HTTP/Status/308
3. https://github.com/ytdl-org/youtube-dl/issues/28768
"""
http_error_301 = http_error_303 = http_error_307 = http_error_308 = compat_urllib_request.HTTPRedirectHandler.http_error_302
def redirect_request(self, req, fp, code, msg, headers, newurl):
"""Return a Request or None in response to a redirect.
This is called by the http_error_30x methods when a
redirection response is received. If a redirection should
take place, return a new Request to allow http_error_30x to
perform the redirect. Otherwise, raise HTTPError if no-one
else should try to handle this url. Return None if you can't
but another Handler might.
"""
m = req.get_method()
if (not (code in (301, 302, 303, 307, 308) and m in ("GET", "HEAD")
[utils] PEP 8
2021-04-16 22:32:04 +02:00
or code in (301, 302, 303) and m == "POST")):
[utils] Add support for support for experimental HTTP response status code 308 Permanent Redirect (refs #27877, refs #28768)
2021-04-16 22:22:13 +02:00
raise compat_HTTPError(req.full_url, code, msg, headers, fp)
# Strictly (according to RFC 2616), 301 or 302 in response to
# a POST MUST NOT cause a redirection without confirmation
# from the user (of urllib.request, in this case). In practice,
# essentially all clients do redirect in this case, so we do
# the same.
# On python 2 urlh.geturl() may sometimes return redirect URL
# as byte string instead of unicode. This workaround allows
# to force it always return unicode.
if sys.version_info[0] < 3:
newurl = compat_str(newurl)
# Be conciliant with URIs containing a space. This is mainly
# redundant with the more complete encoding done in http_error_302(),
# but it is kept for compatibility with other callers.
newurl = newurl.replace(' ', '%20')
CONTENT_HEADERS = ("content-length", "content-type")
# NB: don't use dict comprehension for python 2.6 compatibility
newheaders = dict((k, v) for k, v in req.headers.items()
[utils] PEP 8
2021-04-16 22:32:04 +02:00
if k.lower() not in CONTENT_HEADERS)
return compat_urllib_request.Request(
newurl, headers=newheaders, origin_req_host=req.origin_req_host,
unverifiable=True)
[YoutubeDL] Force redirect URL to unicode on python 2
2020-02-29 13:08:44 +01:00
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
def extract_timezone(date_str):
m = re.search(
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
r'''(?x)
^.{8,}? # >=8 char non-TZ prefix, if present
(?P<tz>Z| # just the UTC Z, or
(?:(?<=.\b\d{4}|\b\d{2}:\d\d)| # preceded by 4 digits or hh:mm or
(?<!.\b[a-zA-Z]{3}|[a-zA-Z]{4}|..\b\d\d)) # not preceded by 3 alpha word or >= 4 alpha or 2 digits
[ ]? # optional space
(?P<sign>\+|-) # +/-
(?P<hours>[0-9]{2}):?(?P<minutes>[0-9]{2}) # hh[:]mm
$)
''', date_str)
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
if not m:
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
m = re.search(r'\d{1,2}:\d{1,2}(?:\.\d+)?(?P<tz>\s*[A-Z]+)$', date_str)
timezone = TIMEZONE_NAMES.get(m and m.group('tz').strip())
if timezone is not None:
date_str = date_str[:-len(m.group('tz'))]
timezone = datetime.timedelta(hours=timezone or 0)
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
else:
date_str = date_str[:-len(m.group('tz'))]
if not m.group('sign'):
timezone = datetime.timedelta()
else:
sign = 1 if m.group('sign') == '+' else -1
timezone = datetime.timedelta(
hours=sign * int(m.group('hours')),
minutes=sign * int(m.group('minutes')))
return timezone, date_str
[camdemy] Simplify and make more robust (#4938) Do not throw errors if view count or upload date extraction fails. Dispose of re.MULTILINE, which had absolutely no effect without any ^ or $ in sight. Follow PEP8 naming conventions.
2015-02-12 08:55:06 +01:00
def parse_iso8601(date_str, delimiter='T', timezone=None):
[instagram] Fix info_dict key name
2014-03-24 01:40:09 +01:00
""" Return a UNIX timestamp from the given date """
if date_str is None:
return None
[utils] Improve parse_iso8601
2015-10-28 16:40:22 +01:00
date_str = re.sub(r'\.[0-9]+', '', date_str)
[camdemy] Simplify and make more robust (#4938) Do not throw errors if view count or upload date extraction fails. Dispose of re.MULTILINE, which had absolutely no effect without any ^ or $ in sight. Follow PEP8 naming conventions.
2015-02-12 08:55:06 +01:00
if timezone is None:
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
timezone, date_str = extract_timezone(date_str)
[utils] Improve parse_iso8601
2015-10-28 16:40:22 +01:00
try:
date_format = '%Y-%m-%d{0}%H:%M:%S'.format(delimiter)
dt = datetime.datetime.strptime(date_str, date_format) - timezone
return calendar.timegm(dt.timetuple())
except ValueError:
pass
[instagram] Fix info_dict key name
2014-03-24 01:40:09 +01:00
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
def date_formats(day_first=True):
return DATE_FORMATS_DAY_FIRST if day_first else DATE_FORMATS_MONTH_FIRST
[cinchcast] Add new extractor (Fixes #4428)
2014-12-12 02:57:36 +01:00
def unified_strdate(date_str, day_first=True):
Fix some IEs that didn't return the uploade_date in the YYYYMMDD format Create a function unified_strdate in utils.py to fix these problems
2013-04-27 15:14:20 +02:00
"""Return a string with the date in the format YYYYMMDD"""
[videolectures] (New extractor)
2014-03-21 14:38:37 +01:00
if date_str is None:
return None
Fix some IEs that didn't return the uploade_date in the YYYYMMDD format Create a function unified_strdate in utils.py to fix these problems
2013-04-27 15:14:20 +02:00
upload_date = None
PEP8 applied
2014-11-23 20:41:03 +01:00
# Replace commas
Fix #2355 (date parsing with dashes)
2014-02-09 18:09:57 +01:00
date_str = date_str.replace(',', ' ')
[cinchcast] Add new extractor (Fixes #4428)
2014-12-12 02:57:36 +01:00
# Remove AM/PM + timezone
[wsj] Add new extractor (Fixes #4854)
2015-02-03 10:58:28 +01:00
date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
_, date_str = extract_timezone(date_str)
[cinchcast] Add new extractor (Fixes #4428)
2014-12-12 02:57:36 +01:00
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
for expression in date_formats(day_first):
Fix some IEs that didn't return the uploade_date in the YYYYMMDD format Create a function unified_strdate in utils.py to fix these problems
2013-04-27 15:14:20 +02:00
try:
upload_date = datetime.datetime.strptime(date_str, expression).strftime('%Y%m%d')
[elpais] Add extractor
2014-02-06 11:29:46 +01:00
except ValueError:
Fix some IEs that didn't return the uploade_date in the YYYYMMDD format Create a function unified_strdate in utils.py to fix these problems
2013-04-27 15:14:20 +02:00
pass
Add support for direct links to a video (#1973)
2013-12-17 12:33:55 +01:00
if upload_date is None:
timetuple = email.utils.parsedate_tz(date_str)
if timetuple:
[utils] Do not fail on unknown date formats in unified_strdate
2016-05-22 04:28:41 +02:00
try:
upload_date = datetime.datetime(*timetuple[:6]).strftime('%Y%m%d')
except ValueError:
pass
[utils] unified_strdate: Return None if the date format can't be recognized (fixes #7340) This issue was introduced with ae12bc3ebb4cb377c2b4337ec255e652b36f5143, it returned 'None'.
2015-11-02 14:08:38 +01:00
if upload_date is not None:
return compat_str(upload_date)
Fix some IEs that didn't return the uploade_date in the YYYYMMDD format Create a function unified_strdate in utils.py to fix these problems
2013-04-27 15:14:20 +02:00
PEP8 applied
2014-11-23 20:41:03 +01:00
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
def unified_timestamp(date_str, day_first=True):
if date_str is None:
return None
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
date_str = re.sub(r'\s+', ' ', re.sub(
r'(?i)[,|]|(mon|tues?|wed(nes)?|thu(rs)?|fri|sat(ur)?)(day)?', '', date_str))
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
[utils] Fix unified_timestamp for formats parsed by parsedate_tz()
2016-08-05 05:41:55 +02:00
pm_delta = 12 if re.search(r'(?i)PM', date_str) else 0
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
timezone, date_str = extract_timezone(date_str)
# Remove AM/PM + timezone
date_str = re.sub(r'(?i)\s*(?:AM|PM)(?:\s+[A-Z]+)?', '', date_str)
[utils] Improve unified_timestamp Seen at http://zaq1.pl/video/xev0e
2017-04-30 16:07:30 +02:00
# Remove unrecognized timezones from ISO 8601 alike timestamps
m = re.search(r'\d{1,2}:\d{1,2}(?:\.\d+)?(?P<tz>\s*[A-Z]+)$', date_str)
if m:
date_str = date_str[:-len(m.group('tz'))]
[tennistv] Add support for tennistv.com
2018-03-14 01:28:40 +01:00
# Python only supports microseconds, so remove nanoseconds
m = re.search(r'^([0-9]{4,}-[0-9]{1,2}-[0-9]{1,2}T[0-9]{1,2}:[0-9]{1,2}:[0-9]{1,2}\.[0-9]{6})[0-9]+$', date_str)
if m:
date_str = m.group(1)
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
for expression in date_formats(day_first):
try:
[utils] Fix unified_timestamp for formats parsed by parsedate_tz()
2016-08-05 05:41:55 +02:00
dt = datetime.datetime.strptime(date_str, expression) - timezone + datetime.timedelta(hours=pm_delta)
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
return calendar.timegm(dt.timetuple())
except ValueError:
pass
timetuple = email.utils.parsedate_tz(date_str)
if timetuple:
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
return calendar.timegm(timetuple) + pm_delta * 3600 - timezone.total_seconds()
[utils] Add unified_timestamp
2016-06-25 17:30:35 +02:00
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
def determine_ext(url, default_ext='unknown_video'):
[openload] Improve ext extraction
2018-06-01 19:16:22 +02:00
if url is None or '.' not in url:
[izlesene] Minor changes
2014-08-01 14:08:09 +02:00
return default_ext
[utils] Check ext with trailing slash against the list of known extensions
2015-11-22 12:27:13 +01:00
guess = url.partition('?')[0].rpartition('.')[2]
[3sat] Add support (Fixes #1001)
2013-07-08 01:13:55 +02:00
if re.match(r'^[A-Za-z0-9]+$', guess):
return guess
[utils] Extract known extensions for reuse
2016-01-03 20:08:34 +01:00
# Try extract ext from URLs like http://example.com/foo/bar.mp4/?download
elif guess.rstrip('/') in KNOWN_EXTENSIONS:
[utils] Check ext with trailing slash against the list of known extensions
2015-11-22 12:27:13 +01:00
return guess.rstrip('/')
[3sat] Add support (Fixes #1001)
2013-07-08 01:13:55 +02:00
else:
Use determine_ext when saving the thumbnail Urls that contain a query produced filenames with wrong extensions
2013-07-12 21:52:59 +02:00
return default_ext
[3sat] Add support (Fixes #1001)
2013-07-08 01:13:55 +02:00
PEP8 applied
2014-11-23 20:41:03 +01:00
[utils] Improve subtitles_filename (closes #22753)
2019-10-17 23:03:53 +02:00
def subtitles_filename(filename, sub_lang, sub_format, expected_real_ext=None):
return replace_extension(filename, sub_lang + '.' + sub_format, expected_real_ext)
Add a post processor for embedding subtitles in mp4 videos (closes #1052)
2013-07-20 12:48:57 +02:00
PEP8 applied
2014-11-23 20:41:03 +01:00
Allow to select videos to download by their upload dates (related #137) Only absolute dates.
2013-04-27 14:01:55 +02:00
def date_from_str(date_str):
Allow to use relative dates in the format (now|today)[+-][0-9](day|week|month|year)(s)? (Closes #137) Also fix DateRange not accepting ranges of one day.
2013-04-28 11:39:37 +02:00
"""
Return a datetime object from a string in the format YYYYMMDD or
(now|today)[+-][0-9](day|week|month|year)(s)?"""
today = datetime.date.today()
[utils] Add "yesterday" as a date keyword
2014-12-11 10:29:30 +01:00
if date_str in ('now', 'today'):
Allow to use relative dates in the format (now|today)[+-][0-9](day|week|month|year)(s)? (Closes #137) Also fix DateRange not accepting ranges of one day.
2013-04-28 11:39:37 +02:00
return today
[utils] Add "yesterday" as a date keyword
2014-12-11 10:29:30 +01:00
if date_str == 'yesterday':
return today - datetime.timedelta(days=1)
Fix "invalid escape sequences" error on Python 3.6
2017-01-02 13:08:07 +01:00
match = re.match(r'(now|today)(?P<sign>[+-])(?P<time>\d+)(?P<unit>day|week|month|year)(s)?', date_str)
Allow to use relative dates in the format (now|today)[+-][0-9](day|week|month|year)(s)? (Closes #137) Also fix DateRange not accepting ranges of one day.
2013-04-28 11:39:37 +02:00
if match is not None:
sign = match.group('sign')
time = int(match.group('time'))
if sign == '-':
time = -time
unit = match.group('unit')
Fix typos Closes #8200.
2016-01-10 16:17:47 +01:00
# A bad approximation?
Allow to use relative dates in the format (now|today)[+-][0-9](day|week|month|year)(s)? (Closes #137) Also fix DateRange not accepting ranges of one day.
2013-04-28 11:39:37 +02:00
if unit == 'month':
unit = 'day'
time *= 30
elif unit == 'year':
unit = 'day'
time *= 365
unit += 's'
delta = datetime.timedelta(**{unit: time})
return today + delta
[refactor] Single quotes consistency
2016-02-14 10:37:17 +01:00
return datetime.datetime.strptime(date_str, '%Y%m%d').date()
PEP8 applied
2014-11-23 20:41:03 +01:00
Added '--xattrs' option which writes metadata to the file's extended attributes using a youtube-dl postprocessor. Works on Linux, OSX, and Windows.
2014-01-02 13:47:28 +01:00
def hyphenate_date(date_str):
"""
Convert a date in 'YYYYMMDD' format to 'YYYY-MM-DD' format"""
match = re.match(r'^(\d\d\d\d)(\d\d)(\d\d)$', date_str)
if match is not None:
return '-'.join(match.groups())
else:
return date_str
PEP8 applied
2014-11-23 20:41:03 +01:00
Allow to select videos to download by their upload dates (related #137) Only absolute dates.
2013-04-27 14:01:55 +02:00
class DateRange(object):
"""Represents a time interval between two dates"""
PEP8 applied
2014-11-23 20:41:03 +01:00
Allow to select videos to download by their upload dates (related #137) Only absolute dates.
2013-04-27 14:01:55 +02:00
def __init__(self, start=None, end=None):
"""start and end must be strings in the format accepted by date"""
if start is not None:
self.start = date_from_str(start)
else:
self.start = datetime.datetime.min.date()
if end is not None:
self.end = date_from_str(end)
else:
self.end = datetime.datetime.max.date()
Allow to use relative dates in the format (now|today)[+-][0-9](day|week|month|year)(s)? (Closes #137) Also fix DateRange not accepting ranges of one day.
2013-04-28 11:39:37 +02:00
if self.start > self.end:
Allow to select videos to download by their upload dates (related #137) Only absolute dates.
2013-04-27 14:01:55 +02:00
raise ValueError('Date range: "%s" , the start date must be before the end date' % self)
PEP8 applied
2014-11-23 20:41:03 +01:00
Allow to select videos to download by their upload dates (related #137) Only absolute dates.
2013-04-27 14:01:55 +02:00
@classmethod
def day(cls, day):
"""Returns a range that only contains the given day"""
PEP8 applied
2014-11-23 20:41:03 +01:00
return cls(day, day)
Allow to select videos to download by their upload dates (related #137) Only absolute dates.
2013-04-27 14:01:55 +02:00
def __contains__(self, date):
"""Check if the date is in the range"""
Allow to use relative dates in the format (now|today)[+-][0-9](day|week|month|year)(s)? (Closes #137) Also fix DateRange not accepting ranges of one day.
2013-04-28 11:39:37 +02:00
if not isinstance(date, datetime.date):
date = date_from_str(date)
return self.start <= date <= self.end
PEP8 applied
2014-11-23 20:41:03 +01:00
Allow to select videos to download by their upload dates (related #137) Only absolute dates.
2013-04-27 14:01:55 +02:00
def __str__(self):
PEP8 applied
2014-11-23 20:41:03 +01:00
return '%s - %s' % (self.start.isoformat(), self.end.isoformat())
Fix platform name in Python 2 with --verbose (Closes #1228)
2013-08-28 12:57:10 +02:00
[devscripts] Improve hack to convert command-line options to API options * define equality for DateRange * don't show default DateRange
2023-04-05 19:47:49 +02:00
def __eq__(self, other):
return (isinstance(other, DateRange)
and self.start == other.start and self.end == other.end)
Fix platform name in Python 2 with --verbose (Closes #1228)
2013-08-28 12:57:10 +02:00
def platform_name():
""" Returns the platform name as a compat_str """
res = platform.platform()
if isinstance(res, bytes):
res = res.decode(preferredencoding())
assert isinstance(res, compat_str)
return res
Merge remote-tracking branch 'rzhxeo/youporn-hd' Conflicts: youtube_dl/utils.py
2013-08-28 18:22:28 +02:00
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
def _windows_write_string(s, out):
""" Returns True if the string was written using special methods,
False if it has yet to be written out."""
# Adapted from http://stackoverflow.com/a/3259271/35070
import ctypes
import ctypes.wintypes
WIN_OUTPUT_IDS = {
1: -11,
2: -12,
}
[utils/_windows_write_string] Be defensive about fileno (Fixes #2820)
2014-04-30 10:07:32 +02:00
try:
fileno = out.fileno()
except AttributeError:
# If the output stream doesn't have a fileno, it's virtual
return False
[utils] Catch strange Windows errors (Closes #4733)
2015-01-23 12:17:12 +01:00
except io.UnsupportedOperation:
# Some strange Windows pseudo files?
return False
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
if fileno not in WIN_OUTPUT_IDS:
return False
[utils] Fix youtube-dl under PyPy3 on Windows
2014-12-12 04:01:08 +01:00
GetStdHandle = compat_ctypes_WINFUNCTYPE(
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
ctypes.wintypes.HANDLE, ctypes.wintypes.DWORD)(
[utils] Fix youtube-dl under PyPy3 on Windows
2014-12-12 04:01:08 +01:00
('GetStdHandle', ctypes.windll.kernel32))
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
h = GetStdHandle(WIN_OUTPUT_IDS[fileno])
[utils] Fix youtube-dl under PyPy3 on Windows
2014-12-12 04:01:08 +01:00
WriteConsoleW = compat_ctypes_WINFUNCTYPE(
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE, ctypes.wintypes.LPWSTR,
ctypes.wintypes.DWORD, ctypes.POINTER(ctypes.wintypes.DWORD),
[utils] Fix youtube-dl under PyPy3 on Windows
2014-12-12 04:01:08 +01:00
ctypes.wintypes.LPVOID)(('WriteConsoleW', ctypes.windll.kernel32))
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
written = ctypes.wintypes.DWORD(0)
[utils] Fix youtube-dl under PyPy3 on Windows
2014-12-12 04:01:08 +01:00
GetFileType = compat_ctypes_WINFUNCTYPE(ctypes.wintypes.DWORD, ctypes.wintypes.DWORD)(('GetFileType', ctypes.windll.kernel32))
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
FILE_TYPE_CHAR = 0x0002
FILE_TYPE_REMOTE = 0x8000
[utils] Fix youtube-dl under PyPy3 on Windows
2014-12-12 04:01:08 +01:00
GetConsoleMode = compat_ctypes_WINFUNCTYPE(
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
ctypes.wintypes.BOOL, ctypes.wintypes.HANDLE,
ctypes.POINTER(ctypes.wintypes.DWORD))(
[utils] Fix youtube-dl under PyPy3 on Windows
2014-12-12 04:01:08 +01:00
('GetConsoleMode', ctypes.windll.kernel32))
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
INVALID_HANDLE_VALUE = ctypes.wintypes.DWORD(-1).value
def not_a_console(handle):
if handle == INVALID_HANDLE_VALUE or handle is None:
return True
Fix W504 and disable W503 (closes #20863)
2019-05-10 22:56:22 +02:00
return ((GetFileType(handle) & ~FILE_TYPE_REMOTE) != FILE_TYPE_CHAR
or GetConsoleMode(handle, ctypes.byref(ctypes.wintypes.DWORD())) == 0)
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
if not_a_console(h):
return False
[utils] Fix _windows_write_string (Fixes #2779) It turns out that the function did not work for outputs longer than 1024 UCS-2 tokens. Write non-BMP characters one by one to ensure that we count correctly.
2014-04-21 04:59:44 +02:00
def next_nonbmp_pos(s):
try:
return next(i for i, c in enumerate(s) if ord(c) > 0xffff)
except StopIteration:
return len(s)
while s:
count = min(next_nonbmp_pos(s), 1024)
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
ret = WriteConsoleW(
[utils] Fix _windows_write_string (Fixes #2779) It turns out that the function did not work for outputs longer than 1024 UCS-2 tokens. Write non-BMP characters one by one to ensure that we count correctly.
2014-04-21 04:59:44 +02:00
h, s, count if count else 2, ctypes.byref(written), None)
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
if ret == 0:
raise OSError('Failed to write string')
[utils] Fix _windows_write_string (Fixes #2779) It turns out that the function did not work for outputs longer than 1024 UCS-2 tokens. Write non-BMP characters one by one to ensure that we count correctly.
2014-04-21 04:59:44 +02:00
if not count: # We just wrote a non-BMP character
assert written.value == 2
s = s[1:]
else:
assert written.value > 0
s = s[written.value:]
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
return True
Use --encoding when outputting
2014-04-07 19:57:42 +02:00
def write_string(s, out=None, encoding=None):
Always correct encoding when writing to sys.stderr (Fixes #1435)
2013-09-16 06:55:33 +02:00
if out is None:
out = sys.stderr
Fix/work around Windows encoding issues (Fixes #2095)
2014-01-05 03:07:55 +01:00
assert type(s) == compat_str
Always correct encoding when writing to sys.stderr (Fixes #1435)
2013-09-16 06:55:33 +02:00
[utils] Completely rewrite Windows output (Fixes #2672)
2014-04-07 22:48:13 +02:00
if sys.platform == 'win32' and encoding is None and hasattr(out, 'fileno'):
if _windows_write_string(s, out):
return
Fix W504 and disable W503 (closes #20863)
2019-05-10 22:56:22 +02:00
if ('b' in getattr(out, 'mode', '')
or sys.version_info[0] < 3): # Python 2 lies about mode of sys.stderr
Use our own encoding when writing strings
2014-04-07 21:40:34 +02:00
byt = s.encode(encoding or preferredencoding(), 'ignore')
out.write(byt)
elif hasattr(out, 'buffer'):
enc = encoding or getattr(out, 'encoding', None) or preferredencoding()
byt = s.encode(enc, 'ignore')
out.buffer.write(byt)
else:
Fix/work around Windows encoding issues (Fixes #2095)
2014-01-05 03:07:55 +01:00
out.write(s)
Always correct encoding when writing to sys.stderr (Fixes #1435)
2013-09-16 06:55:33 +02:00
out.flush()
Allow changes to run under Python 3
2013-08-28 14:28:55 +02:00
def bytes_to_intlist(bs):
if not bs:
return []
if isinstance(bs[0], int): # Python 3
return list(bs)
else:
return [ord(c) for c in bs]
Merge remote-tracking branch 'rzhxeo/youporn-hd' Conflicts: youtube_dl/utils.py
2013-08-28 18:22:28 +02:00
Add intlist_to_bytes to utils.py
2013-08-28 15:59:07 +02:00
def intlist_to_bytes(xs):
if not xs:
return b''
[compat] Rename struct_(un)pack to compat_struct_(un)pack
2016-05-03 10:50:16 +02:00
return compat_struct_pack('%dB' % len(xs), *xs)
[youtube] Simplify cache_dir code (#1529)
2013-10-02 08:41:03 +02:00
Add basic --download-archive option Often, users want to be able to download only videos they haven't seen before, despite the video files having been deleted or moved in the mean time. When --download-archive FILE is given, the extractor and ID of every download is recorded in the specified file. If it is already present, the video in question is skipped.
2013-10-06 04:27:09 +02:00
# Cross-platform file locking
if sys.platform == 'win32':
import ctypes.wintypes
import msvcrt
class OVERLAPPED(ctypes.Structure):
_fields_ = [
('Internal', ctypes.wintypes.LPVOID),
('InternalHigh', ctypes.wintypes.LPVOID),
('Offset', ctypes.wintypes.DWORD),
('OffsetHigh', ctypes.wintypes.DWORD),
('hEvent', ctypes.wintypes.HANDLE),
]
kernel32 = ctypes.windll.kernel32
LockFileEx = kernel32.LockFileEx
LockFileEx.argtypes = [
ctypes.wintypes.HANDLE, # hFile
ctypes.wintypes.DWORD, # dwFlags
ctypes.wintypes.DWORD, # dwReserved
ctypes.wintypes.DWORD, # nNumberOfBytesToLockLow
ctypes.wintypes.DWORD, # nNumberOfBytesToLockHigh
ctypes.POINTER(OVERLAPPED) # Overlapped
]
LockFileEx.restype = ctypes.wintypes.BOOL
UnlockFileEx = kernel32.UnlockFileEx
UnlockFileEx.argtypes = [
ctypes.wintypes.HANDLE, # hFile
ctypes.wintypes.DWORD, # dwReserved
ctypes.wintypes.DWORD, # nNumberOfBytesToLockLow
ctypes.wintypes.DWORD, # nNumberOfBytesToLockHigh
ctypes.POINTER(OVERLAPPED) # Overlapped
]
UnlockFileEx.restype = ctypes.wintypes.BOOL
whole_low = 0xffffffff
whole_high = 0x7fffffff
def _lock_file(f, exclusive):
overlapped = OVERLAPPED()
overlapped.Offset = 0
overlapped.OffsetHigh = 0
overlapped.hEvent = 0
f._lock_file_overlapped_p = ctypes.pointer(overlapped)
handle = msvcrt.get_osfhandle(f.fileno())
if not LockFileEx(handle, 0x2 if exclusive else 0x0, 0,
whole_low, whole_high, f._lock_file_overlapped_p):
raise OSError('Locking file failed: %r' % ctypes.FormatError())
def _unlock_file(f):
assert f._lock_file_overlapped_p
handle = msvcrt.get_osfhandle(f.fileno())
if not UnlockFileEx(handle, 0,
whole_low, whole_high, f._lock_file_overlapped_p):
raise OSError('Unlocking file failed: %r' % ctypes.FormatError())
else:
[utils] Jython support: tolerate missing fcntl module
2016-02-20 20:28:25 +01:00
# Some platforms, such as Jython, is missing fcntl
try:
import fcntl
Add basic --download-archive option Often, users want to be able to download only videos they haven't seen before, despite the video files having been deleted or moved in the mean time. When --download-archive FILE is given, the extractor and ID of every download is recorded in the specified file. If it is already present, the video in question is skipped.
2013-10-06 04:27:09 +02:00
[utils] Jython support: tolerate missing fcntl module
2016-02-20 20:28:25 +01:00
def _lock_file(f, exclusive):
fcntl.flock(f, fcntl.LOCK_EX if exclusive else fcntl.LOCK_SH)
Add basic --download-archive option Often, users want to be able to download only videos they haven't seen before, despite the video files having been deleted or moved in the mean time. When --download-archive FILE is given, the extractor and ID of every download is recorded in the specified file. If it is already present, the video in question is skipped.
2013-10-06 04:27:09 +02:00
[utils] Jython support: tolerate missing fcntl module
2016-02-20 20:28:25 +01:00
def _unlock_file(f):
fcntl.flock(f, fcntl.LOCK_UN)
except ImportError:
UNSUPPORTED_MSG = 'file locking is not supported on this platform'
def _lock_file(f, exclusive):
raise IOError(UNSUPPORTED_MSG)
def _unlock_file(f):
raise IOError(UNSUPPORTED_MSG)
Add basic --download-archive option Often, users want to be able to download only videos they haven't seen before, despite the video files having been deleted or moved in the mean time. When --download-archive FILE is given, the extractor and ID of every download is recorded in the specified file. If it is already present, the video in question is skipped.
2013-10-06 04:27:09 +02:00
class locked_file(object):
def __init__(self, filename, mode, encoding=None):
assert mode in ['r', 'a', 'w']
self.f = io.open(filename, mode, encoding=encoding)
self.mode = mode
def __enter__(self):
exclusive = self.mode != 'r'
try:
_lock_file(self.f, exclusive)
except IOError:
self.f.close()
raise
return self
def __exit__(self, etype, value, traceback):
try:
_unlock_file(self.f)
finally:
self.f.close()
def __iter__(self):
return iter(self.f)
def write(self, *args):
return self.f.write(*args)
def read(self, *args):
return self.f.read(*args)
FFmpegPostProcessor: print the command line used if the --verbose option is given
2013-10-12 13:49:27 +02:00
[core] Decode environment variables with filesystem encoding (Fixes #3854, Fixes #3217, Fixes #2918) Introduces compat versions of os.getenv and os.path.expanduser
2014-09-30 17:27:53 +02:00
def get_filesystem_encoding():
encoding = sys.getfilesystemencoding()
return encoding if encoding is not None else 'utf-8'
FFmpegPostProcessor: print the command line used if the --verbose option is given
2013-10-12 13:49:27 +02:00
def shell_quote(args):
utils.shell_quote: Convert the args to unicode strings The youtube test video failed with `UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 34: ordinal not in range(128)`, the problem was with the filenames being encoded.
2013-11-21 14:09:28 +01:00
quoted_args = []
[core] Decode environment variables with filesystem encoding (Fixes #3854, Fixes #3217, Fixes #2918) Introduces compat versions of os.getenv and os.path.expanduser
2014-09-30 17:27:53 +02:00
encoding = get_filesystem_encoding()
utils.shell_quote: Convert the args to unicode strings The youtube test video failed with `UnicodeDecodeError: 'ascii' codec can't decode byte 0xc3 in position 34: ordinal not in range(128)`, the problem was with the filenames being encoded.
2013-11-21 14:09:28 +01:00
for a in args:
if isinstance(a, bytes):
# We may get a filename encoded with 'encodeFilename'
a = a.decode(encoding)
[utils] Use compat_shlex_quote in shell_quote
2017-06-17 18:48:58 +02:00
quoted_args.append(compat_shlex_quote(a))
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
return ' '.join(quoted_args)
[generic] Support embedded vimeo videos (#1602)
2013-10-15 12:05:13 +02:00
def smuggle_url(url, data):
""" Pass additional data in a URL for internal use. """
[kaltura] add support videos stored on custom kaltura servers(closes #5557)
2016-07-04 18:57:44 +02:00
url, idata = unsmuggle_url(url, {})
data.update(idata)
[compat] Add compat_urllib_parse_urlencode and eliminate encode_dict encode_dict functionality has been improved and moved directly into compat_urllib_parse_urlencode All occurrences of compat_urllib_parse.urlencode throughout the codebase have been replaced by compat_urllib_parse_urlencode Closes #8974
2016-03-25 20:46:57 +01:00
sdata = compat_urllib_parse_urlencode(
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
{'__youtubedl_smuggle': json.dumps(data)})
return url + '#' + sdata
[generic] Support embedded vimeo videos (#1602)
2013-10-15 12:05:13 +02:00
Use original Referer URL in Brightcove requests (Fixes #2110)
2014-01-07 05:34:14 +01:00
def unsmuggle_url(smug_url, default=None):
Fix PEP8 issue E713
2014-12-09 23:11:26 +01:00
if '#__youtubedl_smuggle' not in smug_url:
Use original Referer URL in Brightcove requests (Fixes #2110)
2014-01-07 05:34:14 +01:00
return smug_url, default
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
url, _, sdata = smug_url.rpartition('#')
jsond = compat_parse_qs(sdata)['__youtubedl_smuggle'][0]
[generic] Support embedded vimeo videos (#1602)
2013-10-15 12:05:13 +02:00
data = json.loads(jsond)
return url, data
[zdf/common] Use API in ZDF extractor. This also comes with a lot of extra format fields Fixes #1518
2013-11-25 03:12:26 +01:00
def format_bytes(bytes):
if bytes is None:
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
return 'N/A'
[zdf/common] Use API in ZDF extractor. This also comes with a lot of extra format fields Fixes #1518
2013-11-25 03:12:26 +01:00
if type(bytes) is str:
bytes = float(bytes)
if bytes == 0.0:
exponent = 0
else:
exponent = int(math.log(bytes, 1024.0))
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
suffix = ['B', 'KiB', 'MiB', 'GiB', 'TiB', 'PiB', 'EiB', 'ZiB', 'YiB'][exponent]
[zdf/common] Use API in ZDF extractor. This also comes with a lot of extra format fields Fixes #1518
2013-11-25 03:12:26 +01:00
converted = float(bytes) / float(1024 ** exponent)
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
return '%.2f%s' % (converted, suffix)
[dailymotion] Extract view count (#1895)
2013-12-06 13:36:36 +01:00
Improve --bidi-workaround support
2013-12-09 18:29:07 +01:00
[bbc] Generalize unit table lookup and add parse_count
2016-03-13 11:27:20 +01:00
def lookup_unit_table(unit_table, s):
units_re = '|'.join(re.escape(u) for u in unit_table)
m = re.match(
[utils] lookup_unit_table: Match word boundary instead of end of string
2016-03-19 11:42:35 +01:00
r'(?P<num>[0-9]+(?:[,.][0-9]*)?)\s*(?P<unit>%s)\b' % units_re, s)
[bbc] Generalize unit table lookup and add parse_count
2016-03-13 11:27:20 +01:00
if not m:
return None
num_str = m.group('num').replace(',', '.')
mult = unit_table[m.group('unit')]
return int(float(num_str) * mult)
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
def parse_filesize(s):
if s is None:
return None
Fix typos Closes #8200.
2016-01-10 16:17:47 +01:00
# The lower-case forms are of course incorrect and unofficial,
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
# but we support those too
_UNIT_TABLE = {
'B': 1,
'b': 1,
[utils] Recognize units with full names in parse_filename Reference: https://en.wikipedia.org/wiki/Template:Quantities_of_bytes
2016-08-19 18:12:32 +02:00
'bytes': 1,
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
'KiB': 1024,
'KB': 1000,
'kB': 1024,
'Kb': 1000,
[utils] Recognize lowercase units in parse_filesize
2016-08-18 18:32:00 +02:00
'kb': 1000,
[utils] Recognize units with full names in parse_filename Reference: https://en.wikipedia.org/wiki/Template:Quantities_of_bytes
2016-08-19 18:12:32 +02:00
'kilobytes': 1000,
'kibibytes': 1024,
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
'MiB': 1024 ** 2,
'MB': 1000 ** 2,
'mB': 1024 ** 2,
'Mb': 1000 ** 2,
[utils] Recognize lowercase units in parse_filesize
2016-08-18 18:32:00 +02:00
'mb': 1000 ** 2,
[utils] Recognize units with full names in parse_filename Reference: https://en.wikipedia.org/wiki/Template:Quantities_of_bytes
2016-08-19 18:12:32 +02:00
'megabytes': 1000 ** 2,
'mebibytes': 1024 ** 2,
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
'GiB': 1024 ** 3,
'GB': 1000 ** 3,
'gB': 1024 ** 3,
'Gb': 1000 ** 3,
[utils] Recognize lowercase units in parse_filesize
2016-08-18 18:32:00 +02:00
'gb': 1000 ** 3,
[utils] Recognize units with full names in parse_filename Reference: https://en.wikipedia.org/wiki/Template:Quantities_of_bytes
2016-08-19 18:12:32 +02:00
'gigabytes': 1000 ** 3,
'gibibytes': 1024 ** 3,
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
'TiB': 1024 ** 4,
'TB': 1000 ** 4,
'tB': 1024 ** 4,
'Tb': 1000 ** 4,
[utils] Recognize lowercase units in parse_filesize
2016-08-18 18:32:00 +02:00
'tb': 1000 ** 4,
[utils] Recognize units with full names in parse_filename Reference: https://en.wikipedia.org/wiki/Template:Quantities_of_bytes
2016-08-19 18:12:32 +02:00
'terabytes': 1000 ** 4,
'tebibytes': 1024 ** 4,
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
'PiB': 1024 ** 5,
'PB': 1000 ** 5,
'pB': 1024 ** 5,
'Pb': 1000 ** 5,
[utils] Recognize lowercase units in parse_filesize
2016-08-18 18:32:00 +02:00
'pb': 1000 ** 5,
[utils] Recognize units with full names in parse_filename Reference: https://en.wikipedia.org/wiki/Template:Quantities_of_bytes
2016-08-19 18:12:32 +02:00
'petabytes': 1000 ** 5,
'pebibytes': 1024 ** 5,
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
'EiB': 1024 ** 6,
'EB': 1000 ** 6,
'eB': 1024 ** 6,
'Eb': 1000 ** 6,
[utils] Recognize lowercase units in parse_filesize
2016-08-18 18:32:00 +02:00
'eb': 1000 ** 6,
[utils] Recognize units with full names in parse_filename Reference: https://en.wikipedia.org/wiki/Template:Quantities_of_bytes
2016-08-19 18:12:32 +02:00
'exabytes': 1000 ** 6,
'exbibytes': 1024 ** 6,
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
'ZiB': 1024 ** 7,
'ZB': 1000 ** 7,
'zB': 1024 ** 7,
'Zb': 1000 ** 7,
[utils] Recognize lowercase units in parse_filesize
2016-08-18 18:32:00 +02:00
'zb': 1000 ** 7,
[utils] Recognize units with full names in parse_filename Reference: https://en.wikipedia.org/wiki/Template:Quantities_of_bytes
2016-08-19 18:12:32 +02:00
'zettabytes': 1000 ** 7,
'zebibytes': 1024 ** 7,
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
'YiB': 1024 ** 8,
'YB': 1000 ** 8,
'yB': 1024 ** 8,
'Yb': 1000 ** 8,
[utils] Recognize lowercase units in parse_filesize
2016-08-18 18:32:00 +02:00
'yb': 1000 ** 8,
[utils] Recognize units with full names in parse_filename Reference: https://en.wikipedia.org/wiki/Template:Quantities_of_bytes
2016-08-19 18:12:32 +02:00
'yottabytes': 1000 ** 8,
'yobibytes': 1024 ** 8,
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
}
[bbc] Generalize unit table lookup and add parse_count
2016-03-13 11:27:20 +01:00
return lookup_unit_table(_UNIT_TABLE, s)
def parse_count(s):
if s is None:
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
return None
[bbc] Generalize unit table lookup and add parse_count
2016-03-13 11:27:20 +01:00
s = s.strip()
if re.match(r'^[\d,.]+$', s):
return str_to_int(s)
_UNIT_TABLE = {
'k': 1000,
'K': 1000,
'm': 1000 ** 2,
'M': 1000 ** 2,
'kk': 1000 ** 2,
'KK': 1000 ** 2,
}
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
[bbc] Generalize unit table lookup and add parse_count
2016-03-13 11:27:20 +01:00
return lookup_unit_table(_UNIT_TABLE, s)
[xminus] Simplify and extend (#4302)
2014-11-25 09:54:54 +01:00
[utils] PEP 8
2016-03-13 12:23:08 +01:00
[utils] Add parse_resolution
2018-03-02 17:39:04 +01:00
def parse_resolution(s):
if s is None:
return {}
mobj = re.search(r'\b(?P<w>\d+)\s*[xX×]\s*(?P<h>\d+)\b', s)
if mobj:
return {
'width': int(mobj.group('w')),
'height': int(mobj.group('h')),
}
mobj = re.search(r'\b(\d+)[pPiI]\b', s)
if mobj:
return {'height': int(mobj.group(1))}
mobj = re.search(r'\b([48])[kK]\b', s)
if mobj:
return {'height': int(mobj.group(1)) * 540}
return {}
[utils] Introduce parse_bitrate
2019-03-17 03:07:47 +01:00
def parse_bitrate(s):
if not isinstance(s, compat_str):
return
mobj = re.search(r'\b(\d+)\s*kbps', s)
if mobj:
return int(mobj.group(1))
[utils,franceinter] Add french months' names and fix extraction Update of the "FranceInter" radio extractor : webpages HTML structure had changed, the extractor didn't work. So I updated this extractor to get the mp3 URL and all details.
2016-09-02 18:31:52 +02:00
def month_by_name(name, lang='en'):
[ndtv] Add extractor (Fixes #1924)
2013-12-09 19:39:41 +01:00
""" Return the number of a month by (locale-independently) English name """
[utils] Improve month_by_name and add tests
2016-09-14 18:13:55 +02:00
month_names = MONTH_NAMES.get(lang, MONTH_NAMES['en'])
[utils,franceinter] Add french months' names and fix extraction Update of the "FranceInter" radio extractor : webpages HTML structure had changed, the extractor didn't work. So I updated this extractor to get the mp3 URL and all details.
2016-09-02 18:31:52 +02:00
[ndtv] Add extractor (Fixes #1924)
2013-12-09 19:39:41 +01:00
try:
[utils] Improve month_by_name and add tests
2016-09-14 18:13:55 +02:00
return month_names.index(name) + 1
[Yam] Add new extractor
2015-02-13 08:14:23 +01:00
except ValueError:
return None
def month_by_abbreviation(abbrev):
""" Return the number of a month by (locale-independently) English
abbreviations """
try:
return [s[:3] for s in ENGLISH_MONTH_NAMES].index(abbrev) + 1
[ndtv] Add extractor (Fixes #1924)
2013-12-09 19:39:41 +01:00
except ValueError:
return None
Use `_download_xml` in more extractors
2013-12-10 21:03:53 +01:00
Correct XML ampersand fixup
2014-01-20 22:11:34 +01:00
def fix_xml_ampersands(xml_str):
Use `_download_xml` in more extractors
2013-12-10 21:03:53 +01:00
"""Replace all the '&' by '&amp;' in XML"""
Correct XML ampersand fixup
2014-01-20 22:11:34 +01:00
return re.sub(
r'&(?!amp;|lt;|gt;|apos;|quot;|#x[0-9a-fA-F]{,4};|#[0-9]{,4};)',
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
'&amp;',
Correct XML ampersand fixup
2014-01-20 22:11:34 +01:00
xml_str)
Set process title to youtube-dl This allows killing all youtube-dl processes with killall youtube-dl, and shows up nicer in some programs.
2013-12-16 05:04:12 +01:00
def setproctitle(title):
Fix/work around Windows encoding issues (Fixes #2095)
2014-01-05 03:07:55 +01:00
assert isinstance(title, compat_str)
[utils] Jython support - disable setproctitle() until ctypes is complete
2016-02-20 20:29:02 +01:00
# ctypes in Jython is not complete
# http://bugs.jython.org/issue2148
if sys.platform.startswith('java'):
return
Set process title to youtube-dl This allows killing all youtube-dl processes with killall youtube-dl, and shows up nicer in some programs.
2013-12-16 05:04:12 +01:00
try:
[refactor] Single quotes consistency
2016-02-14 10:37:17 +01:00
libc = ctypes.cdll.LoadLibrary('libc.so.6')
Set process title to youtube-dl This allows killing all youtube-dl processes with killall youtube-dl, and shows up nicer in some programs.
2013-12-16 05:04:12 +01:00
except OSError:
return
utils.py: Workaround TypeError with Python 2.7.13 in Windows Fixes #11540 Tested with Windows Python 2.7.12 and 2.7.13.
2017-02-10 22:05:09 +01:00
except TypeError:
# LoadLibrary in Windows Python 2.7.13 only expects
# a bytestring, but since unicode_literals turns
# every string into a unicode string, it fails.
return
[utils] Simplify setproctitle
2014-03-23 14:28:22 +01:00
title_bytes = title.encode('utf-8')
buf = ctypes.create_string_buffer(len(title_bytes))
buf.value = title_bytes
Set process title to youtube-dl This allows killing all youtube-dl processes with killall youtube-dl, and shows up nicer in some programs.
2013-12-16 05:04:12 +01:00
try:
[utils] Simplify setproctitle
2014-03-23 14:28:22 +01:00
libc.prctl(15, buf, 0, 0, 0)
Set process title to youtube-dl This allows killing all youtube-dl processes with killall youtube-dl, and shows up nicer in some programs.
2013-12-16 05:04:12 +01:00
except AttributeError:
return # Strange libc, just skip this
[blinkx] Add extractor (Fixes #1972)
2013-12-16 13:56:13 +01:00
def remove_start(s, start):
[utils] Allow None in remove_{start,end}
2016-05-19 00:31:30 +02:00
return s[len(start):] if s is not None and s.startswith(start) else s
Add webpage_url_basename info_dict field (Fixes #1938)
2013-12-17 04:13:36 +01:00
[rtve] Add support for live stream At the moment, only RTVE-1 seems to work flawlessly. -2 seems geoblocked right now. -TDP doesn't seem to be available outside of Spain.
2014-08-22 18:40:26 +02:00
def remove_end(s, end):
[utils] Allow None in remove_{start,end}
2016-05-19 00:31:30 +02:00
return s[:-len(end)] if s is not None and s.endswith(end) else s
[rtve] Add support for live stream At the moment, only RTVE-1 seems to work flawlessly. -2 seems geoblocked right now. -TDP doesn't seem to be available outside of Spain.
2014-08-22 18:40:26 +02:00
[utils] Add remove_quotes
2015-12-14 16:30:58 +01:00
def remove_quotes(s):
if s is None or len(s) < 2:
return s
for quote in ('"', "'", ):
if s[0] == quote and s[-1] == quote:
return s[1:-1]
return s
Add webpage_url_basename info_dict field (Fixes #1938)
2013-12-17 04:13:36 +01:00
def url_basename(url):
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
path = compat_urllib_parse.urlparse(url).path
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
return path.strip('/').split('/')[-1]
[aparat] Add support (Fixes #2012)
2013-12-20 17:05:28 +01:00
[utils] Introduce base_url
2016-11-01 20:14:01 +01:00
def base_url(url):
return re.match(r'https?://[^?#&]+/', url).group()
[utils] Add convenience urljoin
2016-12-12 20:23:49 +01:00
def urljoin(base, path):
[utils] Process bytestrings in urljoin (closes #12369)
2017-03-05 21:57:46 +01:00
if isinstance(path, bytes):
path = path.decode('utf-8')
[utils] Add convenience urljoin
2016-12-12 20:23:49 +01:00
if not isinstance(path, compat_str) or not path:
return None
[utils] Fix urljoin for paths with non-http(s) schemes
2019-01-20 14:21:24 +01:00
if re.match(r'^(?:[a-zA-Z][a-zA-Z0-9+-.]*:)?//', path):
[utils] Add convenience urljoin
2016-12-12 20:23:49 +01:00
return path
[utils] Process bytestrings in urljoin (closes #12369)
2017-03-05 21:57:46 +01:00
if isinstance(base, bytes):
base = base.decode('utf-8')
if not isinstance(base, compat_str) or not re.match(
r'^(?:https?:)?//', base):
[utils] Add convenience urljoin
2016-12-12 20:23:49 +01:00
return None
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
return compat_urllib_parse.urljoin(base, path)
[utils] Add convenience urljoin
2016-12-12 20:23:49 +01:00
[aparat] Add support (Fixes #2012)
2013-12-20 17:05:28 +01:00
class HEADRequest(compat_urllib_request.Request):
def get_method(self):
[refactor] Single quotes consistency
2016-02-14 10:37:17 +01:00
return 'HEAD'
[yahoo] Use centralized sorting, and add tbr field
2013-12-25 15:18:40 +01:00
[utils] Add PUTRequest
2016-07-02 21:21:32 +02:00
class PUTRequest(compat_urllib_request.Request):
def get_method(self):
return 'PUT'
[snotr] PEP8 and minor fixes (#3296)
2014-07-21 12:02:44 +02:00
def int_or_none(v, scale=1, default=None, get_attr=None, invscale=1):
[bilibili] Add preliminary support (#2174) The URL http://www.bilibili.tv/video/av636603/index_2.html does not work yet.
2014-04-21 13:45:27 +02:00
if get_attr:
if v is not None:
v = getattr(v, get_attr, None)
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
if v in (None, ''):
[utils] Do not fail in int_or_none on non-numeric data (Closes #7175)
2015-10-14 18:35:01 +02:00
return default
try:
return int(v) * invscale // scale
[jsinterp] Overhaul JSInterp to handle new YT players 4c3f79c5, 324f67b9 (#31170) * back-port from yt-dlp 8f53dc44a0cc1c2d98c35740b9293462c080f5d0, thanks pukkandan * also support void, improve <</>> precedence, improve expressions in comma-list * add more tests
2022-08-14 19:45:45 +02:00
except (ValueError, TypeError, OverflowError):
[utils] Return default on fail in int_or_none
2015-10-14 18:37:03 +02:00
return default
[snotr] PEP8 and minor fixes (#3296)
2014-07-21 12:02:44 +02:00
[appletrailers] Support height-less videos
2014-08-10 13:04:45 +02:00
[reverbnation] The 'uploader_id' field must be a string
2014-08-10 11:00:14 +02:00
def str_or_none(v, default=None):
return default if v is None else compat_str(v)
[snotr] PEP8 and minor fixes (#3296)
2014-07-21 12:02:44 +02:00
def str_to_int(int_str):
[eporner] Simplify and correct (#3629)
2014-08-31 23:51:36 +02:00
""" A more relaxed version of int_or_none """
[utils] Improve str_to_int
2019-12-15 17:15:24 +01:00
if isinstance(int_str, compat_integer_types):
[utils] handle int values passed to str_to_int
2019-11-29 17:05:06 +01:00
return int_str
[utils] Improve str_to_int
2019-12-15 17:15:24 +01:00
elif isinstance(int_str, compat_str):
int_str = re.sub(r'[,\.\+]', '', int_str)
return int_or_none(int_str)
[cnn] Add multiple formats, duration, and upload_date
2013-12-26 13:49:44 +01:00
[snotr] PEP8 and minor fixes (#3296)
2014-07-21 12:02:44 +02:00
def float_or_none(v, scale=1, invscale=1, default=None):
[utils] Do not fail in float_or_none on non-numeric data
2015-10-14 18:36:37 +02:00
if v is None:
return default
try:
return float(v) * invscale / scale
[utils] Improve int_or_none and float_or_none (#20403)
2019-03-22 19:08:54 +01:00
except (ValueError, TypeError):
[utils] Do not fail in float_or_none on non-numeric data
2015-10-14 18:36:37 +02:00
return default
[comedycentral] Duration can now be a float (Fixes #2647)
2014-03-28 23:06:34 +01:00
[utils] Introduce bool_or_none
2017-09-10 14:08:39 +02:00
def bool_or_none(v, default=None):
return v if isinstance(v, bool) else default
[utils] Improve strip_or_none
2019-05-23 18:58:35 +02:00
def strip_or_none(v, default=None):
return v.strip() if isinstance(v, compat_str) else default
[utils] Add strip_or_none
2016-06-25 17:32:02 +02:00
[utils] Introduce url_or_none
2018-07-21 13:01:06 +02:00
def url_or_none(url):
if not url or not isinstance(url, compat_str):
return None
url = url.strip()
[utils] accept only supported protocols in url_or_none
2020-12-30 09:22:30 +01:00
return url if re.match(r'^(?:(?:https?|rt(?:m(?:pt?[es]?|fp)|sp[su]?)|mms|ftps?):)?//', url) else None
[utils] Introduce url_or_none
2018-07-21 13:01:06 +02:00
[cnn] Add multiple formats, duration, and upload_date
2013-12-26 13:49:44 +01:00
def parse_duration(s):
Appease pyflakes8-3
2015-02-01 11:30:56 +01:00
if not isinstance(s, compat_basestring):
[cnn] Add multiple formats, duration, and upload_date
2013-12-26 13:49:44 +01:00
return None
[utils] Improve parse_duration
2014-08-31 01:41:30 +02:00
s = s.strip()
[utils] imporove parse_duration to handle more formats
2016-04-07 20:30:47 +02:00
days, hours, mins, secs, ms = [None] * 5
[utils] Improve parse_duration
2017-01-26 17:23:08 +01:00
m = re.match(r'(?:(?:(?:(?P<days>[0-9]+):)?(?P<hours>[0-9]+):)?(?P<mins>[0-9]+):)?(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?Z?$', s)
[utils] imporove parse_duration to handle more formats
2016-04-07 20:30:47 +02:00
if m:
days, hours, mins, secs, ms = m.groups()
else:
m = re.match(
[utils] Add support for zero years and months in parse_duration
2017-10-29 02:04:48 +02:00
r'''(?ix)(?:P?
(?:
[0-9]+\s*y(?:ears?)?\s*
)?
(?:
[0-9]+\s*m(?:onths?)?\s*
)?
(?:
[0-9]+\s*w(?:eeks?)?\s*
)?
[ntvde] Add new extractor (Fixes #4850)
2015-02-02 21:48:54 +01:00
(?:
[utils] imporove parse_duration to handle more formats
2016-04-07 20:30:47 +02:00
(?P<days>[0-9]+)\s*d(?:ays?)?\s*
[ntvde] Add new extractor (Fixes #4850)
2015-02-02 21:48:54 +01:00
)?
[utils] Add support for zero years and months in parse_duration
2017-10-29 02:04:48 +02:00
T)?
[utils] imporove parse_duration to handle more formats
2016-04-07 20:30:47 +02:00
(?:
(?P<hours>[0-9]+)\s*h(?:ours?)?\s*
)?
(?:
(?P<mins>[0-9]+)\s*m(?:in(?:ute)?s?)?\s*
)?
(?:
(?P<secs>[0-9]+)(?P<ms>\.[0-9]+)?\s*s(?:ec(?:ond)?s?)?\s*
[utils] Improve parse_duration
2017-01-26 17:23:08 +01:00
)?Z?$''', s)
[utils] imporove parse_duration to handle more formats
2016-04-07 20:30:47 +02:00
if m:
days, hours, mins, secs, ms = m.groups()
else:
[utils] Improve parse_duration
2017-01-26 17:23:08 +01:00
m = re.match(r'(?i)(?:(?P<hours>[0-9.]+)\s*(?:hours?)|(?P<mins>[0-9.]+)\s*(?:mins?\.?|minutes?)\s*)Z?$', s)
[utils] imporove parse_duration to handle more formats
2016-04-07 20:30:47 +02:00
if m:
hours, mins = m.groups()
else:
return None
duration = 0
if secs:
duration += float(secs)
if mins:
duration += float(mins) * 60
if hours:
duration += float(hours) * 60 * 60
if days:
duration += float(days) * 24 * 60 * 60
if ms:
duration += float(ms)
return duration
FFmpegMetadataPP; Write temporary file to `something.temp.{ext}` (fixes #2079) ffmpeg correctly recognize the formats of extensions like m4a, but it doesn’t works if it’s passed with the `—format` option.
2014-01-03 12:52:27 +01:00
[utils] Improve prepend_extension Now `ext` is appended to filename if real extension != expected extension.
2015-05-02 19:06:01 +02:00
def prepend_extension(filename, ext, expected_real_ext=None):
PEP8 applied
2014-11-23 20:41:03 +01:00
name, real_ext = os.path.splitext(filename)
[utils] Improve prepend_extension Now `ext` is appended to filename if real extension != expected extension.
2015-05-02 19:06:01 +02:00
return (
'{0}.{1}{2}'.format(name, ext, real_ext)
if not expected_real_ext or real_ext[1:] == expected_real_ext
else '{0}.{1}'.format(filename, ext))
Move check_executable into a helper ufnction
2014-01-07 06:23:41 +01:00
[utils] Add replace_extension
2015-05-02 19:23:06 +02:00
def replace_extension(filename, ext, expected_real_ext=None):
name, real_ext = os.path.splitext(filename)
return '{0}.{1}'.format(
name if not expected_real_ext or real_ext[1:] == expected_real_ext else filename,
ext)
Move check_executable into a helper ufnction
2014-01-07 06:23:41 +01:00
def check_executable(exe, args=[]):
""" Checks if the given binary is installed somewhere in PATH, and returns its name.
args can be a list of arguments for a short output (like -version) """
try:
[utils, etc] Kill child processes when yt-dl is killed * derived from PR #26592, closes #26592 Authored by: Unrud
2021-01-09 13:26:12 +01:00
process_communicate_or_kill(subprocess.Popen(
[exe] + args, stdout=subprocess.PIPE, stderr=subprocess.PIPE))
Move check_executable into a helper ufnction
2014-01-07 06:23:41 +01:00
except OSError:
return False
return exe
Add infrastructure for paged lists This commit allows to download pages in playlists as needed instead of all at once. Before this commit, youtube-dl http://www.youtube.com/user/ANNnewsCH/videos --playlist-end 2 --skip-download took quite some time - now it's almost instantaneous. As an example, the youtube:user extractor has been converted. Fixes #2175
2014-01-20 11:36:47 +01:00
[ffmpeg] Move version detection to utils
2014-11-02 10:50:30 +01:00
def get_exe_version(exe, args=['--version'],
Improve and test ffmpeg version detection
2014-12-14 21:59:59 +01:00
version_re=None, unrecognized='present'):
[ffmpeg] Move version detection to utils
2014-11-02 10:50:30 +01:00
""" Returns the version of the specified executable,
or False if the executable is not present """
try:
[utils] Clarify for redirecting STDIN in get_exe_version()
2016-10-22 07:04:05 +02:00
# STDIN should be redirected too. On UNIX-like systems, ffmpeg triggers
# SIGTTOU if youtube-dl is run in the background.
Start moving to ytdl-org
2019-03-09 13:14:41 +01:00
# See https://github.com/ytdl-org/youtube-dl/issues/955#issuecomment-209789656
[utils, etc] Kill child processes when yt-dl is killed * derived from PR #26592, closes #26592 Authored by: Unrud
2021-01-09 13:26:12 +01:00
out, _ = process_communicate_or_kill(subprocess.Popen(
[utils] get_exe_version: encode executable name (fixes #5647) It failed in python 2.x when $PATH contains a directory with non-ascii characters.
2015-05-08 11:01:24 +02:00
[encodeArgument(exe)] + args,
[get_exe_version] Do version probes with <&- When doing version probes for ffmpeg, do the equivalent of calling it as: ffmpeg -version <&- Where <&- is shell syntax for closing stdin before calling the program. This is roughly equivalent to </dev/null without actually opening /dev/null. This prevents ffmpeg -version from hanging when run in the background. Fixes #955. The reason is that ffmpeg tries to manipulate stdin to set up terminal characteristic, and that causes the kernel to suspend the parent process (youtube-dl). Note that closing stdin is achieved by calling subprocess.Popen() with stdin set to subprocess.PIPE and without passing any input to Popen.communicate(). This is somewhat subtle.
2016-10-22 02:44:49 +02:00
stdin=subprocess.PIPE,
[utils, etc] Kill child processes when yt-dl is killed * derived from PR #26592, closes #26592 Authored by: Unrud
2021-01-09 13:26:12 +01:00
stdout=subprocess.PIPE, stderr=subprocess.STDOUT))
[ffmpeg] Move version detection to utils
2014-11-02 10:50:30 +01:00
except OSError:
return False
Improve and test ffmpeg version detection
2014-12-14 21:59:59 +01:00
if isinstance(out, bytes): # Python 2.x
out = out.decode('ascii', 'ignore')
return detect_exe_version(out, version_re, unrecognized)
def detect_exe_version(output, version_re=None, unrecognized='present'):
assert isinstance(output, compat_str)
if version_re is None:
version_re = r'version\s+([-0-9._a-zA-Z]+)'
m = re.search(version_re, output)
[ffmpeg] Move version detection to utils
2014-11-02 10:50:30 +01:00
if m:
return m.group(1)
else:
return unrecognized
[utils] Backport traverse_obj (etc) from yt-dlp (#31156) * Backport traverse_obj and closely related function from yt-dlp (code by pukkandan) * Backport LazyList, variadic(), try_call (code by pukkandan) * Recast using yt-dlp's newer traverse_obj() implementation and tests (code by grub4k) * Add tests for Unicode case folding support matching Py3.5+ (requires f102e3d) * Improve/add tests for variadic, try_call, join_nonempty Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-11-03 11:09:37 +01:00
class LazyList(compat_collections_abc.Sequence):
"""Lazy immutable list from an iterable
Note that slices of a LazyList are lists and not LazyList"""
class IndexError(IndexError):
def __init__(self, cause=None):
if cause:
# reproduce `raise from`
self.__cause__ = cause
super(IndexError, self).__init__()
def __init__(self, iterable, **kwargs):
# kwarg-only
reverse = kwargs.get('reverse', False)
_cache = kwargs.get('_cache')
self._iterable = iter(iterable)
self._cache = [] if _cache is None else _cache
self._reversed = reverse
def __iter__(self):
if self._reversed:
# We need to consume the entire iterable to iterate in reverse
for item in self.exhaust():
yield item
return
for item in self._cache:
yield item
for item in self._iterable:
self._cache.append(item)
yield item
def _exhaust(self):
self._cache.extend(self._iterable)
self._iterable = [] # Discard the emptied iterable to make it pickle-able
return self._cache
def exhaust(self):
"""Evaluate the entire iterable"""
return self._exhaust()[::-1 if self._reversed else 1]
@staticmethod
def _reverse_index(x):
return None if x is None else ~x
def __getitem__(self, idx):
if isinstance(idx, slice):
if self._reversed:
idx = slice(self._reverse_index(idx.start), self._reverse_index(idx.stop), -(idx.step or 1))
start, stop, step = idx.start, idx.stop, idx.step or 1
elif isinstance(idx, int):
if self._reversed:
idx = self._reverse_index(idx)
start, stop, step = idx, idx, 0
else:
raise TypeError('indices must be integers or slices')
if ((start or 0) < 0 or (stop or 0) < 0
or (start is None and step < 0)
or (stop is None and step > 0)):
# We need to consume the entire iterable to be able to slice from the end
# Obviously, never use this with infinite iterables
self._exhaust()
try:
return self._cache[idx]
except IndexError as e:
raise self.IndexError(e)
n = max(start or 0, stop or 0) - len(self._cache) + 1
if n > 0:
self._cache.extend(itertools.islice(self._iterable, n))
try:
return self._cache[idx]
except IndexError as e:
raise self.IndexError(e)
def __bool__(self):
try:
self[-1] if self._reversed else self[0]
except self.IndexError:
return False
return True
def __len__(self):
self._exhaust()
return len(self._cache)
def __reversed__(self):
return type(self)(self._iterable, reverse=not self._reversed, _cache=self._cache)
def __copy__(self):
return type(self)(self._iterable, reverse=self._reversed, _cache=self._cache)
def __repr__(self):
# repr and str should mimic a list. So we exhaust the iterable
return repr(self.exhaust())
def __str__(self):
return repr(self.exhaust())
Add infrastructure for paged lists This commit allows to download pages in playlists as needed instead of all at once. Before this commit, youtube-dl http://www.youtube.com/user/ANNnewsCH/videos --playlist-end 2 --skip-download took quite some time - now it's almost instantaneous. As an example, the youtube:user extractor has been converted. Fixes #2175
2014-01-20 11:36:47 +01:00
class PagedList(object):
Add __len__ to PagedLists
2014-01-22 21:43:33 +01:00
def __len__(self):
# This is only useful for tests
return len(self.getslice())
[vimeo:likes] Support large like lists (Fixes #3847)
2014-09-29 00:36:06 +02:00
class OnDemandPagedList(PagedList):
[utils] Use in OnDemandPagedList by default Not using cache results in redundant network I/O due to downloading the same pages while using --playlist-items n-m
2017-10-06 18:13:53 +02:00
def __init__(self, pagefunc, pagesize, use_cache=True):
[vimeo:likes] Support large like lists (Fixes #3847)
2014-09-29 00:36:06 +02:00
self._pagefunc = pagefunc
self._pagesize = pagesize
[utils] Implement cache for OnDemandPagedList
2016-02-23 05:17:02 +01:00
self._use_cache = use_cache
if use_cache:
self._cache = {}
[vimeo:likes] Support large like lists (Fixes #3847)
2014-09-29 00:36:06 +02:00
Add infrastructure for paged lists This commit allows to download pages in playlists as needed instead of all at once. Before this commit, youtube-dl http://www.youtube.com/user/ANNnewsCH/videos --playlist-end 2 --skip-download took quite some time - now it's almost instantaneous. As an example, the youtube:user extractor has been converted. Fixes #2175
2014-01-20 11:36:47 +01:00
def getslice(self, start=0, end=None):
res = []
for pagenum in itertools.count(start // self._pagesize):
firstid = pagenum * self._pagesize
nextfirstid = pagenum * self._pagesize + self._pagesize
if start >= nextfirstid:
continue
[utils] Implement cache for OnDemandPagedList
2016-02-23 05:17:02 +01:00
page_results = None
if self._use_cache:
page_results = self._cache.get(pagenum)
if page_results is None:
page_results = list(self._pagefunc(pagenum))
if self._use_cache:
self._cache[pagenum] = page_results
Add infrastructure for paged lists This commit allows to download pages in playlists as needed instead of all at once. Before this commit, youtube-dl http://www.youtube.com/user/ANNnewsCH/videos --playlist-end 2 --skip-download took quite some time - now it's almost instantaneous. As an example, the youtube:user extractor has been converted. Fixes #2175
2014-01-20 11:36:47 +01:00
startv = (
start % self._pagesize
if firstid <= start < nextfirstid
else 0)
endv = (
((end - 1) % self._pagesize) + 1
if (end is not None and firstid <= end <= nextfirstid)
else None)
if startv != 0 or endv is not None:
page_results = page_results[startv:endv]
res.extend(page_results)
# A little optimization - if current page is not "full", ie. does
# not contain page_size videos then we can assume that this page
# is the last one - there are no more ids on further pages -
# i.e. no need to query again.
if len(page_results) + startv < self._pagesize:
break
# If we got the whole page, but the next page is not interesting,
# break out early as well
if end == nextfirstid:
break
return res
[youtube] Correct invalid JSON (Fixes #2353)
2014-02-09 17:56:10 +01:00
[vimeo:likes] Support large like lists (Fixes #3847)
2014-09-29 00:36:06 +02:00
class InAdvancePagedList(PagedList):
def __init__(self, pagefunc, pagecount, pagesize):
self._pagefunc = pagefunc
self._pagecount = pagecount
self._pagesize = pagesize
def getslice(self, start=0, end=None):
res = []
start_page = start // self._pagesize
end_page = (
self._pagecount if end is None else (end // self._pagesize + 1))
skip_elems = start - start_page * self._pagesize
only_more = None if end is None else end - start
for pagenum in range(start_page, end_page):
page = list(self._pagefunc(pagenum))
if skip_elems:
page = page[skip_elems:]
skip_elems = None
if only_more is not None:
if len(page) < only_more:
only_more -= len(page)
else:
page = page[:only_more]
res.extend(page)
break
res.extend(page)
return res
[youtube] Correct invalid JSON (Fixes #2353)
2014-02-09 17:56:10 +01:00
def uppercase_escape(s):
Fix unicode_escape (Fixes #2695)
2014-04-04 23:00:51 +02:00
unicode_escape = codecs.getdecoder('unicode_escape')
[youtube] Correct invalid JSON (Fixes #2353)
2014-02-09 17:56:10 +01:00
return re.sub(
[utils] Correct decoding of large unicode codepoints in uppercase_escape (Fixes #2664)
2014-04-01 13:17:07 +02:00
r'\\U[0-9a-fA-F]{8}',
Fix unicode_escape (Fixes #2695)
2014-04-04 23:00:51 +02:00
lambda m: unicode_escape(m.group(0))[0],
s)
[NBC] Enhance embedURL extraction (closes #2549)
2015-05-04 15:53:05 +02:00
def lowercase_escape(s):
unicode_escape = codecs.getdecoder('unicode_escape')
return re.sub(
r'\\u[0-9a-fA-F]{4}',
lambda m: unicode_escape(m.group(0))[0],
s)
Fix f4m downloading on Python 2.6
2014-02-15 16:24:43 +01:00
[YoutubeDL/utils] Clarify rationale for URL escaping in comment, move escape routines to utils and add some tests
2014-09-13 15:59:16 +02:00
def escape_rfc3986(s):
"""Escape non-ASCII characters as suggested by RFC 3986"""
Appease pyflakes8-3
2015-02-01 11:30:56 +01:00
if sys.version_info < (3, 0) and isinstance(s, compat_str):
[YoutubeDL/utils] Clarify rationale for URL escaping in comment, move escape routines to utils and add some tests
2014-09-13 15:59:16 +02:00
s = s.encode('utf-8')
[utils] Ensure RFC3986 encoding result is unicode
2022-08-21 01:19:19 +02:00
# ensure unicode: after quoting, it can always be converted
return compat_str(compat_urllib_parse.quote(s, b"%/;:@&=+$,!~*'()?#[]"))
[YoutubeDL/utils] Clarify rationale for URL escaping in comment, move escape routines to utils and add some tests
2014-09-13 15:59:16 +02:00
def escape_url(url):
"""Escape URL as suggested by RFC 3986"""
url_parsed = compat_urllib_parse_urlparse(url)
return url_parsed._replace(
[utils] Encode hostnames before passing to urllib With IDN (Internationalized Domain Name) and a proxy, non-ascii URLs are passed down to urllib/urllib2, causing UnicodeEncodeError Fixes #8890
2016-03-23 15:24:52 +01:00
netloc=url_parsed.netloc.encode('idna').decode('ascii'),
[YoutubeDL/utils] Clarify rationale for URL escaping in comment, move escape routines to utils and add some tests
2014-09-13 15:59:16 +02:00
path=escape_rfc3986(url_parsed.path),
params=escape_rfc3986(url_parsed.params),
query=escape_rfc3986(url_parsed.query),
fragment=escape_rfc3986(url_parsed.fragment)
).geturl()
Ignore BOM in batch files (Fixes #2450)
2014-02-25 01:43:17 +01:00
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
def parse_qs(url):
return compat_parse_qs(compat_urllib_parse.urlparse(url).query)
Ignore BOM in batch files (Fixes #2450)
2014-02-25 01:43:17 +01:00
def read_batch_urls(batch_fd):
def fixup(url):
if not isinstance(url, compat_str):
url = url.decode('utf-8', 'replace')
[utils] Remove stray u'
2014-11-17 07:16:12 +01:00
BOM_UTF8 = '\xef\xbb\xbf'
Ignore BOM in batch files (Fixes #2450)
2014-02-25 01:43:17 +01:00
if url.startswith(BOM_UTF8):
url = url[len(BOM_UTF8):]
url = url.strip()
if url.startswith(('#', ';', ']')):
return False
return url
with contextlib.closing(batch_fd) as fd:
return [url for url in map(fixup, fd) if url]
[facebook] Fix login process It was broken and didn't work in python 3. And use `_download_webpage` instead of `compat_urllib_request.urlopen`.
2014-03-07 15:25:33 +01:00
def urlencode_postdata(*args, **kargs):
[compat] Add compat_urllib_parse_urlencode and eliminate encode_dict encode_dict functionality has been improved and moved directly into compat_urllib_parse_urlencode All occurrences of compat_urllib_parse.urlencode throughout the codebase have been replaced by compat_urllib_parse_urlencode Closes #8974
2016-03-25 20:46:57 +01:00
return compat_urllib_parse_urlencode(*args, **kargs).encode('ascii')
[generic] Suppress warning about doctypes in RSS parser
2014-03-10 17:31:32 +01:00
[YouTube] Bypass age-gating for certain restricted videos * Use TVHTML5_SIMPLY_EMBEDDED_PLAYER client * Also add and fix tests * Introduce and use new utility function `update_url()`
2022-01-31 05:28:54 +01:00
def update_url(url, **kwargs):
"""Replace URL components specified by kwargs
url: compat_str or parsed URL tuple
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
if query_update is in kwargs, update query with
its value instead of replacing (overrides any `query`)
returns: compat_str
"""
[YouTube] Bypass age-gating for certain restricted videos * Use TVHTML5_SIMPLY_EMBEDDED_PLAYER client * Also add and fix tests * Introduce and use new utility function `update_url()`
2022-01-31 05:28:54 +01:00
if not kwargs:
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
return compat_urllib_parse.urlunparse(url) if isinstance(url, tuple) else url
[YouTube] Bypass age-gating for certain restricted videos * Use TVHTML5_SIMPLY_EMBEDDED_PLAYER client * Also add and fix tests * Introduce and use new utility function `update_url()`
2022-01-31 05:28:54 +01:00
if not isinstance(url, tuple):
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
url = compat_urllib_parse.urlparse(url)
query = kwargs.pop('query_update', None)
if query:
qs = compat_parse_qs(url.query)
qs.update(query)
kwargs['query'] = compat_urllib_parse_urlencode(qs, True)
kwargs = compat_kwargs(kwargs)
return compat_urllib_parse.urlunparse(url._replace(**kwargs))
def update_url_query(url, query):
return update_url(url, query_update=query)
[YouTube] Bypass age-gating for certain restricted videos * Use TVHTML5_SIMPLY_EMBEDDED_PLAYER client * Also add and fix tests * Introduce and use new utility function `update_url()`
2022-01-31 05:28:54 +01:00
[utils] Add update_Request
2016-03-31 18:55:01 +02:00
def update_Request(req, url=None, data=None, headers={}, query={}):
req_headers = req.headers.copy()
req_headers.update(headers)
req_data = data or req.data
req_url = update_url_query(url or req.get_full_url(), query)
[utils] Add PUTRequest
2016-07-02 21:21:32 +02:00
req_get_method = req.get_method()
if req_get_method == 'HEAD':
req_type = HEADRequest
elif req_get_method == 'PUT':
req_type = PUTRequest
else:
req_type = compat_urllib_request.Request
[utils] Add update_Request
2016-03-31 18:55:01 +02:00
new_req = req_type(
req_url, data=req_data, headers=req_headers,
origin_req_host=req.origin_req_host, unverifiable=req.unverifiable)
if hasattr(req, 'timeout'):
new_req.timeout = req.timeout
return new_req
[utils] Rename try_multipart_encode to _multipart_encode_impl To state that this is an internal function and people should be careful when using it outside youtube-dl.
2017-05-06 13:06:18 +02:00
def _multipart_encode_impl(data, boundary):
[cda] Implement birthday verification (closes #12789)
2017-05-01 17:09:18 +02:00
content_type = 'multipart/form-data; boundary=%s' % boundary
out = b''
for k, v in data.items():
out += b'--' + boundary.encode('ascii') + b'\r\n'
if isinstance(k, compat_str):
k = k.encode('utf-8')
if isinstance(v, compat_str):
v = v.encode('utf-8')
# RFC 2047 requires non-ASCII field names to be encoded, while RFC 7578
# suggests sending UTF-8 directly. Firefox sends UTF-8, too
[utils] Fix multipart_encode for Python < 3.5
2017-05-05 14:51:59 +02:00
content = b'Content-Disposition: form-data; name="' + k + b'"\r\n\r\n' + v + b'\r\n'
[cda] Implement birthday verification (closes #12789)
2017-05-01 17:09:18 +02:00
if boundary.encode('ascii') in content:
raise ValueError('Boundary overlaps with data')
out += content
out += b'--' + boundary.encode('ascii') + b'--\r\n'
return out, content_type
def multipart_encode(data, boundary=None):
'''
Encode a dict to RFC 7578-compliant form-data
data:
A dict where keys and values can be either Unicode or bytes-like
objects.
boundary:
If specified a Unicode object, it's used as the boundary. Otherwise
a random boundary is generated.
Reference: https://tools.ietf.org/html/rfc7578
'''
has_specified_boundary = boundary is not None
while True:
if boundary is None:
boundary = '---------------' + str(random.randrange(0x0fffffff, 0xffffffff))
try:
[utils] Rename try_multipart_encode to _multipart_encode_impl To state that this is an internal function and people should be careful when using it outside youtube-dl.
2017-05-06 13:06:18 +02:00
out, content_type = _multipart_encode_impl(data, boundary)
[cda] Implement birthday verification (closes #12789)
2017-05-01 17:09:18 +02:00
break
except ValueError:
if has_specified_boundary:
raise
boundary = None
return out, content_type
[utils] Backport traverse_obj (etc) from yt-dlp (#31156) * Backport traverse_obj and closely related function from yt-dlp (code by pukkandan) * Backport LazyList, variadic(), try_call (code by pukkandan) * Recast using yt-dlp's newer traverse_obj() implementation and tests (code by grub4k) * Add tests for Unicode case folding support matching Py3.5+ (requires f102e3d) * Improve/add tests for variadic, try_call, join_nonempty Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-11-03 11:09:37 +01:00
def variadic(x, allowed_types=(compat_str, bytes, dict)):
[utils] Ensure `allow_types` for `variadic()` is a tuple
2023-03-19 03:27:46 +01:00
if not isinstance(allowed_types, tuple) and isinstance(allowed_types, compat_collections_abc.Iterable):
allowed_types = tuple(allowed_types)
[utils] Backport traverse_obj (etc) from yt-dlp (#31156) * Backport traverse_obj and closely related function from yt-dlp (code by pukkandan) * Backport LazyList, variadic(), try_call (code by pukkandan) * Recast using yt-dlp's newer traverse_obj() implementation and tests (code by grub4k) * Add tests for Unicode case folding support matching Py3.5+ (requires f102e3d) * Improve/add tests for variadic, try_call, join_nonempty Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-11-03 11:09:37 +01:00
return x if isinstance(x, compat_collections_abc.Iterable) and not isinstance(x, allowed_types) else (x,)
[utils] Add ability to control skipping false values in dict_get
2016-02-07 03:13:04 +01:00
def dict_get(d, key_or_keys, default=None, skip_false_values=True):
[utils] Add dict_get convenience method
2016-02-07 01:12:53 +01:00
if isinstance(key_or_keys, (list, tuple)):
for key in key_or_keys:
[utils] Add ability to control skipping false values in dict_get
2016-02-07 03:13:04 +01:00
if key not in d or d[key] is None or skip_false_values and not d[key]:
continue
return d[key]
[utils] Add dict_get convenience method
2016-02-07 01:12:53 +01:00
return default
return d.get(key_or_keys, default)
[utils] Backport traverse_obj (etc) from yt-dlp (#31156) * Backport traverse_obj and closely related function from yt-dlp (code by pukkandan) * Backport LazyList, variadic(), try_call (code by pukkandan) * Recast using yt-dlp's newer traverse_obj() implementation and tests (code by grub4k) * Add tests for Unicode case folding support matching Py3.5+ (requires f102e3d) * Improve/add tests for variadic, try_call, join_nonempty Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-11-03 11:09:37 +01:00
def try_call(*funcs, **kwargs):
# parameter defaults
expected_type = kwargs.get('expected_type')
fargs = kwargs.get('args', [])
fkwargs = kwargs.get('kwargs', {})
for f in funcs:
try:
val = f(*fargs, **fkwargs)
except (AttributeError, KeyError, TypeError, IndexError, ZeroDivisionError):
pass
else:
if expected_type is None or isinstance(val, expected_type):
return val
[utils] Add try_get To reduce boilerplate when accessing JSON
2016-06-12 01:05:34 +02:00
def try_get(src, getter, expected_type=None):
[extractor/common] Add support multiple getters in try_get
2017-04-18 17:39:58 +02:00
if not isinstance(getter, (list, tuple)):
getter = [getter]
for get in getter:
try:
v = get(src)
except (AttributeError, KeyError, TypeError, IndexError):
pass
else:
if expected_type is None or isinstance(v, expected_type):
return v
[utils] Add try_get To reduce boilerplate when accessing JSON
2016-06-12 01:05:34 +02:00
[utils] Introduce merge_dicts
2018-04-27 21:47:17 +02:00
def merge_dicts(*dicts):
merged = {}
for a_dict in dicts:
for k, v in a_dict.items():
if v is None:
continue
Fix W504 and disable W503 (closes #20863)
2019-05-10 22:56:22 +02:00
if (k not in merged
or (isinstance(v, compat_str) and v
and isinstance(merged[k], compat_str)
and not merged[k])):
[utils] Introduce merge_dicts
2018-04-27 21:47:17 +02:00
merged[k] = v
return merged
[utils] Add encode_compat_str
2015-12-20 01:26:26 +01:00
def encode_compat_str(string, encoding=preferredencoding(), errors='strict'):
return string if isinstance(string, compat_str) else compat_str(string, encoding, errors)
[utils] Add encode_dict
2015-09-06 03:22:20 +02:00
[pbs] Add support for video ratings
2014-03-21 00:59:51 +01:00
US_RATINGS = {
'G': 0,
'PG': 10,
'PG-13': 13,
'R': 16,
'NC': 18,
}
[washingtonpost] Add extractor (Fixes #2622)
2014-03-24 23:21:20 +01:00
[utils] Add support TV Parental Guidelines ratings in parse_age_limit
2016-08-07 15:45:18 +02:00
TV_PARENTAL_GUIDELINES = {
[utils] keep the original TV_PARENTAL_GUIDELINES dict
2018-05-26 00:12:18 +02:00
'TV-Y': 0,
'TV-Y7': 7,
'TV-G': 0,
'TV-PG': 0,
'TV-14': 14,
'TV-MA': 17,
[utils] Add support TV Parental Guidelines ratings in parse_age_limit
2016-08-07 15:45:18 +02:00
}
[utils] Add parse_age_limit
2014-10-03 14:37:25 +02:00
def parse_age_limit(s):
[utils] Add support TV Parental Guidelines ratings in parse_age_limit
2016-08-07 15:45:18 +02:00
if type(s) == int:
return s if 0 <= s <= 21 else None
if not isinstance(s, compat_basestring):
[utils] Default age_limit to None If we can't parse it, it means we don't have any information, not that the content is unrestricted.
2014-10-03 20:17:10 +02:00
return None
[utils] Add parse_age_limit
2014-10-03 14:37:25 +02:00
m = re.match(r'^(?P<age>\d{1,2})\+?$', s)
[utils] Add support TV Parental Guidelines ratings in parse_age_limit
2016-08-07 15:45:18 +02:00
if m:
return int(m.group('age'))
if s in US_RATINGS:
return US_RATINGS[s]
[utils] keep the original TV_PARENTAL_GUIDELINES dict
2018-05-26 00:12:18 +02:00
m = re.match(r'^TV[_-]?(%s)$' % '|'.join(k[3:] for k in TV_PARENTAL_GUIDELINES), s)
[utils] Relax TV Parental Guidelines matching
2018-05-23 13:12:20 +02:00
if m:
[utils] keep the original TV_PARENTAL_GUIDELINES dict
2018-05-26 00:12:18 +02:00
return TV_PARENTAL_GUIDELINES['TV-' + m.group(1)]
[utils] Relax TV Parental Guidelines matching
2018-05-23 13:12:20 +02:00
return None
[utils] Add parse_age_limit
2014-10-03 14:37:25 +02:00
[washingtonpost] Add extractor (Fixes #2622)
2014-03-24 23:21:20 +01:00
def strip_jsonp(code):
[npo] Improve npo.nl (Fixes #4173)
2014-11-13 16:28:05 +01:00
return re.sub(
[utils] Recognize more patterns in strip_jsonp() Used in Youku Show pages
2017-05-26 15:58:18 +02:00
r'''(?sx)^
[utils] Allow JSONP with empty func name (closes #17028)
2018-07-21 07:30:18 +02:00
(?:window\.)?(?P<func_name>[a-zA-Z0-9_.$]*)
[utils] Recognize more patterns in strip_jsonp() Used in Youku Show pages
2017-05-26 15:58:18 +02:00
(?:\s*&&\s*(?P=func_name))?
\s*\(\s*(?P<callback_data>.*)\);?
\s*?(?://[^\n]*)*$''',
r'\g<callback_data>', code)
[clubic] Add extractor (Fixes #2773)
2014-04-21 07:12:02 +02:00
[patreon] Simplify (#3390)
2014-08-22 02:33:29 +02:00
def js_to_json(code):
[utils] Improve comments processing in js_to_json (closes #11947)
2017-02-02 20:55:06 +01:00
COMMENT_RE = r'/\*(?:(?!\*/).)*?\*/|//[^\n]*'
SKIP_RE = r'\s*(?:{comment})?\s*'.format(comment=COMMENT_RE)
INTEGER_TABLE = (
(r'(?s)^(0[xX][0-9a-fA-F]+){skip}:?$'.format(skip=SKIP_RE), 16),
(r'(?s)^(0+[0-7]+){skip}:?$'.format(skip=SKIP_RE), 8),
)
[patreon] Simplify (#3390)
2014-08-22 02:33:29 +02:00
def fix_kv(m):
[utils] Improve and test js_to_json
2014-09-30 11:12:59 +02:00
v = m.group(0)
if v in ('true', 'false', 'null'):
return v
[utils] Skip ! prefixed code in js_to_json
2020-11-16 19:30:43 +01:00
elif v.startswith('/*') or v.startswith('//') or v.startswith('!') or v == ',':
[utils] js_to_json: various improvements now JS object literals like { /* " */ 0: ",]\xaa<\/p>", } will be correctly converted to JSON.
2016-03-13 12:29:15 +01:00
return ""
if v[0] in ("'", '"'):
v = re.sub(r'(?s)\\.|"', lambda m: {
[utils] Improve and test js_to_json
2014-09-30 11:12:59 +02:00
'"': '\\"',
[utils] js_to_json: various improvements now JS object literals like { /* " */ 0: ",]\xaa<\/p>", } will be correctly converted to JSON.
2016-03-13 12:29:15 +01:00
"\\'": "'",
'\\\n': '',
'\\x': '\\u00',
}.get(m.group(0), m.group(0)), v[1:-1])
[utils] Don't attempt to coerce JS strings to numbers in js_to_json (#26851) The current logic in `js_to_json` tries to rewrite octal/hex numbers to decimal. However, when the logic actually happens the `"` or `'` have already been trimmed off. This causes what were originally strings, that happen to look like octal/hex numbers, to get rewritten to decimal and returned as a number rather than a string. In practive something like: ```js { "0x40": "foo", "040": "bar", } ``` would get rewritten as: ```json { 64: "foo", 32: "bar } ``` This is problematic since this isn't valid JSON as you cannot have non-string keys.
2020-10-17 19:10:41 +02:00
else:
for regex, base in INTEGER_TABLE:
im = re.match(regex, v)
if im:
i = int(im.group(1), base)
return '"%d":' % i if v.endswith(':') else '%d' % i
[utils] Process non-base 10 integers in js_to_json
2016-05-14 16:39:58 +02:00
[utils] Improve and test js_to_json
2014-09-30 11:12:59 +02:00
return '"%s"' % v
[patreon] Simplify (#3390)
2014-08-22 02:33:29 +02:00
[utils] js_to_json: various improvements now JS object literals like { /* " */ 0: ",]\xaa<\/p>", } will be correctly converted to JSON.
2016-03-13 12:29:15 +01:00
return re.sub(r'''(?sx)
"(?:[^"\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^"\\]*"|
'(?:[^'\\]*(?:\\\\|\\['"nurtbfx/\n]))*[^'\\]*'|
[utils] Improve comments processing in js_to_json (closes #11947)
2017-02-02 20:55:06 +01:00
{comment}|,(?={skip}[\]}}])|
[util] Improve scientific notation handling in js_to_json (closes #14789)
2018-01-20 16:54:21 +01:00
(?:(?<![0-9])[eE]|[a-df-zA-DF-Z_])[.a-zA-Z_0-9]*|
[utils] Improve comments processing in js_to_json (closes #11947)
2017-02-02 20:55:06 +01:00
\b(?:0[xX][0-9a-fA-F]+|0+[0-7]+)(?:{skip}:)?|
[utils] Skip ! prefixed code in js_to_json
2020-11-16 19:30:43 +01:00
[0-9]+(?={skip}:)|
!+
[utils] Improve comments processing in js_to_json (closes #11947)
2017-02-02 20:55:06 +01:00
'''.format(comment=COMMENT_RE, skip=SKIP_RE), fix_kv, code)
[patreon] Simplify (#3390)
2014-08-22 02:33:29 +02:00
[clubic] Add extractor (Fixes #2773)
2014-04-21 07:12:02 +02:00
def qualities(quality_ids):
""" Get a numeric quality value out of a list of possible values """
def q(qid):
try:
return quality_ids.index(qid)
except ValueError:
return -1
return q
[YoutubeDL] Do not require default output template to be set
2014-04-30 10:02:03 +02:00
DEFAULT_OUTTMPL = '%(title)s-%(id)s.%(ext)s'
Provide compatibility check_output for 2.6 (Fixes #2926)
2014-05-16 12:03:59 +02:00
[facebook] Fix support for untitled videos (Fixes #3757)
2014-09-15 15:10:24 +02:00
def limit_length(s, length):
""" Add ellipses to overly long strings """
if s is None:
return None
ELLIPSES = '...'
if len(s) > length:
return s[:length - len(ELLIPSES)] + ELLIPSES
return s
[ffmpeg] Warn if ffmpeg/avconv version is too old (Fixes #4026)
2014-10-26 16:46:34 +01:00
def version_tuple(v):
[ffmpeg] Improve version check and call it from hls (Fixes #4377)
2014-12-06 12:14:26 +01:00
return tuple(int(e) for e in re.split(r'[-.]', v))
[ffmpeg] Warn if ffmpeg/avconv version is too old (Fixes #4026)
2014-10-26 16:46:34 +01:00
def is_outdated_version(version, limit, assume_new=True):
if not version:
return not assume_new
try:
return version_tuple(version) < version_tuple(limit)
except ValueError:
return not assume_new
[utils] Improve update on error message somewhat We still may want to implement a bulletproof check for the current version, and a better place to add this message so that it works for all kind of other errors too.
2014-11-20 12:14:28 +01:00
def ytdl_is_updateable():
""" Returns if youtube-dl can be updated with -U """
from zipimport import zipimporter
return isinstance(globals().get('__loader__'), zipimporter) or hasattr(sys, 'frozen')
Provide guidance when called with a YouTube ID starting with a dash. Reported at https://news.ycombinator.com/item?id=8648121
2014-11-23 10:49:19 +01:00
def args_to_str(args):
# Get a short string representation for a subprocess command
[compat] Rename shlex_quote and remove unused subprocess_check_output
2016-05-10 09:58:25 +02:00
return ' '.join(compat_shlex_quote(a) for a in args)
[soulanime] Fix under Python 3
2015-01-04 02:20:45 +01:00
Rename error_to_str to error_to_compat_str
2015-12-20 02:00:39 +01:00
def error_to_compat_str(err):
[utils] Add error_to_str
2015-12-20 00:26:47 +01:00
err_str = str(err)
# On python 2 error byte string must be decoded with proper
# encoding rather than ascii
if sys.version_info[0] < 3:
err_str = err_str.decode(preferredencoding())
return err_str
[sandia] Add new extractor (#4974)
2015-02-19 00:31:01 +01:00
def mimetype2ext(mt):
[utils] Allow None mimetypes in mimetype2ext
2016-04-24 20:03:12 +02:00
if mt is None:
return None
[utils] mimetype2ext: return 'm4a' for 'audio/mp4' (fixes #8620) The youtube extractor was using 'mp4' for them, therefore filters like 'bestaudio[ext=m4a]' stopped working (94278f720272c5ad2cd5900f59f8e71f31d46633 broke it).
2016-02-20 19:55:10 +01:00
ext = {
'audio/mp4': 'm4a',
[utils] Add audio/mpeg to mimetype2ext() Used in WDR live radios (#6147)
2016-06-09 06:58:24 +02:00
# Per RFC 3003, audio/mpeg can be .mp1, .mp2 or .mp3. Here use .mp3 as
# it's the most popular one
'audio/mpeg': 'mp3',
[utils] mimetype2ext: return 'm4a' for 'audio/mp4' (fixes #8620) The youtube extractor was using 'mp4' for them, therefore filters like 'bestaudio[ext=m4a]' stopped working (94278f720272c5ad2cd5900f59f8e71f31d46633 broke it).
2016-02-20 19:55:10 +01:00
}.get(mt)
if ext is not None:
return ext
[sandia] Add new extractor (#4974)
2015-02-19 00:31:01 +01:00
_, _, res = mt.rpartition('/')
[utils] Improve mimetype2ext
2016-09-02 17:57:48 +02:00
res = res.split(';')[0].strip().lower()
[sandia] Add new extractor (#4974)
2015-02-19 00:31:01 +01:00
return {
[utils] Add more items to mimetype2ext (#8293) These are used in Youtube formats
2016-01-24 17:58:53 +01:00
'3gpp': '3gp',
add more subtitles mime types to mimetype2ext and fix the platform subtitle extraction
2016-02-20 22:02:03 +01:00
'smptett+xml': 'tt',
'ttaf+xml': 'dfxp',
[utils] Reorder items in mimetype2ext alphabetically
2016-01-24 18:01:15 +01:00
'ttml+xml': 'ttml',
[utils] Add more items to mimetype2ext (#8293) These are used in Youtube formats
2016-01-24 17:58:53 +01:00
'x-flv': 'flv',
[utils] Reorder items in mimetype2ext alphabetically
2016-01-24 18:01:15 +01:00
'x-mp4-fragmented': 'mp4',
[utils] add sami mimetype to mimetype2ext
2017-12-03 00:04:43 +01:00
'x-ms-sami': 'sami',
[utils] Reorder items in mimetype2ext alphabetically
2016-01-24 18:01:15 +01:00
'x-ms-wmv': 'wmv',
[utils] add mimetypes to determine manifest ext(m3u8, f4m, mpd)
2016-07-06 10:06:28 +02:00
'mpegurl': 'm3u8',
'x-mpegurl': 'm3u8',
'vnd.apple.mpegurl': 'm3u8',
'dash+xml': 'mpd',
'f4m+xml': 'f4m',
[utils] Add another f4m mimetype to mimetype2ext
2016-07-23 11:48:59 +02:00
'hds+xml': 'f4m',
[brightcove] skip ism manifests
2016-07-14 15:13:57 +02:00
'vnd.ms-sstr+xml': 'ism',
[utils] Add quicktime to mimetype2ext
2016-09-02 18:50:42 +02:00
'quicktime': 'mov',
[utils] add video/mp2t to mimetype2ext
2017-04-30 10:01:05 +02:00
'mp2t': 'ts',
[utils] Recognize wav mimetype (closes #26463)
2020-09-06 06:19:53 +02:00
'x-wav': 'wav',
[sandia] Add new extractor (#4974)
2015-02-19 00:31:01 +01:00
}.get(res, res)
[utils] add helper function for parsing codecs
2016-03-16 18:48:06 +01:00
def parse_codecs(codecs_str):
# http://tools.ietf.org/html/rfc6381
if not codecs_str:
return {}
Fix typos (#27084) * spelling: authorization Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: brightcove Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: creation Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exceeded Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exception Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extension Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extracting Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extraction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: frontline Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: improve Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: length Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: listsubtitles Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: multimedia Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: obfuscated Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: partitioning Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlist Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlists Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: restriction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: services Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: split Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: srmediathek Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: support Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: thumbnail Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: verification Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: whitespaces Signed-off-by: Josh Soref <jsoref@users.noreply.github.com>
2020-11-21 16:00:05 +01:00
split_codecs = list(filter(None, map(
[utils] add helper function for parsing codecs
2016-03-16 18:48:06 +01:00
lambda str: str.strip(), codecs_str.strip().strip(',').split(','))))
vcodec, acodec = None, None
Fix typos (#27084) * spelling: authorization Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: brightcove Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: creation Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exceeded Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exception Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extension Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extracting Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extraction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: frontline Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: improve Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: length Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: listsubtitles Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: multimedia Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: obfuscated Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: partitioning Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlist Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlists Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: restriction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: services Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: split Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: srmediathek Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: support Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: thumbnail Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: verification Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: whitespaces Signed-off-by: Josh Soref <jsoref@users.noreply.github.com>
2020-11-21 16:00:05 +01:00
for full_codec in split_codecs:
[utils] add helper function for parsing codecs
2016-03-16 18:48:06 +01:00
codec = full_codec.split('.')[0]
[utils] Restrict parse_codecs and add theora as known vcodec (#21381)
2019-06-13 20:56:17 +02:00
if codec in ('avc1', 'avc2', 'avc3', 'avc4', 'vp9', 'vp8', 'hev1', 'hev2', 'h263', 'h264', 'mp4v', 'hvc1', 'av01', 'theora'):
[utils] add helper function for parsing codecs
2016-03-16 18:48:06 +01:00
if not vcodec:
vcodec = full_codec
[utils] Recognize more audio codecs (#13081)
2017-05-14 07:33:33 +02:00
elif codec in ('mp4a', 'opus', 'vorbis', 'mp3', 'aac', 'ac-3', 'ec-3', 'eac3', 'dtsc', 'dtse', 'dtsh', 'dtsl'):
[utils] add helper function for parsing codecs
2016-03-16 18:48:06 +01:00
if not acodec:
acodec = full_codec
else:
[utils] Recognize more audio codecs (#13081)
2017-05-14 07:33:33 +02:00
write_string('WARNING: Unknown codec %s\n' % full_codec, sys.stderr)
[utils] add helper function for parsing codecs
2016-03-16 18:48:06 +01:00
if not vcodec and not acodec:
Fix typos (#27084) * spelling: authorization Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: brightcove Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: creation Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exceeded Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exception Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extension Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extracting Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extraction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: frontline Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: improve Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: length Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: listsubtitles Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: multimedia Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: obfuscated Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: partitioning Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlist Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlists Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: restriction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: services Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: split Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: srmediathek Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: support Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: thumbnail Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: verification Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: whitespaces Signed-off-by: Josh Soref <jsoref@users.noreply.github.com>
2020-11-21 16:00:05 +01:00
if len(split_codecs) == 2:
[utils] add helper function for parsing codecs
2016-03-16 18:48:06 +01:00
return {
Fix typos (#27084) * spelling: authorization Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: brightcove Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: creation Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exceeded Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exception Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extension Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extracting Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extraction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: frontline Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: improve Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: length Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: listsubtitles Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: multimedia Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: obfuscated Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: partitioning Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlist Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlists Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: restriction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: services Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: split Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: srmediathek Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: support Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: thumbnail Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: verification Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: whitespaces Signed-off-by: Josh Soref <jsoref@users.noreply.github.com>
2020-11-21 16:00:05 +01:00
'vcodec': split_codecs[0],
'acodec': split_codecs[1],
[utils] add helper function for parsing codecs
2016-03-16 18:48:06 +01:00
}
else:
return {
'vcodec': vcodec or 'none',
'acodec': acodec or 'none',
}
return {}
[soulanime] Fix under Python 3
2015-01-04 02:20:45 +01:00
def urlhandle_detect_ext(url_handle):
[utils] Fix getheader in urlhandle_detect_ext Fixes #7049, related to #9440
2016-05-15 09:32:54 +02:00
getheader = url_handle.headers.get
[soulanime] Fix under Python 3
2015-01-04 02:20:45 +01:00
[hearthisat] Add support for more high-quality download links
2015-01-22 12:04:07 +01:00
cd = getheader('Content-Disposition')
if cd:
m = re.match(r'attachment;\s*filename="(?P<filename>[^"]+)"', cd)
if m:
e = determine_ext(m.group('filename'), default_ext=None)
if e:
return e
[sandia] Add new extractor (#4974)
2015-02-19 00:31:01 +01:00
return mimetype2ext(getheader('Content-Type'))
Respect age_limit when listing extractors (Fixes #4653)
2015-01-07 07:20:20 +01:00
[letv] Fix extraction Using data URIs for passing the decrypted M3U8 manifest, which is supported by ffmpeg only.
2015-07-22 14:03:05 +02:00
def encode_data_uri(data, mime_type):
return 'data:%s;base64,%s' % (mime_type, base64.b64encode(data).decode('ascii'))
Respect age_limit when listing extractors (Fixes #4653)
2015-01-07 07:20:20 +01:00
def age_restricted(content_limit, age_limit):
Revert "fix typos" This reverts commit 36a0e46c39ea4f211dea9944177976e8f8364736.
2016-01-10 19:27:22 +01:00
""" Returns True iff the content should be blocked """
Respect age_limit when listing extractors (Fixes #4653)
2015-01-07 07:20:20 +01:00
if age_limit is None: # No limit set
return False
if content_limit is None:
return False # Content available for everyone
return age_limit < content_limit
[generic] Add support for BOMs (Fixes #4753)
2015-01-23 01:21:30 +01:00
def is_html(first_bytes):
""" Detect whether a file contains HTML by examining its first bytes. """
BOMS = [
(b'\xef\xbb\xbf', 'utf-8'),
(b'\x00\x00\xfe\xff', 'utf-32-be'),
(b'\xff\xfe\x00\x00', 'utf-32-le'),
(b'\xff\xfe', 'utf-16-le'),
(b'\xfe\xff', 'utf-16-be'),
]
for bom, enc in BOMS:
if first_bytes.startswith(bom):
s = first_bytes[len(bom):].decode(enc, 'replace')
break
else:
s = first_bytes.decode('utf-8', 'replace')
return re.match(r'^\s*<', s)
[downloader] Improve downloader selection
2015-01-23 23:50:31 +01:00
def determine_protocol(info_dict):
protocol = info_dict.get('protocol')
if protocol is not None:
return protocol
url = info_dict['url']
if url.startswith('rtmp'):
return 'rtmp'
elif url.startswith('mms'):
return 'mms'
elif url.startswith('rtsp'):
return 'rtsp'
ext = determine_ext(url)
if ext == 'm3u8':
return 'm3u8'
elif ext == 'f4m':
return 'f4m'
return compat_urllib_parse_urlparse(url).scheme
Add --list-thumbnails
2015-01-25 02:38:47 +01:00
def render_table(header_row, data):
""" Render a list of rows, each as a list of values """
table = [header_row] + data
max_lens = [max(len(compat_str(v)) for v in col) for col in zip(*table)]
format_str = ' '.join('%-' + compat_str(ml + 1) + 's' for ml in max_lens[:-1]) + '%s'
return '\n'.join(format_str % tuple(row) for row in table)
[YoutubeDL] Add generic video filtering (Fixes #4916) This functionality is intended to eventually encompass the current format filtering.
2015-02-10 03:32:21 +01:00
def _match_one(filter_part, dct):
COMPARISON_OPERATORS = {
'<': operator.lt,
'<=': operator.le,
'>': operator.gt,
'>=': operator.ge,
'=': operator.eq,
'!=': operator.ne,
}
operator_rex = re.compile(r'''(?x)\s*
(?P<key>[a-z_]+)
\s*(?P<op>%s)(?P<none_inclusive>\s*\?)?\s*
(?:
(?P<intval>[0-9.]+(?:[kKmMgGtTpPeEzZyY]i?[Bb]?)?)|
[utils] Add support for quoted string literals in --match-filter (closes #8050, closes #12142, closes #12144)
2017-02-15 17:12:10 +01:00
(?P<quote>["\'])(?P<quotedstrval>(?:\\.|(?!(?P=quote)|\\).)+?)(?P=quote)|
[YoutubeDL] Add generic video filtering (Fixes #4916) This functionality is intended to eventually encompass the current format filtering.
2015-02-10 03:32:21 +01:00
(?P<strval>(?![0-9.])[a-z0-9A-Z]*)
)
\s*$
''' % '|'.join(map(re.escape, COMPARISON_OPERATORS.keys())))
m = operator_rex.search(filter_part)
if m:
op = COMPARISON_OPERATORS[m.group('op')]
[utils] Fix --match-filter for int-like strings (closes #11082)
2016-10-31 17:32:08 +01:00
actual_value = dct.get(m.group('key'))
Fix W504 and disable W503 (closes #20863)
2019-05-10 22:56:22 +02:00
if (m.group('quotedstrval') is not None
or m.group('strval') is not None
[utils] Fix --match-filter for int-like strings (closes #11082)
2016-10-31 17:32:08 +01:00
# If the original field is a string and matching comparisonvalue is
# a number we should respect the origin of the original field
# and process comparison value as a string (see
Start moving to ytdl-org
2019-03-09 13:14:41 +01:00
# https://github.com/ytdl-org/youtube-dl/issues/11082).
Fix W504 and disable W503 (closes #20863)
2019-05-10 22:56:22 +02:00
or actual_value is not None and m.group('intval') is not None
and isinstance(actual_value, compat_str)):
[YoutubeDL] Add generic video filtering (Fixes #4916) This functionality is intended to eventually encompass the current format filtering.
2015-02-10 03:32:21 +01:00
if m.group('op') not in ('=', '!='):
raise ValueError(
'Operator %s does not support string values!' % m.group('op'))
[utils] Add support for quoted string literals in --match-filter (closes #8050, closes #12142, closes #12144)
2017-02-15 17:12:10 +01:00
comparison_value = m.group('quotedstrval') or m.group('strval') or m.group('intval')
quote = m.group('quote')
if quote is not None:
comparison_value = comparison_value.replace(r'\%s' % quote, quote)
[YoutubeDL] Add generic video filtering (Fixes #4916) This functionality is intended to eventually encompass the current format filtering.
2015-02-10 03:32:21 +01:00
else:
try:
comparison_value = int(m.group('intval'))
except ValueError:
comparison_value = parse_filesize(m.group('intval'))
if comparison_value is None:
comparison_value = parse_filesize(m.group('intval') + 'B')
if comparison_value is None:
raise ValueError(
'Invalid integer value %r in filter part %r' % (
m.group('intval'), filter_part))
if actual_value is None:
return m.group('none_inclusive')
return op(actual_value, comparison_value)
UNARY_OPERATORS = {
[utils] Fix match_str for boolean meta fields
2018-04-24 18:49:30 +02:00
'': lambda v: (v is True) if isinstance(v, bool) else (v is not None),
'!': lambda v: (v is False) if isinstance(v, bool) else (v is None),
[YoutubeDL] Add generic video filtering (Fixes #4916) This functionality is intended to eventually encompass the current format filtering.
2015-02-10 03:32:21 +01:00
}
operator_rex = re.compile(r'''(?x)\s*
(?P<op>%s)\s*(?P<key>[a-z_]+)
\s*$
''' % '|'.join(map(re.escape, UNARY_OPERATORS.keys())))
m = operator_rex.search(filter_part)
if m:
op = UNARY_OPERATORS[m.group('op')]
actual_value = dct.get(m.group('key'))
return op(actual_value)
raise ValueError('Invalid filter part %r' % filter_part)
def match_str(filter_str, dct):
""" Filter a dictionary with a simple string syntax. Returns True (=passes filter) or false """
return all(
_match_one(filter_part, dct) for filter_part in filter_str.split('&'))
def match_filter_func(filter_str):
def _match_func(info_dict):
if match_str(filter_str, info_dict):
return None
else:
video_title = info_dict.get('title', info_dict.get('id', 'video'))
return '%s does not pass filter %s, skipping ..' % (video_title, filter_str)
return _match_func
[letv] Add --cn-verification-proxy (Closes #5077)
2015-03-03 00:03:06 +01:00
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
def parse_dfxp_time_expr(time_expr):
if not time_expr:
[utils] Fix TTML conversion Tolerate invalid timestamps (closes #7909)
2015-12-19 11:21:42 +01:00
return
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
mobj = re.match(r'^(?P<time_offset>\d+(?:\.\d+)?)s?$', time_expr)
if mobj:
return float(mobj.group('time_offset'))
[utils] Support alternative timestamp format in TTML Fixes #7608
2015-12-19 12:29:51 +01:00
mobj = re.match(r'^(\d+):(\d\d):(\d\d(?:(?:\.|:)\d+)?)$', time_expr)
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
if mobj:
[utils] Support alternative timestamp format in TTML Fixes #7608
2015-12-19 12:29:51 +01:00
return 3600 * int(mobj.group(1)) + 60 * int(mobj.group(2)) + float(mobj.group(3).replace(':', '.'))
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
[utils,common] Merge format_srt_time and _subtitles_timecode format_srt_time uses a comma as the delimiter between seconds and milliseconds while _subtitles_timecode uses a dot. All .srt examples I found on the Internet uses a comma, so I use a comma in the merged version. See http://matroska.org/technical/specs/subtitles/srt.html and http://devel.aegisub.org/wiki/SubtitleFormats/SRT
2015-05-12 07:04:54 +02:00
def srt_subtitles_timecode(seconds):
return '%02d:%02d:%02d,%03d' % (seconds / 3600, (seconds % 3600) / 60, seconds % 60, (seconds % 1) * 1000)
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
def dfxp2srt(dfxp_data):
[utils] Use bytes-like objects in dfxp2srt This fixes handling of non-UTF8 TTML subtitles Closes #14191
2017-09-16 06:18:38 +02:00
'''
@param dfxp_data A bytes-like object containing DFXP data
@returns A unicode object containing converted SRT data
'''
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
LEGACY_NAMESPACES = (
[utils] Use bytes-like objects in dfxp2srt This fixes handling of non-UTF8 TTML subtitles Closes #14191
2017-09-16 06:18:38 +02:00
(b'http://www.w3.org/ns/ttml', [
b'http://www.w3.org/2004/11/ttaf1',
b'http://www.w3.org/2006/04/ttaf1',
b'http://www.w3.org/2006/10/ttaf1',
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
]),
[utils] Use bytes-like objects in dfxp2srt This fixes handling of non-UTF8 TTML subtitles Closes #14191
2017-09-16 06:18:38 +02:00
(b'http://www.w3.org/ns/ttml#styling', [
b'http://www.w3.org/ns/ttml#style',
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
]),
)
SUPPORTED_STYLING = [
'color',
'fontFamily',
'fontSize',
'fontStyle',
'fontWeight',
'textDecoration'
]
[utils] Support ttaf1 namespace in TTML It's found in bbc.co.uk. See #6038
2015-06-21 13:16:59 +02:00
_x = functools.partial(xpath_with_ns, ns_map={
[utils] fix style id extraction for namespaced id attribute(closes #16551)
2018-05-26 15:35:47 +02:00
'xml': 'http://www.w3.org/XML/1998/namespace',
[utils] Support ttaf1 namespace in TTML It's found in bbc.co.uk. See #6038
2015-06-21 13:16:59 +02:00
'ttml': 'http://www.w3.org/ns/ttml',
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
'tts': 'http://www.w3.org/ns/ttml#styling',
[utils] Support ttaf1 namespace in TTML It's found in bbc.co.uk. See #6038
2015-06-21 13:16:59 +02:00
})
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
styles = {}
default_style = {}
[utils] dfxp2srt: make TTMLPElementParser inherit from object For consistency between python 2 and 3.
2016-02-02 22:30:13 +01:00
class TTMLPElementParser(object):
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
_out = ''
_unclosed_elements = []
_applied_styles = []
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
[utils] fix dfxp2srt text extraction(fixes #8055)
2016-01-28 12:38:34 +01:00
def start(self, tag, attrib):
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
if tag in (_x('ttml:br'), 'br'):
self._out += '\n'
else:
unclosed_elements = []
style = {}
element_style_id = attrib.get('style')
if default_style:
style.update(default_style)
if element_style_id:
style.update(styles.get(element_style_id, {}))
for prop in SUPPORTED_STYLING:
prop_val = attrib.get(_x('tts:' + prop))
if prop_val:
style[prop] = prop_val
if style:
font = ''
for k, v in sorted(style.items()):
if self._applied_styles and self._applied_styles[-1].get(k) == v:
continue
if k == 'color':
font += ' color="%s"' % v
elif k == 'fontSize':
font += ' size="%s"' % v
elif k == 'fontFamily':
font += ' face="%s"' % v
elif k == 'fontWeight' and v == 'bold':
self._out += '<b>'
unclosed_elements.append('b')
elif k == 'fontStyle' and v == 'italic':
self._out += '<i>'
unclosed_elements.append('i')
elif k == 'textDecoration' and v == 'underline':
self._out += '<u>'
unclosed_elements.append('u')
if font:
self._out += '<font' + font + '>'
unclosed_elements.append('font')
applied_style = {}
if self._applied_styles:
applied_style.update(self._applied_styles[-1])
applied_style.update(style)
self._applied_styles.append(applied_style)
self._unclosed_elements.append(unclosed_elements)
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
[utils] fix dfxp2srt text extraction(fixes #8055)
2016-01-28 12:38:34 +01:00
def end(self, tag):
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
if tag not in (_x('ttml:br'), 'br'):
unclosed_elements = self._unclosed_elements.pop()
for element in reversed(unclosed_elements):
self._out += '</%s>' % element
if unclosed_elements and self._applied_styles:
self._applied_styles.pop()
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
[utils] fix dfxp2srt text extraction(fixes #8055)
2016-01-28 12:38:34 +01:00
def data(self, data):
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
self._out += data
[utils] fix dfxp2srt text extraction(fixes #8055)
2016-01-28 12:38:34 +01:00
def close(self):
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
return self._out.strip()
[utils] fix dfxp2srt text extraction(fixes #8055)
2016-01-28 12:38:34 +01:00
def parse_node(node):
target = TTMLPElementParser()
parser = xml.etree.ElementTree.XMLParser(target=target)
parser.feed(xml.etree.ElementTree.tostring(node))
return parser.close()
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
for k, v in LEGACY_NAMESPACES:
for ns in v:
dfxp_data = dfxp_data.replace(ns, k)
[utils] Use bytes-like objects in dfxp2srt This fixes handling of non-UTF8 TTML subtitles Closes #14191
2017-09-16 06:18:38 +02:00
dfxp = compat_etree_fromstring(dfxp_data)
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
out = []
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
paras = dfxp.findall(_x('.//ttml:p')) or dfxp.findall('.//p')
[utils] Support TTML without default namespace In a strict sense such TTML is invalid, but Yahoo uses it.
2015-05-18 18:45:01 +02:00
if not paras:
raise ValueError('Invalid dfxp/TTML subtitle')
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
repeat = False
while True:
for style in dfxp.findall(_x('.//ttml:style')):
[utils] fix style id extraction for namespaced id attribute(closes #16551)
2018-05-26 15:35:47 +02:00
style_id = style.get('id') or style.get(_x('xml:id'))
if not style_id:
continue
[utils] add support for ttml styles
2017-02-23 18:46:20 +01:00
parent_style_id = style.get('style')
if parent_style_id:
if parent_style_id not in styles:
repeat = True
continue
styles[style_id] = styles[parent_style_id].copy()
for prop in SUPPORTED_STYLING:
prop_val = style.get(_x('tts:' + prop))
if prop_val:
styles.setdefault(style_id, {})[prop] = prop_val
if repeat:
repeat = False
else:
break
for p in ('body', 'div'):
ele = xpath_element(dfxp, [_x('.//ttml:' + p), './/' + p])
if ele is None:
continue
style = styles.get(ele.get('style'))
if not style:
continue
default_style.update(style)
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
for para, index in zip(paras, itertools.count(1)):
[utils] Fix TTML conversion Tolerate invalid timestamps (closes #7909)
2015-12-19 11:21:42 +01:00
begin_time = parse_dfxp_time_expr(para.attrib.get('begin'))
[utils] Support 'dur' field in TTML
2015-05-12 06:47:37 +02:00
end_time = parse_dfxp_time_expr(para.attrib.get('end'))
[utils] Fix TTML conversion Tolerate invalid timestamps (closes #7909)
2015-12-19 11:21:42 +01:00
dur = parse_dfxp_time_expr(para.attrib.get('dur'))
if begin_time is None:
continue
[utils] Support 'dur' field in TTML
2015-05-12 06:47:37 +02:00
if not end_time:
[utils] Fix TTML conversion Tolerate invalid timestamps (closes #7909)
2015-12-19 11:21:42 +01:00
if not dur:
continue
end_time = begin_time + dur
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
out.append('%d\n%s --> %s\n%s\n\n' % (
index,
[utils,common] Merge format_srt_time and _subtitles_timecode format_srt_time uses a comma as the delimiter between seconds and milliseconds while _subtitles_timecode uses a dot. All .srt examples I found on the Internet uses a comma, so I use a comma in the merged version. See http://matroska.org/technical/specs/subtitles/srt.html and http://devel.aegisub.org/wiki/SubtitleFormats/SRT
2015-05-12 07:04:54 +02:00
srt_subtitles_timecode(begin_time),
srt_subtitles_timecode(end_time),
[ffmpeg] Add dfxp (TTML) subtitles support (#3432, #5146)
2015-04-25 17:15:05 +02:00
parse_node(para)))
return ''.join(out)
[utils] Generalize cli option converters
2015-09-04 23:05:11 +02:00
def cli_option(params, command_option, param):
param = params.get(param)
[external/curl] respect more downloader options and display progress
2016-08-12 13:30:02 +02:00
if param:
param = compat_str(param)
[utils] Generalize cli option converters
2015-09-04 23:05:11 +02:00
return [command_option, param] if param is not None else []
def cli_bool_option(params, command_option, param, true_value='true', false_value='false', separator=None):
param = params.get(param)
[utils] Skip missing params in cli_bool_option (closes #13865)
2017-08-09 17:28:19 +02:00
if param is None:
return []
[utils] Generalize cli option converters
2015-09-04 23:05:11 +02:00
assert isinstance(param, bool)
if separator:
return [command_option + separator + (true_value if param else false_value)]
return [command_option, true_value if param else false_value]
def cli_valueless_option(params, command_option, param, expected_value=True):
param = params.get(param)
return [command_option] if param == expected_value else []
def cli_configuration_args(params, param, default=[]):
ex_args = params.get(param)
if ex_args is None:
return default
assert isinstance(ex_args, list)
return ex_args
[utils/ffmpeg] Move ISO 639 related codes to utils
2015-06-21 12:53:17 +02:00
class ISO639Utils(object):
# See http://www.loc.gov/standards/iso639-2/ISO-639-2_utf-8.txt
_lang_map = {
'aa': 'aar',
'ab': 'abk',
'ae': 'ave',
'af': 'afr',
'ak': 'aka',
'am': 'amh',
'an': 'arg',
'ar': 'ara',
'as': 'asm',
'av': 'ava',
'ay': 'aym',
'az': 'aze',
'ba': 'bak',
'be': 'bel',
'bg': 'bul',
'bh': 'bih',
'bi': 'bis',
'bm': 'bam',
'bn': 'ben',
'bo': 'bod',
'br': 'bre',
'bs': 'bos',
'ca': 'cat',
'ce': 'che',
'ch': 'cha',
'co': 'cos',
'cr': 'cre',
'cs': 'ces',
'cu': 'chu',
'cv': 'chv',
'cy': 'cym',
'da': 'dan',
'de': 'deu',
'dv': 'div',
'dz': 'dzo',
'ee': 'ewe',
'el': 'ell',
'en': 'eng',
'eo': 'epo',
'es': 'spa',
'et': 'est',
'eu': 'eus',
'fa': 'fas',
'ff': 'ful',
'fi': 'fin',
'fj': 'fij',
'fo': 'fao',
'fr': 'fra',
'fy': 'fry',
'ga': 'gle',
'gd': 'gla',
'gl': 'glg',
'gn': 'grn',
'gu': 'guj',
'gv': 'glv',
'ha': 'hau',
'he': 'heb',
[utils] Add language codes replaced in 1989 revision of ISO 639 to ISO639Utils (closes #18765)
2019-01-06 18:55:39 +01:00
'iw': 'heb', # Replaced by he in 1989 revision
[utils/ffmpeg] Move ISO 639 related codes to utils
2015-06-21 12:53:17 +02:00
'hi': 'hin',
'ho': 'hmo',
'hr': 'hrv',
'ht': 'hat',
'hu': 'hun',
'hy': 'hye',
'hz': 'her',
'ia': 'ina',
'id': 'ind',
[utils] Add language codes replaced in 1989 revision of ISO 639 to ISO639Utils (closes #18765)
2019-01-06 18:55:39 +01:00
'in': 'ind', # Replaced by id in 1989 revision
[utils/ffmpeg] Move ISO 639 related codes to utils
2015-06-21 12:53:17 +02:00
'ie': 'ile',
'ig': 'ibo',
'ii': 'iii',
'ik': 'ipk',
'io': 'ido',
'is': 'isl',
'it': 'ita',
'iu': 'iku',
'ja': 'jpn',
'jv': 'jav',
'ka': 'kat',
'kg': 'kon',
'ki': 'kik',
'kj': 'kua',
'kk': 'kaz',
'kl': 'kal',
'km': 'khm',
'kn': 'kan',
'ko': 'kor',
'kr': 'kau',
'ks': 'kas',
'ku': 'kur',
'kv': 'kom',
'kw': 'cor',
'ky': 'kir',
'la': 'lat',
'lb': 'ltz',
'lg': 'lug',
'li': 'lim',
'ln': 'lin',
'lo': 'lao',
'lt': 'lit',
'lu': 'lub',
'lv': 'lav',
'mg': 'mlg',
'mh': 'mah',
'mi': 'mri',
'mk': 'mkd',
'ml': 'mal',
'mn': 'mon',
'mr': 'mar',
'ms': 'msa',
'mt': 'mlt',
'my': 'mya',
'na': 'nau',
'nb': 'nob',
'nd': 'nde',
'ne': 'nep',
'ng': 'ndo',
'nl': 'nld',
'nn': 'nno',
'no': 'nor',
'nr': 'nbl',
'nv': 'nav',
'ny': 'nya',
'oc': 'oci',
'oj': 'oji',
'om': 'orm',
'or': 'ori',
'os': 'oss',
'pa': 'pan',
'pi': 'pli',
'pl': 'pol',
'ps': 'pus',
'pt': 'por',
'qu': 'que',
'rm': 'roh',
'rn': 'run',
'ro': 'ron',
'ru': 'rus',
'rw': 'kin',
'sa': 'san',
'sc': 'srd',
'sd': 'snd',
'se': 'sme',
'sg': 'sag',
'si': 'sin',
'sk': 'slk',
'sl': 'slv',
'sm': 'smo',
'sn': 'sna',
'so': 'som',
'sq': 'sqi',
'sr': 'srp',
'ss': 'ssw',
'st': 'sot',
'su': 'sun',
'sv': 'swe',
'sw': 'swa',
'ta': 'tam',
'te': 'tel',
'tg': 'tgk',
'th': 'tha',
'ti': 'tir',
'tk': 'tuk',
'tl': 'tgl',
'tn': 'tsn',
'to': 'ton',
'tr': 'tur',
'ts': 'tso',
'tt': 'tat',
'tw': 'twi',
'ty': 'tah',
'ug': 'uig',
'uk': 'ukr',
'ur': 'urd',
'uz': 'uzb',
've': 'ven',
'vi': 'vie',
'vo': 'vol',
'wa': 'wln',
'wo': 'wol',
'xh': 'xho',
'yi': 'yid',
[utils] Fix typo
2019-01-06 19:02:34 +01:00
'ji': 'yid', # Replaced by yi in 1989 revision
[utils/ffmpeg] Move ISO 639 related codes to utils
2015-06-21 12:53:17 +02:00
'yo': 'yor',
'za': 'zha',
'zh': 'zho',
'zu': 'zul',
}
@classmethod
def short2long(cls, code):
"""Convert language code from ISO 639-1 to ISO 639-2/T"""
return cls._lang_map.get(code[:2])
@classmethod
def long2short(cls, code):
"""Convert language code from ISO 639-2/T to ISO 639-1"""
for short_name, long_name in cls._lang_map.items():
if long_name == code:
return short_name
[utils] Add ISO3166Utils
2015-06-27 07:13:57 +02:00
class ISO3166Utils(object):
# From http://data.okfn.org/data/core/country-list
_country_map = {
'AF': 'Afghanistan',
'AX': 'Åland Islands',
'AL': 'Albania',
'DZ': 'Algeria',
'AS': 'American Samoa',
'AD': 'Andorra',
'AO': 'Angola',
'AI': 'Anguilla',
'AQ': 'Antarctica',
'AG': 'Antigua and Barbuda',
'AR': 'Argentina',
'AM': 'Armenia',
'AW': 'Aruba',
'AU': 'Australia',
'AT': 'Austria',
'AZ': 'Azerbaijan',
'BS': 'Bahamas',
'BH': 'Bahrain',
'BD': 'Bangladesh',
'BB': 'Barbados',
'BY': 'Belarus',
'BE': 'Belgium',
'BZ': 'Belize',
'BJ': 'Benin',
'BM': 'Bermuda',
'BT': 'Bhutan',
'BO': 'Bolivia, Plurinational State of',
'BQ': 'Bonaire, Sint Eustatius and Saba',
'BA': 'Bosnia and Herzegovina',
'BW': 'Botswana',
'BV': 'Bouvet Island',
'BR': 'Brazil',
'IO': 'British Indian Ocean Territory',
'BN': 'Brunei Darussalam',
'BG': 'Bulgaria',
'BF': 'Burkina Faso',
'BI': 'Burundi',
'KH': 'Cambodia',
'CM': 'Cameroon',
'CA': 'Canada',
'CV': 'Cape Verde',
'KY': 'Cayman Islands',
'CF': 'Central African Republic',
'TD': 'Chad',
'CL': 'Chile',
'CN': 'China',
'CX': 'Christmas Island',
'CC': 'Cocos (Keeling) Islands',
'CO': 'Colombia',
'KM': 'Comoros',
'CG': 'Congo',
'CD': 'Congo, the Democratic Republic of the',
'CK': 'Cook Islands',
'CR': 'Costa Rica',
'CI': 'Côte d\'Ivoire',
'HR': 'Croatia',
'CU': 'Cuba',
'CW': 'Curaçao',
'CY': 'Cyprus',
'CZ': 'Czech Republic',
'DK': 'Denmark',
'DJ': 'Djibouti',
'DM': 'Dominica',
'DO': 'Dominican Republic',
'EC': 'Ecuador',
'EG': 'Egypt',
'SV': 'El Salvador',
'GQ': 'Equatorial Guinea',
'ER': 'Eritrea',
'EE': 'Estonia',
'ET': 'Ethiopia',
'FK': 'Falkland Islands (Malvinas)',
'FO': 'Faroe Islands',
'FJ': 'Fiji',
'FI': 'Finland',
'FR': 'France',
'GF': 'French Guiana',
'PF': 'French Polynesia',
'TF': 'French Southern Territories',
'GA': 'Gabon',
'GM': 'Gambia',
'GE': 'Georgia',
'DE': 'Germany',
'GH': 'Ghana',
'GI': 'Gibraltar',
'GR': 'Greece',
'GL': 'Greenland',
'GD': 'Grenada',
'GP': 'Guadeloupe',
'GU': 'Guam',
'GT': 'Guatemala',
'GG': 'Guernsey',
'GN': 'Guinea',
'GW': 'Guinea-Bissau',
'GY': 'Guyana',
'HT': 'Haiti',
'HM': 'Heard Island and McDonald Islands',
'VA': 'Holy See (Vatican City State)',
'HN': 'Honduras',
'HK': 'Hong Kong',
'HU': 'Hungary',
'IS': 'Iceland',
'IN': 'India',
'ID': 'Indonesia',
'IR': 'Iran, Islamic Republic of',
'IQ': 'Iraq',
'IE': 'Ireland',
'IM': 'Isle of Man',
'IL': 'Israel',
'IT': 'Italy',
'JM': 'Jamaica',
'JP': 'Japan',
'JE': 'Jersey',
'JO': 'Jordan',
'KZ': 'Kazakhstan',
'KE': 'Kenya',
'KI': 'Kiribati',
'KP': 'Korea, Democratic People\'s Republic of',
'KR': 'Korea, Republic of',
'KW': 'Kuwait',
'KG': 'Kyrgyzstan',
'LA': 'Lao People\'s Democratic Republic',
'LV': 'Latvia',
'LB': 'Lebanon',
'LS': 'Lesotho',
'LR': 'Liberia',
'LY': 'Libya',
'LI': 'Liechtenstein',
'LT': 'Lithuania',
'LU': 'Luxembourg',
'MO': 'Macao',
'MK': 'Macedonia, the Former Yugoslav Republic of',
'MG': 'Madagascar',
'MW': 'Malawi',
'MY': 'Malaysia',
'MV': 'Maldives',
'ML': 'Mali',
'MT': 'Malta',
'MH': 'Marshall Islands',
'MQ': 'Martinique',
'MR': 'Mauritania',
'MU': 'Mauritius',
'YT': 'Mayotte',
'MX': 'Mexico',
'FM': 'Micronesia, Federated States of',
'MD': 'Moldova, Republic of',
'MC': 'Monaco',
'MN': 'Mongolia',
'ME': 'Montenegro',
'MS': 'Montserrat',
'MA': 'Morocco',
'MZ': 'Mozambique',
'MM': 'Myanmar',
'NA': 'Namibia',
'NR': 'Nauru',
'NP': 'Nepal',
'NL': 'Netherlands',
'NC': 'New Caledonia',
'NZ': 'New Zealand',
'NI': 'Nicaragua',
'NE': 'Niger',
'NG': 'Nigeria',
'NU': 'Niue',
'NF': 'Norfolk Island',
'MP': 'Northern Mariana Islands',
'NO': 'Norway',
'OM': 'Oman',
'PK': 'Pakistan',
'PW': 'Palau',
'PS': 'Palestine, State of',
'PA': 'Panama',
'PG': 'Papua New Guinea',
'PY': 'Paraguay',
'PE': 'Peru',
'PH': 'Philippines',
'PN': 'Pitcairn',
'PL': 'Poland',
'PT': 'Portugal',
'PR': 'Puerto Rico',
'QA': 'Qatar',
'RE': 'Réunion',
'RO': 'Romania',
'RU': 'Russian Federation',
'RW': 'Rwanda',
'BL': 'Saint Barthélemy',
'SH': 'Saint Helena, Ascension and Tristan da Cunha',
'KN': 'Saint Kitts and Nevis',
'LC': 'Saint Lucia',
'MF': 'Saint Martin (French part)',
'PM': 'Saint Pierre and Miquelon',
'VC': 'Saint Vincent and the Grenadines',
'WS': 'Samoa',
'SM': 'San Marino',
'ST': 'Sao Tome and Principe',
'SA': 'Saudi Arabia',
'SN': 'Senegal',
'RS': 'Serbia',
'SC': 'Seychelles',
'SL': 'Sierra Leone',
'SG': 'Singapore',
'SX': 'Sint Maarten (Dutch part)',
'SK': 'Slovakia',
'SI': 'Slovenia',
'SB': 'Solomon Islands',
'SO': 'Somalia',
'ZA': 'South Africa',
'GS': 'South Georgia and the South Sandwich Islands',
'SS': 'South Sudan',
'ES': 'Spain',
'LK': 'Sri Lanka',
'SD': 'Sudan',
'SR': 'Suriname',
'SJ': 'Svalbard and Jan Mayen',
'SZ': 'Swaziland',
'SE': 'Sweden',
'CH': 'Switzerland',
'SY': 'Syrian Arab Republic',
'TW': 'Taiwan, Province of China',
'TJ': 'Tajikistan',
'TZ': 'Tanzania, United Republic of',
'TH': 'Thailand',
'TL': 'Timor-Leste',
'TG': 'Togo',
'TK': 'Tokelau',
'TO': 'Tonga',
'TT': 'Trinidad and Tobago',
'TN': 'Tunisia',
'TR': 'Turkey',
'TM': 'Turkmenistan',
'TC': 'Turks and Caicos Islands',
'TV': 'Tuvalu',
'UG': 'Uganda',
'UA': 'Ukraine',
'AE': 'United Arab Emirates',
'GB': 'United Kingdom',
'US': 'United States',
'UM': 'United States Minor Outlying Islands',
'UY': 'Uruguay',
'UZ': 'Uzbekistan',
'VU': 'Vanuatu',
'VE': 'Venezuela, Bolivarian Republic of',
'VN': 'Viet Nam',
'VG': 'Virgin Islands, British',
'VI': 'Virgin Islands, U.S.',
'WF': 'Wallis and Futuna',
'EH': 'Western Sahara',
'YE': 'Yemen',
'ZM': 'Zambia',
'ZW': 'Zimbabwe',
}
@classmethod
def short2full(cls, code):
"""Convert an ISO 3166-2 country code to the corresponding full name"""
return cls._country_map.get(code.upper())
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
class GeoUtils(object):
# Major IPv4 address blocks per country
_country_ip_map = {
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'AD': '46.172.224.0/19',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'AE': '94.200.0.0/13',
'AF': '149.54.0.0/17',
'AG': '209.59.64.0/18',
'AI': '204.14.248.0/21',
'AL': '46.99.0.0/16',
'AM': '46.70.0.0/15',
'AO': '105.168.0.0/13',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'AP': '182.50.184.0/21',
'AQ': '23.154.160.0/24',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'AR': '181.0.0.0/12',
'AS': '202.70.112.0/20',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'AT': '77.116.0.0/14',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'AU': '1.128.0.0/11',
'AW': '181.41.0.0/18',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'AX': '185.217.4.0/22',
'AZ': '5.197.0.0/16',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'BA': '31.176.128.0/17',
'BB': '65.48.128.0/17',
'BD': '114.130.0.0/16',
'BE': '57.0.0.0/8',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'BF': '102.178.0.0/15',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'BG': '95.42.0.0/15',
'BH': '37.131.0.0/17',
'BI': '154.117.192.0/18',
'BJ': '137.255.0.0/16',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'BL': '185.212.72.0/23',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'BM': '196.12.64.0/18',
'BN': '156.31.0.0/16',
'BO': '161.56.0.0/16',
'BQ': '161.0.80.0/20',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'BR': '191.128.0.0/12',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'BS': '24.51.64.0/18',
'BT': '119.2.96.0/19',
'BW': '168.167.0.0/16',
'BY': '178.120.0.0/13',
'BZ': '179.42.192.0/18',
'CA': '99.224.0.0/11',
'CD': '41.243.0.0/16',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'CF': '197.242.176.0/21',
'CG': '160.113.0.0/16',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'CH': '85.0.0.0/13',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'CI': '102.136.0.0/14',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'CK': '202.65.32.0/19',
'CL': '152.172.0.0/14',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'CM': '102.244.0.0/14',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'CN': '36.128.0.0/10',
'CO': '181.240.0.0/12',
'CR': '201.192.0.0/12',
'CU': '152.206.0.0/15',
'CV': '165.90.96.0/19',
'CW': '190.88.128.0/17',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'CY': '31.153.0.0/16',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'CZ': '88.100.0.0/14',
'DE': '53.0.0.0/8',
'DJ': '197.241.0.0/17',
'DK': '87.48.0.0/12',
'DM': '192.243.48.0/20',
'DO': '152.166.0.0/15',
'DZ': '41.96.0.0/12',
'EC': '186.68.0.0/15',
'EE': '90.190.0.0/15',
'EG': '156.160.0.0/11',
'ER': '196.200.96.0/20',
'ES': '88.0.0.0/11',
'ET': '196.188.0.0/14',
'EU': '2.16.0.0/13',
'FI': '91.152.0.0/13',
'FJ': '144.120.0.0/16',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'FK': '80.73.208.0/21',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'FM': '119.252.112.0/20',
'FO': '88.85.32.0/19',
'FR': '90.0.0.0/9',
'GA': '41.158.0.0/15',
'GB': '25.0.0.0/8',
'GD': '74.122.88.0/21',
'GE': '31.146.0.0/16',
'GF': '161.22.64.0/18',
'GG': '62.68.160.0/19',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'GH': '154.160.0.0/12',
'GI': '95.164.0.0/16',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'GL': '88.83.0.0/19',
'GM': '160.182.0.0/15',
'GN': '197.149.192.0/18',
'GP': '104.250.0.0/19',
'GQ': '105.235.224.0/20',
'GR': '94.64.0.0/13',
'GT': '168.234.0.0/16',
'GU': '168.123.0.0/16',
'GW': '197.214.80.0/20',
'GY': '181.41.64.0/18',
'HK': '113.252.0.0/14',
'HN': '181.210.0.0/16',
'HR': '93.136.0.0/13',
'HT': '148.102.128.0/17',
'HU': '84.0.0.0/14',
'ID': '39.192.0.0/10',
'IE': '87.32.0.0/12',
'IL': '79.176.0.0/13',
'IM': '5.62.80.0/20',
'IN': '117.192.0.0/10',
'IO': '203.83.48.0/21',
'IQ': '37.236.0.0/14',
'IR': '2.176.0.0/12',
'IS': '82.221.0.0/16',
'IT': '79.0.0.0/10',
'JE': '87.244.64.0/18',
'JM': '72.27.0.0/17',
'JO': '176.29.0.0/16',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'JP': '133.0.0.0/8',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'KE': '105.48.0.0/12',
'KG': '158.181.128.0/17',
'KH': '36.37.128.0/17',
'KI': '103.25.140.0/22',
'KM': '197.255.224.0/20',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'KN': '198.167.192.0/19',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'KP': '175.45.176.0/22',
'KR': '175.192.0.0/10',
'KW': '37.36.0.0/14',
'KY': '64.96.0.0/15',
'KZ': '2.72.0.0/13',
'LA': '115.84.64.0/18',
'LB': '178.135.0.0/16',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'LC': '24.92.144.0/20',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'LI': '82.117.0.0/19',
'LK': '112.134.0.0/15',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'LR': '102.183.0.0/16',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'LS': '129.232.0.0/17',
'LT': '78.56.0.0/13',
'LU': '188.42.0.0/16',
'LV': '46.109.0.0/16',
'LY': '41.252.0.0/14',
'MA': '105.128.0.0/11',
'MC': '88.209.64.0/18',
'MD': '37.246.0.0/16',
'ME': '178.175.0.0/17',
'MF': '74.112.232.0/21',
'MG': '154.126.0.0/17',
'MH': '117.103.88.0/21',
'MK': '77.28.0.0/15',
'ML': '154.118.128.0/18',
'MM': '37.111.0.0/17',
'MN': '49.0.128.0/17',
'MO': '60.246.0.0/16',
'MP': '202.88.64.0/20',
'MQ': '109.203.224.0/19',
'MR': '41.188.64.0/18',
'MS': '208.90.112.0/22',
'MT': '46.11.0.0/16',
'MU': '105.16.0.0/12',
'MV': '27.114.128.0/18',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'MW': '102.70.0.0/15',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'MX': '187.192.0.0/11',
'MY': '175.136.0.0/13',
'MZ': '197.218.0.0/15',
'NA': '41.182.0.0/16',
'NC': '101.101.0.0/18',
'NE': '197.214.0.0/18',
'NF': '203.17.240.0/22',
'NG': '105.112.0.0/12',
'NI': '186.76.0.0/15',
'NL': '145.96.0.0/11',
'NO': '84.208.0.0/13',
'NP': '36.252.0.0/15',
'NR': '203.98.224.0/19',
'NU': '49.156.48.0/22',
'NZ': '49.224.0.0/14',
'OM': '5.36.0.0/15',
'PA': '186.72.0.0/15',
'PE': '186.160.0.0/14',
'PF': '123.50.64.0/18',
'PG': '124.240.192.0/19',
'PH': '49.144.0.0/13',
'PK': '39.32.0.0/11',
'PL': '83.0.0.0/11',
'PM': '70.36.0.0/20',
'PR': '66.50.0.0/16',
'PS': '188.161.0.0/16',
'PT': '85.240.0.0/13',
'PW': '202.124.224.0/20',
'PY': '181.120.0.0/14',
'QA': '37.210.0.0/15',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'RE': '102.35.0.0/16',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'RO': '79.112.0.0/13',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'RS': '93.86.0.0/15',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'RU': '5.136.0.0/13',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'RW': '41.186.0.0/16',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'SA': '188.48.0.0/13',
'SB': '202.1.160.0/19',
'SC': '154.192.0.0/11',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'SD': '102.120.0.0/13',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'SE': '78.64.0.0/12',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'SG': '8.128.0.0/10',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'SI': '188.196.0.0/14',
'SK': '78.98.0.0/15',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'SL': '102.143.0.0/17',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'SM': '89.186.32.0/19',
'SN': '41.82.0.0/15',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'SO': '154.115.192.0/18',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'SR': '186.179.128.0/17',
'SS': '105.235.208.0/21',
'ST': '197.159.160.0/19',
'SV': '168.243.0.0/16',
'SX': '190.102.0.0/20',
'SY': '5.0.0.0/16',
'SZ': '41.84.224.0/19',
'TC': '65.255.48.0/20',
'TD': '154.68.128.0/19',
'TG': '196.168.0.0/14',
'TH': '171.96.0.0/13',
'TJ': '85.9.128.0/18',
'TK': '27.96.24.0/21',
'TL': '180.189.160.0/20',
'TM': '95.85.96.0/19',
'TN': '197.0.0.0/11',
'TO': '175.176.144.0/21',
'TR': '78.160.0.0/11',
'TT': '186.44.0.0/15',
'TV': '202.2.96.0/19',
'TW': '120.96.0.0/11',
'TZ': '156.156.0.0/14',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'UA': '37.52.0.0/14',
'UG': '102.80.0.0/13',
'US': '6.0.0.0/8',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'UY': '167.56.0.0/13',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'UZ': '84.54.64.0/18',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'VA': '212.77.0.0/19',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'VC': '207.191.240.0/21',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'VE': '186.88.0.0/13',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'VG': '66.81.192.0/20',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
'VI': '146.226.0.0/16',
'VN': '14.160.0.0/11',
'VU': '202.80.32.0/20',
'WF': '117.20.32.0/21',
'WS': '202.4.32.0/19',
'YE': '134.35.0.0/16',
'YT': '41.242.116.0/22',
'ZA': '41.0.0.0/11',
[utils] Actualize major IPv4 address blocks per country
2019-10-29 00:10:20 +01:00
'ZM': '102.144.0.0/13',
'ZW': '102.177.192.0/18',
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
}
@classmethod
Improve geo bypass mechanism * Introduce geo bypass context * Add ability to bypass based on IP blocks in CIDR notation * Introduce --geo-bypass-ip-block
2018-05-02 02:18:01 +02:00
def random_ipv4(cls, code_or_block):
if len(code_or_block) == 2:
block = cls._country_ip_map.get(code_or_block.upper())
if not block:
return None
else:
block = code_or_block
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
addr, preflen = block.split('/')
addr_min = compat_struct_unpack('!L', socket.inet_aton(addr))[0]
addr_max = addr_min | (0xffffffff >> int(preflen))
[utils] Make random_ipv4 return unicode string
2017-02-04 14:26:43 +01:00
return compat_str(socket.inet_ntoa(
Improve geo bypass mechanism * Rename options to preffixly match with --geo-verification-proxy * Introduce _GEO_COUNTRIES for extractors * Implement faking IP right away for sites with known geo restriction
2017-02-18 21:53:23 +01:00
compat_struct_pack('!L', random.randint(addr_min, addr_max))))
Add experimental geo restriction bypass mechanism Based on faking X-Forwarded-For HTTP header
2017-02-04 12:49:58 +01:00
[letv] Add --cn-verification-proxy (Closes #5077)
2015-03-03 00:03:06 +01:00
class PerRequestProxyHandler(compat_urllib_request.ProxyHandler):
[utils] Correct per-request proxy handling
2015-03-03 13:56:06 +01:00
def __init__(self, proxies=None):
# Set default handlers
for type in ('http', 'https'):
setattr(self, '%s_open' % type,
lambda r, proxy='__noproxy__', type=type, meth=self.proxy_open:
meth(r, proxy, type))
[utils] Remove return from __init__
2018-07-29 00:52:42 +02:00
compat_urllib_request.ProxyHandler.__init__(self, proxies)
[utils] Correct per-request proxy handling
2015-03-03 13:56:06 +01:00
[letv] Add --cn-verification-proxy (Closes #5077)
2015-03-03 00:03:06 +01:00
def proxy_open(self, req, proxy, type):
[utils] Correct per-request proxy handling
2015-03-03 13:56:06 +01:00
req_proxy = req.headers.get('Ytdl-request-proxy')
[letv] Add --cn-verification-proxy (Closes #5077)
2015-03-03 00:03:06 +01:00
if req_proxy is not None:
proxy = req_proxy
[utils] Correct per-request proxy handling
2015-03-03 13:56:06 +01:00
del req.headers['Ytdl-request-proxy']
if proxy == '__noproxy__':
return None # No Proxy
[utils] Add parse_qs, update_url [skip ci]
2023-02-05 14:46:43 +01:00
if compat_urllib_parse.urlparse(proxy).scheme.lower() in ('socks', 'socks4', 'socks4a', 'socks5'):
[socks] Support SOCKS proxies
2016-04-23 15:30:06 +02:00
req.add_header('Ytdl-socks-proxy', proxy)
# youtube-dl's http/https handlers do wrapping the socket with socks
return None
[letv] Add --cn-verification-proxy (Closes #5077)
2015-03-03 00:03:06 +01:00
return compat_urllib_request.ProxyHandler.proxy_open(
self, req, proxy, type)
[utils] Add OHDave's RSA encryption function
2016-02-16 23:01:44 +01:00
[utils] Add bytes_to_long() and long_to_bytes() Used in daisuki.net (#4738) Both are adapted from public domain PyCrypto: https://github.com/dlitz/pycrypto/blob/master/lib/Crypto/Util/number.py
2017-02-28 12:16:55 +01:00
# Both long_to_bytes and bytes_to_long are adapted from PyCrypto, which is
# released into Public Domain
# https://github.com/dlitz/pycrypto/blob/master/lib/Crypto/Util/number.py#L387
def long_to_bytes(n, blocksize=0):
"""long_to_bytes(n:long, blocksize:int) : string
Convert a long integer to a byte string.
If optional blocksize is given and greater than zero, pad the front of the
byte string with binary zeros so that the length is a multiple of
blocksize.
"""
# after much testing, this algorithm was deemed to be the fastest
s = b''
n = int(n)
while n > 0:
s = compat_struct_pack('>I', n & 0xffffffff) + s
n = n >> 32
# strip off leading zeros
for i in range(len(s)):
if s[i] != b'\000'[0]:
break
else:
# only happens when n == 0
s = b'\000'
i = 0
s = s[i:]
# add back some pad bytes. this could be done more efficiently w.r.t. the
# de-padding being done above, but sigh...
if blocksize > 0 and len(s) % blocksize:
s = (blocksize - len(s) % blocksize) * b'\000' + s
return s
def bytes_to_long(s):
"""bytes_to_long(string) : long
Convert a byte string to a long integer.
This is (essentially) the inverse of long_to_bytes().
"""
acc = 0
length = len(s)
if length % 4:
extra = (4 - length % 4)
s = b'\000' * extra + s
length = length + extra
for i in range(0, length, 4):
acc = (acc << 32) + compat_struct_unpack('>I', s[i:i + 4])[0]
return acc
[utils] Add OHDave's RSA encryption function
2016-02-16 23:01:44 +01:00
def ohdave_rsa_encrypt(data, exponent, modulus):
'''
Implement OHDave's RSA algorithm. See http://www.ohdave.com/rsa/
Input:
data: data to encrypt, bytes-like object
exponent, modulus: parameter e and N of RSA algorithm, both integer
Output: hex string of encrypted data
Limitation: supports one block encryption only
'''
payload = int(binascii.hexlify(data[::-1]), 16)
encrypted = pow(payload, exponent, modulus)
return '%x' % encrypted
[utils] Move base62 to utils
2016-02-24 15:08:40 +01:00
[utils] Add pkcs1pad Used in daisuki.net (#4738)
2017-02-27 11:50:19 +01:00
def pkcs1pad(data, length):
"""
Padding input data with PKCS#1 scheme
@param {int[]} data input data
@param {int} length target length
@returns {int[]} padded data
"""
if len(data) > length - 11:
raise ValueError('Input data too long for PKCS#1 padding')
pseudo_random = [random.randint(0, 254) for _ in range(length - len(data) - 3)]
return [0, 2] + pseudo_random + [0] + data
[utils] Multiple changes to base_n() 1. Renamed to encode_base_n() 2. Allow tables longer than 62 characters 3. Raise ValueError instead of AssertionError for invalid input data 4. Return the first character in the table instead of '0' for number 0 5. Add tests
2016-02-26 20:19:50 +01:00
def encode_base_n(num, n, table=None):
[utils] Merge base_n functions
2016-02-26 07:37:20 +01:00
FULL_TABLE = '0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ'
if not table:
table = FULL_TABLE[:n]
[utils] Multiple changes to base_n() 1. Renamed to encode_base_n() 2. Allow tables longer than 62 characters 3. Raise ValueError instead of AssertionError for invalid input data 4. Return the first character in the table instead of '0' for number 0 5. Add tests
2016-02-26 20:19:50 +01:00
if n > len(table):
raise ValueError('base %d exceeds table length %d' % (n, len(table)))
if num == 0:
return table[0]
[utils] Move base62 to utils
2016-02-24 15:08:40 +01:00
ret = ''
while num:
ret = table[num % n] + ret
num = num // n
return ret
[utils] Move codes for handling eval() from iqiyi.py
2016-02-26 07:58:29 +01:00
def decode_packed_codes(code):
[utils] Expose PACKED_CODES_RE
2016-10-19 18:28:49 +02:00
mobj = re.search(PACKED_CODES_RE, code)
Fix typos (#27084) * spelling: authorization Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: brightcove Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: creation Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exceeded Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exception Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extension Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extracting Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extraction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: frontline Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: improve Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: length Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: listsubtitles Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: multimedia Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: obfuscated Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: partitioning Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlist Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlists Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: restriction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: services Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: split Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: srmediathek Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: support Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: thumbnail Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: verification Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: whitespaces Signed-off-by: Josh Soref <jsoref@users.noreply.github.com>
2020-11-21 16:00:05 +01:00
obfuscated_code, base, count, symbols = mobj.groups()
[utils] Move codes for handling eval() from iqiyi.py
2016-02-26 07:58:29 +01:00
base = int(base)
count = int(count)
symbols = symbols.split('|')
symbol_table = {}
while count:
count -= 1
[utils] Multiple changes to base_n() 1. Renamed to encode_base_n() 2. Allow tables longer than 62 characters 3. Raise ValueError instead of AssertionError for invalid input data 4. Return the first character in the table instead of '0' for number 0 5. Add tests
2016-02-26 20:19:50 +01:00
base_n_count = encode_base_n(count, base)
[utils] Move codes for handling eval() from iqiyi.py
2016-02-26 07:58:29 +01:00
symbol_table[base_n_count] = symbols[count] or base_n_count
return re.sub(
r'\b(\w+)\b', lambda mobj: symbol_table[mobj.group(0)],
Fix typos (#27084) * spelling: authorization Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: brightcove Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: creation Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exceeded Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: exception Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extension Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extracting Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: extraction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: frontline Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: improve Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: length Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: listsubtitles Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: multimedia Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: obfuscated Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: partitioning Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlist Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: playlists Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: restriction Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: services Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: split Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: srmediathek Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: support Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: thumbnail Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: verification Signed-off-by: Josh Soref <jsoref@users.noreply.github.com> * spelling: whitespaces Signed-off-by: Josh Soref <jsoref@users.noreply.github.com>
2020-11-21 16:00:05 +01:00
obfuscated_code)
[downloader/hls] Add support for AES-128 encrypted segments in hlsnative downloader
2016-01-10 20:09:53 +01:00
[utils] Add generic caesar cipher and rot47
2019-11-26 20:26:42 +01:00
def caesar(s, alphabet, shift):
if shift == 0:
return s
l = len(alphabet)
return ''.join(
alphabet[(alphabet.index(c) + shift) % l] if c in alphabet else c
for c in s)
def rot47(s):
return caesar(s, r'''!"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\]^_`abcdefghijklmnopqrstuvwxyz{|}~''', 47)
[downloader/hls] Add support for AES-128 encrypted segments in hlsnative downloader
2016-01-10 20:09:53 +01:00
def parse_m3u8_attributes(attrib):
info = {}
for (key, val) in re.findall(r'(?P<key>[A-Z0-9-]+)=(?P<val>"[^"]+"|[^",]+)(?:,|$)', attrib):
if val.startswith('"'):
val = val[1:-1]
info[key] = val
return info
[utils] Add urshift() Used in IqiyiIE and LeIE
2016-06-26 09:16:49 +02:00
def urshift(val, n):
return val >> n if val >= 0 else (val + 0x100000000) >> n
[utils] Add decode_png for openload (#9706)
2016-08-06 20:42:58 +02:00
# Based on png2str() written by @gdkchan and improved by @yokrysty
Start moving to ytdl-org
2019-03-09 13:14:41 +01:00
# Originally posted at https://github.com/ytdl-org/youtube-dl/issues/9706
[utils] Add decode_png for openload (#9706)
2016-08-06 20:42:58 +02:00
def decode_png(png_data):
# Reference: https://www.w3.org/TR/PNG/
header = png_data[8:]
if png_data[:8] != b'\x89PNG\x0d\x0a\x1a\x0a' or header[4:8] != b'IHDR':
raise IOError('Not a valid PNG file.')
int_map = {1: '>B', 2: '>H', 4: '>I'}
unpack_integer = lambda x: compat_struct_unpack(int_map[len(x)], x)[0]
chunks = []
while header:
length = unpack_integer(header[:4])
header = header[4:]
chunk_type = header[:4]
header = header[4:]
chunk_data = header[:length]
header = header[length:]
header = header[4:] # Skip CRC
chunks.append({
'type': chunk_type,
'length': length,
'data': chunk_data
})
ihdr = chunks[0]['data']
width = unpack_integer(ihdr[:4])
height = unpack_integer(ihdr[4:8])
idat = b''
for chunk in chunks:
if chunk['type'] == b'IDAT':
idat += chunk['data']
if not idat:
raise IOError('Unable to read PNG data.')
decompressed_data = bytearray(zlib.decompress(idat))
stride = width * 3
pixels = []
def _get_pixel(idx):
x = idx % stride
y = idx // stride
return pixels[y][x]
for y in range(height):
basePos = y * (1 + stride)
filter_type = decompressed_data[basePos]
current_row = []
pixels.append(current_row)
for x in range(stride):
color = decompressed_data[1 + basePos + x]
basex = y * stride + x
left = 0
up = 0
if x > 2:
left = _get_pixel(basex - 3)
if y > 0:
up = _get_pixel(basex - stride)
if filter_type == 1: # Sub
color = (color + left) & 0xff
elif filter_type == 2: # Up
color = (color + up) & 0xff
elif filter_type == 3: # Average
color = (color + ((left + up) >> 1)) & 0xff
elif filter_type == 4: # Paeth
a = left
b = up
c = 0
if x > 2 and y > 0:
c = _get_pixel(basex - stride - 3)
p = a + b - c
pa = abs(p - a)
pb = abs(p - b)
pc = abs(p - c)
if pa <= pb and pa <= pc:
color = (color + a) & 0xff
elif pb <= pc:
color = (color + b) & 0xff
else:
color = (color + c) & 0xff
current_row.append(color)
return width, height, pixels
Move write_xattr to utils.py There are some other places that use xattr functions. It's better to move it to a common place so that others can use it.
2016-09-29 18:28:32 +02:00
def write_xattr(path, key, value):
# This mess below finds the best xattr tool for the job
try:
# try the pyxattr module...
import xattr
[utils] Support xattr as well as pyxattr Closes #9054 There are two xattr packages in Python, pyxattr [1] and xattr [2]. They have different APIs. In old days pyxattr supports Linux only and xattr supports Linux, Mac, FreeBSD and Solaris, and pyxattr supports Linux only. Recently pyxattr adds support for Mac OS X. [3] An old version of [2] is shipped with Mac OS X. However, some Linux distributions have pyxattr only, for example PLD-Linux [4] and old Arch Linux. [5] As a result, supporting both is the way to go. [1] https://github.com/iustin/pyxattr [2] https://github.com/xattr/xattr [3] https://github.com/iustin/pyxattr/pull/9 [4] https://github.com/rg3/youtube-dl/issues/5498 [5] https://git.archlinux.org/svntogit/community.git/commit/?id=427c4c76401e386d865ccddea4fbfdc74df80492 https://git.archlinux.org/svntogit/community.git/commit/?id=59b40da7b69622a6761d364a8b07909e9cccaa56 python-xattr is added on 2016/06/29 while pyxattr is there for more than 6 years
2016-10-01 14:13:04 +02:00
if hasattr(xattr, 'set'): # pyxattr
# Unicode arguments are not supported in python-pyxattr until
# version 0.5.0
Start moving to ytdl-org
2019-03-09 13:14:41 +01:00
# See https://github.com/ytdl-org/youtube-dl/issues/5498
[utils] Support xattr as well as pyxattr Closes #9054 There are two xattr packages in Python, pyxattr [1] and xattr [2]. They have different APIs. In old days pyxattr supports Linux only and xattr supports Linux, Mac, FreeBSD and Solaris, and pyxattr supports Linux only. Recently pyxattr adds support for Mac OS X. [3] An old version of [2] is shipped with Mac OS X. However, some Linux distributions have pyxattr only, for example PLD-Linux [4] and old Arch Linux. [5] As a result, supporting both is the way to go. [1] https://github.com/iustin/pyxattr [2] https://github.com/xattr/xattr [3] https://github.com/iustin/pyxattr/pull/9 [4] https://github.com/rg3/youtube-dl/issues/5498 [5] https://git.archlinux.org/svntogit/community.git/commit/?id=427c4c76401e386d865ccddea4fbfdc74df80492 https://git.archlinux.org/svntogit/community.git/commit/?id=59b40da7b69622a6761d364a8b07909e9cccaa56 python-xattr is added on 2016/06/29 while pyxattr is there for more than 6 years
2016-10-01 14:13:04 +02:00
pyxattr_required_version = '0.5.0'
if version_tuple(xattr.__version__) < version_tuple(pyxattr_required_version):
# TODO: fallback to CLI tools
raise XAttrUnavailableError(
'python-pyxattr is detected but is too old. '
'youtube-dl requires %s or above while your version is %s. '
'Falling back to other xattr implementations' % (
pyxattr_required_version, xattr.__version__))
setxattr = xattr.set
else: # xattr
setxattr = xattr.setxattr
Move write_xattr to utils.py There are some other places that use xattr functions. It's better to move it to a common place so that others can use it.
2016-09-29 18:28:32 +02:00
try:
[utils] Support xattr as well as pyxattr Closes #9054 There are two xattr packages in Python, pyxattr [1] and xattr [2]. They have different APIs. In old days pyxattr supports Linux only and xattr supports Linux, Mac, FreeBSD and Solaris, and pyxattr supports Linux only. Recently pyxattr adds support for Mac OS X. [3] An old version of [2] is shipped with Mac OS X. However, some Linux distributions have pyxattr only, for example PLD-Linux [4] and old Arch Linux. [5] As a result, supporting both is the way to go. [1] https://github.com/iustin/pyxattr [2] https://github.com/xattr/xattr [3] https://github.com/iustin/pyxattr/pull/9 [4] https://github.com/rg3/youtube-dl/issues/5498 [5] https://git.archlinux.org/svntogit/community.git/commit/?id=427c4c76401e386d865ccddea4fbfdc74df80492 https://git.archlinux.org/svntogit/community.git/commit/?id=59b40da7b69622a6761d364a8b07909e9cccaa56 python-xattr is added on 2016/06/29 while pyxattr is there for more than 6 years
2016-10-01 14:13:04 +02:00
setxattr(path, key, value)
Move write_xattr to utils.py There are some other places that use xattr functions. It's better to move it to a common place so that others can use it.
2016-09-29 18:28:32 +02:00
except EnvironmentError as e:
raise XAttrMetadataError(e.errno, e.strerror)
except ImportError:
if compat_os_name == 'nt':
# Write xattrs to NTFS Alternate Data Streams:
# http://en.wikipedia.org/wiki/NTFS#Alternate_data_streams_.28ADS.29
assert ':' not in key
assert os.path.exists(path)
ads_fn = path + ':' + key
try:
with open(ads_fn, 'wb') as f:
f.write(value)
except EnvironmentError as e:
raise XAttrMetadataError(e.errno, e.strerror)
else:
user_has_setfattr = check_executable('setfattr', ['--version'])
user_has_xattr = check_executable('xattr', ['-h'])
if user_has_setfattr or user_has_xattr:
value = value.decode('utf-8')
if user_has_setfattr:
executable = 'setfattr'
opts = ['-n', key, '-v', value]
elif user_has_xattr:
executable = 'xattr'
opts = ['-w', key, value]
Fix W504 and disable W503 (closes #20863)
2019-05-10 22:56:22 +02:00
cmd = ([encodeFilename(executable, True)]
+ [encodeArgument(o) for o in opts]
+ [encodeFilename(path, True)])
Move write_xattr to utils.py There are some other places that use xattr functions. It's better to move it to a common place so that others can use it.
2016-09-29 18:28:32 +02:00
try:
p = subprocess.Popen(
cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, stdin=subprocess.PIPE)
except EnvironmentError as e:
raise XAttrMetadataError(e.errno, e.strerror)
[utils, etc] Kill child processes when yt-dl is killed * derived from PR #26592, closes #26592 Authored by: Unrud
2021-01-09 13:26:12 +01:00
stdout, stderr = process_communicate_or_kill(p)
Move write_xattr to utils.py There are some other places that use xattr functions. It's better to move it to a common place so that others can use it.
2016-09-29 18:28:32 +02:00
stderr = stderr.decode('utf-8', 'replace')
if p.returncode != 0:
raise XAttrMetadataError(p.returncode, stderr)
else:
# On Unix, and can't find pyxattr, setfattr, or xattr.
if sys.platform.startswith('linux'):
raise XAttrUnavailableError(
"Couldn't find a tool to set the xattrs. "
"Install either the python 'pyxattr' or 'xattr' "
"modules, or the GNU 'attr' package "
"(which contains the 'setfattr' tool).")
else:
raise XAttrUnavailableError(
"Couldn't find a tool to set the xattrs. "
"Install either the python 'xattr' module, "
"or the 'xattr' binary.")
[cda] Implement birthday verification (closes #12789)
2017-05-01 17:09:18 +02:00
def random_birthday(year_field, month_field, day_field):
[utils] Fix random_birthday to generate existing dates only
2018-12-01 18:05:15 +01:00
start_date = datetime.date(1950, 1, 1)
end_date = datetime.date(1995, 12, 31)
offset = random.randint(0, (end_date - start_date).days)
random_date = start_date + datetime.timedelta(offset)
[cda] Implement birthday verification (closes #12789)
2017-05-01 17:09:18 +02:00
return {
[utils] Fix random_birthday to generate existing dates only
2018-12-01 18:05:15 +01:00
year_field: str(random_date.year),
month_field: str(random_date.month),
day_field: str(random_date.day),
[cda] Implement birthday verification (closes #12789)
2017-05-01 17:09:18 +02:00
}
[utils] add a function to clean podcast URLs
2021-01-04 00:51:55 +01:00
def clean_podcast_url(url):
return re.sub(r'''(?x)
(?:
(?:
chtbl\.com/track|
media\.blubrry\.com| # https://create.blubrry.com/resources/podcast-media-download-statistics/getting-started/
play\.podtrac\.com
)/[^/]+|
(?:dts|www)\.podtrac\.com/(?:pts/)?redirect\.[0-9a-z]{3,4}| # http://analytics.podtrac.com/how-to-measure
flex\.acast\.com|
pd(?:
cn\.co| # https://podcorn.com/analytics-prefix/
st\.fm # https://podsights.com/docs/
)/e
)/''', '', url)
[utils] Backport traverse_obj (etc) from yt-dlp (#31156) * Backport traverse_obj and closely related function from yt-dlp (code by pukkandan) * Backport LazyList, variadic(), try_call (code by pukkandan) * Recast using yt-dlp's newer traverse_obj() implementation and tests (code by grub4k) * Add tests for Unicode case folding support matching Py3.5+ (requires f102e3d) * Improve/add tests for variadic, try_call, join_nonempty Co-authored-by: dirkf <fieldhouse@gmx.net>
2022-11-03 11:09:37 +01:00
def traverse_obj(obj, *paths, **kwargs):
"""
Safely traverse nested `dict`s and `Sequence`s
>>> obj = [{}, {"key": "value"}]
>>> traverse_obj(obj, (1, "key"))
"value"
Each of the provided `paths` is tested and the first producing a valid result will be returned.
The next path will also be tested if the path branched but no results could be found.
Supported values for traversal are `Mapping`, `Sequence` and `re.Match`.
A value of None is treated as the absence of a value.
The paths will be wrapped in `variadic`, so that `'key'` is conveniently the same as `('key', )`.
The keys in the path can be one of:
- `None`: Return the current object.
- `str`/`int`: Return `obj[key]`. For `re.Match, return `obj.group(key)`.
- `slice`: Branch out and return all values in `obj[key]`.
- `Ellipsis`: Branch out and return a list of all values.
- `tuple`/`list`: Branch out and return a list of all matching values.
Read as: `[traverse_obj(obj, branch) for branch in branches]`.
- `function`: Branch out and return values filtered by the function.
Read as: `[value for key, value in obj if function(key, value)]`.
For `Sequence`s, `key` is the index of the value.
- `dict` Transform the current object and return a matching dict.
Read as: `{key: traverse_obj(obj, path) for key, path in dct.items()}`.
`tuple`, `list`, and `dict` all support nested paths and branches.
@params paths Paths which to traverse by.
Keyword arguments:
@param default Value to return if the paths do not match.
@param expected_type If a `type`, only accept final values of this type.
If any other callable, try to call the function on each result.
@param get_all If `False`, return the first matching result, otherwise all matching ones.
@param casesense If `False`, consider string dictionary keys as case insensitive.
The following are only meant to be used by YoutubeDL.prepare_outtmpl and are not part of the API
@param _is_user_input Whether the keys are generated from user input.
If `True` strings get converted to `int`/`slice` if needed.
@param _traverse_string Whether to traverse into objects as strings.
If `True`, any non-compatible object will first be
converted into a string and then traversed into.
@returns The result of the object traversal.
If successful, `get_all=True`, and the path branches at least once,
then a list of results is returned instead.
A list is always returned if the last path branches and no `default` is given.
"""
# parameter defaults
default = kwargs.get('default', NO_DEFAULT)
expected_type = kwargs.get('expected_type')
get_all = kwargs.get('get_all', True)
casesense = kwargs.get('casesense', True)
_is_user_input = kwargs.get('_is_user_input', False)
_traverse_string = kwargs.get('_traverse_string', False)
# instant compat
str = compat_str
is_sequence = lambda x: isinstance(x, compat_collections_abc.Sequence) and not isinstance(x, (str, bytes))
casefold = lambda k: compat_casefold(k) if isinstance(k, str) else k
if isinstance(expected_type, type):
type_test = lambda val: val if isinstance(val, expected_type) else None
else:
type_test = lambda val: try_call(expected_type or IDENTITY, args=(val,))
def from_iterable(iterables):
# chain.from_iterable(['ABC', 'DEF']) --> A B C D E F
for it in iterables:
for item in it:
yield item
def apply_key(key, obj):
if obj is None:
return
elif key is None:
yield obj
elif isinstance(key, (list, tuple)):
for branch in key:
_, result = apply_path(obj, branch)
for item in result:
yield item
elif key is Ellipsis:
result = []
if isinstance(obj, compat_collections_abc.Mapping):
result = obj.values()
elif is_sequence(obj):
result = obj
elif isinstance(obj, compat_re_Match):
result = obj.groups()
elif _traverse_string:
result = str(obj)
for item in result:
yield item
elif callable(key):
if is_sequence(obj):
iter_obj = enumerate(obj)
elif isinstance(obj, compat_collections_abc.Mapping):
iter_obj = obj.items()
elif isinstance(obj, compat_re_Match):
iter_obj = enumerate(itertools.chain([obj.group()], obj.groups()))
elif _traverse_string:
iter_obj = enumerate(str(obj))
else:
return
for item in (v for k, v in iter_obj if try_call(key, args=(k, v))):
yield item
elif isinstance(key, dict):
iter_obj = ((k, _traverse_obj(obj, v)) for k, v in key.items())
yield dict((k, v if v is not None else default) for k, v in iter_obj
if v is not None or default is not NO_DEFAULT)
elif isinstance(obj, compat_collections_abc.Mapping):
yield (obj.get(key) if casesense or (key in obj)
else next((v for k, v in obj.items() if casefold(k) == key), None))
elif isinstance(obj, compat_re_Match):
if isinstance(key, int) or casesense:
try:
yield obj.group(key)
return
except IndexError:
pass
if not isinstance(key, str):
return
yield next((v for k, v in obj.groupdict().items() if casefold(k) == key), None)
else:
if _is_user_input:
key = (int_or_none(key) if ':' not in key
else slice(*map(int_or_none, key.split(':'))))
if not isinstance(key, (int, slice)):
return
if not is_sequence(obj):
if not _traverse_string:
return
obj = str(obj)
try:
yield obj[key]
except IndexError:
pass
def apply_path(start_obj, path):
objs = (start_obj,)
has_branched = False
for key in variadic(path):
if _is_user_input and key == ':':
key = Ellipsis
if not casesense and isinstance(key, str):
key = compat_casefold(key)
if key is Ellipsis or isinstance(key, (list, tuple)) or callable(key):
has_branched = True
key_func = functools.partial(apply_key, key)
objs = from_iterable(map(key_func, objs))
return has_branched, objs
def _traverse_obj(obj, path, use_list=True):
has_branched, results = apply_path(obj, path)
results = LazyList(x for x in map(type_test, results) if x is not None)
if get_all and has_branched:
return results.exhaust() if results or use_list else None
return results[0] if results else None
for index, path in enumerate(paths, 1):
use_list = default is NO_DEFAULT and index == len(paths)
result = _traverse_obj(obj, path, use_list)
if result is not None:
return result
return None if default is NO_DEFAULT else default
def get_first(obj, keys, **kwargs):
return traverse_obj(obj, (Ellipsis,) + tuple(variadic(keys)), get_all=False, **kwargs)
def join_nonempty(*values, **kwargs):
# parameter defaults
delim = kwargs.get('delim', '-')
from_dict = kwargs.get('from_dict')
if from_dict is not None:
values = (traverse_obj(from_dict, variadic(v)) for v in values)
return delim.join(map(compat_str, filter(None, values)))
Reference in a new issue Copy permalink