Added Pornotube support (for Laborers of Love)

This commit is contained in:
Jeff Crouse 2012-11-12 16:17:55 -05:00
parent 0526e4f55a
commit 110d4f4c91
7 changed files with 91 additions and 241 deletions

9
.gitignore vendored
View file

@ -3,3 +3,12 @@
*~ *~
wine-py2exe/ wine-py2exe/
py2exe.log py2exe.log
#OS X
.DS_Store
.AppleDouble
.LSOverride
Icon
._*
.Spotlight-V100
.Trashes

View file

@ -1 +0,0 @@
2012.10.09

Binary file not shown.

View file

@ -1,240 +0,0 @@
.TH youtube-dl 1 ""
.SH NAME
.PP
youtube-dl
.SH SYNOPSIS
.PP
\f[B]youtube-dl\f[] [OPTIONS] URL [URL...]
.SH DESCRIPTION
.PP
\f[B]youtube-dl\f[] is a small command-line program to download videos
from YouTube.com and a few more sites.
It requires the Python interpreter, version 2.x (x being at least 6),
and it is not platform specific.
It should work in your Unix box, in Windows or in Mac OS X.
It is released to the public domain, which means you can modify it,
redistribute it or use it however you like.
.SH OPTIONS
.IP
.nf
\f[C]
-h,\ --help\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ print\ this\ help\ text\ and\ exit
--version\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ print\ program\ version\ and\ exit
-U,\ --update\ \ \ \ \ \ \ \ \ \ \ \ \ update\ this\ program\ to\ latest\ version
-i,\ --ignore-errors\ \ \ \ \ \ continue\ on\ download\ errors
-r,\ --rate-limit\ LIMIT\ \ \ download\ rate\ limit\ (e.g.\ 50k\ or\ 44.6m)
-R,\ --retries\ RETRIES\ \ \ \ number\ of\ retries\ (default\ is\ 10)
--dump-user-agent\ \ \ \ \ \ \ \ display\ the\ current\ browser\ identification
--user-agent\ UA\ \ \ \ \ \ \ \ \ \ specify\ a\ custom\ user\ agent
--list-extractors\ \ \ \ \ \ \ \ List\ all\ supported\ extractors\ and\ the\ URLs\ they
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ would\ handle
\f[]
.fi
.SS Video Selection:
.IP
.nf
\f[C]
--playlist-start\ NUMBER\ \ playlist\ video\ to\ start\ at\ (default\ is\ 1)
--playlist-end\ NUMBER\ \ \ \ playlist\ video\ to\ end\ at\ (default\ is\ last)
--match-title\ REGEX\ \ \ \ \ \ download\ only\ matching\ titles\ (regex\ or\ caseless
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ sub-string)
--reject-title\ REGEX\ \ \ \ \ skip\ download\ for\ matching\ titles\ (regex\ or
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ caseless\ sub-string)
--max-downloads\ NUMBER\ \ \ Abort\ after\ downloading\ NUMBER\ files
\f[]
.fi
.SS Filesystem Options:
.IP
.nf
\f[C]
-t,\ --title\ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ title\ in\ file\ name
--id\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ video\ ID\ in\ file\ name
-l,\ --literal\ \ \ \ \ \ \ \ \ \ \ \ use\ literal\ title\ in\ file\ name
-A,\ --auto-number\ \ \ \ \ \ \ \ number\ downloaded\ files\ starting\ from\ 00000
-o,\ --output\ TEMPLATE\ \ \ \ output\ filename\ template.\ Use\ %(stitle)s\ to\ get\ the
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ title,\ %(uploader)s\ for\ the\ uploader\ name,
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(autonumber)s\ to\ get\ an\ automatically\ incremented
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ number,\ %(ext)s\ for\ the\ filename\ extension,
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(upload_date)s\ for\ the\ upload\ date\ (YYYYMMDD),
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ %(extractor)s\ for\ the\ provider\ (youtube,\ metacafe,
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ etc),\ %(id)s\ for\ the\ video\ id\ and\ %%\ for\ a\ literal
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ percent.\ Use\ -\ to\ output\ to\ stdout.
-a,\ --batch-file\ FILE\ \ \ \ file\ containing\ URLs\ to\ download\ (\[aq]-\[aq]\ for\ stdin)
-w,\ --no-overwrites\ \ \ \ \ \ do\ not\ overwrite\ files
-c,\ --continue\ \ \ \ \ \ \ \ \ \ \ resume\ partially\ downloaded\ files
--no-continue\ \ \ \ \ \ \ \ \ \ \ \ do\ not\ resume\ partially\ downloaded\ files\ (restart
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ from\ beginning)
--cookies\ FILE\ \ \ \ \ \ \ \ \ \ \ file\ to\ read\ cookies\ from\ and\ dump\ cookie\ jar\ in
--no-part\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ do\ not\ use\ .part\ files
--no-mtime\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ do\ not\ use\ the\ Last-modified\ header\ to\ set\ the\ file
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ modification\ time
--write-description\ \ \ \ \ \ write\ video\ description\ to\ a\ .description\ file
--write-info-json\ \ \ \ \ \ \ \ write\ video\ metadata\ to\ a\ .info.json\ file
\f[]
.fi
.SS Verbosity / Simulation Options:
.IP
.nf
\f[C]
-q,\ --quiet\ \ \ \ \ \ \ \ \ \ \ \ \ \ activates\ quiet\ mode
-s,\ --simulate\ \ \ \ \ \ \ \ \ \ \ do\ not\ download\ the\ video\ and\ do\ not\ write\ anything
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ to\ disk
--skip-download\ \ \ \ \ \ \ \ \ \ do\ not\ download\ the\ video
-g,\ --get-url\ \ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ URL
-e,\ --get-title\ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ title
--get-thumbnail\ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ thumbnail\ URL
--get-description\ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ video\ description
--get-filename\ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ output\ filename
--get-format\ \ \ \ \ \ \ \ \ \ \ \ \ simulate,\ quiet\ but\ print\ output\ format
--no-progress\ \ \ \ \ \ \ \ \ \ \ \ do\ not\ print\ progress\ bar
--console-title\ \ \ \ \ \ \ \ \ \ display\ progress\ in\ console\ titlebar
-v,\ --verbose\ \ \ \ \ \ \ \ \ \ \ \ print\ various\ debugging\ information
\f[]
.fi
.SS Video Format Options:
.IP
.nf
\f[C]
-f,\ --format\ FORMAT\ \ \ \ \ \ video\ format\ code
--all-formats\ \ \ \ \ \ \ \ \ \ \ \ download\ all\ available\ video\ formats
--prefer-free-formats\ \ \ \ prefer\ free\ video\ formats\ unless\ a\ specific\ one\ is
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ requested
--max-quality\ FORMAT\ \ \ \ \ highest\ quality\ format\ to\ download
-F,\ --list-formats\ \ \ \ \ \ \ list\ all\ available\ formats\ (currently\ youtube\ only)
--write-srt\ \ \ \ \ \ \ \ \ \ \ \ \ \ write\ video\ closed\ captions\ to\ a\ .srt\ file
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (currently\ youtube\ only)
--srt-lang\ LANG\ \ \ \ \ \ \ \ \ \ language\ of\ the\ closed\ captions\ to\ download
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ (optional)\ use\ IETF\ language\ tags\ like\ \[aq]en\[aq]
\f[]
.fi
.SS Authentication Options:
.IP
.nf
\f[C]
-u,\ --username\ USERNAME\ \ account\ username
-p,\ --password\ PASSWORD\ \ account\ password
-n,\ --netrc\ \ \ \ \ \ \ \ \ \ \ \ \ \ use\ .netrc\ authentication\ data
\f[]
.fi
.SS Post-processing Options:
.IP
.nf
\f[C]
-x,\ --extract-audio\ \ \ \ \ \ convert\ video\ files\ to\ audio-only\ files\ (requires
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ ffmpeg\ or\ avconv\ and\ ffprobe\ or\ avprobe)
--audio-format\ FORMAT\ \ \ \ "best",\ "aac",\ "vorbis",\ "mp3",\ "m4a",\ or\ "wav";
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ best\ by\ default
--audio-quality\ QUALITY\ \ ffmpeg/avconv\ audio\ quality\ specification,\ insert\ a
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ value\ between\ 0\ (better)\ and\ 9\ (worse)\ for\ VBR\ or\ a
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ specific\ bitrate\ like\ 128K\ (default\ 5)
-k,\ --keep-video\ \ \ \ \ \ \ \ \ keeps\ the\ video\ file\ on\ disk\ after\ the\ post-
\ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ \ processing;\ the\ video\ is\ erased\ by\ default
\f[]
.fi
.SH FAQ
.SS Can you please put the -b option back?
.PP
Most people asking this question are not aware that youtube-dl now
defaults to downloading the highest available quality as reported by
YouTube, which will be 1080p or 720p in some cases, so you no longer
need the -b option.
For some specific videos, maybe YouTube does not report them to be
available in a specific high quality format you\[aq]\[aq]re interested
in.
In that case, simply request it with the -f option and youtube-dl will
try to download it.
.SS I get HTTP error 402 when trying to download a video. What\[aq]s
this?
.PP
Apparently YouTube requires you to pass a CAPTCHA test if you download
too much.
We\[aq]\[aq]re considering to provide a way to let you solve the
CAPTCHA (https://github.com/rg3/youtube-dl/issues/154), but at the
moment, your best course of action is pointing a webbrowser to the
youtube URL, solving the CAPTCHA, and restart youtube-dl.
.SS I have downloaded a video but how can I play it?
.PP
Once the video is fully downloaded, use any video player, such as
vlc (http://www.videolan.org) or mplayer (http://www.mplayerhq.hu/).
.SS The links provided by youtube-dl -g are not working anymore
.PP
The URLs youtube-dl outputs require the downloader to have the correct
cookies.
Use the \f[C]--cookies\f[] option to write the required cookies into a
file, and advise your downloader to read cookies from that file.
Some sites also require a common user agent to be used, use
\f[C]--dump-user-agent\f[] to see the one in use by youtube-dl.
.SS ERROR: no fmt_url_map or conn information found in video info
.PP
youtube has switched to a new video info format in July 2011 which is
not supported by old versions of youtube-dl.
You can update youtube-dl with \f[C]sudo\ youtube-dl\ --update\f[].
.SS ERROR: unable to download video
.PP
youtube requires an additional signature since September 2012 which is
not supported by old versions of youtube-dl.
You can update youtube-dl with \f[C]sudo\ youtube-dl\ --update\f[].
.SS SyntaxError: Non-ASCII character
.PP
The error
.IP
.nf
\f[C]
File\ "youtube-dl",\ line\ 2
SyntaxError:\ Non-ASCII\ character\ \[aq]\\x93\[aq]\ ...
\f[]
.fi
.PP
means you\[aq]re using an outdated version of Python.
Please update to Python 2.6 or 2.7.
.PP
To run youtube-dl under Python 2.5, you\[aq]ll have to manually check it
out like this:
.IP
.nf
\f[C]
git\ clone\ git://github.com/rg3/youtube-dl.git
cd\ youtube-dl
python\ -m\ youtube_dl\ --help
\f[]
.fi
.PP
Please note that Python 2.5 is not supported anymore.
.SS What is this binary file? Where has the code gone?
.PP
Since June 2012 (#342) youtube-dl is packed as an executable zipfile,
simply unzip it (might need renaming to \f[C]youtube-dl.zip\f[] first on
some systems) or clone the git repo to see the code.
If you modify the code, you can run it by executing the
\f[C]__main__.py\f[] file.
To recompile the executable, run \f[C]make\ compile\f[].
.SS The exe throws a \f[I]Runtime error from Visual C++\f[]
.PP
To run the exe you need to install first the Microsoft Visual C++ 2008
Redistributable
Package (http://www.microsoft.com/en-us/download/details.aspx?id=29).
.SH COPYRIGHT
.PP
youtube-dl is released into the public domain by the copyright holders.
.PP
This README file was originally written by Daniel Bolton
(<https://github.com/dbbolton>) and is likewise released into the public
domain.
.SH BUGS
.PP
Bugs and suggestions should be reported at:
<https://github.com/rg3/youtube-dl/issues>
.PP
Please include:
.IP \[bu] 2
Your exact command line, like
\f[C]youtube-dl\ -t\ "http://www.youtube.com/watch?v=uHlDtZ6Oc3s&feature=channel_video_title"\f[].
A common mistake is not to escape the \f[C]&\f[].
Putting URLs in quotes should solve this problem.
.IP \[bu] 2
The output of \f[C]youtube-dl\ --version\f[]
.IP \[bu] 2
The output of \f[C]python\ --version\f[]
.IP \[bu] 2
The name and version of your Operating System ("Ubuntu 11.04 x64" or
"Windows 7 x64" is usually enough).

Binary file not shown.

View file

@ -94,6 +94,8 @@ class InfoExtractor(object):
pass pass
class YoutubeIE(InfoExtractor): class YoutubeIE(InfoExtractor):
"""Information extractor for youtube.com.""" """Information extractor for youtube.com."""
@ -3368,3 +3370,82 @@ class GooglePlusIE(InfoExtractor):
'format': u'NA', 'format': u'NA',
'player_url': None, 'player_url': None,
}] }]
class PornotubeIE(InfoExtractor):
"""Information extractor for pornotube.com."""
_VALID_URL = r'^(?:https?://)?(?:\w+\.)?pornotube\.com(/c/(?P<channel>[0-9]+))?(/m/(?P<videoid>[0-9]+))(/(?P<title>.+))$'
IE_NAME = u'pornotube'
VIDEO_URL_RE = r'url: "(?P<url>http://video[0-9].pornotube.com/.+\.flv)",'
VIDEO_UPLOADED_RE = r'<div class="video_added_by">Added (?P<date>[0-9\/]+) by'
def __init__(self, downloader=None):
InfoExtractor.__init__(self, downloader)
def report_extract_entry(self, url):
"""Report downloading extry"""
self._downloader.to_screen(u'[pornotube] Downloading entry: %s' % url.decode('utf-8'))
def report_date(self, upload_date):
"""Report finding uploaded date"""
self._downloader.to_screen(u'[pornotube] Entry date: %s' % upload_date)
def report_webpage(self, url):
"""Report downloading page"""
self._downloader.to_screen(u'[pornotube] Downloaded page: %s' % url)
def report_title(self, video_title):
"""Report downloading extry"""
self._downloader.to_screen(u'[pornotube] Title: %s' % video_title.decode('utf-8'))
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
if mobj is None:
self._downloader.trouble(u'ERROR: invalid URL: %s' % url)
return
video_id = mobj.group('videoid').decode('utf-8')
video_title = mobj.group('title').decode('utf-8')
self.report_title(video_title);
# Get webpage content
try:
webpage = urllib2.urlopen(url).read()
except (urllib2.URLError, httplib.HTTPException, socket.error), err:
self._downloader.trouble(u'ERROR: unable to download video webpage: %s' % err)
return
self.report_webpage(url)
# Get the video URL
result = re.search(self.VIDEO_URL_RE, webpage)
if result is None:
self._downloader.trouble(u'ERROR: unable to extract video url')
return
video_url = urllib.unquote(result.group('url').decode('utf-8'))
self.report_extract_entry(video_url)
#Get the uploaded date
result = re.search(self.VIDEO_UPLOADED_RE, webpage)
if result is None:
self._downloader.trouble(u'ERROR: unable to extract video title')
return
upload_date = result.group('date').decode('utf-8')
self.report_date(upload_date);
info = {'id': video_id,
'url': video_url,
'uploader': None,
'upload_date': upload_date,
'title': video_title,
'ext': 'flv',
'format': 'flv',
'thumbnail': None,
'description': None,
'player_url': None}
return [info]

View file

@ -361,6 +361,7 @@ def gen_extractors():
YoukuIE(), YoukuIE(),
XNXXIE(), XNXXIE(),
GooglePlusIE(), GooglePlusIE(),
PornotubeIE(),
GenericIE() GenericIE()
] ]