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

[apa] Fix extraction

Browse source
This commit is contained in:
Adrian Heine 2021-01-09 22:06:24 +01:00 committed by Sergey M․
parent 919d764600
commit 36abc16c3c
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 8 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

27
youtube_dl/extractor/apa.py
View file

@ -7,7 +7,6 @@ from .common import InfoExtractor
from ..utils import ( from ..utils import (
determine_ext, determine_ext,
js_to_json, js_to_json,
url_or_none,
) )
@ -17,14 +16,10 @@ class APAIE(InfoExtractor):
'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029', 'url': 'http://uvp.apa.at/embed/293f6d17-692a-44e3-9fd5-7b178f3a1029',
'md5': '2b12292faeb0a7d930c778c7a5b4759b', 'md5': '2b12292faeb0a7d930c778c7a5b4759b',
'info_dict': { 'info_dict': {
'id': 'jjv85FdZ', 'id': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'ext': 'mp4', 'ext': 'mp4',
'title': '"Blau ist mysteriös": Die Blue Man Group im Interview', 'title': '293f6d17-692a-44e3-9fd5-7b178f3a1029',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'thumbnail': r're:^https?://.*\.jpg$', 'thumbnail': r're:^https?://.*\.jpg$',
'duration': 254,
'timestamp': 1519211149,
'upload_date': '20180221',
}, },
}, { }, {
'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78', 'url': 'https://uvp-apapublisher.sf.apa.at/embed/2f94e9e6-d945-4db2-9548-f9a41ebf7b78',
@ -48,7 +43,7 @@ class APAIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage('https://uvp.apa.at/player/%s' % video_id, video_id)
jwplatform_id = self._search_regex( jwplatform_id = self._search_regex(
r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage, r'media[iI]d\s*:\s*["\'](?P<id>[a-zA-Z0-9]{8})', webpage,
@ -59,18 +54,12 @@ class APAIE(InfoExtractor):
'jwplatform:' + jwplatform_id, ie='JWPlatform', 'jwplatform:' + jwplatform_id, ie='JWPlatform',
video_id=video_id) video_id=video_id)
sources = self._parse_json( sources = self._parse_json("{" + self._search_regex(
self._search_regex( r'("hls"\s*:\s*"[^"]+"\s*,\s*"progressive"\s*:\s*"[^"]+")', webpage, 'sources')
r'sources\s*=\s*(\[.+?\])\s*;', webpage, 'sources'), + "}", video_id, transform_source=js_to_json)
video_id, transform_source=js_to_json)
formats = [] formats = []
for source in sources: for (format, source_url) in sources.items():
if not isinstance(source, dict):
continue
source_url = url_or_none(source.get('file'))
if not source_url:
continue
ext = determine_ext(source_url) ext = determine_ext(source_url)
if ext == 'm3u8': if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats( formats.extend(self._extract_m3u8_formats(
@ -83,7 +72,7 @@ class APAIE(InfoExtractor):
self._sort_formats(formats) self._sort_formats(formats)
thumbnail = self._search_regex( thumbnail = self._search_regex(
r'image\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage, r'"poster"\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
'thumbnail', fatal=False, group='url') 'thumbnail', fatal=False, group='url')
return { return {