pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-16 18:42:38 +09:00
Code Issues Projects Releases Wiki Activity

[yahoo] Support pages that use an alias (fixes #8084)

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2016-01-01 14:32:00 +01:00
parent 32f9036447
commit ca227c8698
1 changed files with 26 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
youtube_dl/extractor/yahoo.py
View File

@ -155,7 +155,16 @@ class YahooIE(InfoExtractor):
'description': 'md5:8fc39608213295748e1e289807838c97', 'description': 'md5:8fc39608213295748e1e289807838c97',
'duration': 1646, 'duration': 1646,
}, },
} }, {
# it uses an alias to get the video_id
'url': 'https://www.yahoo.com/movies/the-stars-of-daddys-home-have-very-different-212843197.html',
'info_dict': {
'id': '40eda9c8-8e5f-3552-8745-830f67d0c737',
'ext': 'mp4',
'title': 'Will Ferrell & Mark Wahlberg Are Pro-Spanking',
'description': 'While they play feuding fathers in \'Daddy\'s Home,\' star Will Ferrell & Mark Wahlberg share their true feelings on parenthood.',
},
},
] ]
def _real_extract(self, url): def _real_extract(self, url):
@ -199,13 +208,22 @@ class YahooIE(InfoExtractor):
r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE, r'mediaItems: ({.*?})$', webpage, 'items', flags=re.MULTILINE,
default=None) default=None)
if items_json is None: if items_json is None:
alias = self._search_regex(
r'"aliases":{"video":"(.*?)"', webpage, 'alias', default=None)
if alias is not None:
alias_info = self._download_json(
'https://www.yahoo.com/_td/api/resource/VideoService.videos;video_aliases=["%s"]' % alias,
display_id, 'Downloading alias info')
video_id = alias_info[0]['id']
else:
CONTENT_ID_REGEXES = [ CONTENT_ID_REGEXES = [
r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"', r'YUI\.namespace\("Media"\)\.CONTENT_ID\s*=\s*"([^"]+)"',
r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"', r'root\.App\.Cache\.context\.videoCache\.curVideo = \{"([^"]+)"',
r'"first_videoid"\s*:\s*"([^"]+)"', r'"first_videoid"\s*:\s*"([^"]+)"',
r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id), r'%s[^}]*"ccm_id"\s*:\s*"([^"]+)"' % re.escape(page_id),
] ]
video_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') video_id = self._search_regex(
CONTENT_ID_REGEXES, webpage, 'content ID')
else: else:
items = json.loads(items_json) items = json.loads(items_json)
info = items['mediaItems']['query']['results']['mediaObj'][0] info = items['mediaItems']['query']['results']['mediaObj'][0]