pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-11-05 09:57:59 +09:00
Code Issues Projects Releases Wiki Activity

[yahoo] Improve video id detection (fixes #4521)

Browse Source
This commit is contained in:
Jaime Marquínez Ferrándiz 2014-12-21 12:33:30 +01:00
parent 2c2a42587b
commit 3aa9176f08
1 changed files with 14 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
youtube_dl/extractor/yahoo.py
View File

@ -12,6 +12,7 @@ from ..compat import (
) )
from ..utils import ( from ..utils import (
clean_html, clean_html,
unescapeHTML,
ExtractorError, ExtractorError,
int_or_none, int_or_none,
) )
@ -116,6 +117,16 @@ class YahooIE(InfoExtractor):
'description': 'md5:1428185051cfd1949807ad4ff6d3686a', 'description': 'md5:1428185051cfd1949807ad4ff6d3686a',
'duration': 201, 'duration': 201,
} }
}, {
'url': 'https://www.yahoo.com/movies/v/true-story-trailer-173000497.html',
'md5': '989396ae73d20c6f057746fb226aa215',
'info_dict': {
'id': '071c4013-ce30-3a93-a5b2-e0413cd4a9d1',
'ext': 'mp4',
'title': '\'True Story\' Trailer',
'description': 'True Story',
'duration': 150,
},
}, { }, {
'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html', 'url': 'https://gma.yahoo.com/pizza-delivery-man-surprised-huge-tip-college-kids-195200785.html',
'only_matching': True, 'only_matching': True,
@ -125,6 +136,7 @@ class YahooIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
display_id = mobj.group('display_id') display_id = mobj.group('display_id')
page_id = mobj.group('id')
url = mobj.group('url') url = mobj.group('url')
host = mobj.group('host') host = mobj.group('host')
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
@ -149,6 +161,7 @@ class YahooIE(InfoExtractor):
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),
] ]
video_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID') video_id = self._search_regex(CONTENT_ID_REGEXES, webpage, 'content ID')
else: else:
@ -211,7 +224,7 @@ class YahooIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id, 'display_id': display_id,
'title': meta['title'], 'title': unescapeHTML(meta['title']),
'formats': formats, 'formats': formats,
'description': clean_html(meta['description']), 'description': clean_html(meta['description']),
'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage), 'thumbnail': meta['thumbnail'] if meta.get('thumbnail') else self._og_search_thumbnail(webpage),