R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[tf1] proper multipattern and relaxed regex

Browse Source
This commit is contained in:
Emmanuel Froissart 2019-06-12 15:21:54 +02:00
parent 77d6e33ac6
commit ae4df7d346
1 changed files with 4 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
youtube_dl/extractor/tf1.py
View File

@ -64,13 +64,8 @@ class TF1IE(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(url, video_id)
try:
wat_id = self._html_search_regex( wat_id = self._html_search_regex(
# the old pattern. Should no longer work as of 2019-06-12 [r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1',
r'(["\'])(?:https?:)?//www\.wat\.tv/embedframe/.*?(?P<id>\d{8})\1', r'(["\']?)streamId\1\s*:\s*["\']?(?P<id>\d+)'],
webpage, 'wat id', group='id')
except RegexNotFoundError:
wat_id = self._html_search_regex(
r'\bstreamId\W+(?P<id>\d+)',
webpage, 'wat id', group='id') webpage, 'wat id', group='id')
return self.url_result('wat:%s' % wat_id, 'Wat') return self.url_result('wat:%s' % wat_id, 'Wat')