minhngoc25a
/
yt-dlc
mirror of https://github.com/blackjack4494/yt-dlc
1
0
Fork 1
Code Issues Releases Wiki Activity

[breakcom] Cover more URLs with _VALID_URL (Closes #3876)

This commit is contained in:
Sergey M․ 2014-10-03 18:57:18 +07:00
parent 8489578df4
commit f78c01f68b
1 changed files with 13 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
youtube_dl/extractor/breakcom.py
View File

@ -7,25 +7,27 @@ from .common import InfoExtractor
class BreakIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)'
_TEST = {
_VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b',
'md5': '33aa4ff477ecd124d18d7b5d23b87ce5',
'info_dict': {
'id': '2468056',
'ext': 'mp4',
'title': 'When Girls Act Like D-Bags',
}
}
}, {
'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
'only_matching': True,
}]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1).split("-")[-1]
embed_url = 'http://www.break.com/embed/%s' % video_id
webpage = self._download_webpage(embed_url, video_id)
info_json = self._search_regex(r'var embedVars = ({.*})\s*?</script>',
webpage, 'info json', flags=re.DOTALL)
info = json.loads(info_json)
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://www.break.com/embed/%s' % video_id, video_id)
info = json.loads(self._search_regex(
r'var embedVars = ({.*})\s*?</script>',
webpage, 'info json', flags=re.DOTALL))
video_url = info['videoUri']
youtube_id = info.get('youtubeId')
if youtube_id: