[cspan] Fix extraction (fixes #8032)

This commit is contained in:
Jaime Marquínez Ferrándiz 2015-12-28 13:48:10 +01:00
parent 04e24906be
commit 6c6b8bd5cc
1 changed files with 6 additions and 4 deletions

View File

@ -60,11 +60,13 @@ class CSpanIE(InfoExtractor):
video_id = self._match_id(url) video_id = self._match_id(url)
video_type = None video_type = None
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage) # We first look for clipid, because clipprog always appears before
if matches: patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
results = list(filter(None, (re.search(p, webpage) for p in patterns)))
if results:
matches = results[0]
video_type, video_id = matches.groups() video_type, video_id = matches.groups()
if video_type == 'prog': video_type = 'clip' if video_type == 'id' else 'program'
video_type = 'program'
else: else:
senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
if senate_isvp_url: if senate_isvp_url: