diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2015-12-28 13:48:10 +0100 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2015-12-28 13:50:29 +0100 |
| commit | 6c6b8bd5ccef10aad73ee5a556830f9b00b93661 (patch) | |
| tree | 6e7ce5d0810b531f5ce29bef85cba024875563cb | |
| parent | 04e24906be1dd0b6626b50de7e65609219a88116 (diff) | |
| download | youtube-dl-6c6b8bd5ccef10aad73ee5a556830f9b00b93661.zip youtube-dl-6c6b8bd5ccef10aad73ee5a556830f9b00b93661.tar.gz youtube-dl-6c6b8bd5ccef10aad73ee5a556830f9b00b93661.tar.bz2 | |
[cspan] Fix extraction (fixes #8032)
| -rw-r--r-- | youtube_dl/extractor/cspan.py | 10 |
1 files changed, 6 insertions, 4 deletions
diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 154bddb..b3ee670 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -60,11 +60,13 @@ class CSpanIE(InfoExtractor): video_id = self._match_id(url) video_type = None webpage = self._download_webpage(url, video_id) - matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage) - if matches: + # We first look for clipid, because clipprog always appears before + 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() - if video_type == 'prog': - video_type = 'program' + video_type = 'clip' if video_type == 'id' else 'program' else: senate_isvp_url = SenateISVPIE._search_iframe_url(webpage) if senate_isvp_url: |