diff options
| author | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-01-22 11:06:03 +0100 |
|---|---|---|
| committer | Jaime Marquínez Ferrándiz <jaime.marquinez.ferrandiz@gmail.com> | 2014-01-22 11:06:03 +0100 |
| commit | 407ae733ab24dbe4fdbd5b996aef6438f16834a2 (patch) | |
| tree | ecd3f7d230a553e60dbf85f479219843f407f8ca | |
| parent | c39f7013e1070a55729d143817690a282a5b3f10 (diff) | |
[cspan] Make ‘www’ optional and improve the regex for extracting the id (fixes #2194)
| -rw-r--r-- | youtube_dl/extractor/cspan.py | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index a2cbd4d8d..521bbdee0 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -10,7 +10,7 @@ from ..utils import ( class CSpanIE(InfoExtractor): - _VALID_URL = r'http://www\.c-spanvideo\.org/program/(.*)' + _VALID_URL = r'http://(?:www\.)?c-spanvideo\.org/program/(?P<name>.*)' IE_DESC = 'C-SPAN' _TEST = { 'url': 'http://www.c-spanvideo.org/program/HolderonV', @@ -24,9 +24,9 @@ class CSpanIE(InfoExtractor): def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) - prog_name = mobj.group(1) + prog_name = mobj.group('name') webpage = self._download_webpage(url, prog_name) - video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id') + video_id = self._search_regex(r'prog(?:ram)?id=(.*?)&', webpage, 'video id') title = self._html_search_regex( r'<!-- title -->\n\s*<h1[^>]*>(.*?)</h1>', webpage, 'title') |