diff options
| author | Sergey M․ <dstftw@gmail.com> | 2014-08-18 19:20:53 +0700 |
|---|---|---|
| committer | Sergey M․ <dstftw@gmail.com> | 2014-08-18 19:20:53 +0700 |
| commit | 4d9bd478f9d846291c722da002266504fce824ba (patch) | |
| tree | 58c0181f825b46fb2cf0f0da111128ec8ee98dde | |
| parent | c1d293cfa68031e0ec1a4190041f280d22c2b026 (diff) | |
| download | youtube-dl-4d9bd478f9d846291c722da002266504fce824ba.tar.xz | |
[pbs] Extract coveplayerid (Closes #3522)
| -rw-r--r-- | youtube_dl/extractor/pbs.py | 42 |
1 files changed, 29 insertions, 13 deletions
diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index ec95d0704..09bee6561 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -20,17 +20,30 @@ class PBSIE(InfoExtractor): ) ''' - _TEST = { - 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', - 'md5': 'ce1888486f0908d555a8093cac9a7362', - 'info_dict': { - 'id': '2365006249', - 'ext': 'mp4', - 'title': 'A More Perfect Union', - 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', - 'duration': 3190, + _TESTS = [ + { + 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', + 'md5': 'ce1888486f0908d555a8093cac9a7362', + 'info_dict': { + 'id': '2365006249', + 'ext': 'mp4', + 'title': 'A More Perfect Union', + 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', + 'duration': 3190, + }, + }, + { + 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/', + 'md5': 'b19856d7f5351b17a5ab1dc6a64be633', + 'info_dict': { + 'id': '2201174722', + 'ext': 'mp4', + 'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist', + 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28', + 'duration': 801, + }, }, - } + ] def _extract_ids(self, url): mobj = re.match(self._VALID_URL, url) @@ -40,10 +53,13 @@ class PBSIE(InfoExtractor): if presumptive_id: webpage = self._download_webpage(url, display_id) - # frontline video embed + MEDIA_ID_REGEXES = [ + r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed + r'class="coveplayerid">([^<]+)<', # coveplayer + ] + media_id = self._search_regex( - r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", - webpage, 'frontline video ID', fatal=False, default=None) + MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None) if media_id: return media_id, presumptive_id |