diff options
author | Sergey M․ <dstftw@gmail.com> | 2014-08-02 19:09:36 +0700 |
---|---|---|
committer | Sergey M․ <dstftw@gmail.com> | 2014-08-02 19:09:36 +0700 |
commit | 8d7d9d34521bcfa1b846964f404e8769d2e85ba0 (patch) | |
tree | 19fd2eb1528e16b383da525ec6df04b54fdc48a2 | |
parent | 7a5e7b303c6186f01e475789de7ef8cc3f9eea94 (diff) |
[pbs] Add support for frontline videos (Closes #3414 #3405)
-rw-r--r-- | youtube_dl/extractor/pbs.py | 15 |
1 files changed, 14 insertions, 1 deletions
diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 64cded707..ec95d0704 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -32,13 +32,21 @@ class PBSIE(InfoExtractor): }, } - def _real_extract(self, url): + def _extract_ids(self, url): mobj = re.match(self._VALID_URL, url) presumptive_id = mobj.group('presumptive_id') display_id = presumptive_id if presumptive_id: webpage = self._download_webpage(url, display_id) + + # frontline video embed + media_id = self._search_regex( + r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", + webpage, 'frontline video ID', fatal=False, default=None) + if media_id: + return media_id, presumptive_id + url = self._search_regex( r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', webpage, 'player URL') @@ -57,6 +65,11 @@ class PBSIE(InfoExtractor): video_id = mobj.group('id') display_id = video_id + return video_id, display_id + + def _real_extract(self, url): + video_id, display_id = self._extract_ids(url) + info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id info = self._download_json(info_url, display_id) |