Upstream/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-03 08:19:57 +01:00
Code Issues Packages Projects Releases Wiki Activity

[pbs] Add support for tabbed frontline videos (Closes #4006)

Browse Source
This commit is contained in:
Sergey M․ 2014-10-23 20:41:45 +07:00
parent 6b445558ff
commit 9bbec55255
1 changed files with 19 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

20
youtube_dl/extractor/pbs.py
View File

@ -80,8 +80,14 @@ class PBSIE(InfoExtractor):
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20140122', 'upload_date': '20140122',
} }
},
{
'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
'info_dict': {
'id': 'united-states-of-secrets',
},
'playlist_count': 2,
} }
] ]
def _extract_webpage(self, url): def _extract_webpage(self, url):
@ -96,6 +102,12 @@ def _extract_webpage(self, url):
r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"', r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
webpage, 'upload date', default=None)) webpage, 'upload date', default=None))
# tabbed frontline videos
tabbed_videos = re.findall(
r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
if tabbed_videos:
return tabbed_videos, presumptive_id, upload_date
MEDIA_ID_REGEXES = [ MEDIA_ID_REGEXES = [
r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
r'class="coveplayerid">([^<]+)<', # coveplayer r'class="coveplayerid">([^<]+)<', # coveplayer
@ -130,6 +142,12 @@ def _extract_webpage(self, url):
def _real_extract(self, url): def _real_extract(self, url):
video_id, display_id, upload_date = self._extract_webpage(url) video_id, display_id, upload_date = self._extract_webpage(url)
if isinstance(video_id, list):
entries = [self.url_result(
'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
for vid_id in video_id]
return self.playlist_result(entries, display_id)
info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
info = self._download_json(info_url, display_id) info = self._download_json(info_url, display_id)