summary refs log tree commit diff
diff options
context:
space:
mode:
authorSergey M․ <dstftw@gmail.com>2014-10-23 20:41:45 +0700
committerSergey M․ <dstftw@gmail.com>2014-10-23 20:41:45 +0700
commit9bbec55255bdf7189f782e42c1acaeb596eb9bf8 (patch)
treeb1ca4c63b3dc89071913db725860b48eee3e05e1
parent6b445558ffe292c11327862ab510b1abf4e36616 (diff)
downloadyoutube-dl-9bbec55255bdf7189f782e42c1acaeb596eb9bf8.tar.gz
youtube-dl-9bbec55255bdf7189f782e42c1acaeb596eb9bf8.tar.xz
youtube-dl-9bbec55255bdf7189f782e42c1acaeb596eb9bf8.zip
[pbs] Add support for tabbed frontline videos (Closes #4006)
-rw-r--r--youtube_dl/extractor/pbs.py20
1 files changed, 19 insertions, 1 deletions
diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index 8f140d626..6118ed5c2 100644
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -80,8 +80,14 @@ class PBSIE(InfoExtractor):
                 'thumbnail': 're:^https?://.*\.jpg$',
                 '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):
@@ -96,6 +102,12 @@ class PBSIE(InfoExtractor):
                 r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
                 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 = [
                 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'",  # frontline video embed
                 r'class="coveplayerid">([^<]+)<',                       # coveplayer
@@ -130,6 +142,12 @@ class PBSIE(InfoExtractor):
     def _real_extract(self, 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 = self._download_json(info_url, display_id)