aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/pbs.py
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor/pbs.py')
-rw-r--r--youtube_dl/extractor/pbs.py36
1 files changed, 34 insertions, 2 deletions
diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py
index 8f140d626..afce732e1 100644
--- a/youtube_dl/extractor/pbs.py
+++ b/youtube_dl/extractor/pbs.py
@@ -4,6 +4,7 @@ import re
from .common import InfoExtractor
from ..utils import (
+ ExtractorError,
unified_strdate,
US_RATINGS,
)
@@ -80,8 +81,14 @@ 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 +103,12 @@ 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
@@ -130,9 +143,28 @@ 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)
+ redirect_url = info['alternate_encoding']['url']
+ redirect_info = self._download_json(
+ redirect_url + '?format=json', display_id,
+ 'Downloading video url info')
+ if redirect_info['status'] == 'error':
+ if redirect_info['http_code'] == 403:
+ message = (
+ 'The video is not available in your region due to '
+ 'right restrictions')
+ else:
+ message = redirect_info['message']
+ raise ExtractorError(message, expected=True)
+
rating_str = info.get('rating')
if rating_str is not None:
rating_str = rating_str.rpartition('-')[2]
@@ -142,7 +174,7 @@ class PBSIE(InfoExtractor):
'id': video_id,
'display_id': display_id,
'title': info['title'],
- 'url': info['alternate_encoding']['url'],
+ 'url': redirect_info['url'],
'ext': 'mp4',
'description': info['program'].get('description'),
'thumbnail': info.get('image_url'),