dbrun
/
youtube-dl
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[pbs] Add support for series/jwplayer type video (Fixes #3849)

This commit is contained in:
Philipp Hagemeister 2014-09-29 04:48:50 +02:00
parent f5b7e6a842
commit 27aede9074
1 changed files with 31 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

35
youtube_dl/extractor/pbs.py
View File

@ -4,6 +4,7 @@ import re
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
unified_strdate,
US_RATINGS, US_RATINGS,
) )
@ -13,8 +14,8 @@ class PBSIE(InfoExtractor):
(?: (?:
# Direct video URL # Direct video URL
video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? | video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
# Article with embedded player # Article with embedded player (or direct video)
(?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+)/?(?:$|[?\#]) | (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
# Player # Player
video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/ video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
) )
@ -65,10 +66,25 @@ class PBSIE(InfoExtractor):
'duration': 6559, 'duration': 6559,
'thumbnail': 're:^https?://.*\.jpg$', 'thumbnail': 're:^https?://.*\.jpg$',
} }
},
{
'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
'md5': '908f3e5473a693b266b84e25e1cf9703',
'info_dict': {
'id': '2365160389',
'display_id': 'killer-typhoon',
'ext': 'mp4',
'description': 'md5:c741d14e979fc53228c575894094f157',
'title': 'Killer Typhoon',
'duration': 3172,
'thumbnail': 're:^https?://.*\.jpg$',
'upload_date': '20140122',
} }
}
] ]
def _extract_ids(self, url): def _extract_webpage(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
presumptive_id = mobj.group('presumptive_id') presumptive_id = mobj.group('presumptive_id')
@ -76,15 +92,20 @@ class PBSIE(InfoExtractor):
if presumptive_id: if presumptive_id:
webpage = self._download_webpage(url, display_id) webpage = self._download_webpage(url, display_id)
upload_date = unified_strdate(self._search_regex(
r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
webpage, 'upload date', default=None))
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
r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer
] ]
media_id = self._search_regex( media_id = self._search_regex(
MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None) MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
if media_id: if media_id:
return media_id, presumptive_id return media_id, presumptive_id, upload_date
url = self._search_regex( url = self._search_regex(
r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>', r'<iframe\s+(?:class|id)=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
@ -104,10 +125,10 @@ class PBSIE(InfoExtractor):
video_id = mobj.group('id') video_id = mobj.group('id')
display_id = video_id display_id = video_id
return video_id, display_id return video_id, display_id, None
def _real_extract(self, url): def _real_extract(self, url):
video_id, display_id = self._extract_ids(url) video_id, display_id, upload_date = self._extract_webpage(url)
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)
@ -119,6 +140,7 @@ class PBSIE(InfoExtractor):
return { return {
'id': video_id, 'id': video_id,
'display_id': display_id,
'title': info['title'], 'title': info['title'],
'url': info['alternate_encoding']['url'], 'url': info['alternate_encoding']['url'],
'ext': 'mp4', 'ext': 'mp4',
@ -126,4 +148,5 @@ class PBSIE(InfoExtractor):
'thumbnail': info.get('image_url'), 'thumbnail': info.get('image_url'),
'duration': info.get('duration'), 'duration': info.get('duration'),
'age_limit': age_limit, 'age_limit': age_limit,
'upload_date': upload_date,
} }