From 27aede907436fa58600cd46bb04e7eae6e1e9279 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Mon, 29 Sep 2014 04:48:50 +0200 Subject: [PATCH] [pbs] Add support for series/jwplayer type video (Fixes #3849) --- youtube_dl/extractor/pbs.py | 39 +++++++++++++++++++++++++++++-------- 1 file changed, 31 insertions(+), 8 deletions(-) diff --git a/youtube_dl/extractor/pbs.py b/youtube_dl/extractor/pbs.py index 2adfde909..8f140d626 100644 --- a/youtube_dl/extractor/pbs.py +++ b/youtube_dl/extractor/pbs.py @@ -4,6 +4,7 @@ from .common import InfoExtractor from ..utils import ( + unified_strdate, US_RATINGS, ) @@ -11,10 +12,10 @@ class PBSIE(InfoExtractor): _VALID_URL = r'''(?x)https?:// (?: - # Direct video URL - video\.pbs\.org/(?:viralplayer|video)/(?P[0-9]+)/? | - # Article with embedded player - (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P[^/]+)/?(?:$|[?\#]) | + # Direct video URL + video\.pbs\.org/(?:viralplayer|video)/(?P[0-9]+)/? | + # Article with embedded player (or direct video) + (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P[^/]+?)(?:\.html)?/?(?:$|[?\#]) | # Player video\.pbs\.org/(?:widget/)?partnerplayer/(?P[^/]+)/ ) @@ -65,10 +66,25 @@ class PBSIE(InfoExtractor): 'duration': 6559, '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) presumptive_id = mobj.group('presumptive_id') @@ -76,15 +92,20 @@ def _extract_ids(self, url): if presumptive_id: webpage = self._download_webpage(url, display_id) + upload_date = unified_strdate(self._search_regex( + r'([^<]+)<', # coveplayer + r'', # jwplayer ] media_id = self._search_regex( MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None) if media_id: - return media_id, presumptive_id + return media_id, presumptive_id, upload_date url = self._search_regex( r'', @@ -104,10 +125,10 @@ def _extract_ids(self, url): video_id = mobj.group('id') display_id = video_id - return video_id, display_id + return video_id, display_id, None 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 = self._download_json(info_url, display_id) @@ -119,6 +140,7 @@ def _real_extract(self, url): return { 'id': video_id, + 'display_id': display_id, 'title': info['title'], 'url': info['alternate_encoding']['url'], 'ext': 'mp4', @@ -126,4 +148,5 @@ def _real_extract(self, url): 'thumbnail': info.get('image_url'), 'duration': info.get('duration'), 'age_limit': age_limit, + 'upload_date': upload_date, }