from __future__ import unicode_literals import re from .common import InfoExtractor from ..utils import ( US_RATINGS, ) 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[^/]+)/?(?:$|[?\#]) | # Player video\.pbs\.org/(?:widget/)?partnerplayer/(?P[^/]+)/ ) ''' _TESTS = [ { 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/', 'md5': 'ce1888486f0908d555a8093cac9a7362', 'info_dict': { 'id': '2365006249', 'ext': 'mp4', 'title': 'A More Perfect Union', 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a', 'duration': 3190, }, }, { 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/', 'md5': 'b19856d7f5351b17a5ab1dc6a64be633', 'info_dict': { 'id': '2201174722', 'ext': 'mp4', 'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist', 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28', 'duration': 801, }, }, ] def _extract_ids(self, url): mobj = re.match(self._VALID_URL, url) presumptive_id = mobj.group('presumptive_id') display_id = presumptive_id if presumptive_id: webpage = self._download_webpage(url, display_id) MEDIA_ID_REGEXES = [ r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed r'class="coveplayerid">([^<]+)<', # coveplayer ] media_id = self._search_regex( MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None) if media_id: return media_id, presumptive_id url = self._search_regex( r'', webpage, 'player URL') mobj = re.match(self._VALID_URL, url) player_id = mobj.group('player_id') if not display_id: display_id = player_id if player_id: player_page = self._download_webpage( url, display_id, note='Downloading player page', errnote='Could not download player page') video_id = self._search_regex( r'