1 from __future__ import unicode_literals
5 from .common import InfoExtractor
11 class PBSIE(InfoExtractor):
12 _VALID_URL = r'''(?x)https?://
15 video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
16 # Article with embedded player
17 (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+)/?(?:$|[?\#]) |
19 video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
25 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
26 'md5': 'ce1888486f0908d555a8093cac9a7362',
30 'title': 'A More Perfect Union',
31 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
36 'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
37 'md5': '143c98aa54a346738a3d78f54c925321',
41 'title': 'Losing Iraq',
42 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
47 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
48 'md5': 'b19856d7f5351b17a5ab1dc6a64be633',
52 'title': 'Cyber Schools Gain Popularity, but Quality Questions Persist',
53 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28',
59 def _extract_ids(self, url):
60 mobj = re.match(self._VALID_URL, url)
62 presumptive_id = mobj.group('presumptive_id')
63 display_id = presumptive_id
65 webpage = self._download_webpage(url, display_id)
68 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
69 r'class="coveplayerid">([^<]+)<', # coveplayer
72 media_id = self._search_regex(
73 MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
75 return media_id, presumptive_id
77 url = self._search_regex(
78 r'<iframe\s+id=["\']partnerPlayer["\'].*?\s+src=["\'](.*?)["\']>',
79 webpage, 'player URL')
80 mobj = re.match(self._VALID_URL, url)
82 player_id = mobj.group('player_id')
84 display_id = player_id
86 player_page = self._download_webpage(
87 url, display_id, note='Downloading player page',
88 errnote='Could not download player page')
89 video_id = self._search_regex(
90 r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
92 video_id = mobj.group('id')
95 return video_id, display_id
97 def _real_extract(self, url):
98 video_id, display_id = self._extract_ids(url)
100 info_url = 'http://video.pbs.org/videoInfo/%s?format=json' % video_id
101 info = self._download_json(info_url, display_id)
103 rating_str = info.get('rating')
104 if rating_str is not None:
105 rating_str = rating_str.rpartition('-')[2]
106 age_limit = US_RATINGS.get(rating_str)
110 'title': info['title'],
111 'url': info['alternate_encoding']['url'],
113 'description': info['program'].get('description'),
114 'thumbnail': info.get('image_url'),
115 'duration': info.get('duration'),
116 'age_limit': age_limit,