2 from __future__ import unicode_literals
6 from .common import InfoExtractor
16 class PBSIE(InfoExtractor):
17 _VALID_URL = r'''(?x)https?://
20 video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
21 # Article with embedded player (or direct video)
22 (?:www\.)?pbs\.org/(?:[^/]+/){2,5}(?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
24 video\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
30 'url': 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/',
31 'md5': 'ce1888486f0908d555a8093cac9a7362',
35 'title': 'Constitution USA with Peter Sagal - A More Perfect Union',
36 'description': 'md5:ba0c207295339c8d6eced00b7c363c6a',
40 'skip_download': True, # requires ffmpeg
44 'url': 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/',
45 'md5': '143c98aa54a346738a3d78f54c925321',
49 'title': 'FRONTLINE - Losing Iraq',
50 'description': 'md5:f5bfbefadf421e8bb8647602011caf8e',
54 'skip_download': True, # requires ffmpeg
58 'url': 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/',
59 'md5': 'b19856d7f5351b17a5ab1dc6a64be633',
63 'title': 'PBS NewsHour - Cyber Schools Gain Popularity, but Quality Questions Persist',
64 'description': 'md5:5871c15cba347c1b3d28ac47a73c7c28',
69 'url': 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/',
70 'md5': 'c62859342be2a0358d6c9eb306595978',
74 'description': 'md5:68d87ef760660eb564455eb30ca464fe',
75 'title': 'Great Performances - Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full',
77 'thumbnail': 're:^https?://.*\.jpg$',
80 'skip_download': True, # requires ffmpeg
84 'url': 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html',
85 'md5': '908f3e5473a693b266b84e25e1cf9703',
88 'display_id': 'killer-typhoon',
90 'description': 'md5:c741d14e979fc53228c575894094f157',
91 'title': 'NOVA - Killer Typhoon',
93 'thumbnail': 're:^https?://.*\.jpg$',
94 'upload_date': '20140122',
97 'skip_download': True, # requires ffmpeg
101 'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
103 'id': 'united-states-of-secrets',
108 'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
111 'display_id': 'player',
113 'title': 'American Experience - Death and the Civil War',
114 'description': 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
116 'thumbnail': 're:^https?://.*\.jpg$',
119 'skip_download': True, # requires ffmpeg
123 'url': 'http://video.pbs.org/video/2365367186/',
126 'display_id': '2365367186',
128 'title': 'To Catch A Comet - Full Episode',
129 'description': 'On November 12, 2014, billions of kilometers from Earth, spacecraft orbiter Rosetta and lander Philae did what no other had dared to attempt \u2014 land on the volatile surface of a comet as it zooms around the sun at 67,000 km/hr. The European Space Agency hopes this mission can help peer into our past and unlock secrets of our origins.',
131 'thumbnail': 're:^https?://.*\.jpg$',
134 'skip_download': True, # requires ffmpeg
139 def _extract_webpage(self, url):
140 mobj = re.match(self._VALID_URL, url)
142 presumptive_id = mobj.group('presumptive_id')
143 display_id = presumptive_id
145 webpage = self._download_webpage(url, display_id)
147 upload_date = unified_strdate(self._search_regex(
148 r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
149 webpage, 'upload date', default=None))
151 # tabbed frontline videos
152 tabbed_videos = re.findall(
153 r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
155 return tabbed_videos, presumptive_id, upload_date
158 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
159 r'class="coveplayerid">([^<]+)<', # coveplayer
160 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer
163 media_id = self._search_regex(
164 MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
166 return media_id, presumptive_id, upload_date
168 url = self._search_regex(
169 r'<iframe\s+[^>]*\s+src=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
170 webpage, 'player URL')
171 mobj = re.match(self._VALID_URL, url)
173 player_id = mobj.group('player_id')
175 display_id = player_id
177 player_page = self._download_webpage(
178 url, display_id, note='Downloading player page',
179 errnote='Could not download player page')
180 video_id = self._search_regex(
181 r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
183 video_id = mobj.group('id')
184 display_id = video_id
186 return video_id, display_id, None
188 def _real_extract(self, url):
189 video_id, display_id, upload_date = self._extract_webpage(url)
191 if isinstance(video_id, list):
192 entries = [self.url_result(
193 'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
194 for vid_id in video_id]
195 return self.playlist_result(entries, display_id)
197 info = self._download_json(
198 'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
202 for encoding_name in ('recommended_encoding', 'alternate_encoding'):
203 redirect = info.get(encoding_name)
206 redirect_url = redirect.get('url')
210 redirect_info = self._download_json(
211 redirect_url + '?format=json', display_id,
212 'Downloading %s video url info' % encoding_name)
214 if redirect_info['status'] == 'error':
215 if redirect_info['http_code'] == 403:
217 'The video is not available in your region due to '
218 'right restrictions')
220 message = redirect_info['message']
221 raise ExtractorError(message, expected=True)
223 format_url = redirect_info.get('url')
227 if determine_ext(format_url) == 'm3u8':
228 formats.extend(self._extract_m3u8_formats(
229 format_url, display_id, 'mp4', preference=1, m3u8_id='hls'))
233 'format_id': redirect.get('eeid'),
235 self._sort_formats(formats)
237 rating_str = info.get('rating')
238 if rating_str is not None:
239 rating_str = rating_str.rpartition('-')[2]
240 age_limit = US_RATINGS.get(rating_str)
243 closed_captions_url = info.get('closed_captions_url')
244 if closed_captions_url:
247 'url': closed_captions_url,
250 # video.pbs.org video.pbs.org/videoInfo/... frequently provides an obscure 'title' value, like
251 # 'Full Episode', 'Episode 5', etc. prepend program->title
252 alt_title = info.get('program', {}).get('title', '')
254 info['title'] = alt_title + ' - ' + re.sub(r'^' + alt_title + '[\s\-\:]+', '', info['title'])
258 'display_id': display_id,
259 'title': info['title'],
260 'description': info['program'].get('description'),
261 'thumbnail': info.get('image_url'),
262 'duration': int_or_none(info.get('duration')),
263 'age_limit': age_limit,
264 'upload_date': upload_date,
266 'subtitles': subtitles,