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$',
94 'upload_date': '20140122',
98 'skip_download': True, # requires ffmpeg
102 'url': 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/',
104 'id': 'united-states-of-secrets',
109 'url': 'http://www.pbs.org/wgbh/americanexperience/films/death/player/',
112 'display_id': 'player',
114 'title': 'American Experience - Death and the Civil War',
115 'description': 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.',
117 'thumbnail': 're:^https?://.*\.jpg$',
120 'skip_download': True, # requires ffmpeg
124 'url': 'http://video.pbs.org/video/2365367186/',
127 'display_id': '2365367186',
129 'title': 'To Catch A Comet - Full Episode',
130 '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.',
132 'thumbnail': 're:^https?://.*\.jpg$',
135 'skip_download': True, # requires ffmpeg
140 def _extract_webpage(self, url):
141 mobj = re.match(self._VALID_URL, url)
143 presumptive_id = mobj.group('presumptive_id')
144 display_id = presumptive_id
146 webpage = self._download_webpage(url, display_id)
148 upload_date = unified_strdate(self._search_regex(
149 r'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"',
150 webpage, 'upload date', default=None))
152 # tabbed frontline videos
153 tabbed_videos = re.findall(
154 r'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"', webpage)
156 return tabbed_videos, presumptive_id, upload_date
159 r"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'", # frontline video embed
160 r'class="coveplayerid">([^<]+)<', # coveplayer
161 r'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>', # jwplayer
164 media_id = self._search_regex(
165 MEDIA_ID_REGEXES, webpage, 'media ID', fatal=False, default=None)
167 return media_id, presumptive_id, upload_date
169 url = self._search_regex(
170 r'<iframe\s+[^>]*\s+src=["\']([^\'"]+partnerplayer[^\'"]+)["\']',
171 webpage, 'player URL')
172 mobj = re.match(self._VALID_URL, url)
174 player_id = mobj.group('player_id')
176 display_id = player_id
178 player_page = self._download_webpage(
179 url, display_id, note='Downloading player page',
180 errnote='Could not download player page')
181 video_id = self._search_regex(
182 r'<div\s+id="video_([0-9]+)"', player_page, 'video ID')
184 video_id = mobj.group('id')
185 display_id = video_id
187 return video_id, display_id, None
189 def _real_extract(self, url):
190 video_id, display_id, upload_date = self._extract_webpage(url)
192 if isinstance(video_id, list):
193 entries = [self.url_result(
194 'http://video.pbs.org/video/%s' % vid_id, 'PBS', vid_id)
195 for vid_id in video_id]
196 return self.playlist_result(entries, display_id)
198 info = self._download_json(
199 'http://video.pbs.org/videoInfo/%s?format=json&type=partner' % video_id,
203 for encoding_name in ('recommended_encoding', 'alternate_encoding'):
204 redirect = info.get(encoding_name)
207 redirect_url = redirect.get('url')
211 redirect_info = self._download_json(
212 redirect_url + '?format=json', display_id,
213 'Downloading %s video url info' % encoding_name)
215 if redirect_info['status'] == 'error':
216 if redirect_info['http_code'] == 403:
218 'The video is not available in your region due to '
219 'right restrictions')
221 message = redirect_info['message']
222 raise ExtractorError(message, expected=True)
224 format_url = redirect_info.get('url')
228 if determine_ext(format_url) == 'm3u8':
229 formats.extend(self._extract_m3u8_formats(
230 format_url, display_id, 'mp4', preference=1, m3u8_id='hls'))
234 'format_id': redirect.get('eeid'),
236 self._sort_formats(formats)
238 rating_str = info.get('rating')
239 if rating_str is not None:
240 rating_str = rating_str.rpartition('-')[2]
241 age_limit = US_RATINGS.get(rating_str)
244 closed_captions_url = info.get('closed_captions_url')
245 if closed_captions_url:
248 'url': closed_captions_url,
251 # info['title'] is often incomplete (e.g. 'Full Episode', 'Episode 5', etc)
252 # Try turning it to 'program - title' naming scheme if possible
253 alt_title = info.get('program', {}).get('title')
255 info['title'] = alt_title + ' - ' + re.sub(r'^' + alt_title + '[\s\-:]+', '', info['title'])
259 'display_id': display_id,
260 'title': info['title'],
261 'description': info['program'].get('description'),
262 'thumbnail': info.get('image_url'),
263 'duration': int_or_none(info.get('duration')),
264 'age_limit': age_limit,
265 'upload_date': upload_date,
267 'subtitles': subtitles,