]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/pbs.py
2 from __future__
import unicode_literals
6 from . common
import InfoExtractor
17 class PBSIE ( InfoExtractor
):
18 _VALID_URL
= r
'''(?x)https?://
21 video\.pbs\.org/(?:viralplayer|video)/(?P<id>[0-9]+)/? |
22 # Article with embedded player (or direct video)
23 (?:www\.)?pbs\.org/(?:[^/]+/) {2,5} (?P<presumptive_id>[^/]+?)(?:\.html)?/?(?:$|[?\#]) |
25 (?:video|player)\.pbs\.org/(?:widget/)?partnerplayer/(?P<player_id>[^/]+)/
31 'url' : 'http://www.pbs.org/tpt/constitution-usa-peter-sagal/watch/a-more-perfect-union/' ,
32 'md5' : 'ce1888486f0908d555a8093cac9a7362' ,
36 'title' : 'Constitution USA with Peter Sagal - A More Perfect Union' ,
37 'description' : 'md5:ba0c207295339c8d6eced00b7c363c6a' ,
41 'skip_download' : True , # requires ffmpeg
45 'url' : 'http://www.pbs.org/wgbh/pages/frontline/losing-iraq/' ,
46 'md5' : '143c98aa54a346738a3d78f54c925321' ,
50 'title' : 'FRONTLINE - Losing Iraq' ,
51 'description' : 'md5:f5bfbefadf421e8bb8647602011caf8e' ,
55 'skip_download' : True , # requires ffmpeg
59 'url' : 'http://www.pbs.org/newshour/bb/education-jan-june12-cyberschools_02-23/' ,
60 'md5' : 'b19856d7f5351b17a5ab1dc6a64be633' ,
64 'title' : 'PBS NewsHour - Cyber Schools Gain Popularity, but Quality Questions Persist' ,
65 'description' : 'md5:5871c15cba347c1b3d28ac47a73c7c28' ,
70 'url' : 'http://www.pbs.org/wnet/gperf/dudamel-conducts-verdi-requiem-hollywood-bowl-full-episode/3374/' ,
71 'md5' : 'c62859342be2a0358d6c9eb306595978' ,
75 'description' : 'md5:68d87ef760660eb564455eb30ca464fe' ,
76 'title' : 'Great Performances - Dudamel Conducts Verdi Requiem at the Hollywood Bowl - Full' ,
78 'thumbnail' : 're:^https?://.*\.jpg$' ,
81 'skip_download' : True , # requires ffmpeg
85 'url' : 'http://www.pbs.org/wgbh/nova/earth/killer-typhoon.html' ,
86 'md5' : '908f3e5473a693b266b84e25e1cf9703' ,
89 'display_id' : 'killer-typhoon' ,
91 'description' : 'md5:c741d14e979fc53228c575894094f157' ,
92 'title' : 'NOVA - Killer Typhoon' ,
94 'thumbnail' : 're:^https?://.*\.jpg$' ,
95 'upload_date' : '20140122' ,
99 'skip_download' : True , # requires ffmpeg
103 'url' : 'http://www.pbs.org/wgbh/pages/frontline/united-states-of-secrets/' ,
105 'id' : 'united-states-of-secrets' ,
110 'url' : 'http://www.pbs.org/wgbh/americanexperience/films/death/player/' ,
113 'display_id' : 'player' ,
115 'title' : 'American Experience - Death and the Civil War, Chapter 1' ,
116 'description' : 'American Experience, TV’s most-watched history series, brings to life the compelling stories from our past that inform our understanding of the world today.' ,
118 'thumbnail' : 're:^https?://.*\.jpg$' ,
121 'skip_download' : True , # requires ffmpeg
125 'url' : 'http://video.pbs.org/video/2365367186/' ,
128 'display_id' : '2365367186' ,
130 'title' : 'To Catch A Comet - Full Episode' ,
131 '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.' ,
133 'thumbnail' : 're:^https?://.*\.jpg$' ,
136 'skip_download' : True , # requires ffmpeg
141 # Video embedded in iframe containing angle brackets as attribute's value (e.g.
142 # "<iframe style='position: absolute;<br />\ntop: 0; left: 0;' ...", see
143 # https://github.com/rg3/youtube-dl/issues/7059)
144 'url' : 'http://www.pbs.org/food/features/a-chefs-life-season-3-episode-5-prickly-business/' ,
147 'display_id' : 'a-chefs-life-season-3-episode-5-prickly-business' ,
149 'title' : "A Chef's Life - Season 3, Ep. 5: Prickly Business" ,
150 'description' : 'md5:61db2ddf27c9912f09c241014b118ed1' ,
152 'thumbnail' : 're:^https?://.*\.jpg$' ,
155 'skip_download' : True , # requires ffmpeg
159 # Frontline video embedded via flp2012.js
160 'url' : 'http://www.pbs.org/wgbh/pages/frontline/the-atomic-artists' ,
163 'display_id' : 'the-atomic-artists' ,
165 'title' : 'FRONTLINE - The Atomic Artists' ,
166 'description' : 'md5:f5bfbefadf421e8bb8647602011caf8e' ,
168 'thumbnail' : 're:^https?://.*\.jpg$' ,
171 'skip_download' : True , # requires ffmpeg
175 'url' : 'http://player.pbs.org/widget/partnerplayer/2365297708/?start=0&end=0&chapterbar=false&endscreen=false&topbar=true' ,
176 'only_matching' : True ,
180 101 : 'We \' re sorry, but this video is not yet available.' ,
181 403 : 'We \' re sorry, but this video is not available in your region due to right restrictions.' ,
182 404 : 'We are experiencing technical difficulties that are preventing us from playing the video at this time. Please check back again soon.' ,
183 410 : 'This video has expired and is no longer available for online streaming.' ,
186 def _extract_webpage ( self
, url
):
187 mobj
= re
. match ( self
._ VALID
_U RL
, url
)
189 presumptive_id
= mobj
. group ( 'presumptive_id' )
190 display_id
= presumptive_id
192 webpage
= self
._ download
_ webpage
( url
, display_id
)
194 upload_date
= unified_strdate ( self
._ search
_ regex
(
195 r
'<input type="hidden" id="air_date_[0-9]+" value="([^"]+)"' ,
196 webpage
, 'upload date' , default
= None ))
198 # tabbed frontline videos
199 tabbed_videos
= re
. findall (
200 r
'<div[^>]+class="videotab[^"]*"[^>]+vid="(\d+)"' , webpage
)
202 return tabbed_videos
, presumptive_id
, upload_date
205 r
"div\s*:\s*'videoembed'\s*,\s*mediaid\s*:\s*'(\d+)'" , # frontline video embed
206 r
'class="coveplayerid">([^<]+)<' , # coveplayer
207 r
'<input type="hidden" id="pbs_video_id_[0-9]+" value="([0-9]+)"/>' , # jwplayer
210 media_id
= self
._ search
_ regex
(
211 MEDIA_ID_REGEXES
, webpage
, 'media ID' , fatal
= False , default
= None )
213 return media_id
, presumptive_id
, upload_date
215 # Fronline video embedded via flp
216 video_id
= self
._ search
_ regex
(
217 r
'videoid\s*:\s*"([\d+a-z] {7,} )"' , webpage
, 'videoid' , default
= None )
219 # pkg_id calculation is reverse engineered from
220 # http://www.pbs.org/wgbh/pages/frontline/js/flp2012.js
221 prg_id
= self
._ search
_ regex
(
222 r
'videoid\s*:\s*"([\d+a-z] {7,} )"' , webpage
, 'videoid' )[ 7 :]
224 prg_id
= prg_id
. split ( 'q' )[ 1 ]
225 prg_id
= int ( prg_id
, 16 )
226 getdir
= self
._ download
_ json
(
227 'http://www.pbs.org/wgbh/pages/frontline/.json/getdir/getdir %d .json' % prg_id
,
228 presumptive_id
, 'Downloading getdir JSON' ,
229 transform_source
= strip_jsonp
)
230 return getdir
[ 'mid' ], presumptive_id
, upload_date
232 for iframe
in re
. findall ( r
'(?s)<iframe(.+?)></iframe>' , webpage
):
233 url
= self
._ search
_ regex
(
234 r
'src=(["\' ])( ?P
< url
>.+ ?partnerplayer
.+ ?
) \
1 ', iframe,
235 ' player URL
', default=None, group=' url
')
239 mobj = re.match(self._VALID_URL, url)
241 player_id = mobj.group(' player_id
')
243 display_id = player_id
245 player_page = self._download_webpage(
246 url, display_id, note=' Downloading player page
',
247 errnote=' Could
not download player page
')
248 video_id = self._search_regex(
249 r' < div\s
+ id = "video_([0-9]+)" ', player_page, ' video ID
')
251 video_id = mobj.group(' id ')
252 display_id = video_id
254 return video_id, display_id, None
256 def _real_extract(self, url):
257 video_id, display_id, upload_date = self._extract_webpage(url)
259 if isinstance(video_id, list):
260 entries = [self.url_result(
261 ' http
:// video
. pbs
. org
/ video
/ %s ' % vid_id, ' PBS
', vid_id)
262 for vid_id in video_id]
263 return self.playlist_result(entries, display_id)
265 info = self._download_json(
266 ' http
:// player
. pbs
. org
/ videoInfo
/ %s ?format
= json
& type = partner
' % video_id,
270 for encoding_name in (' recommended_encoding
', ' alternate_encoding
'):
271 redirect = info.get(encoding_name)
274 redirect_url = redirect.get(' url
')
278 redirect_info = self._download_json(
279 redirect_url + ' ?format
= json
', display_id,
280 ' Downloading
%s video url info
' % encoding_name)
282 if redirect_info[' status
'] == ' error
':
283 raise ExtractorError(
286 self._ERRORS.get(redirect_info[' http_code
'], redirect_info[' message
'])),
289 format_url = redirect_info.get(' url
')
293 if determine_ext(format_url) == ' m3u8
':
294 formats.extend(self._extract_m3u8_formats(
295 format_url, display_id, ' mp4
', preference=1, m3u8_id=' hls
'))
299 ' format_id
': redirect.get(' eeid
'),
301 self._sort_formats(formats)
303 rating_str = info.get(' rating
')
304 if rating_str is not None:
305 rating_str = rating_str.rpartition(' - ')[2]
306 age_limit = US_RATINGS.get(rating_str)
309 closed_captions_url = info.get(' closed_captions_url
')
310 if closed_captions_url:
313 ' url
': closed_captions_url,
316 # info[' title
'] is often incomplete (e.g. ' Full Episode
', ' Episode
5 ', etc)
317 # Try turning it to ' program
- title
' naming scheme if possible
318 alt_title = info.get(' program
', {}).get(' title
')
320 info[' title
'] = alt_title + ' - ' + re.sub(r' ^
' + alt_title + ' [ \s\
-:]+ ', ' ', info[' title
'])
324 ' display_id
': display_id,
325 ' title
': info[' title
'],
326 ' description
': info[' program
'].get(' description
'),
327 ' thumbnail
': info.get(' image_url
'),
328 ' duration
': int_or_none(info.get(' duration
')),
329 ' age_limit
': age_limit,
330 ' upload_date
': upload_date,
332 ' subtitles
': subtitles,