]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/abc.py
6 from . common
import InfoExtractor
7 from .. compat
import compat_str
23 class ABCIE ( InfoExtractor
):
24 IE_NAME
= 'abc.net.au'
25 _VALID_URL
= r
'https?://(?:www\.)?abc\.net\.au/(?:news|btn)/(?:[^/]+/) {1,4} (?P<id>\d {5,} )'
28 'url' : 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334' ,
29 'md5' : 'cb3dd03b18455a661071ee1e28344d9f' ,
33 'title' : 'Australia to help staff Ebola treatment centre in Sierra Leone' ,
34 'description' : 'md5:809ad29c67a05f54eb41f2a105693a67' ,
36 'skip' : 'this video has expired' ,
38 'url' : 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326' ,
39 'md5' : '4ebd61bdc82d9a8b722f64f1f4b4d121' ,
43 'upload_date' : '20150816' ,
44 'uploader' : 'ABC News (Australia)' ,
45 'description' : 'Government backbencher Warren Entsch introduces a cross-party sponsored bill to legalise same-sex marriage, saying the bill is designed to promote "an inclusive Australia, not a divided one.". Read more here: http://ab.co/1Mwc6ef' ,
46 'uploader_id' : 'NewsOnABC' ,
47 'title' : 'Marriage Equality: Warren Entsch introduces same sex marriage bill' ,
49 'add_ie' : [ 'Youtube' ],
50 'skip' : 'Not accessible from Travis CI server' ,
52 'url' : 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080' ,
53 'md5' : 'b96eee7c9edf4fc5a358a0252881cc1f' ,
57 'title' : 'NAB lifts interest rates, following Westpac and CBA' ,
58 'description' : 'md5:f13d8edc81e462fce4a0437c7dc04728' ,
61 'url' : 'http://www.abc.net.au/news/2015-10-19/6866214' ,
62 'only_matching' : True ,
64 'url' : 'https://www.abc.net.au/btn/classroom/wwi-centenary/10527914' ,
68 'title' : 'WWI Centenary' ,
69 'description' : 'md5:c2379ec0ca84072e86b446e536954546' ,
72 'url' : 'https://www.abc.net.au/news/programs/the-world/2020-06-10/black-lives-matter-protests-spawn-support-for/12342074' ,
76 'title' : 'Black Lives Matter protests spawn support for Papuans in Indonesia' ,
77 'description' : 'md5:2961a17dc53abc558589ccd0fb8edd6f' ,
80 'url' : 'https://www.abc.net.au/btn/newsbreak/btn-newsbreak-20200814/12560476' ,
84 'title' : 'Fortnite Banned From Apple and Google App Stores' ,
85 'description' : 'md5:a6df3f36ce8f816b74af4bd6462f5651' ,
86 'upload_date' : '20200813' ,
87 'uploader' : 'Behind the News' ,
88 'uploader_id' : 'behindthenews' ,
91 'url' : 'https://www.abc.net.au/news/2023-06-25/wagner-boss-orders-troops-back-to-bases-to-avoid-bloodshed/102520540' ,
94 'title' : 'Wagner Group retreating from Russia, leader Prigozhin to move to Belarus' ,
96 'description' : 'Wagner troops leave Rostov-on-Don and \xa0 Yevgeny Prigozhin will move to Belarus under a deal brokered by Belarusian President Alexander Lukashenko to end the mutiny.' ,
97 'thumbnail' : 'https://live-production.wcms.abc-cdn.net.au/0c170f5b57f0105c432f366c0e8e267b?impolicy=wcms_crop_resize&cropH=2813&cropW=5000&xPos=0&yPos=249&width=862&height=485' ,
101 def _real_extract ( self
, url
):
102 video_id
= self
._ match
_ id
( url
)
103 webpage
= self
._ download
_ webpage
( url
, video_id
)
105 mobj
= re
. search ( r
'<a\s+href="(?P<url>[^"]+)"\s+data-duration="\d+"\s+title="Download audio directly">' , webpage
)
107 urls_info
= mobj
. groupdict ()
111 mobj
= re
. search ( r
'<a href="(?P<url>http://www\.youtube\.com/watch\?v=[^"]+)"><span><strong>External Link:</strong>' ,
114 mobj
= re
. search ( r
'<iframe width="100%" src="(?P<url>//www\.youtube-nocookie\.com/embed/[^?"]+)' , webpage
)
116 urls_info
= mobj
. groupdict ()
121 mobj
= re
. search ( r
'(?P<type>)"(?:sources|files|renditions)":\s*(?P<json_data>\[[^\]]+\])' , webpage
)
124 r
'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);' ,
127 expired
= self
._ html
_ search
_ regex
( r
'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>' , webpage
, 'expired' , None )
129 raise ExtractorError ( ' %s said: %s ' % ( self
. IE_NAME
, expired
), expected
= True )
130 raise ExtractorError ( 'Unable to extract video urls' )
132 urls_info
= self
._ parse
_ json
(
133 mobj
. group ( 'json_data' ), video_id
, transform_source
= js_to_json
)
134 youtube
= mobj
. group ( 'type' ) == 'YouTube'
135 video
= mobj
. group ( 'type' ) == 'Video' or traverse_obj (
136 urls_info
, ( 0 , ( 'contentType' , 'MIMEType' )), get_all
= False ) == 'video/mp4'
138 if not isinstance ( urls_info
, list ):
139 urls_info
= [ urls_info
]
142 return self
. playlist_result ([
143 self
. url_result ( url_info
[ 'url' ]) for url_info
in urls_info
])
146 for url_info
in urls_info
:
147 height
= int_or_none ( url_info
. get ( 'height' ))
148 bitrate
= int_or_none ( url_info
. get ( 'bitrate' ))
149 width
= int_or_none ( url_info
. get ( 'width' ))
151 mobj
= re
. search ( r
'_(?:(?P<height>\d+)|(?P<bitrate>\d+)k)\.mp4$' , url_info
[ 'url' ])
153 height_from_url
= mobj
. group ( 'height' )
155 height
= height
or int_or_none ( height_from_url
)
156 width
= width
or int_or_none ( url_info
. get ( 'label' ))
158 bitrate
= bitrate
or int_or_none ( mobj
. group ( 'bitrate' ))
159 format_id
= str_or_none ( url_info
. get ( 'label' ))
161 'url' : url_info
[ 'url' ],
162 'vcodec' : url_info
. get ( 'codec' ) if video
else 'none' ,
166 'filesize' : int_or_none ( url_info
. get ( 'filesize' )),
167 'format_id' : format_id
172 'title' : self
._ og
_ search
_ title
( webpage
),
174 'description' : self
._ og
_ search
_ description
( webpage
),
175 'thumbnail' : self
._ og
_ search
_ thumbnail
( webpage
),
179 class ABCIViewIE ( InfoExtractor
):
180 IE_NAME
= 'abc.net.au:iview'
181 _VALID_URL
= r
'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P<id>[^/?#]+)'
182 _GEO_COUNTRIES
= [ 'AU' ]
185 'url' : 'https://iview.abc.net.au/show/utopia/series/1/video/CO1211V001S00' ,
186 'md5' : '52a942bfd7a0b79a6bfe9b4ce6c9d0ed' ,
188 'id' : 'CO1211V001S00' ,
190 'title' : 'Series 1 Ep 1 Wood For The Trees' ,
192 'description' : 'md5:0cfb2c183c1b952d1548fd65c8a95c00' ,
193 'upload_date' : '20230726' ,
194 'uploader_id' : 'abc1' ,
195 'series_id' : 'CO1211V' ,
196 'episode_id' : 'CO1211V001S00' ,
198 'season' : 'Season 1' ,
200 'episode' : 'Wood For The Trees' ,
201 'thumbnail' : 'https://cdn.iview.abc.net.au/thumbs/i/co/CO1211V001S00_5ad8353f4df09_1280.jpg' ,
202 'timestamp' : 1690403700 ,
205 'skip_download' : True ,
208 'note' : 'No episode name' ,
209 'url' : 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00' ,
210 'md5' : '67715ce3c78426b11ba167d875ac6abf' ,
212 'id' : 'LE1927H001S00' ,
214 'title' : 'Series 11 Ep 1' ,
216 'description' : 'md5:52cc744ad35045baf6aded2ce7287f67' ,
217 'upload_date' : '20190925' ,
218 'uploader_id' : 'abc1' ,
219 'series_id' : 'LE1927H' ,
220 'episode_id' : 'LE1927H001S00' ,
222 'season' : 'Season 11' ,
224 'episode' : 'Episode 1' ,
225 'thumbnail' : 'https://cdn.iview.abc.net.au/thumbs/i/le/LE1927H001S00_5d954fbd79e25_1280.jpg' ,
226 'timestamp' : 1569445289 ,
228 'expected_warnings' : [ 'Ignoring subtitle tracks found in the HLS manifest' ],
230 'skip_download' : True ,
233 'note' : 'No episode number' ,
234 'url' : 'https://iview.abc.net.au/show/four-corners/series/2022/video/NC2203H039S00' ,
235 'md5' : '77cb7d8434440e3b28fbebe331c2456a' ,
237 'id' : 'NC2203H039S00' ,
239 'title' : 'Series 2022 Locking Up Kids' ,
240 'series' : 'Four Corners' ,
241 'description' : 'md5:54829ca108846d1a70e1fcce2853e720' ,
242 'upload_date' : '20221114' ,
243 'uploader_id' : 'abc1' ,
244 'series_id' : 'NC2203H' ,
245 'episode_id' : 'NC2203H039S00' ,
246 'season_number' : 2022 ,
247 'season' : 'Season 2022' ,
248 'episode_number' : None ,
249 'episode' : 'Locking Up Kids' ,
250 'thumbnail' : 'https://cdn.iview.abc.net.au/thumbs/i/nc/NC2203H039S00_636d8a0944a22_1920.jpg' ,
251 'timestamp' : 1668460497 ,
254 'expected_warnings' : [ 'Ignoring subtitle tracks found in the HLS manifest' ],
256 'skip_download' : True ,
259 'note' : 'No episode name or number' ,
260 'url' : 'https://iview.abc.net.au/show/landline/series/2021/video/RF2004Q043S00' ,
261 'md5' : '2e17dec06b13cc81dc119d2565289396' ,
263 'id' : 'RF2004Q043S00' ,
265 'title' : 'Series 2021' ,
266 'series' : 'Landline' ,
267 'description' : 'md5:c9f30d9c0c914a7fd23842f6240be014' ,
268 'upload_date' : '20211205' ,
269 'uploader_id' : 'abc1' ,
270 'series_id' : 'RF2004Q' ,
271 'episode_id' : 'RF2004Q043S00' ,
272 'season_number' : 2021 ,
273 'season' : 'Season 2021' ,
274 'episode_number' : None ,
276 'thumbnail' : 'https://cdn.iview.abc.net.au/thumbs/i/rf/RF2004Q043S00_61a950639dbc0_1920.jpg' ,
277 'timestamp' : 1638710705 ,
280 'expected_warnings' : [ 'Ignoring subtitle tracks found in the HLS manifest' ],
282 'skip_download' : True ,
286 def _real_extract ( self
, url
):
287 video_id
= self
._ match
_ id
( url
)
288 video_params
= self
._ download
_ json
(
289 'https://iview.abc.net.au/api/programs/' + video_id
, video_id
)
290 title
= unescapeHTML ( video_params
. get ( 'title' ) or video_params
[ 'seriesTitle' ])
291 stream
= next ( s
for s
in video_params
[ 'playlist' ] if s
. get ( 'type' ) in ( 'program' , 'livestream' ))
293 house_number
= video_params
. get ( 'episodeHouseNumber' ) or video_id
294 path
= '/auth/hls/sign?ts= {0} &hn= {1} &d=android-tablet' . format (
295 int ( time
. time ()), house_number
)
297 b
'android.content.res.Resources' ,
298 path
. encode ( 'utf-8' ), hashlib
. sha256
). hexdigest ()
299 token
= self
._ download
_ webpage
(
300 'http://iview.abc.net.au {0} &sig= {1} ' . format ( path
, sig
), video_id
)
302 def tokenize_url ( url
, token
):
303 return update_url_query ( url
, {
307 for sd
in ( '1080' , '720' , 'sd' , 'sd-low' ):
309 stream
, lambda x
: x
[ 'streams' ][ 'hls' ][ sd
], compat_str
)
312 formats
= self
._ extract
_ m
3u8_ formats
(
313 tokenize_url ( sd_url
, token
), video_id
, 'mp4' ,
314 entry_protocol
= 'm3u8_native' , m3u8_id
= 'hls' , fatal
= False )
319 src_vtt
= stream
. get ( 'captions' , {}). get ( 'src-vtt' )
326 is_live
= video_params
. get ( 'livestream' ) == '1'
331 'description' : video_params
. get ( 'description' ),
332 'thumbnail' : video_params
. get ( 'thumbnail' ),
333 'duration' : int_or_none ( video_params
. get ( 'eventDuration' )),
334 'timestamp' : parse_iso8601 ( video_params
. get ( 'pubDate' ), ' ' ),
335 'series' : unescapeHTML ( video_params
. get ( 'seriesTitle' )),
336 'series_id' : video_params
. get ( 'seriesHouseNumber' ) or video_id
[: 7 ],
337 'season_number' : int_or_none ( self
._ search
_ regex
(
338 r
'\bSeries\s+(\d+)\b' , title
, 'season number' , default
= None )),
339 'episode_number' : int_or_none ( self
._ search
_ regex
(
340 r
'\bEp\s+(\d+)\b' , title
, 'episode number' , default
= None )),
341 'episode_id' : house_number
,
342 'episode' : self
._ search
_ regex
(
343 r
'^(?:Series\s+\d+)?\s*(?:Ep\s+\d+)?\s*(.*)$' , title
, 'episode' , default
= '' ) or None ,
344 'uploader_id' : video_params
. get ( 'channel' ),
346 'subtitles' : subtitles
,
351 class ABCIViewShowSeriesIE ( InfoExtractor
):
352 IE_NAME
= 'abc.net.au:iview:showseries'
353 _VALID_URL
= r
'https?://iview\.abc\.net\.au/show/(?P<id>[^/]+)(?:/series/\d+)?$'
354 _GEO_COUNTRIES
= [ 'AU' ]
357 'url' : 'https://iview.abc.net.au/show/upper-middle-bogan' ,
361 'description' : 'md5:93119346c24a7c322d446d8eece430ff' ,
362 'series' : 'Upper Middle Bogan' ,
363 'season' : 'Series 1' ,
364 'thumbnail' : r
're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
368 'url' : 'https://iview.abc.net.au/show/upper-middle-bogan' ,
370 'id' : 'CO1108V001S00' ,
372 'title' : 'Series 1 Ep 1 I \' m A Swan' ,
373 'description' : 'md5:7b676758c1de11a30b79b4d301e8da93' ,
374 'series' : 'Upper Middle Bogan' ,
375 'uploader_id' : 'abc1' ,
376 'upload_date' : '20210630' ,
377 'timestamp' : 1625036400 ,
381 'skip_download' : 'm3u8' ,
384 # 'videoEpisodes' is a dict with `items` key
385 'url' : 'https://iview.abc.net.au/show/7-30-mark-humphries-satire' ,
389 'description' : 'Satirist Mark Humphries brings his unique perspective on current political events for 7.30.' ,
390 'series' : '7.30 Mark Humphries Satire' ,
391 'season' : 'Episodes' ,
392 'thumbnail' : r
're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
394 'playlist_count' : 15 ,
397 def _real_extract ( self
, url
):
398 show_id
= self
._ match
_ id
( url
)
399 webpage
= self
._ download
_ webpage
( url
, show_id
)
400 webpage_data
= self
._ search
_ regex
(
401 r
'window\.__INITIAL_STATE__\s*=\s*[\' "](.+?)[ \' " ] \s
*; ',
402 webpage, ' initial state
')
403 video_data = self._parse_json(
404 unescapeHTML(webpage_data).encode(' utf
- 8 ').decode(' unicode_escape
'), show_id)
405 video_data = video_data[' route
'][' pageData
'][' _embedded
']
407 highlight = try_get(video_data, lambda x: x[' highlightVideo
'][' shareUrl
'])
408 if not self._yes_playlist(show_id, bool(highlight), video_label=' highlight video
'):
409 return self.url_result(highlight, ie=ABCIViewIE.ie_key())
411 series = video_data[' selectedSeries
']
414 ' entries
': [self.url_result(episode_url, ABCIViewIE)
415 for episode_url in traverse_obj(series, (
416 ' _embedded
', ' videoEpisodes
', (None, ' items
'), ..., ' shareUrl
', {url_or_none} ))],
417 ' id ': series.get(' id '),
418 ' title
': dict_get(series, (' title
', ' displaySubtitle
')),
419 ' description
': series.get(' description
'),
420 ' series
': dict_get(series, (' showTitle
', ' displayTitle
')),
421 ' season
': dict_get(series, (' title
', ' displaySubtitle
')),
422 ' thumbnail
': traverse_obj(
423 series, ' thumbnail
', (' images
', lambda _, v: v[' name
'] == ' seriesThumbnail
', ' url
'), get_all=False),