]>
jfr.im git - yt-dlp.git/blob - yt_dlp/extractor/abc.py
6 from . common
import InfoExtractor
7 from .. compat
import compat_str
22 class ABCIE ( InfoExtractor
):
23 IE_NAME
= 'abc.net.au'
24 _VALID_URL
= r
'https?://(?:www\.)?abc\.net\.au/(?:news|btn)/(?:[^/]+/) {1,4} (?P<id>\d {5,} )'
27 'url' : 'http://www.abc.net.au/news/2014-11-05/australia-to-staff-ebola-treatment-centre-in-sierra-leone/5868334' ,
28 'md5' : 'cb3dd03b18455a661071ee1e28344d9f' ,
32 'title' : 'Australia to help staff Ebola treatment centre in Sierra Leone' ,
33 'description' : 'md5:809ad29c67a05f54eb41f2a105693a67' ,
35 'skip' : 'this video has expired' ,
37 'url' : 'http://www.abc.net.au/news/2015-08-17/warren-entsch-introduces-same-sex-marriage-bill/6702326' ,
38 'md5' : '4ebd61bdc82d9a8b722f64f1f4b4d121' ,
42 'upload_date' : '20150816' ,
43 'uploader' : 'ABC News (Australia)' ,
44 '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' ,
45 'uploader_id' : 'NewsOnABC' ,
46 'title' : 'Marriage Equality: Warren Entsch introduces same sex marriage bill' ,
48 'add_ie' : [ 'Youtube' ],
49 'skip' : 'Not accessible from Travis CI server' ,
51 'url' : 'http://www.abc.net.au/news/2015-10-23/nab-lifts-interest-rates-following-westpac-and-cba/6880080' ,
52 'md5' : 'b96eee7c9edf4fc5a358a0252881cc1f' ,
56 'title' : 'NAB lifts interest rates, following Westpac and CBA' ,
57 'description' : 'md5:f13d8edc81e462fce4a0437c7dc04728' ,
60 'url' : 'http://www.abc.net.au/news/2015-10-19/6866214' ,
61 'only_matching' : True ,
63 'url' : 'https://www.abc.net.au/btn/classroom/wwi-centenary/10527914' ,
67 'title' : 'WWI Centenary' ,
68 'description' : 'md5:c2379ec0ca84072e86b446e536954546' ,
71 'url' : 'https://www.abc.net.au/news/programs/the-world/2020-06-10/black-lives-matter-protests-spawn-support-for/12342074' ,
75 'title' : 'Black Lives Matter protests spawn support for Papuans in Indonesia' ,
76 'description' : 'md5:2961a17dc53abc558589ccd0fb8edd6f' ,
79 'url' : 'https://www.abc.net.au/btn/newsbreak/btn-newsbreak-20200814/12560476' ,
83 'title' : 'Fortnite Banned From Apple and Google App Stores' ,
84 'description' : 'md5:a6df3f36ce8f816b74af4bd6462f5651' ,
85 'upload_date' : '20200813' ,
86 'uploader' : 'Behind the News' ,
87 'uploader_id' : 'behindthenews' ,
90 'url' : 'https://www.abc.net.au/news/2023-06-25/wagner-boss-orders-troops-back-to-bases-to-avoid-bloodshed/102520540' ,
93 'title' : 'Wagner Group retreating from Russia, leader Prigozhin to move to Belarus' ,
95 '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.' ,
96 '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' ,
100 def _real_extract ( self
, url
):
101 video_id
= self
._ match
_ id
( url
)
102 webpage
= self
._ download
_ webpage
( url
, video_id
)
104 mobj
= re
. search ( r
'<a\s+href="(?P<url>[^"]+)"\s+data-duration="\d+"\s+title="Download audio directly">' , webpage
)
106 urls_info
= mobj
. groupdict ()
110 mobj
= re
. search ( r
'<a href="(?P<url>http://www\.youtube\.com/watch\?v=[^"]+)"><span><strong>External Link:</strong>' ,
113 mobj
= re
. search ( r
'<iframe width="100%" src="(?P<url>//www\.youtube-nocookie\.com/embed/[^?"]+)' , webpage
)
115 urls_info
= mobj
. groupdict ()
120 mobj
= re
. search ( r
'(?P<type>)"(?:sources|files|renditions)":\s*(?P<json_data>\[[^\]]+\])' , webpage
)
123 r
'inline(?P<type>Video|Audio|YouTube)Data\.push\((?P<json_data>[^)]+)\);' ,
126 expired
= self
._ html
_ search
_ regex
( r
'(?s)class="expired-(?:video|audio)".+?<span>(.+?)</span>' , webpage
, 'expired' , None )
128 raise ExtractorError ( ' %s said: %s ' % ( self
. IE_NAME
, expired
), expected
= True )
129 raise ExtractorError ( 'Unable to extract video urls' )
131 urls_info
= self
._ parse
_ json
(
132 mobj
. group ( 'json_data' ), video_id
, transform_source
= js_to_json
)
133 youtube
= mobj
. group ( 'type' ) == 'YouTube'
134 video
= mobj
. group ( 'type' ) == 'Video' or traverse_obj (
135 urls_info
, ( 0 , ( 'contentType' , 'MIMEType' )), get_all
= False ) == 'video/mp4'
137 if not isinstance ( urls_info
, list ):
138 urls_info
= [ urls_info
]
141 return self
. playlist_result ([
142 self
. url_result ( url_info
[ 'url' ]) for url_info
in urls_info
])
145 for url_info
in urls_info
:
146 height
= int_or_none ( url_info
. get ( 'height' ))
147 bitrate
= int_or_none ( url_info
. get ( 'bitrate' ))
148 width
= int_or_none ( url_info
. get ( 'width' ))
150 mobj
= re
. search ( r
'_(?:(?P<height>\d+)|(?P<bitrate>\d+)k)\.mp4$' , url_info
[ 'url' ])
152 height_from_url
= mobj
. group ( 'height' )
154 height
= height
or int_or_none ( height_from_url
)
155 width
= width
or int_or_none ( url_info
. get ( 'label' ))
157 bitrate
= bitrate
or int_or_none ( mobj
. group ( 'bitrate' ))
158 format_id
= str_or_none ( url_info
. get ( 'label' ))
160 'url' : url_info
[ 'url' ],
161 'vcodec' : url_info
. get ( 'codec' ) if video
else 'none' ,
165 'filesize' : int_or_none ( url_info
. get ( 'filesize' )),
166 'format_id' : format_id
171 'title' : self
._ og
_ search
_ title
( webpage
),
173 'description' : self
._ og
_ search
_ description
( webpage
),
174 'thumbnail' : self
._ og
_ search
_ thumbnail
( webpage
),
178 class ABCIViewIE ( InfoExtractor
):
179 IE_NAME
= 'abc.net.au:iview'
180 _VALID_URL
= r
'https?://iview\.abc\.net\.au/(?:[^/]+/)*video/(?P<id>[^/?#]+)'
181 _GEO_COUNTRIES
= [ 'AU' ]
183 # ABC iview programs are normally available for 14 days only.
185 'url' : 'https://iview.abc.net.au/show/gruen/series/11/video/LE1927H001S00' ,
186 'md5' : '67715ce3c78426b11ba167d875ac6abf' ,
188 'id' : 'LE1927H001S00' ,
190 'title' : "Series 11 Ep 1" ,
192 'description' : 'md5:52cc744ad35045baf6aded2ce7287f67' ,
193 'upload_date' : '20190925' ,
194 'uploader_id' : 'abc1' ,
195 'timestamp' : 1569445289 ,
198 'skip_download' : True ,
202 def _real_extract ( self
, url
):
203 video_id
= self
._ match
_ id
( url
)
204 video_params
= self
._ download
_ json
(
205 'https://iview.abc.net.au/api/programs/' + video_id
, video_id
)
206 title
= unescapeHTML ( video_params
. get ( 'title' ) or video_params
[ 'seriesTitle' ])
207 stream
= next ( s
for s
in video_params
[ 'playlist' ] if s
. get ( 'type' ) in ( 'program' , 'livestream' ))
209 house_number
= video_params
. get ( 'episodeHouseNumber' ) or video_id
210 path
= '/auth/hls/sign?ts= {0} &hn= {1} &d=android-tablet' . format (
211 int ( time
. time ()), house_number
)
213 b
'android.content.res.Resources' ,
214 path
. encode ( 'utf-8' ), hashlib
. sha256
). hexdigest ()
215 token
= self
._ download
_ webpage
(
216 'http://iview.abc.net.au {0} &sig= {1} ' . format ( path
, sig
), video_id
)
218 def tokenize_url ( url
, token
):
219 return update_url_query ( url
, {
223 for sd
in ( '1080' , '720' , 'sd' , 'sd-low' ):
225 stream
, lambda x
: x
[ 'streams' ][ 'hls' ][ sd
], compat_str
)
228 formats
= self
._ extract
_ m
3u8_ formats
(
229 tokenize_url ( sd_url
, token
), video_id
, 'mp4' ,
230 entry_protocol
= 'm3u8_native' , m3u8_id
= 'hls' , fatal
= False )
235 src_vtt
= stream
. get ( 'captions' , {}). get ( 'src-vtt' )
242 is_live
= video_params
. get ( 'livestream' ) == '1'
247 'description' : video_params
. get ( 'description' ),
248 'thumbnail' : video_params
. get ( 'thumbnail' ),
249 'duration' : int_or_none ( video_params
. get ( 'eventDuration' )),
250 'timestamp' : parse_iso8601 ( video_params
. get ( 'pubDate' ), ' ' ),
251 'series' : unescapeHTML ( video_params
. get ( 'seriesTitle' )),
252 'series_id' : video_params
. get ( 'seriesHouseNumber' ) or video_id
[: 7 ],
253 'season_number' : int_or_none ( self
._ search
_ regex
(
254 r
'\bSeries\s+(\d+)\b' , title
, 'season number' , default
= None )),
255 'episode_number' : int_or_none ( self
._ search
_ regex
(
256 r
'\bEp\s+(\d+)\b' , title
, 'episode number' , default
= None )),
257 'episode_id' : house_number
,
258 'uploader_id' : video_params
. get ( 'channel' ),
260 'subtitles' : subtitles
,
265 class ABCIViewShowSeriesIE ( InfoExtractor
):
266 IE_NAME
= 'abc.net.au:iview:showseries'
267 _VALID_URL
= r
'https?://iview\.abc\.net\.au/show/(?P<id>[^/]+)(?:/series/\d+)?$'
268 _GEO_COUNTRIES
= [ 'AU' ]
271 'url' : 'https://iview.abc.net.au/show/upper-middle-bogan' ,
275 'description' : 'md5:93119346c24a7c322d446d8eece430ff' ,
276 'series' : 'Upper Middle Bogan' ,
277 'season' : 'Series 1' ,
278 'thumbnail' : r
're:^https?://cdn\.iview\.abc\.net\.au/thumbs/.*\.jpg$'
282 'url' : 'https://iview.abc.net.au/show/upper-middle-bogan' ,
284 'id' : 'CO1108V001S00' ,
286 'title' : 'Series 1 Ep 1 I \' m A Swan' ,
287 'description' : 'md5:7b676758c1de11a30b79b4d301e8da93' ,
288 'series' : 'Upper Middle Bogan' ,
289 'uploader_id' : 'abc1' ,
290 'upload_date' : '20210630' ,
291 'timestamp' : 1625036400 ,
295 'skip_download' : 'm3u8' ,
299 def _real_extract ( self
, url
):
300 show_id
= self
._ match
_ id
( url
)
301 webpage
= self
._ download
_ webpage
( url
, show_id
)
302 webpage_data
= self
._ search
_ regex
(
303 r
'window\.__INITIAL_STATE__\s*=\s*[\' "](.+?)[ \' " ] \s
*; ',
304 webpage, ' initial state
')
305 video_data = self._parse_json(
306 unescapeHTML(webpage_data).encode(' utf
- 8 ').decode(' unicode_escape
'), show_id)
307 video_data = video_data[' route
'][' pageData
'][' _embedded
']
309 highlight = try_get(video_data, lambda x: x[' highlightVideo
'][' shareUrl
'])
310 if not self._yes_playlist(show_id, bool(highlight), video_label=' highlight video
'):
311 return self.url_result(highlight, ie=ABCIViewIE.ie_key())
313 series = video_data[' selectedSeries
']
316 ' entries
': [self.url_result(episode[' shareUrl
'])
317 for episode in series[' _embedded
'][' videoEpisodes
']],
318 ' id ': series.get(' id '),
319 ' title
': dict_get(series, (' title
', ' displaySubtitle
')),
320 ' description
': series.get(' description
'),
321 ' series
': dict_get(series, (' showTitle
', ' displayTitle
')),
322 ' season
': dict_get(series, (' title
', ' displaySubtitle
')),
323 ' thumbnail
': series.get(' thumbnail
'),