2 from __future__
import unicode_literals
6 from .common
import InfoExtractor
10 compat_urllib_parse_unquote
,
11 compat_urllib_parse_urlparse
,
28 from .periscope
import (
34 class TwitterBaseIE(InfoExtractor
):
35 _API_BASE
= 'https://api.twitter.com/1.1/'
36 _BASE_REGEX
= r
'https?://(?:(?:www|m(?:obile)?)\.)?twitter\.com/'
39 def _extract_variant_formats(self
, variant
, video_id
):
40 variant_url
= variant
.get('url')
43 elif '.m3u8' in variant_url
:
44 return self
._extract
_m
3u8_formats
_and
_subtitles
(
45 variant_url
, video_id
, 'mp4', 'm3u8_native',
46 m3u8_id
='hls', fatal
=False)
48 tbr
= int_or_none(dict_get(variant
, ('bitrate', 'bit_rate')), 1000) or None
51 'format_id': 'http' + ('-%d' % tbr
if tbr
else ''),
54 self
._search
_dimensions
_in
_video
_url
(f
, variant_url
)
57 def _extract_formats_from_vmap_url(self
, vmap_url
, video_id
):
58 vmap_url
= url_or_none(vmap_url
)
61 vmap_data
= self
._download
_xml
(vmap_url
, video_id
)
65 for video_variant
in vmap_data
.findall('.//{http://twitter.com/schema/videoVMapV2.xsd}videoVariant'):
66 video_variant
.attrib
['url'] = compat_urllib_parse_unquote(
67 video_variant
.attrib
['url'])
68 urls
.append(video_variant
.attrib
['url'])
69 fmts
, subs
= self
._extract
_variant
_formats
(
70 video_variant
.attrib
, video_id
)
72 subtitles
= self
._merge
_subtitles
(subtitles
, subs
)
73 video_url
= strip_or_none(xpath_text(vmap_data
, './/MediaFile'))
74 if video_url
not in urls
:
75 fmts
, subs
= self
._extract
_variant
_formats
({'url': video_url}
, video_id
)
77 subtitles
= self
._merge
_subtitles
(subtitles
, subs
)
78 return formats
, subtitles
81 def _search_dimensions_in_video_url(a_format
, video_url
):
82 m
= re
.search(r
'/(?P<width>\d+)x(?P<height>\d+)/', video_url
)
85 'width': int(m
.group('width')),
86 'height': int(m
.group('height')),
89 def _call_api(self
, path
, video_id
, query
={}):
91 'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAPYXBAAAAAAACLXUNDekMxqa8h%2F40K4moUkGsoc%3DTYfbDKbT3jJPCEVnMYqilB28NHfOPqkca3qaAxGfsyKCs0wRbw',
93 token
= self
._get
_cookies
(self
._API
_BASE
).get('ct0')
95 headers
['x-csrf-token'] = token
.value
96 if not self
._GUEST
_TOKEN
:
97 self
._GUEST
_TOKEN
= self
._download
_json
(
98 self
._API
_BASE
+ 'guest/activate.json', video_id
,
99 'Downloading guest token', data
=b
'',
100 headers
=headers
)['guest_token']
101 headers
['x-guest-token'] = self
._GUEST
_TOKEN
103 return self
._download
_json
(
104 self
._API
_BASE
+ path
, video_id
, headers
=headers
, query
=query
)
105 except ExtractorError
as e
:
106 if isinstance(e
.cause
, compat_HTTPError
) and e
.cause
.code
== 403:
107 raise ExtractorError(self
._parse
_json
(
108 e
.cause
.read().decode(),
109 video_id
)['errors'][0]['message'], expected
=True)
113 class TwitterCardIE(InfoExtractor
):
114 IE_NAME
= 'twitter:card'
115 _VALID_URL
= TwitterBaseIE
._BASE
_REGEX
+ r
'i/(?:cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)'
118 'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
119 # MD5 checksums are different in different places
121 'id': '560070183650213889',
123 'title': "Twitter - You can now shoot, edit and share video on Twitter. Capture life's most moving moments from your perspective.",
124 'description': 'md5:18d3e24bb4f6e5007487dd546e53bd96',
125 'uploader': 'Twitter',
126 'uploader_id': 'Twitter',
127 'thumbnail': r
're:^https?://.*\.jpg',
129 'timestamp': 1422366112,
130 'upload_date': '20150127',
134 'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768',
135 'md5': '7137eca597f72b9abbe61e5ae0161399',
137 'id': '623160978427936768',
139 'title': "NASA - Fly over Pluto's icy Norgay Mountains and Sputnik Plain in this @NASANewHorizons #PlutoFlyby video.",
140 'description': "Fly over Pluto's icy Norgay Mountains and Sputnik Plain in this @NASANewHorizons #PlutoFlyby video. https://t.co/BJYgOjSeGA",
142 'uploader_id': 'NASA',
143 'timestamp': 1437408129,
144 'upload_date': '20150720',
148 'url': 'https://twitter.com/i/cards/tfw/v1/654001591733886977',
149 'md5': 'b6d9683dd3f48e340ded81c0e917ad46',
153 'title': 'Ubuntu 11.10 Overview',
154 'description': 'md5:a831e97fa384863d6e26ce48d1c43376',
155 'upload_date': '20111013',
156 'uploader': 'OMG! UBUNTU!',
157 'uploader_id': 'omgubuntu',
159 'add_ie': ['Youtube'],
162 'url': 'https://twitter.com/i/cards/tfw/v1/665289828897005568',
163 'md5': '6dabeaca9e68cbb71c99c322a4b42a11',
167 'upload_date': '20151113',
168 'uploader_id': '1189339351084113920',
169 'uploader': 'ArsenalTerje',
170 'title': 'Vine by ArsenalTerje',
171 'timestamp': 1447451307,
175 'url': 'https://twitter.com/i/videos/tweet/705235433198714880',
176 'md5': '884812a2adc8aaf6fe52b15ccbfa3b88',
178 'id': '705235433198714880',
180 'title': "Brent Yarina - Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight.",
181 'description': "Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight. https://t.co/OrxcJ28Bns",
182 'uploader': 'Brent Yarina',
183 'uploader_id': 'BTNBrentYarina',
184 'timestamp': 1456976204,
185 'upload_date': '20160303',
187 'skip': 'This content is no longer available.',
189 'url': 'https://twitter.com/i/videos/752274308186120192',
190 'only_matching': True,
194 def _real_extract(self
, url
):
195 status_id
= self
._match
_id
(url
)
196 return self
.url_result(
197 'https://twitter.com/statuses/' + status_id
,
198 TwitterIE
.ie_key(), status_id
)
201 class TwitterIE(TwitterBaseIE
):
203 _VALID_URL
= TwitterBaseIE
._BASE
_REGEX
+ r
'(?:(?:i/web|[^/]+)/status|statuses)/(?P<id>\d+)'
206 'url': 'https://twitter.com/freethenipple/status/643211948184596480',
208 'id': '643211948184596480',
210 'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!',
211 'thumbnail': r
're:^https?://.*\.jpg',
212 'description': 'FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ',
213 'uploader': 'FREE THE NIPPLE',
214 'uploader_id': 'freethenipple',
216 'timestamp': 1442188653,
217 'upload_date': '20150913',
221 'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1',
222 'md5': 'f36dcd5fb92bf7057f155e7d927eeb42',
224 'id': '657991469417025536',
226 'title': 'Gifs - tu vai cai tu vai cai tu nao eh capaz disso tu vai cai',
227 'description': 'Gifs on Twitter: "tu vai cai tu vai cai tu nao eh capaz disso tu vai cai https://t.co/tM46VHFlO5"',
228 'thumbnail': r
're:^https?://.*\.png',
230 'uploader_id': 'giphz',
232 'expected_warnings': ['height', 'width'],
233 'skip': 'Account suspended',
235 'url': 'https://twitter.com/starwars/status/665052190608723968',
237 'id': '665052190608723968',
239 'title': 'Star Wars - A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens.',
240 'description': 'A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens. https://t.co/OkSqT2fjWJ',
241 'uploader_id': 'starwars',
242 'uploader': 'Star Wars',
243 'timestamp': 1447395772,
244 'upload_date': '20151113',
247 'url': 'https://twitter.com/BTNBrentYarina/status/705235433198714880',
249 'id': '705235433198714880',
251 'title': "Brent Yarina - Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight.",
252 'description': "Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight. https://t.co/OrxcJ28Bns",
253 'uploader_id': 'BTNBrentYarina',
254 'uploader': 'Brent Yarina',
255 'timestamp': 1456976204,
256 'upload_date': '20160303',
259 # The same video as https://twitter.com/i/videos/tweet/705235433198714880
260 # Test case of TwitterCardIE
261 'skip_download': True,
264 'url': 'https://twitter.com/jaydingeer/status/700207533655363584',
266 'id': '700207533655363584',
268 'title': 'simon vertugo - BEAT PROD: @suhmeduh #Damndaniel',
269 'description': 'BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ',
270 'thumbnail': r
're:^https?://.*\.jpg',
271 'uploader': 'simon vertugo',
272 'uploader_id': 'simonvertugo',
274 'timestamp': 1455777459,
275 'upload_date': '20160218',
278 'url': 'https://twitter.com/Filmdrunk/status/713801302971588609',
279 'md5': '89a15ed345d13b86e9a5a5e051fa308a',
283 'title': 'Dr.Pepperの飲み方 #japanese #バカ #ドクペ #電動ガン',
284 'uploader': 'TAKUMA',
285 'uploader_id': '1004126642786242560',
286 'timestamp': 1402826626,
287 'upload_date': '20140615',
291 'url': 'https://twitter.com/captainamerica/status/719944021058060289',
293 'id': '719944021058060289',
295 'title': 'Captain America - @King0fNerd Are you sure you made the right choice? Find out in theaters.',
296 'description': '@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI',
297 'uploader_id': 'CaptainAmerica',
298 'uploader': 'Captain America',
300 'timestamp': 1460483005,
301 'upload_date': '20160412',
304 'url': 'https://twitter.com/OPP_HSD/status/779210622571536384',
306 'id': '1zqKVVlkqLaKB',
308 'title': 'Sgt Kerry Schmidt - Ontario Provincial Police - Road rage, mischief, assault, rollover and fire in one occurrence',
309 'upload_date': '20160923',
310 'uploader_id': '1PmKqpJdOJQoY',
311 'uploader': 'Sgt Kerry Schmidt - Ontario Provincial Police',
312 'timestamp': 1474613214,
314 'add_ie': ['Periscope'],
316 # has mp4 formats via mobile API
317 'url': 'https://twitter.com/news_al3alm/status/852138619213144067',
319 'id': '852138619213144067',
321 'title': 'عالم الأخبار - كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة',
322 'description': 'كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة https://t.co/xg6OhpyKfN',
323 'uploader': 'عالم الأخبار',
324 'uploader_id': 'news_al3alm',
326 'timestamp': 1492000653,
327 'upload_date': '20170412',
329 'skip': 'Account suspended',
331 'url': 'https://twitter.com/i/web/status/910031516746514432',
333 'id': '910031516746514432',
335 'title': 'Préfet de Guadeloupe - [Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre.',
336 'thumbnail': r
're:^https?://.*\.jpg',
337 'description': '[Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre. https://t.co/mwx01Rs4lo',
338 'uploader': 'Préfet de Guadeloupe',
339 'uploader_id': 'Prefet971',
341 'timestamp': 1505803395,
342 'upload_date': '20170919',
345 'skip_download': True, # requires ffmpeg
348 # card via api.twitter.com/1.1/videos/tweet/config
349 'url': 'https://twitter.com/LisPower1/status/1001551623938805763',
351 'id': '1001551623938805763',
353 'title': 're:.*?Shep is on a roll today.*?',
354 'thumbnail': r
're:^https?://.*\.jpg',
355 'description': 'md5:37b9f2ff31720cef23b2bd42ee8a0f09',
356 'uploader': 'Lis Power',
357 'uploader_id': 'LisPower1',
359 'timestamp': 1527623489,
360 'upload_date': '20180529',
363 'skip_download': True, # requires ffmpeg
366 'url': 'https://twitter.com/foobar/status/1087791357756956680',
368 'id': '1087791357756956680',
370 'title': 'Twitter - A new is coming. Some of you got an opt-in to try it now. Check out the emoji button, quick keyboard shortcuts, upgraded trends, advanced search, and more. Let us know your thoughts!',
371 'thumbnail': r
're:^https?://.*\.jpg',
372 'description': 'md5:6dfd341a3310fb97d80d2bf7145df976',
373 'uploader': 'Twitter',
374 'uploader_id': 'Twitter',
376 'timestamp': 1548184644,
377 'upload_date': '20190122',
380 # not available in Periscope
381 'url': 'https://twitter.com/ViviEducation/status/1136534865145286656',
383 'id': '1vOGwqejwoWxB',
385 'title': 'Vivi - Vivi founder @lior_rauchy announcing our new student feedback tool live at @EduTECH_AU #EduTECH2019',
387 'uploader_id': '1eVjYOLGkGrQL',
389 'add_ie': ['TwitterBroadcast'],
392 'url': 'https://twitter.com/BrooklynNets/status/1349794411333394432?s=20',
394 'id': '1349794411333394432',
396 'title': 'md5:d1c4941658e4caaa6cb579260d85dcba',
397 'thumbnail': r
're:^https?://.*\.jpg',
398 'description': 'md5:71ead15ec44cee55071547d6447c6a3e',
399 'uploader': 'Brooklyn Nets',
400 'uploader_id': 'BrooklynNets',
402 'timestamp': 1610651040,
403 'upload_date': '20210114',
406 'skip_download': True,
410 'url': 'https://twitter.com/GunB1g/status/1163218564784017422',
411 'only_matching': True,
413 # promo_video_website card
414 'url': 'https://twitter.com/GunB1g/status/1163218564784017422',
415 'only_matching': True,
417 # promo_video_convo card
418 'url': 'https://twitter.com/poco_dandy/status/1047395834013384704',
419 'only_matching': True,
422 'url': 'https://twitter.com/poco_dandy/status/1150646424461176832',
423 'only_matching': True,
425 # video_direct_message card
426 'url': 'https://twitter.com/qarev001/status/1348948114569269251',
427 'only_matching': True,
429 # poll2choice_video card
430 'url': 'https://twitter.com/CAF_Online/status/1349365911120195585',
431 'only_matching': True,
433 # poll3choice_video card
434 'url': 'https://twitter.com/SamsungMobileSA/status/1348609186725289984',
435 'only_matching': True,
437 # poll4choice_video card
438 'url': 'https://twitter.com/SouthamptonFC/status/1347577658079641604',
439 'only_matching': True,
442 def _real_extract(self
, url
):
443 twid
= self
._match
_id
(url
)
444 status
= self
._call
_api
(
445 'statuses/show/%s.json' % twid
, twid
, {
446 'cards_platform': 'Web-12',
448 'include_reply_count': 1,
449 'include_user_entities': 0,
450 'tweet_mode': 'extended',
453 title
= description
= status
['full_text'].replace('\n', ' ')
454 # strip 'https -_t.co_BJYgOjSeGA' junk from filenames
455 title
= re
.sub(r
'\s+(https?://[^ ]+)', '', title
)
456 user
= status
.get('user') or {}
457 uploader
= user
.get('name')
459 title
= '%s - %s' % (uploader
, title
)
460 uploader_id
= user
.get('screen_name')
463 for hashtag
in (try_get(status
, lambda x
: x
['entities']['hashtags'], list) or []):
464 hashtag_text
= hashtag
.get('text')
467 tags
.append(hashtag_text
)
472 'description': description
,
473 'uploader': uploader
,
474 'timestamp': unified_timestamp(status
.get('created_at')),
475 'uploader_id': uploader_id
,
476 'uploader_url': format_field(uploader_id
, template
='https://twitter.com/%s'),
477 'like_count': int_or_none(status
.get('favorite_count')),
478 'repost_count': int_or_none(status
.get('retweet_count')),
479 'comment_count': int_or_none(status
.get('reply_count')),
480 'age_limit': 18 if status
.get('possibly_sensitive') else 0,
484 def extract_from_video_info(media
):
485 video_info
= media
.get('video_info') or {}
489 for variant
in video_info
.get('variants', []):
490 fmts
, subs
= self
._extract
_variant
_formats
(variant
, twid
)
491 subtitles
= self
._merge
_subtitles
(subtitles
, subs
)
493 self
._sort
_formats
(formats
, ('res', 'br', 'size', 'proto')) # The codec of http formats are unknown
496 media_url
= media
.get('media_url_https') or media
.get('media_url')
498 def add_thumbnail(name
, size
):
501 'url': update_url_query(media_url
, {'name': name}
),
502 'width': int_or_none(size
.get('w') or size
.get('width')),
503 'height': int_or_none(size
.get('h') or size
.get('height')),
505 for name
, size
in media
.get('sizes', {}).items():
506 add_thumbnail(name
, size
)
507 add_thumbnail('orig', media
.get('original_info') or {})
511 'subtitles': subtitles
,
512 'thumbnails': thumbnails
,
513 'duration': float_or_none(video_info
.get('duration_millis'), 1000),
516 media
= traverse_obj(status
, ((None, 'quoted_status'), 'extended_entities', 'media', 0), get_all
=False)
517 if media
and media
.get('type') != 'photo':
518 extract_from_video_info(media
)
520 card
= status
.get('card')
522 binding_values
= card
['binding_values']
524 def get_binding_value(k
):
525 o
= binding_values
.get(k
) or {}
526 return try_get(o
, lambda x
: x
[x
['type'].lower() + '_value'])
528 card_name
= card
['name'].split(':')[-1]
529 if card_name
== 'player':
532 'url': get_binding_value('player_url'),
534 elif card_name
== 'periscope_broadcast':
537 'url': get_binding_value('url') or get_binding_value('player_url'),
538 'ie_key': PeriscopeIE
.ie_key(),
540 elif card_name
== 'broadcast':
543 'url': get_binding_value('broadcast_url'),
544 'ie_key': TwitterBroadcastIE
.ie_key(),
546 elif card_name
== 'summary':
549 'url': get_binding_value('card_url'),
551 elif card_name
== 'unified_card':
552 media_entities
= self
._parse
_json
(get_binding_value('unified_card'), twid
)['media_entities']
553 extract_from_video_info(next(iter(media_entities
.values())))
554 # amplify, promo_video_website, promo_video_convo, appplayer,
555 # video_direct_message, poll2choice_video, poll3choice_video,
556 # poll4choice_video, ...
558 is_amplify
= card_name
== 'amplify'
559 vmap_url
= get_binding_value('amplify_url_vmap') if is_amplify
else get_binding_value('player_stream_url')
560 content_id
= get_binding_value('%s_content_id' % (card_name
if is_amplify
else 'player'))
561 formats
, subtitles
= self
._extract
_formats
_from
_vmap
_url
(vmap_url
, content_id
or twid
)
562 self
._sort
_formats
(formats
)
565 for suffix
in ('_small', '', '_large', '_x_large', '_original'):
566 image
= get_binding_value('player_image' + suffix
) or {}
567 image_url
= image
.get('url')
568 if not image_url
or '/player-placeholder' in image_url
:
571 'id': suffix
[1:] if suffix
else 'medium',
573 'width': int_or_none(image
.get('width')),
574 'height': int_or_none(image
.get('height')),
579 'subtitles': subtitles
,
580 'thumbnails': thumbnails
,
581 'duration': int_or_none(get_binding_value(
582 'content_duration_seconds')),
585 expanded_url
= try_get(status
, lambda x
: x
['entities']['urls'][0]['expanded_url'])
587 raise ExtractorError("There's no video in this tweet.")
595 class TwitterAmplifyIE(TwitterBaseIE
):
596 IE_NAME
= 'twitter:amplify'
597 _VALID_URL
= r
'https?://amp\.twimg\.com/v/(?P<id>[0-9a-f\-]{36})'
600 'url': 'https://amp.twimg.com/v/0ba0c3c7-0af3-4c0a-bed5-7efd1ffa2951',
601 'md5': '7df102d0b9fd7066b86f3159f8e81bf6',
603 'id': '0ba0c3c7-0af3-4c0a-bed5-7efd1ffa2951',
605 'title': 'Twitter Video',
606 'thumbnail': 're:^https?://.*',
610 def _real_extract(self
, url
):
611 video_id
= self
._match
_id
(url
)
612 webpage
= self
._download
_webpage
(url
, video_id
)
614 vmap_url
= self
._html
_search
_meta
(
615 'twitter:amplify:vmap', webpage
, 'vmap url')
616 formats
= self
._extract
_formats
_from
_vmap
_url
(vmap_url
, video_id
)
619 thumbnail
= self
._html
_search
_meta
(
620 'twitter:image:src', webpage
, 'thumbnail', fatal
=False)
622 def _find_dimension(target
):
623 w
= int_or_none(self
._html
_search
_meta
(
624 'twitter:%s:width' % target
, webpage
, fatal
=False))
625 h
= int_or_none(self
._html
_search
_meta
(
626 'twitter:%s:height' % target
, webpage
, fatal
=False))
630 thumbnail_w
, thumbnail_h
= _find_dimension('image')
633 'width': thumbnail_w
,
634 'height': thumbnail_h
,
637 video_w
, video_h
= _find_dimension('player')
645 'title': 'Twitter Video',
647 'thumbnails': thumbnails
,
651 class TwitterBroadcastIE(TwitterBaseIE
, PeriscopeBaseIE
):
652 IE_NAME
= 'twitter:broadcast'
653 _VALID_URL
= TwitterBaseIE
._BASE
_REGEX
+ r
'i/broadcasts/(?P<id>[0-9a-zA-Z]{13})'
656 # untitled Periscope video
657 'url': 'https://twitter.com/i/broadcasts/1yNGaQLWpejGj',
659 'id': '1yNGaQLWpejGj',
661 'title': 'Andrea May Sahouri - Periscope Broadcast',
662 'uploader': 'Andrea May Sahouri',
663 'uploader_id': '1PXEdBZWpGwKe',
667 def _real_extract(self
, url
):
668 broadcast_id
= self
._match
_id
(url
)
669 broadcast
= self
._call
_api
(
670 'broadcasts/show.json', broadcast_id
,
671 {'ids': broadcast_id}
)['broadcasts'][broadcast_id
]
672 info
= self
._parse
_broadcast
_data
(broadcast
, broadcast_id
)
673 media_key
= broadcast
['media_key']
674 source
= self
._call
_api
(
675 'live_video_stream/status/' + media_key
, media_key
)['source']
676 m3u8_url
= source
.get('noRedirectPlaybackUrl') or source
['location']
677 if '/live_video_stream/geoblocked/' in m3u8_url
:
678 self
.raise_geo_restricted()
679 m3u8_id
= compat_parse_qs(compat_urllib_parse_urlparse(
680 m3u8_url
).query
).get('type', [None])[0]
681 state
, width
, height
= self
._extract
_common
_format
_info
(broadcast
)
682 info
['formats'] = self
._extract
_pscp
_m
3u8_formats
(
683 m3u8_url
, broadcast_id
, m3u8_id
, state
, width
, height
)
687 class TwitterShortenerIE(TwitterBaseIE
):
688 IE_NAME
= 'twitter:shortener'
689 _VALID_URL
= r
'https?://t.co/(?P<id>[^?]+)|tco:(?P<eid>[^?]+)'
690 _BASE_URL
= 'https://t.co/'
692 def _real_extract(self
, url
):
693 mobj
= self
._match
_valid
_url
(url
)
694 eid
, id = mobj
.group('eid', 'id')
697 url
= self
._BASE
_URL
+ id
698 new_url
= self
._request
_webpage
(url
, id, headers
={'User-Agent': 'curl'}
).geturl()
699 __UNSAFE_LINK
= "https://twitter.com/safety/unsafe_link_warning?unsafe_link="
700 if new_url
.startswith(__UNSAFE_LINK
):
701 new_url
= new_url
.replace(__UNSAFE_LINK
, "")
702 return self
.url_result(new_url
)