2 from __future__
import unicode_literals
10 from .common
import InfoExtractor
11 from ..compat
import (
12 compat_urllib_parse_unquote
,
13 compat_urllib_parse_urlparse
22 srt_subtitles_timecode
,
31 class TikTokBaseIE(InfoExtractor
):
32 _APP_VERSIONS
= [('20.9.3', '293'), ('20.4.3', '243'), ('20.2.1', '221'), ('20.1.2', '212'), ('20.0.4', '204')]
33 _WORKING_APP_VERSION
= None
36 _API_HOSTNAME
= 'api-h2.tiktokv.com'
37 _UPLOADER_URL_FORMAT
= 'https://www.tiktok.com/@%s'
38 _WEBPAGE_HOST
= 'https://www.tiktok.com/'
39 QUALITIES
= ('360p', '540p', '720p', '1080p')
41 def _call_api_impl(self
, ep
, query
, manifest_app_version
, video_id
, fatal
=True,
42 note
='Downloading API JSON', errnote
='Unable to download API page'):
43 self
._set
_cookie
(self
._API
_HOSTNAME
, 'odin_tt', ''.join(random
.choice('0123456789abcdef') for _
in range(160)))
44 webpage_cookies
= self
._get
_cookies
(self
._WEBPAGE
_HOST
)
45 if webpage_cookies
.get('sid_tt'):
46 self
._set
_cookie
(self
._API
_HOSTNAME
, 'sid_tt', webpage_cookies
['sid_tt'].value
)
47 return self
._download
_json
(
48 'https://%s/aweme/v1/%s/' % (self
._API
_HOSTNAME
, ep
), video_id
=video_id
,
49 fatal
=fatal
, note
=note
, errnote
=errnote
, headers
={
50 'User-Agent': f
'com.ss.android.ugc.trill/{manifest_app_version} (Linux; U; Android 10; en_US; Pixel 4; Build/QQ3A.200805.001; Cronet/58.0.2991.0)',
51 'Accept': 'application/json',
54 def _build_api_query(self
, query
, app_version
, manifest_app_version
):
57 'version_name': app_version
,
58 'version_code': manifest_app_version
,
59 'build_number': app_version
,
60 'manifest_version_code': manifest_app_version
,
61 'update_version_code': manifest_app_version
,
62 'openudid': ''.join(random
.choice('0123456789abcdef') for _
in range(16)),
63 'uuid': ''.join([random
.choice(string
.digits
) for _
in range(16)]),
64 '_rticket': int(time
.time() * 1000),
65 'ts': int(time
.time()),
66 'device_brand': 'Google',
67 'device_type': 'Pixel 4',
68 'device_platform': 'android',
69 'resolution': '1080*1920',
73 'carrier_region': 'US',
76 'app_name': self
._APP
_NAME
,
79 'timezone_name': 'America/New_York',
80 'timezone_offset': '-14400',
81 'channel': 'googleplay',
88 'cp': 'cbfhckdckkde1',
91 def _call_api(self
, ep
, query
, video_id
, fatal
=True,
92 note
='Downloading API JSON', errnote
='Unable to download API page'):
93 if not self
._WORKING
_APP
_VERSION
:
94 app_version
= self
._configuration
_arg
('app_version', [''], ie_key
=TikTokIE
.ie_key())[0]
95 manifest_app_version
= self
._configuration
_arg
('manifest_app_version', [''], ie_key
=TikTokIE
.ie_key())[0]
96 if app_version
and manifest_app_version
:
97 self
._WORKING
_APP
_VERSION
= (app_version
, manifest_app_version
)
98 self
.write_debug('Imported app version combo from extractor arguments')
99 elif app_version
or manifest_app_version
:
100 self
.report_warning('Only one of the two required version params are passed as extractor arguments', only_once
=True)
102 if self
._WORKING
_APP
_VERSION
:
103 app_version
, manifest_app_version
= self
._WORKING
_APP
_VERSION
104 real_query
= self
._build
_api
_query
(query
, app_version
, manifest_app_version
)
105 return self
._call
_api
_impl
(ep
, real_query
, manifest_app_version
, video_id
, fatal
, note
, errnote
)
107 for count
, (app_version
, manifest_app_version
) in enumerate(self
._APP
_VERSIONS
, start
=1):
108 real_query
= self
._build
_api
_query
(query
, app_version
, manifest_app_version
)
110 res
= self
._call
_api
_impl
(ep
, real_query
, manifest_app_version
, video_id
, fatal
, note
, errnote
)
111 self
._WORKING
_APP
_VERSION
= (app_version
, manifest_app_version
)
113 except ExtractorError
as e
:
114 if isinstance(e
.cause
, json
.JSONDecodeError
) and e
.cause
.pos
== 0:
115 if count
== len(self
._APP
_VERSIONS
):
119 self
.report_warning(str(e
.cause
or e
.msg
))
121 self
.report_warning('%s. Retrying... (attempt %s of %s)' % (str(e
.cause
or e
.msg
), count
, len(self
._APP
_VERSIONS
)))
125 def _get_subtitles(self
, aweme_detail
, aweme_id
):
126 # TODO: Extract text positioning info
128 captions_info
= traverse_obj(
129 aweme_detail
, ('interaction_stickers', ..., 'auto_video_caption_info', 'auto_captions', ...), expected_type
=dict, default
=[])
130 for caption
in captions_info
:
131 caption_url
= traverse_obj(caption
, ('url', 'url_list', ...), expected_type
=url_or_none
, get_all
=False)
134 caption_json
= self
._download
_json
(
135 caption_url
, aweme_id
, note
='Downloading captions', errnote
='Unable to download captions', fatal
=False)
138 subtitles
.setdefault(caption
.get('language', 'en'), []).append({
141 f
'{i + 1}\n{srt_subtitles_timecode(line["start_time"] / 1000)} --> {srt_subtitles_timecode(line["end_time"] / 1000)}\n{line["text"]}'
142 for i
, line
in enumerate(caption_json
['utterances']) if line
.get('text'))
146 def _parse_aweme_video_app(self
, aweme_detail
):
147 aweme_id
= aweme_detail
['aweme_id']
148 video_info
= aweme_detail
['video']
150 def parse_url_key(url_key
):
151 format_id
, codec
, res
, bitrate
= self
._search
_regex
(
152 r
'v[^_]+_(?P<id>(?P<codec>[^_]+)_(?P<res>\d+p)_(?P<bitrate>\d+))', url_key
,
153 'url key', default
=(None, None, None, None), group
=('id', 'codec', 'res', 'bitrate'))
157 'format_id': format_id
,
158 'vcodec': 'h265' if codec
== 'bytevc1' else codec
,
159 'tbr': int_or_none(bitrate
, scale
=1000) or None,
160 'quality': qualities(self
.QUALITIES
)(res
),
163 known_resolutions
= {}
165 def extract_addr(addr
, add_meta
={}):
166 parsed_meta
, res
= parse_url_key(addr
.get('url_key', ''))
168 known_resolutions
.setdefault(res
, {}).setdefault('height', add_meta
.get('height'))
169 known_resolutions
[res
].setdefault('width', add_meta
.get('width'))
170 parsed_meta
.update(known_resolutions
.get(res
, {}))
171 add_meta
.setdefault('height', int_or_none(res
[:-1]))
174 'filesize': int_or_none(addr
.get('data_size')),
177 'source_preference': -2 if 'aweme/v1' in url
else -1, # Downloads from API might get blocked
178 **add_meta
, **parsed_meta
,
179 'format_note': join_nonempty(
180 add_meta
.get('format_note'), '(API)' if 'aweme/v1' in url
else None, delim
=' ')
181 } for url
in addr
.get('url_list') or []]
183 # Hack: Add direct video links first to prioritize them when removing duplicate formats
185 if video_info
.get('play_addr'):
186 formats
.extend(extract_addr(video_info
['play_addr'], {
187 'format_id': 'play_addr',
188 'format_note': 'Direct video',
189 'vcodec': 'h265' if traverse_obj(
190 video_info
, 'is_bytevc1', 'is_h265') else 'h264', # TODO: Check for "direct iOS" videos, like https://www.tiktok.com/@cookierun_dev/video/7039716639834656002
191 'width': video_info
.get('width'),
192 'height': video_info
.get('height'),
194 if video_info
.get('download_addr'):
195 formats
.extend(extract_addr(video_info
['download_addr'], {
196 'format_id': 'download_addr',
197 'format_note': 'Download video%s' % (', watermarked' if video_info
.get('has_watermark') else ''),
199 'width': video_info
.get('width'),
200 'height': video_info
.get('height'),
201 'preference': -2 if video_info
.get('has_watermark') else -1,
203 if video_info
.get('play_addr_h264'):
204 formats
.extend(extract_addr(video_info
['play_addr_h264'], {
205 'format_id': 'play_addr_h264',
206 'format_note': 'Direct video',
209 if video_info
.get('play_addr_bytevc1'):
210 formats
.extend(extract_addr(video_info
['play_addr_bytevc1'], {
211 'format_id': 'play_addr_bytevc1',
212 'format_note': 'Direct video',
216 for bitrate
in video_info
.get('bit_rate', []):
217 if bitrate
.get('play_addr'):
218 formats
.extend(extract_addr(bitrate
['play_addr'], {
219 'format_id': bitrate
.get('gear_name'),
220 'format_note': 'Playback video',
221 'tbr': try_get(bitrate
, lambda x
: x
['bit_rate'] / 1000),
222 'vcodec': 'h265' if traverse_obj(
223 bitrate
, 'is_bytevc1', 'is_h265') else 'h264',
224 'fps': bitrate
.get('FPS'),
227 self
._remove
_duplicate
_formats
(formats
)
228 auth_cookie
= self
._get
_cookies
(self
._WEBPAGE
_HOST
).get('sid_tt')
231 self
._set
_cookie
(compat_urllib_parse_urlparse(f
['url']).hostname
, 'sid_tt', auth_cookie
.value
)
232 self
._sort
_formats
(formats
, ('quality', 'codec', 'size', 'br'))
235 for cover_id
in ('cover', 'ai_dynamic_cover', 'animated_cover', 'ai_dynamic_cover_bak',
236 'origin_cover', 'dynamic_cover'):
237 cover
= video_info
.get(cover_id
)
239 for cover_url
in cover
['url_list']:
245 stats_info
= aweme_detail
.get('statistics', {})
246 author_info
= aweme_detail
.get('author', {})
247 music_info
= aweme_detail
.get('music', {})
248 user_url
= self
._UPLOADER
_URL
_FORMAT
% (traverse_obj(author_info
,
249 'sec_uid', 'id', 'uid', 'unique_id',
250 expected_type
=str_or_none
, get_all
=False))
251 labels
= traverse_obj(aweme_detail
, ('hybrid_label', ..., 'text'), expected_type
=str, default
=[])
253 contained_music_track
= traverse_obj(
254 music_info
, ('matched_song', 'title'), ('matched_pgc_sound', 'title'), expected_type
=str)
255 contained_music_author
= traverse_obj(
256 music_info
, ('matched_song', 'author'), ('matched_pgc_sound', 'author'), 'author', expected_type
=str)
258 is_generic_og_trackname
= music_info
.get('is_original_sound') and music_info
.get('title') == 'original sound - %s' % music_info
.get('owner_handle')
259 if is_generic_og_trackname
:
260 music_track
, music_author
= contained_music_track
or 'original sound', contained_music_author
262 music_track
, music_author
= music_info
.get('title'), music_info
.get('author')
266 'title': aweme_detail
.get('desc'),
267 'description': aweme_detail
['desc'],
268 'view_count': int_or_none(stats_info
.get('play_count')),
269 'like_count': int_or_none(stats_info
.get('digg_count')),
270 'repost_count': int_or_none(stats_info
.get('share_count')),
271 'comment_count': int_or_none(stats_info
.get('comment_count')),
272 'uploader': str_or_none(author_info
.get('unique_id')),
273 'creator': str_or_none(author_info
.get('nickname')),
274 'uploader_id': str_or_none(author_info
.get('uid')),
275 'uploader_url': user_url
,
276 'track': music_track
,
277 'album': str_or_none(music_info
.get('album')) or None,
278 'artist': music_author
,
279 'timestamp': int_or_none(aweme_detail
.get('create_time')),
281 'subtitles': self
.extract_subtitles(aweme_detail
, aweme_id
),
282 'thumbnails': thumbnails
,
283 'duration': int_or_none(traverse_obj(video_info
, 'duration', ('download_addr', 'duration')), scale
=1000),
284 'availability': self
._availability
(
285 is_private
='Private' in labels
,
286 needs_subscription
='Friends only' in labels
,
287 is_unlisted
='Followers only' in labels
)
290 def _parse_aweme_video_web(self
, aweme_detail
, webpage_url
):
291 video_info
= aweme_detail
['video']
292 author_info
= traverse_obj(aweme_detail
, 'authorInfo', 'author', expected_type
=dict, default
={})
293 music_info
= aweme_detail
.get('music') or {}
294 stats_info
= aweme_detail
.get('stats') or {}
295 user_url
= self
._UPLOADER
_URL
_FORMAT
% (traverse_obj(author_info
,
296 'secUid', 'id', 'uid', 'uniqueId',
297 expected_type
=str_or_none
, get_all
=False)
298 or aweme_detail
.get('authorSecId'))
301 play_url
= video_info
.get('playAddr')
302 width
= video_info
.get('width')
303 height
= video_info
.get('height')
304 if isinstance(play_url
, str):
306 'url': self
._proto
_relative
_url
(play_url
),
311 elif isinstance(play_url
, list):
313 'url': self
._proto
_relative
_url
(url
),
317 } for url
in traverse_obj(play_url
, (..., 'src'), expected_type
=url_or_none
, default
=[]) if url
]
319 download_url
= url_or_none(video_info
.get('downloadAddr')) or traverse_obj(video_info
, ('download', 'url'), expected_type
=url_or_none
)
322 'format_id': 'download',
323 'url': self
._proto
_relative
_url
(download_url
),
328 self
._remove
_duplicate
_formats
(formats
)
329 self
._sort
_formats
(formats
)
332 for thumbnail_name
in ('thumbnail', 'cover', 'dynamicCover', 'originCover'):
333 if aweme_detail
.get(thumbnail_name
):
335 'url': self
._proto
_relative
_url
(aweme_detail
[thumbnail_name
]),
341 'id': traverse_obj(aweme_detail
, 'id', 'awemeId', expected_type
=str_or_none
),
342 'title': aweme_detail
.get('desc'),
343 'duration': try_get(aweme_detail
, lambda x
: x
['video']['duration'], int),
344 'view_count': int_or_none(stats_info
.get('playCount')),
345 'like_count': int_or_none(stats_info
.get('diggCount')),
346 'repost_count': int_or_none(stats_info
.get('shareCount')),
347 'comment_count': int_or_none(stats_info
.get('commentCount')),
348 'timestamp': int_or_none(aweme_detail
.get('createTime')),
349 'creator': str_or_none(author_info
.get('nickname')),
350 'uploader': str_or_none(author_info
.get('uniqueId') or aweme_detail
.get('author')),
351 'uploader_id': str_or_none(author_info
.get('id') or aweme_detail
.get('authorId')),
352 'uploader_url': user_url
,
353 'track': str_or_none(music_info
.get('title')),
354 'album': str_or_none(music_info
.get('album')) or None,
355 'artist': str_or_none(music_info
.get('authorName')),
357 'thumbnails': thumbnails
,
358 'description': str_or_none(aweme_detail
.get('desc')),
360 'Referer': webpage_url
365 class TikTokIE(TikTokBaseIE
):
366 _VALID_URL
= r
'https?://www\.tiktok\.com/@[\w\.-]+/video/(?P<id>\d+)'
369 'url': 'https://www.tiktok.com/@leenabhushan/video/6748451240264420610',
370 'md5': '736bb7a466c6f0a6afeb597da1e6f5b7',
372 'id': '6748451240264420610',
374 'title': '#jassmanak #lehanga #leenabhushan',
375 'description': '#jassmanak #lehanga #leenabhushan',
379 'uploader': 'leenabhushan',
380 'uploader_id': '6691488002098119685',
381 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA_Eb4t1vodM1IuTy_cvp9CY22RAb59xqrO0Xtz9CYQJvgXaDvZxYnZYRzDWhhgJmy',
382 'creator': 'facestoriesbyleenabh',
383 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
384 'upload_date': '20191016',
385 'timestamp': 1571246252,
389 'comment_count': int,
392 'url': 'https://www.tiktok.com/@patroxofficial/video/6742501081818877190?langCountry=en',
393 'md5': '6f3cf8cdd9b28cb8363fe0a9a160695b',
395 'id': '6742501081818877190',
397 'title': 'md5:5e2a23877420bb85ce6521dbee39ba94',
398 'description': 'md5:5e2a23877420bb85ce6521dbee39ba94',
402 'uploader': 'patrox',
403 'uploader_id': '18702747',
404 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws',
406 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
407 'upload_date': '20190930',
408 'timestamp': 1569860870,
412 'comment_count': int,
415 # Banned audio, only available on the app
416 'url': 'https://www.tiktok.com/@barudakhb_/video/6984138651336838402',
418 'id': '6984138651336838402',
420 'title': 'Balas @yolaaftwsr hayu yu ? #SquadRandom_ 🔥',
421 'description': 'Balas @yolaaftwsr hayu yu ? #SquadRandom_ 🔥',
422 'uploader': 'barudakhb_',
423 'creator': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6',
424 'uploader_id': '6974687867511718913',
425 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAbhBwQC-R1iKoix6jDFsF-vBdfx2ABoDjaZrM9fX6arU3w71q3cOWgWuTXn1soZ7d',
426 'track': 'Boka Dance',
427 'artist': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6',
428 'timestamp': 1626121503,
430 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
431 'upload_date': '20210712',
435 'comment_count': int,
438 # Sponsored video, only available with feed workaround
439 'url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_/video/7042692929109986561',
441 'id': '7042692929109986561',
443 'title': 'Slap and Run!',
444 'description': 'Slap and Run!',
445 'uploader': 'user440922249',
446 'creator': 'Slap And Run',
447 'uploader_id': '7036055384943690754',
448 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_',
449 'track': 'Promoted Music',
450 'timestamp': 1639754738,
452 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
453 'upload_date': '20211217',
457 'comment_count': int,
459 'expected_warnings': ['Video not available']
461 # Video without title and description
462 'url': 'https://www.tiktok.com/@pokemonlife22/video/7059698374567611694',
464 'id': '7059698374567611694',
468 'uploader': 'pokemonlife22',
469 'creator': 'Pokemon',
470 'uploader_id': '6820838815978423302',
471 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA0tF1nBwQVVMyrGu3CqttkNgM68Do1OXUFuCY0CRQk8fEtSVDj89HqoqvbSTmUP2W',
472 'track': 'original sound',
473 'timestamp': 1643714123,
475 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
476 'upload_date': '20220201',
481 'comment_count': int,
483 'expected_warnings': ['Video not available']
485 # Auto-captions available
486 'url': 'https://www.tiktok.com/@hankgreen1/video/7047596209028074758',
487 'only_matching': True
490 def _extract_aweme_app(self
, aweme_id
):
492 aweme_detail
= self
._call
_api
('aweme/detail', {'aweme_id': aweme_id}
, aweme_id
,
493 note
='Downloading video details', errnote
='Unable to download video details').get('aweme_detail')
495 raise ExtractorError('Video not available', video_id
=aweme_id
)
496 except ExtractorError
as e
:
497 self
.report_warning(f
'{e}; Retrying with feed workaround')
498 feed_list
= self
._call
_api
('feed', {'aweme_id': aweme_id}
, aweme_id
,
499 note
='Downloading video feed', errnote
='Unable to download video feed').get('aweme_list') or []
500 aweme_detail
= next((aweme
for aweme
in feed_list
if str(aweme
.get('aweme_id')) == aweme_id
), None)
502 raise ExtractorError('Unable to find video in feed', video_id
=aweme_id
)
503 return self
._parse
_aweme
_video
_app
(aweme_detail
)
505 def _real_extract(self
, url
):
506 video_id
= self
._match
_id
(url
)
509 return self
._extract
_aweme
_app
(video_id
)
510 except ExtractorError
as e
:
511 self
.report_warning(f
'{e}; Retrying with webpage')
513 # If we only call once, we get a 403 when downlaoding the video.
514 self
._download
_webpage
(url
, video_id
)
515 webpage
= self
._download
_webpage
(url
, video_id
, note
='Downloading video webpage')
516 next_data
= self
._search
_nextjs
_data
(webpage
, video_id
, default
='{}')
519 status
= traverse_obj(next_data
, ('props', 'pageProps', 'statusCode'), expected_type
=int) or 0
520 video_data
= traverse_obj(next_data
, ('props', 'pageProps', 'itemInfo', 'itemStruct'), expected_type
=dict)
522 sigi_json
= self
._search
_regex
(
523 r
'>\s*window\[[\'"]SIGI_STATE[\'"]\
]\s
*=\s
*(?P
<sigi_state
>{.+}
);',
524 webpage, 'sigi data
', group='sigi_state
')
525 sigi_data = self._parse_json(sigi_json, video_id)
526 status = traverse_obj(sigi_data, ('VideoPage
', 'statusCode
'), expected_type=int) or 0
527 video_data = traverse_obj(sigi_data, ('ItemModule
', video_id), expected_type=dict)
530 return self._parse_aweme_video_web(video_data, url)
531 elif status == 10216:
532 raise ExtractorError('This video
is private
', expected=True)
533 raise ExtractorError('Video
not available
', video_id=video_id)
536 class TikTokUserIE(TikTokBaseIE):
537 IE_NAME = 'tiktok
:user
'
538 _VALID_URL = r'https?
://(?
:www\
.)?tiktok\
.com
/@(?P
<id>[\w\
.-]+)/?
(?
:$|
[#?])'
540 'url': 'https://tiktok.com/@corgibobaa?lang=en',
541 'playlist_mincount': 45,
543 'id': '6935371178089399301',
544 'title': 'corgibobaa',
545 'thumbnail': r
're:https://.+_1080x1080\.webp'
547 'expected_warnings': ['Retrying']
549 'url': 'https://www.tiktok.com/@6820838815978423302',
550 'playlist_mincount': 5,
552 'id': '6820838815978423302',
553 'title': '6820838815978423302',
554 'thumbnail': r
're:https://.+_1080x1080\.webp'
556 'expected_warnings': ['Retrying']
558 'url': 'https://www.tiktok.com/@meme',
559 'playlist_mincount': 593,
561 'id': '79005827461758976',
563 'thumbnail': r
're:https://.+_1080x1080\.webp'
565 'expected_warnings': ['Retrying']
568 r
''' # TODO: Fix by adding _signature to api_url
569 def _entries(self, webpage, user_id, username):
570 secuid = self._search_regex(r'\"secUid\":\"(?P<secUid>[^\"]+)', webpage, username)
571 verifyfp_cookie = self._get_cookies('https://www.tiktok.com').get('s_v_web_id')
572 if not verifyfp_cookie:
573 raise ExtractorError('Improper cookies (missing s_v_web_id).', expected=True)
574 api_url = f'https://m.tiktok.com/api/post/item_list/?aid=1988&cookie_enabled=true&count=30&verifyFp={verifyfp_cookie.value}&secUid={secuid}&cursor='
576 for page in itertools.count():
577 data_json = self._download_json(api_url + cursor, username, note='Downloading Page %d' % page)
578 for video in data_json.get('itemList', []):
579 video_id = video['id']
580 video_url = f'https://www.tiktok.com/@{user_id}/video/{video_id}'
581 yield self._url_result(video_url, 'TikTok', video_id, str_or_none(video.get('desc')))
582 if not data_json.get('hasMore'):
584 cursor = data_json['cursor']
587 def _video_entries_api(self
, webpage
, user_id
, username
):
593 'retry_type': 'no_retry',
594 'device_id': ''.join(random
.choice(string
.digits
) for _
in range(19)), # Some endpoints don't like randomized device_id, so it isn't directly set in _call_api.
597 max_retries
= self
.get_param('extractor_retries', 3)
598 for page
in itertools
.count(1):
599 for retries
in itertools
.count():
601 post_list
= self
._call
_api
('aweme/post', query
, username
,
602 note
='Downloading user video list page %d%s' % (page
, f
' (attempt {retries})' if retries
!= 0 else ''),
603 errnote
='Unable to download user video list')
604 except ExtractorError
as e
:
605 if isinstance(e
.cause
, json
.JSONDecodeError
) and e
.cause
.pos
== 0 and retries
!= max_retries
:
606 self
.report_warning('%s. Retrying...' % str(e
.cause
or e
.msg
))
610 yield from post_list
.get('aweme_list', [])
611 if not post_list
.get('has_more'):
613 query
['max_cursor'] = post_list
['max_cursor']
615 def _entries_api(self
, user_id
, videos
):
618 **self
._parse
_aweme
_video
_app
(video
),
619 'extractor_key': TikTokIE
.ie_key(),
620 'extractor': 'TikTok',
621 'webpage_url': f
'https://tiktok.com/@{user_id}/video/{video["aweme_id"]}',
624 def _real_extract(self
, url
):
625 user_name
= self
._match
_id
(url
)
626 webpage
= self
._download
_webpage
(url
, user_name
, headers
={
627 'User-Agent': 'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)'
629 user_id
= self
._html
_search
_regex
(r
'snssdk\d*://user/profile/(\d+)', webpage
, 'user ID', default
=None) or user_name
631 videos
= LazyList(self
._video
_entries
_api
(webpage
, user_id
, user_name
))
632 thumbnail
= traverse_obj(videos
, (0, 'author', 'avatar_larger', 'url_list', 0))
634 return self
.playlist_result(self
._entries
_api
(user_id
, videos
), user_id
, user_name
, thumbnail
=thumbnail
)
637 class TikTokBaseListIE(TikTokBaseIE
):
638 def _entries(self
, list_id
, display_id
):
640 self
._QUERY
_NAME
: list_id
,
644 'device_id': ''.join(random
.choice(string
.digits
) for i
in range(19))
647 max_retries
= self
.get_param('extractor_retries', 3)
648 for page
in itertools
.count(1):
649 for retries
in itertools
.count():
651 post_list
= self
._call
_api
(self
._API
_ENDPOINT
, query
, display_id
,
652 note
='Downloading video list page %d%s' % (page
, f
' (attempt {retries})' if retries
!= 0 else ''),
653 errnote
='Unable to download video list')
654 except ExtractorError
as e
:
655 if isinstance(e
.cause
, json
.JSONDecodeError
) and e
.cause
.pos
== 0 and retries
!= max_retries
:
656 self
.report_warning('%s. Retrying...' % str(e
.cause
or e
.msg
))
660 for video
in post_list
.get('aweme_list', []):
662 **self
._parse
_aweme
_video
_app
(video
),
663 'extractor_key': TikTokIE
.ie_key(),
664 'extractor': 'TikTok',
665 'webpage_url': f
'https://tiktok.com/@_/video/{video["aweme_id"]}',
667 if not post_list
.get('has_more'):
669 query
['cursor'] = post_list
['cursor']
671 def _real_extract(self
, url
):
672 list_id
= self
._match
_id
(url
)
673 return self
.playlist_result(self
._entries
(list_id
, list_id
), list_id
)
676 class TikTokSoundIE(TikTokBaseListIE
):
677 IE_NAME
= 'tiktok:sound'
678 _VALID_URL
= r
'https?://(?:www\.)?tiktok\.com/music/[\w\.-]+-(?P<id>[\d]+)[/?#&]?'
679 _QUERY_NAME
= 'music_id'
680 _API_ENDPOINT
= 'music/aweme'
682 'url': 'https://www.tiktok.com/music/Build-a-Btch-6956990112127585029?lang=en',
683 'playlist_mincount': 100,
685 'id': '6956990112127585029'
687 'expected_warnings': ['Retrying']
689 # Actual entries are less than listed video count
690 'url': 'https://www.tiktok.com/music/jiefei-soap-remix-7036843036118469381',
691 'playlist_mincount': 2182,
693 'id': '7036843036118469381'
695 'expected_warnings': ['Retrying']
699 class TikTokEffectIE(TikTokBaseListIE
):
700 IE_NAME
= 'tiktok:effect'
701 _VALID_URL
= r
'https?://(?:www\.)?tiktok\.com/sticker/[\w\.-]+-(?P<id>[\d]+)[/?#&]?'
702 _QUERY_NAME
= 'sticker_id'
703 _API_ENDPOINT
= 'sticker/aweme'
705 'url': 'https://www.tiktok.com/sticker/MATERIAL-GWOOORL-1258156',
706 'playlist_mincount': 100,
710 'expected_warnings': ['Retrying']
712 # Different entries between mobile and web, depending on region
713 'url': 'https://www.tiktok.com/sticker/Elf-Friend-479565',
714 'only_matching': True
718 class TikTokTagIE(TikTokBaseListIE
):
719 IE_NAME
= 'tiktok:tag'
720 _VALID_URL
= r
'https?://(?:www\.)?tiktok\.com/tag/(?P<id>[^/?#&]+)'
721 _QUERY_NAME
= 'ch_id'
722 _API_ENDPOINT
= 'challenge/aweme'
724 'url': 'https://tiktok.com/tag/hello2018',
725 'playlist_mincount': 39,
728 'title': 'hello2018',
730 'expected_warnings': ['Retrying']
732 'url': 'https://tiktok.com/tag/fypシ?is_copy_url=0&is_from_webapp=v1',
733 'only_matching': True
736 def _real_extract(self
, url
):
737 display_id
= self
._match
_id
(url
)
738 webpage
= self
._download
_webpage
(url
, display_id
, headers
={
739 'User-Agent': 'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)'
741 tag_id
= self
._html
_search
_regex
(r
'snssdk\d*://challenge/detail/(\d+)', webpage
, 'tag ID')
742 return self
.playlist_result(self
._entries
(tag_id
, display_id
), tag_id
, display_id
)
745 class DouyinIE(TikTokIE
):
746 _VALID_URL
= r
'https?://(?:www\.)?douyin\.com/video/(?P<id>[0-9]+)'
748 'url': 'https://www.douyin.com/video/6961737553342991651',
749 'md5': '10523312c8b8100f353620ac9dc8f067',
751 'id': '6961737553342991651',
753 'title': '#杨超越 小小水手带你去远航❤️',
755 'upload_date': '20210513',
756 'timestamp': 1620905839,
757 'uploader_id': '110403406559',
761 'comment_count': int,
764 'url': 'https://www.douyin.com/video/6982497745948921092',
765 'md5': 'd78408c984b9b5102904cf6b6bc2d712',
767 'id': '6982497745948921092',
769 'title': '这个夏日和小羊@杨超越 一起遇见白色幻想',
770 'uploader': '杨超越工作室',
771 'upload_date': '20210708',
772 'timestamp': 1625739481,
773 'uploader_id': '408654318141572',
777 'comment_count': int,
780 'url': 'https://www.douyin.com/video/6953975910773099811',
781 'md5': '72e882e24f75064c218b76c8b713c185',
783 'id': '6953975910773099811',
785 'title': '#一起看海 出现在你的夏日里',
787 'upload_date': '20210422',
788 'timestamp': 1619098692,
789 'uploader_id': '110403406559',
793 'comment_count': int,
796 'url': 'https://www.douyin.com/video/6950251282489675042',
797 'md5': 'b4db86aec367ef810ddd38b1737d2fed',
799 'id': '6950251282489675042',
801 'title': '哈哈哈,成功了哈哈哈哈哈哈',
803 'upload_date': '20210412',
804 'timestamp': 1618231483,
805 'uploader_id': '110403406559',
809 'comment_count': int,
812 'url': 'https://www.douyin.com/video/6963263655114722595',
813 'md5': '1abe1c477d05ee62efb40bf2329957cf',
815 'id': '6963263655114722595',
817 'title': '#哪个爱豆的105度最甜 换个角度看看我哈哈',
819 'upload_date': '20210517',
820 'timestamp': 1621261163,
821 'uploader_id': '110403406559',
825 'comment_count': int,
828 _APP_VERSIONS
= [('9.6.0', '960')]
831 _API_HOSTNAME
= 'aweme.snssdk.com'
832 _UPLOADER_URL_FORMAT
= 'https://www.douyin.com/user/%s'
833 _WEBPAGE_HOST
= 'https://www.douyin.com/'
835 def _real_extract(self
, url
):
836 video_id
= self
._match
_id
(url
)
839 return self
._extract
_aweme
_app
(video_id
)
840 except ExtractorError
as e
:
841 self
.report_warning(f
'{e}; Retrying with webpage')
843 webpage
= self
._download
_webpage
(url
, video_id
)
844 render_data_json
= self
._search
_regex
(
845 r
'<script [^>]*\bid=[\'"]RENDER_DATA[\'"][^
>]*>(%7B
.+%7D
)</script
>',
846 webpage, 'render data
', default=None)
847 if not render_data_json:
848 # TODO: Run verification challenge code to generate signature cookies
849 raise ExtractorError('Fresh
cookies (not necessarily logged
in) are needed
')
851 render_data = self._parse_json(
852 render_data_json, video_id, transform_source=compat_urllib_parse_unquote)
853 return self._parse_aweme_video_web(get_first(render_data, ('aweme
', 'detail
')), url)
856 class TikTokVMIE(InfoExtractor):
857 _VALID_URL = r'https?
://(?
:vm|vt
)\
.tiktok\
.com
/(?P
<id>\w
+)'
858 IE_NAME = 'vm
.tiktok
'
861 'url
': 'https
://vm
.tiktok
.com
/ZSe4FqkKd
',
863 'id': '7023491746608712966',
865 'title
': 'md5
:5607564db90271abbbf8294cca77eddd
',
866 'description
': 'md5
:5607564db90271abbbf8294cca77eddd
',
868 'upload_date
': '20211026',
869 'uploader_id
': '7007385080558846981',
872 'track
': 'original sound
',
873 'uploader
': 'susmandem
',
874 'timestamp
': 1635284105,
875 'thumbnail
': r're
:https
://.+\
.webp
.*',
878 'comment_count
': int,
880 'uploader_url
': 'https
://www
.tiktok
.com
/@MS4wLjABAAAAXcNoOEOxVyBzuII_E--T0MeCrLP0ay1Sm6x_n3dluiWEoWZD0VlQOytwad4W0i0n
',
883 'url
': 'https
://vt
.tiktok
.com
/ZSe4FqkKd
',
884 'only_matching
': True,
887 def _real_extract(self, url):
888 return self.url_result(self._request_webpage(
889 HEADRequest(url), self._match_id(url), headers={'User-Agent': 'facebookexternalhit/1.1'}).geturl(), TikTokIE)