8 from .common
import InfoExtractor
9 from ..compat
import compat_urllib_parse_unquote
, compat_urllib_parse_urlparse
10 from ..networking
import HEADRequest
25 srt_subtitles_timecode
,
34 class TikTokBaseIE(InfoExtractor
):
35 _APP_VERSIONS
= [('26.1.3', '260103'), ('26.1.2', '260102'), ('26.1.1', '260101'), ('25.6.2', '250602')]
36 _WORKING_APP_VERSION
= None
39 _UPLOADER_URL_FORMAT
= 'https://www.tiktok.com/@%s'
40 _WEBPAGE_HOST
= 'https://www.tiktok.com/'
41 QUALITIES
= ('360p', '540p', '720p', '1080p')
44 def _API_HOSTNAME(self
):
45 return self
._configuration
_arg
(
46 'api_hostname', ['api16-normal-c-useast1a.tiktokv.com'], ie_key
=TikTokIE
)[0]
49 def _create_url(user_id
, video_id
):
50 return f
'https://www.tiktok.com/@{user_id or "_"}/video/{video_id}'
52 def _get_sigi_state(self
, webpage
, display_id
):
53 return self
._parse
_json
(get_element_by_id(
54 'SIGI_STATE|sigi-persisted-data', webpage
, escape_value
=False), display_id
)
56 def _call_api_impl(self
, ep
, query
, manifest_app_version
, video_id
, fatal
=True,
57 note
='Downloading API JSON', errnote
='Unable to download API page'):
58 self
._set
_cookie
(self
._API
_HOSTNAME
, 'odin_tt', ''.join(random
.choices('0123456789abcdef', k
=160)))
59 webpage_cookies
= self
._get
_cookies
(self
._WEBPAGE
_HOST
)
60 if webpage_cookies
.get('sid_tt'):
61 self
._set
_cookie
(self
._API
_HOSTNAME
, 'sid_tt', webpage_cookies
['sid_tt'].value
)
62 return self
._download
_json
(
63 'https://%s/aweme/v1/%s/' % (self
._API
_HOSTNAME
, ep
), video_id
=video_id
,
64 fatal
=fatal
, note
=note
, errnote
=errnote
, headers
={
65 'User-Agent': f
'com.ss.android.ugc.{self._APP_NAME}/{manifest_app_version} (Linux; U; Android 13; en_US; Pixel 7; Build/TD1A.220804.031; Cronet/58.0.2991.0)',
66 'Accept': 'application/json',
69 def _build_api_query(self
, query
, app_version
, manifest_app_version
):
72 'version_name': app_version
,
73 'version_code': manifest_app_version
,
74 'build_number': app_version
,
75 'manifest_version_code': manifest_app_version
,
76 'update_version_code': manifest_app_version
,
77 'openudid': ''.join(random
.choices('0123456789abcdef', k
=16)),
78 'uuid': ''.join(random
.choices(string
.digits
, k
=16)),
79 '_rticket': int(time
.time() * 1000),
80 'ts': int(time
.time()),
81 'device_brand': 'Google',
82 'device_type': 'Pixel 7',
83 'device_platform': 'android',
84 'resolution': '1080*2400',
88 'carrier_region': 'US',
91 'app_name': self
._APP
_NAME
,
94 'timezone_name': 'America/New_York',
95 'timezone_offset': '-14400',
96 'channel': 'googleplay',
103 'cp': 'cbfhckdckkde1',
106 def _call_api(self
, ep
, query
, video_id
, fatal
=True,
107 note
='Downloading API JSON', errnote
='Unable to download API page'):
108 if not self
._WORKING
_APP
_VERSION
:
109 app_version
= self
._configuration
_arg
('app_version', [''], ie_key
=TikTokIE
.ie_key())[0]
110 manifest_app_version
= self
._configuration
_arg
('manifest_app_version', [''], ie_key
=TikTokIE
.ie_key())[0]
111 if app_version
and manifest_app_version
:
112 self
._WORKING
_APP
_VERSION
= (app_version
, manifest_app_version
)
113 self
.write_debug('Imported app version combo from extractor arguments')
114 elif app_version
or manifest_app_version
:
115 self
.report_warning('Only one of the two required version params are passed as extractor arguments', only_once
=True)
117 if self
._WORKING
_APP
_VERSION
:
118 app_version
, manifest_app_version
= self
._WORKING
_APP
_VERSION
119 real_query
= self
._build
_api
_query
(query
, app_version
, manifest_app_version
)
120 return self
._call
_api
_impl
(ep
, real_query
, manifest_app_version
, video_id
, fatal
, note
, errnote
)
122 for count
, (app_version
, manifest_app_version
) in enumerate(self
._APP
_VERSIONS
, start
=1):
123 real_query
= self
._build
_api
_query
(query
, app_version
, manifest_app_version
)
125 res
= self
._call
_api
_impl
(ep
, real_query
, manifest_app_version
, video_id
, fatal
, note
, errnote
)
126 self
._WORKING
_APP
_VERSION
= (app_version
, manifest_app_version
)
128 except ExtractorError
as e
:
129 if isinstance(e
.cause
, json
.JSONDecodeError
) and e
.cause
.pos
== 0:
130 if count
== len(self
._APP
_VERSIONS
):
134 self
.report_warning(str(e
.cause
or e
.msg
))
136 self
.report_warning('%s. Retrying... (attempt %s of %s)' % (str(e
.cause
or e
.msg
), count
, len(self
._APP
_VERSIONS
)))
140 def _extract_aweme_app(self
, aweme_id
):
141 feed_list
= self
._call
_api
(
142 'feed', {'aweme_id': aweme_id}
, aweme_id
, note
='Downloading video feed',
143 errnote
='Unable to download video feed').get('aweme_list') or []
144 aweme_detail
= next((aweme
for aweme
in feed_list
if str(aweme
.get('aweme_id')) == aweme_id
), None)
146 raise ExtractorError('Unable to find video in feed', video_id
=aweme_id
)
147 return self
._parse
_aweme
_video
_app
(aweme_detail
)
149 def _get_subtitles(self
, aweme_detail
, aweme_id
):
150 # TODO: Extract text positioning info
152 # aweme/detail endpoint subs
153 captions_info
= traverse_obj(
154 aweme_detail
, ('interaction_stickers', ..., 'auto_video_caption_info', 'auto_captions', ...), expected_type
=dict)
155 for caption
in captions_info
:
156 caption_url
= traverse_obj(caption
, ('url', 'url_list', ...), expected_type
=url_or_none
, get_all
=False)
159 caption_json
= self
._download
_json
(
160 caption_url
, aweme_id
, note
='Downloading captions', errnote
='Unable to download captions', fatal
=False)
163 subtitles
.setdefault(caption
.get('language', 'en'), []).append({
166 f
'{i + 1}\n{srt_subtitles_timecode(line["start_time"] / 1000)} --> {srt_subtitles_timecode(line["end_time"] / 1000)}\n{line["text"]}'
167 for i
, line
in enumerate(caption_json
['utterances']) if line
.get('text'))
171 for caption
in traverse_obj(aweme_detail
, ('video', 'cla_info', 'caption_infos', ...), expected_type
=dict):
172 if not caption
.get('url'):
174 subtitles
.setdefault(caption
.get('lang') or 'en', []).append({
175 'ext': remove_start(caption
.get('caption_format'), 'web'),
176 'url': caption
['url'],
180 for caption
in traverse_obj(aweme_detail
, ('video', 'subtitleInfos', ...), expected_type
=dict):
181 if not caption
.get('Url'):
183 subtitles
.setdefault(caption
.get('LanguageCodeName') or 'en', []).append({
184 'ext': remove_start(caption
.get('Format'), 'web'),
185 'url': caption
['Url'],
189 def _parse_aweme_video_app(self
, aweme_detail
):
190 aweme_id
= aweme_detail
['aweme_id']
191 video_info
= aweme_detail
['video']
193 def parse_url_key(url_key
):
194 format_id
, codec
, res
, bitrate
= self
._search
_regex
(
195 r
'v[^_]+_(?P<id>(?P<codec>[^_]+)_(?P<res>\d+p)_(?P<bitrate>\d+))', url_key
,
196 'url key', default
=(None, None, None, None), group
=('id', 'codec', 'res', 'bitrate'))
200 'format_id': format_id
,
201 'vcodec': 'h265' if codec
== 'bytevc1' else codec
,
202 'tbr': int_or_none(bitrate
, scale
=1000) or None,
203 'quality': qualities(self
.QUALITIES
)(res
),
206 known_resolutions
= {}
210 'format_note': 'Music track',
216 } if determine_ext(url
) == 'mp3' else {}
218 def extract_addr(addr
, add_meta
={}):
219 parsed_meta
, res
= parse_url_key(addr
.get('url_key', ''))
221 known_resolutions
.setdefault(res
, {}).setdefault('height', add_meta
.get('height') or addr
.get('height'))
222 known_resolutions
[res
].setdefault('width', add_meta
.get('width') or addr
.get('width'))
223 parsed_meta
.update(known_resolutions
.get(res
, {}))
224 add_meta
.setdefault('height', int_or_none(res
[:-1]))
227 'filesize': int_or_none(addr
.get('data_size')),
230 'source_preference': -2 if 'aweme/v1' in url
else -1, # Downloads from API might get blocked
231 **add_meta
, **parsed_meta
,
232 'format_note': join_nonempty(
233 add_meta
.get('format_note'), '(API)' if 'aweme/v1' in url
else None, delim
=' '),
235 } for url
in addr
.get('url_list') or []]
237 # Hack: Add direct video links first to prioritize them when removing duplicate formats
239 if video_info
.get('play_addr'):
240 formats
.extend(extract_addr(video_info
['play_addr'], {
241 'format_id': 'play_addr',
242 'format_note': 'Direct video',
243 'vcodec': 'h265' if traverse_obj(
244 video_info
, 'is_bytevc1', 'is_h265') else 'h264', # TODO: Check for "direct iOS" videos, like https://www.tiktok.com/@cookierun_dev/video/7039716639834656002
245 'width': video_info
.get('width'),
246 'height': video_info
.get('height'),
248 if video_info
.get('download_addr'):
249 formats
.extend(extract_addr(video_info
['download_addr'], {
250 'format_id': 'download_addr',
251 'format_note': 'Download video%s' % (', watermarked' if video_info
.get('has_watermark') else ''),
253 'width': video_info
.get('width'),
254 'height': video_info
.get('height'),
255 'preference': -2 if video_info
.get('has_watermark') else -1,
257 if video_info
.get('play_addr_h264'):
258 formats
.extend(extract_addr(video_info
['play_addr_h264'], {
259 'format_id': 'play_addr_h264',
260 'format_note': 'Direct video',
263 if video_info
.get('play_addr_bytevc1'):
264 formats
.extend(extract_addr(video_info
['play_addr_bytevc1'], {
265 'format_id': 'play_addr_bytevc1',
266 'format_note': 'Direct video',
270 for bitrate
in video_info
.get('bit_rate', []):
271 if bitrate
.get('play_addr'):
272 formats
.extend(extract_addr(bitrate
['play_addr'], {
273 'format_id': bitrate
.get('gear_name'),
274 'format_note': 'Playback video',
275 'tbr': try_get(bitrate
, lambda x
: x
['bit_rate'] / 1000),
276 'vcodec': 'h265' if traverse_obj(
277 bitrate
, 'is_bytevc1', 'is_h265') else 'h264',
278 'fps': bitrate
.get('FPS'),
281 self
._remove
_duplicate
_formats
(formats
)
282 auth_cookie
= self
._get
_cookies
(self
._WEBPAGE
_HOST
).get('sid_tt')
285 self
._set
_cookie
(compat_urllib_parse_urlparse(f
['url']).hostname
, 'sid_tt', auth_cookie
.value
)
288 for cover_id
in ('cover', 'ai_dynamic_cover', 'animated_cover', 'ai_dynamic_cover_bak',
289 'origin_cover', 'dynamic_cover'):
290 for cover_url
in traverse_obj(video_info
, (cover_id
, 'url_list', ...)):
296 stats_info
= aweme_detail
.get('statistics') or {}
297 author_info
= aweme_detail
.get('author') or {}
298 music_info
= aweme_detail
.get('music') or {}
299 user_url
= self
._UPLOADER
_URL
_FORMAT
% (traverse_obj(author_info
,
300 'sec_uid', 'id', 'uid', 'unique_id',
301 expected_type
=str_or_none
, get_all
=False))
302 labels
= traverse_obj(aweme_detail
, ('hybrid_label', ..., 'text'), expected_type
=str)
304 contained_music_track
= traverse_obj(
305 music_info
, ('matched_song', 'title'), ('matched_pgc_sound', 'title'), expected_type
=str)
306 contained_music_author
= traverse_obj(
307 music_info
, ('matched_song', 'author'), ('matched_pgc_sound', 'author'), 'author', expected_type
=str)
309 is_generic_og_trackname
= music_info
.get('is_original_sound') and music_info
.get('title') == 'original sound - %s' % music_info
.get('owner_handle')
310 if is_generic_og_trackname
:
311 music_track
, music_author
= contained_music_track
or 'original sound', contained_music_author
313 music_track
, music_author
= music_info
.get('title'), music_info
.get('author')
317 'extractor_key': TikTokIE
.ie_key(),
318 'extractor': TikTokIE
.IE_NAME
,
319 'webpage_url': self
._create
_url
(author_info
.get('uid'), aweme_id
),
320 **traverse_obj(aweme_detail
, {
321 'title': ('desc', {str}
),
322 'description': ('desc', {str}
),
323 'timestamp': ('create_time', {int_or_none}
),
325 **traverse_obj(stats_info
, {
326 'view_count': 'play_count',
327 'like_count': 'digg_count',
328 'repost_count': 'share_count',
329 'comment_count': 'comment_count',
330 }, expected_type
=int_or_none
),
331 **traverse_obj(author_info
, {
332 'uploader': 'unique_id',
333 'uploader_id': 'uid',
334 'creator': 'nickname',
335 'channel_id': 'sec_uid',
336 }, expected_type
=str_or_none
),
337 'uploader_url': user_url
,
338 'track': music_track
,
339 'album': str_or_none(music_info
.get('album')) or None,
340 'artist': music_author
or None,
342 'subtitles': self
.extract_subtitles(aweme_detail
, aweme_id
),
343 'thumbnails': thumbnails
,
344 'duration': int_or_none(traverse_obj(video_info
, 'duration', ('download_addr', 'duration')), scale
=1000),
345 'availability': self
._availability
(
346 is_private
='Private' in labels
,
347 needs_subscription
='Friends only' in labels
,
348 is_unlisted
='Followers only' in labels
),
349 '_format_sort_fields': ('quality', 'codec', 'size', 'br'),
352 def _parse_aweme_video_web(self
, aweme_detail
, webpage_url
, video_id
):
353 video_info
= aweme_detail
['video']
354 author_info
= traverse_obj(aweme_detail
, 'authorInfo', 'author', expected_type
=dict, default
={})
355 music_info
= aweme_detail
.get('music') or {}
356 stats_info
= aweme_detail
.get('stats') or {}
357 channel_id
= traverse_obj(author_info
or aweme_detail
, (('authorSecId', 'secUid'), {str}
), get_all
=False)
358 user_url
= self
._UPLOADER
_URL
_FORMAT
% channel_id
if channel_id
else None
361 width
= int_or_none(video_info
.get('width'))
362 height
= int_or_none(video_info
.get('height'))
364 for play_url
in traverse_obj(video_info
, ('playAddr', ((..., 'src'), None), {url_or_none}
)):
366 'url': self
._proto
_relative
_url
(play_url
),
372 for download_url
in traverse_obj(video_info
, (('downloadAddr', ('download', 'url')), {url_or_none}
)):
374 'format_id': 'download',
375 'url': self
._proto
_relative
_url
(download_url
),
381 self
._remove
_duplicate
_formats
(formats
)
384 for thumb_url
in traverse_obj(aweme_detail
, (
385 (None, 'video'), ('thumbnail', 'cover', 'dynamicCover', 'originCover'), {url_or_none}
)):
387 'url': self
._proto
_relative
_url
(thumb_url
),
394 **traverse_obj(aweme_detail
, {
395 'title': ('desc', {str}
),
396 'description': ('desc', {str}
),
397 'duration': ('video', 'duration', {int_or_none}
),
398 'timestamp': ('createTime', {int_or_none}
),
400 **traverse_obj(author_info
or aweme_detail
, {
401 'creator': ('nickname', {str}
),
402 'uploader': (('uniqueId', 'author'), {str}
),
403 'uploader_id': (('authorId', 'uid', 'id'), {str_or_none}
),
405 **traverse_obj(stats_info
, {
406 'view_count': 'playCount',
407 'like_count': 'diggCount',
408 'repost_count': 'shareCount',
409 'comment_count': 'commentCount',
410 }, expected_type
=int_or_none
),
411 **traverse_obj(music_info
, {
413 'album': ('album', {lambda x: x or None}
),
414 'artist': 'authorName',
415 }, expected_type
=str),
416 'channel_id': channel_id
,
417 'uploader_url': user_url
,
419 'thumbnails': thumbnails
,
421 'Referer': webpage_url
,
426 class TikTokIE(TikTokBaseIE
):
427 _VALID_URL
= r
'https?://www\.tiktok\.com/(?:embed|@(?P<user_id>[\w\.-]+)?/video)/(?P<id>\d+)'
428 _EMBED_REGEX
= [rf
'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})']
431 'url': 'https://www.tiktok.com/@leenabhushan/video/6748451240264420610',
432 'md5': '736bb7a466c6f0a6afeb597da1e6f5b7',
434 'id': '6748451240264420610',
436 'title': '#jassmanak #lehanga #leenabhushan',
437 'description': '#jassmanak #lehanga #leenabhushan',
441 'uploader': 'leenabhushan',
442 'uploader_id': '6691488002098119685',
443 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA_Eb4t1vodM1IuTy_cvp9CY22RAb59xqrO0Xtz9CYQJvgXaDvZxYnZYRzDWhhgJmy',
444 'creator': 'facestoriesbyleenabh',
445 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
446 'upload_date': '20191016',
447 'timestamp': 1571246252,
451 'comment_count': int,
452 'artist': 'Ysrbeats',
456 'skip': '404 Not Found',
458 'url': 'https://www.tiktok.com/@patroxofficial/video/6742501081818877190?langCountry=en',
459 'md5': '6f3cf8cdd9b28cb8363fe0a9a160695b',
461 'id': '6742501081818877190',
463 'title': 'md5:5e2a23877420bb85ce6521dbee39ba94',
464 'description': 'md5:5e2a23877420bb85ce6521dbee39ba94',
468 'uploader': 'patrox',
469 'uploader_id': '18702747',
470 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws',
471 'channel_id': 'MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws',
473 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
474 'upload_date': '20190930',
475 'timestamp': 1569860870,
479 'comment_count': int,
480 'artist': 'Evan Todd, Jessica Keenan Wynn, Alice Lee, Barrett Wilbert Weed & Jon Eidson',
484 # Banned audio, only available on the app
485 'url': 'https://www.tiktok.com/@barudakhb_/video/6984138651336838402',
487 'id': '6984138651336838402',
489 'title': 'Balas @yolaaftwsr hayu yu ? #SquadRandom_ 🔥',
490 'description': 'Balas @yolaaftwsr hayu yu ? #SquadRandom_ 🔥',
491 'uploader': 'barudakhb_',
492 'creator': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6',
493 'uploader_id': '6974687867511718913',
494 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAbhBwQC-R1iKoix6jDFsF-vBdfx2ABoDjaZrM9fX6arU3w71q3cOWgWuTXn1soZ7d',
495 'channel_id': 'MS4wLjABAAAAbhBwQC-R1iKoix6jDFsF-vBdfx2ABoDjaZrM9fX6arU3w71q3cOWgWuTXn1soZ7d',
496 'track': 'Boka Dance',
497 'artist': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6',
498 'timestamp': 1626121503,
500 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
501 'upload_date': '20210712',
505 'comment_count': int,
508 # Sponsored video, only available with feed workaround
509 'url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_/video/7042692929109986561',
511 'id': '7042692929109986561',
513 'title': 'Slap and Run!',
514 'description': 'Slap and Run!',
515 'uploader': 'user440922249',
516 'creator': 'Slap And Run',
517 'uploader_id': '7036055384943690754',
518 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_',
519 'channel_id': 'MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_',
520 'track': 'Promoted Music',
521 'timestamp': 1639754738,
523 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
524 'upload_date': '20211217',
528 'comment_count': int,
531 # Video without title and description
532 'url': 'https://www.tiktok.com/@pokemonlife22/video/7059698374567611694',
534 'id': '7059698374567611694',
536 'title': 'TikTok video #7059698374567611694',
538 'uploader': 'pokemonlife22',
539 'creator': 'Pokemon',
540 'uploader_id': '6820838815978423302',
541 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA0tF1nBwQVVMyrGu3CqttkNgM68Do1OXUFuCY0CRQk8fEtSVDj89HqoqvbSTmUP2W',
542 'channel_id': 'MS4wLjABAAAA0tF1nBwQVVMyrGu3CqttkNgM68Do1OXUFuCY0CRQk8fEtSVDj89HqoqvbSTmUP2W',
543 'track': 'original sound',
544 'timestamp': 1643714123,
546 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
547 'upload_date': '20220201',
552 'comment_count': int,
555 # hydration JSON is sent in a <script> element
556 'url': 'https://www.tiktok.com/@denidil6/video/7065799023130643713',
558 'id': '7065799023130643713',
560 'title': '#denidil#денидил',
561 'description': '#denidil#денидил',
562 'uploader': 'denidil6',
563 'uploader_id': '7046664115636405250',
564 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAsvMSzFdQ4ikl3uR2TEJwMBbB2yZh2Zxwhx-WCo3rbDpAharE3GQCrFuJArI3C8QJ',
565 'artist': 'Holocron Music',
566 'album': 'Wolf Sounds (1 Hour) Enjoy the Company of the Animal That Is the Majestic King of the Night',
567 'track': 'Wolf Sounds (1 Hour) Enjoy the Company of the Animal That Is the Majestic King of the Night',
568 'timestamp': 1645134536,
570 'upload_date': '20220217',
574 'comment_count': int,
576 'skip': 'This video is unavailable',
578 # slideshow audio-only mp3 format
579 'url': 'https://www.tiktok.com/@_le_cannibale_/video/7139980461132074283',
581 'id': '7139980461132074283',
583 'title': 'TikTok video #7139980461132074283',
585 'creator': 'Antaura',
586 'uploader': '_le_cannibale_',
587 'uploader_id': '6604511138619654149',
588 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAoShJqaw_5gvy48y3azFeFcT4jeyKWbB0VVYasOCt2tTLwjNFIaDcHAM4D-QGXFOP',
589 'channel_id': 'MS4wLjABAAAAoShJqaw_5gvy48y3azFeFcT4jeyKWbB0VVYasOCt2tTLwjNFIaDcHAM4D-QGXFOP',
590 'artist': 'nathan !',
591 'track': 'grahamscott canon',
592 'upload_date': '20220905',
593 'timestamp': 1662406249,
597 'comment_count': int,
598 'thumbnail': r
're:^https://.+\.webp',
601 # only available via web
602 'url': 'https://www.tiktok.com/@moxypatch/video/7206382937372134662',
603 'md5': '8d8c0be14127020cd9f5def4a2e6b411',
605 'id': '7206382937372134662',
607 'title': 'md5:1d95c0b96560ca0e8a231af4172b2c0a',
608 'description': 'md5:1d95c0b96560ca0e8a231af4172b2c0a',
609 'creator': 'MoxyPatch',
610 'uploader': 'moxypatch',
611 'uploader_id': '7039142049363379205',
612 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAFhqKnngMHJSsifL0w1vFOP5kn3Ndo1ODp0XuIBkNMBCkALTvwILdpu12g3pTtL4V',
613 'channel_id': 'MS4wLjABAAAAFhqKnngMHJSsifL0w1vFOP5kn3Ndo1ODp0XuIBkNMBCkALTvwILdpu12g3pTtL4V',
614 'artist': 'your worst nightmare',
615 'track': 'original sound',
616 'upload_date': '20230303',
617 'timestamp': 1677866781,
622 'comment_count': int,
623 'thumbnail': r
're:^https://.+',
624 'thumbnails': 'count:3',
626 'expected_warnings': ['Unable to find video in feed'],
629 'url': 'https://www.tiktok.com/@tatemcrae/video/7107337212743830830',
630 'md5': '982512017a8a917124d5a08c8ae79621',
632 'id': '7107337212743830830',
634 'title': 'new music video 4 don’t come backkkk🧸🖤 i hope u enjoy !! @musicontiktok',
635 'description': 'new music video 4 don’t come backkkk🧸🖤 i hope u enjoy !! @musicontiktok',
636 'uploader': 'tatemcrae',
637 'uploader_id': '86328792343818240',
638 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA-0bQT0CqebTRr6I4IkYvMDMKSRSJHLNPBo5HrSklJwyA2psXLSZG5FP-LMNpHnJd',
639 'channel_id': 'MS4wLjABAAAA-0bQT0CqebTRr6I4IkYvMDMKSRSJHLNPBo5HrSklJwyA2psXLSZG5FP-LMNpHnJd',
642 'track': 'original sound',
643 'upload_date': '20220609',
644 'timestamp': 1654805899,
649 'comment_count': int,
650 'thumbnail': r
're:^https://.+\.webp',
652 'params': {'format': 'bytevc1_1080p_808907-0'}
,
654 # Auto-captions available
655 'url': 'https://www.tiktok.com/@hankgreen1/video/7047596209028074758',
656 'only_matching': True
659 def _real_extract(self
, url
):
660 video_id
, user_id
= self
._match
_valid
_url
(url
).group('id', 'user_id')
662 return self
._extract
_aweme
_app
(video_id
)
663 except ExtractorError
as e
:
664 self
.report_warning(f
'{e}; trying with webpage')
666 url
= self
._create
_url
(user_id
, video_id
)
667 webpage
= self
._download
_webpage
(url
, video_id
, headers
={'User-Agent': 'Mozilla/5.0'}
)
668 next_data
= self
._search
_nextjs
_data
(webpage
, video_id
, default
='{}')
670 status
= traverse_obj(next_data
, ('props', 'pageProps', 'statusCode'), expected_type
=int) or 0
671 video_data
= traverse_obj(next_data
, ('props', 'pageProps', 'itemInfo', 'itemStruct'), expected_type
=dict)
673 sigi_data
= self
._get
_sigi
_state
(webpage
, video_id
)
674 status
= traverse_obj(sigi_data
, ('VideoPage', 'statusCode'), expected_type
=int) or 0
675 video_data
= traverse_obj(sigi_data
, ('ItemModule', video_id
), expected_type
=dict)
678 return self
._parse
_aweme
_video
_web
(video_data
, url
, video_id
)
679 elif status
== 10216:
680 raise ExtractorError('This video is private', expected
=True)
681 raise ExtractorError('Video not available', video_id
=video_id
)
684 class TikTokUserIE(TikTokBaseIE
):
685 IE_NAME
= 'tiktok:user'
686 _VALID_URL
= r
'https?://(?:www\.)?tiktok\.com/@(?P<id>[\w\.-]+)/?(?:$|[#?])'
689 'url': 'https://tiktok.com/@corgibobaa?lang=en',
690 'playlist_mincount': 45,
692 'id': '6935371178089399301',
693 'title': 'corgibobaa',
694 'thumbnail': r
're:https://.+_1080x1080\.webp'
696 'expected_warnings': ['Retrying']
698 'url': 'https://www.tiktok.com/@6820838815978423302',
699 'playlist_mincount': 5,
701 'id': '6820838815978423302',
702 'title': '6820838815978423302',
703 'thumbnail': r
're:https://.+_1080x1080\.webp'
705 'expected_warnings': ['Retrying']
707 'url': 'https://www.tiktok.com/@meme',
708 'playlist_mincount': 593,
710 'id': '79005827461758976',
712 'thumbnail': r
're:https://.+_1080x1080\.webp'
714 'expected_warnings': ['Retrying']
717 r
''' # TODO: Fix by adding _signature to api_url
718 def _entries(self, webpage, user_id, username):
719 secuid = self._search_regex(r'\"secUid\":\"(?P<secUid>[^\"]+)', webpage, username)
720 verifyfp_cookie = self._get_cookies('https://www.tiktok.com').get('s_v_web_id')
721 if not verifyfp_cookie:
722 raise ExtractorError('Improper cookies (missing s_v_web_id).', expected=True)
723 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='
725 for page in itertools.count():
726 data_json = self._download_json(api_url + cursor, username, note='Downloading Page %d' % page)
727 for video in data_json.get('itemList', []):
728 video_id = video['id']
729 video_url = f'https://www.tiktok.com/@{user_id}/video/{video_id}'
730 yield self._url_result(video_url, 'TikTok', video_id, str_or_none(video.get('desc')))
731 if not data_json.get('hasMore'):
733 cursor = data_json['cursor']
736 def _video_entries_api(self
, webpage
, user_id
, username
):
742 'retry_type': 'no_retry',
743 'device_id': ''.join(random
.choices(string
.digits
, k
=19)), # Some endpoints don't like randomized device_id, so it isn't directly set in _call_api.
746 for page
in itertools
.count(1):
747 for retry
in self
.RetryManager():
749 post_list
= self
._call
_api
(
750 'aweme/post', query
, username
, note
=f
'Downloading user video list page {page}',
751 errnote
='Unable to download user video list')
752 except ExtractorError
as e
:
753 if isinstance(e
.cause
, json
.JSONDecodeError
) and e
.cause
.pos
== 0:
757 yield from post_list
.get('aweme_list', [])
758 if not post_list
.get('has_more'):
760 query
['max_cursor'] = post_list
['max_cursor']
762 def _entries_api(self
, user_id
, videos
):
765 **self
._parse
_aweme
_video
_app
(video
),
766 'extractor_key': TikTokIE
.ie_key(),
767 'extractor': 'TikTok',
768 'webpage_url': f
'https://tiktok.com/@{user_id}/video/{video["aweme_id"]}',
771 def _real_extract(self
, url
):
772 user_name
= self
._match
_id
(url
)
773 webpage
= self
._download
_webpage
(url
, user_name
, headers
={
774 'User-Agent': 'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)'
776 user_id
= self
._html
_search
_regex
(r
'snssdk\d*://user/profile/(\d+)', webpage
, 'user ID', default
=None) or user_name
778 videos
= LazyList(self
._video
_entries
_api
(webpage
, user_id
, user_name
))
779 thumbnail
= traverse_obj(videos
, (0, 'author', 'avatar_larger', 'url_list', 0))
781 return self
.playlist_result(self
._entries
_api
(user_id
, videos
), user_id
, user_name
, thumbnail
=thumbnail
)
784 class TikTokBaseListIE(TikTokBaseIE
): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor
785 def _entries(self
, list_id
, display_id
):
787 self
._QUERY
_NAME
: list_id
,
791 'device_id': ''.join(random
.choices(string
.digits
, k
=19))
794 for page
in itertools
.count(1):
795 for retry
in self
.RetryManager():
797 post_list
= self
._call
_api
(
798 self
._API
_ENDPOINT
, query
, display_id
, note
=f
'Downloading video list page {page}',
799 errnote
='Unable to download video list')
800 except ExtractorError
as e
:
801 if isinstance(e
.cause
, json
.JSONDecodeError
) and e
.cause
.pos
== 0:
805 for video
in post_list
.get('aweme_list', []):
807 **self
._parse
_aweme
_video
_app
(video
),
808 'extractor_key': TikTokIE
.ie_key(),
809 'extractor': 'TikTok',
810 'webpage_url': f
'https://tiktok.com/@_/video/{video["aweme_id"]}',
812 if not post_list
.get('has_more'):
814 query
['cursor'] = post_list
['cursor']
816 def _real_extract(self
, url
):
817 list_id
= self
._match
_id
(url
)
818 return self
.playlist_result(self
._entries
(list_id
, list_id
), list_id
)
821 class TikTokSoundIE(TikTokBaseListIE
):
822 IE_NAME
= 'tiktok:sound'
823 _VALID_URL
= r
'https?://(?:www\.)?tiktok\.com/music/[\w\.-]+-(?P<id>[\d]+)[/?#&]?'
825 _QUERY_NAME
= 'music_id'
826 _API_ENDPOINT
= 'music/aweme'
828 'url': 'https://www.tiktok.com/music/Build-a-Btch-6956990112127585029?lang=en',
829 'playlist_mincount': 100,
831 'id': '6956990112127585029'
833 'expected_warnings': ['Retrying']
835 # Actual entries are less than listed video count
836 'url': 'https://www.tiktok.com/music/jiefei-soap-remix-7036843036118469381',
837 'playlist_mincount': 2182,
839 'id': '7036843036118469381'
841 'expected_warnings': ['Retrying']
845 class TikTokEffectIE(TikTokBaseListIE
):
846 IE_NAME
= 'tiktok:effect'
847 _VALID_URL
= r
'https?://(?:www\.)?tiktok\.com/sticker/[\w\.-]+-(?P<id>[\d]+)[/?#&]?'
849 _QUERY_NAME
= 'sticker_id'
850 _API_ENDPOINT
= 'sticker/aweme'
852 'url': 'https://www.tiktok.com/sticker/MATERIAL-GWOOORL-1258156',
853 'playlist_mincount': 100,
857 'expected_warnings': ['Retrying']
859 # Different entries between mobile and web, depending on region
860 'url': 'https://www.tiktok.com/sticker/Elf-Friend-479565',
861 'only_matching': True
865 class TikTokTagIE(TikTokBaseListIE
):
866 IE_NAME
= 'tiktok:tag'
867 _VALID_URL
= r
'https?://(?:www\.)?tiktok\.com/tag/(?P<id>[^/?#&]+)'
869 _QUERY_NAME
= 'ch_id'
870 _API_ENDPOINT
= 'challenge/aweme'
872 'url': 'https://tiktok.com/tag/hello2018',
873 'playlist_mincount': 39,
876 'title': 'hello2018',
878 'expected_warnings': ['Retrying']
880 'url': 'https://tiktok.com/tag/fypシ?is_copy_url=0&is_from_webapp=v1',
881 'only_matching': True
884 def _real_extract(self
, url
):
885 display_id
= self
._match
_id
(url
)
886 webpage
= self
._download
_webpage
(url
, display_id
, headers
={
887 'User-Agent': 'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)'
889 tag_id
= self
._html
_search
_regex
(r
'snssdk\d*://challenge/detail/(\d+)', webpage
, 'tag ID')
890 return self
.playlist_result(self
._entries
(tag_id
, display_id
), tag_id
, display_id
)
893 class DouyinIE(TikTokBaseIE
):
894 _VALID_URL
= r
'https?://(?:www\.)?douyin\.com/video/(?P<id>[0-9]+)'
896 'url': 'https://www.douyin.com/video/6961737553342991651',
897 'md5': 'a97db7e3e67eb57bf40735c022ffa228',
899 'id': '6961737553342991651',
901 'title': '#杨超越 小小水手带你去远航❤️',
902 'description': '#杨超越 小小水手带你去远航❤️',
903 'uploader_id': '110403406559',
904 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
905 'channel_id': 'MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
908 'timestamp': 1620905839,
909 'upload_date': '20210513',
910 'track': '@杨超越创作的原声',
914 'comment_count': int,
915 'thumbnail': r
're:https?://.+\.jpe?g',
918 'url': 'https://www.douyin.com/video/6982497745948921092',
919 'md5': '34a87ebff3833357733da3fe17e37c0e',
921 'id': '6982497745948921092',
923 'title': '这个夏日和小羊@杨超越 一起遇见白色幻想',
924 'description': '这个夏日和小羊@杨超越 一起遇见白色幻想',
925 'uploader_id': '408654318141572',
926 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAZJpnglcjW2f_CMVcnqA_6oVBXKWMpH0F8LIHuUu8-lA',
927 'channel_id': 'MS4wLjABAAAAZJpnglcjW2f_CMVcnqA_6oVBXKWMpH0F8LIHuUu8-lA',
930 'timestamp': 1625739481,
931 'upload_date': '20210708',
932 'track': '@杨超越工作室创作的原声',
936 'comment_count': int,
937 'thumbnail': r
're:https?://.+\.jpe?g',
940 'url': 'https://www.douyin.com/video/6953975910773099811',
941 'md5': 'dde3302460f19db59c47060ff013b902',
943 'id': '6953975910773099811',
945 'title': '#一起看海 出现在你的夏日里',
946 'description': '#一起看海 出现在你的夏日里',
947 'uploader_id': '110403406559',
948 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
949 'channel_id': 'MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
952 'timestamp': 1619098692,
953 'upload_date': '20210422',
954 'track': '@杨超越创作的原声',
958 'comment_count': int,
959 'thumbnail': r
're:https?://.+\.jpe?g',
962 'url': 'https://www.douyin.com/video/6950251282489675042',
963 'md5': 'b4db86aec367ef810ddd38b1737d2fed',
965 'id': '6950251282489675042',
967 'title': '哈哈哈,成功了哈哈哈哈哈哈',
969 'upload_date': '20210412',
970 'timestamp': 1618231483,
971 'uploader_id': '110403406559',
975 'comment_count': int,
977 'skip': 'No longer available',
979 'url': 'https://www.douyin.com/video/6963263655114722595',
980 'md5': 'cf9f11f0ec45d131445ec2f06766e122',
982 'id': '6963263655114722595',
984 'title': '#哪个爱豆的105度最甜 换个角度看看我哈哈',
985 'description': '#哪个爱豆的105度最甜 换个角度看看我哈哈',
986 'uploader_id': '110403406559',
987 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
988 'channel_id': 'MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
991 'timestamp': 1621261163,
992 'upload_date': '20210517',
993 'track': '@杨超越创作的原声',
997 'comment_count': int,
998 'thumbnail': r
're:https?://.+\.jpe?g',
1001 _APP_VERSIONS
= [('23.3.0', '230300')]
1004 _API_HOSTNAME
= 'aweme.snssdk.com'
1005 _UPLOADER_URL_FORMAT
= 'https://www.douyin.com/user/%s'
1006 _WEBPAGE_HOST
= 'https://www.douyin.com/'
1008 def _real_extract(self
, url
):
1009 video_id
= self
._match
_id
(url
)
1012 return self
._extract
_aweme
_app
(video_id
)
1013 except ExtractorError
as e
:
1015 self
.to_screen(f
'{e}; trying with webpage')
1017 webpage
= self
._download
_webpage
(url
, video_id
)
1018 render_data
= self
._search
_json
(
1019 r
'<script [^>]*\bid=[\'"]RENDER_DATA[\'"][^
>]*>', webpage, 'render data
', video_id,
1020 contains_pattern=r'%7B(?s
:.+)%7D
', fatal=False, transform_source=compat_urllib_parse_unquote)
1022 # TODO: Run verification challenge code to generate signature cookies
1023 cookies = self._get_cookies(self._WEBPAGE_HOST)
1024 expected = not cookies.get('s_v_web_id
') or not cookies.get('ttwid
')
1025 raise ExtractorError(
1026 'Fresh
cookies (not necessarily logged
in) are needed
', expected=expected)
1028 return self._parse_aweme_video_web(get_first(render_data, ('aweme
', 'detail
')), url, video_id)
1031 class TikTokVMIE(InfoExtractor):
1032 _VALID_URL = r'https?
://(?
:(?
:vm|vt
)\
.tiktok\
.com|
(?
:www\
.)tiktok\
.com
/t
)/(?P
<id>\w
+)'
1033 IE_NAME = 'vm
.tiktok
'
1036 'url
': 'https
://www
.tiktok
.com
/t
/ZTRC5xgJp
',
1038 'id': '7170520270497680683',
1040 'title
': 'md5
:c64f6152330c2efe98093ccc8597871c
',
1041 'uploader_id
': '6687535061741700102',
1042 'upload_date
': '20221127',
1045 'comment_count
': int,
1046 'uploader_url
': 'https
://www
.tiktok
.com
/@MS4wLjABAAAAObqu3WCTXxmw2xwZ3iLEHnEecEIw7ks6rxWqOqOhaPja9BI7gqUQnjw8_5FSoDXX',
1047 'album
': 'Wave of Mutilation
: Best of Pixies
',
1048 'thumbnail
': r're
:https
://.+\
.webp
.*',
1050 'timestamp
': 1669516858,
1051 'repost_count
': int,
1053 'track
': 'Where Is My Mind?
',
1054 'description
': 'md5
:c64f6152330c2efe98093ccc8597871c
',
1055 'uploader
': 'sigmachaddeus
',
1056 'creator
': 'SigmaChad
',
1059 'url
': 'https
://vm
.tiktok
.com
/ZTR45GpSF
/',
1061 'id': '7106798200794926362',
1063 'title
': 'md5
:edc3e7ea587847f8537468f2fe51d074
',
1064 'uploader_id
': '6997695878846268418',
1065 'upload_date
': '20220608',
1068 'comment_count
': int,
1069 'thumbnail
': r're
:https
://.+\
.webp
.*',
1070 'uploader_url
': 'https
://www
.tiktok
.com
/@MS4wLjABAAAAdZ_NcPPgMneaGrW0hN8O_J_bwLshwNNERRF5DxOw2HKIzk0kdlLrR8RkVl1ksrMO',
1072 'timestamp
': 1654680400,
1073 'repost_count
': int,
1074 'artist
': 'Akihitoko
',
1075 'track
': 'original sound
',
1076 'description
': 'md5
:edc3e7ea587847f8537468f2fe51d074
',
1077 'uploader
': 'akihitoko1
',
1078 'creator
': 'Akihitoko
',
1081 'url
': 'https
://vt
.tiktok
.com
/ZSe4FqkKd
',
1082 'only_matching
': True,
1085 def _real_extract(self, url):
1086 new_url = self._request_webpage(
1087 HEADRequest(url), self._match_id(url), headers={'User-Agent': 'facebookexternalhit/1.1'}).url
1088 if self.suitable(new_url): # Prevent infinite loop in case redirect fails
1089 raise UnsupportedError(new_url)
1090 return self.url_result(new_url)
1093 class TikTokLiveIE(TikTokBaseIE):
1094 _VALID_URL = r'''(?x)https?://(?:
1095 (?:www\.)?tiktok\.com/@(?P<uploader>[\w.-]+)/live|
1096 m\.tiktok\.com/share/live/(?P<id>\d+)
1098 IE_NAME = 'tiktok
:live
'
1101 'url
': 'https
://www
.tiktok
.com
/@weathernewslive/live
',
1103 'id': '7210809319192726273',
1105 'title
': r're
:ウェザーニュースLiVE
[\d\s
:-]*',
1106 'creator
': 'ウェザーニュースLiVE
',
1107 'uploader
': 'weathernewslive
',
1108 'uploader_id
': '6621496731283095554',
1109 'uploader_url
': 'https
://www
.tiktok
.com
/@weathernewslive',
1110 'live_status
': 'is_live
',
1111 'concurrent_view_count
': int,
1113 'params
': {'skip_download': 'm3u8'},
1115 'url
': 'https
://www
.tiktok
.com
/@pilarmagenta/live
',
1117 'id': '7209423610325322522',
1120 'creator
': 'Pilarmagenta
',
1121 'uploader
': 'pilarmagenta
',
1122 'uploader_id
': '6624846890674683909',
1123 'uploader_url
': 'https
://www
.tiktok
.com
/@pilarmagenta',
1124 'live_status
': 'is_live
',
1125 'concurrent_view_count
': int,
1127 'skip
': 'Livestream
',
1129 'url
': 'https
://m
.tiktok
.com
/share
/live
/7209423610325322522/?language
=en
',
1130 'only_matching
': True,
1132 'url
': 'https
://www
.tiktok
.com
/@iris04201/live
',
1133 'only_matching
': True,
1136 def _call_api(self, url, param, room_id, uploader, key=None):
1137 response = traverse_obj(self._download_json(
1138 url, room_id, fatal=False, query={
1141 }), (key, {dict}), default={})
1143 # status == 2 if live else 4
1144 if int_or_none(response.get('status
')) == 2:
1146 # If room_id is obtained via mobile share URL and cannot be refreshed, do not wait for live
1148 raise ExtractorError('This livestream has ended
', expected=True)
1149 raise UserNotLive(video_id=uploader)
1151 def _real_extract(self, url):
1152 uploader, room_id = self._match_valid_url(url).group('uploader
', 'id')
1153 webpage = self._download_webpage(
1154 url, uploader or room_id, headers={'User-Agent': 'Mozilla/5.0'}, fatal=not room_id)
1157 data = try_call(lambda: self._get_sigi_state(webpage, uploader or room_id))
1158 room_id = (traverse_obj(data, ('UserModule
', 'users
', ..., 'roomId
', {str_or_none}), get_all=False)
1159 or self._search_regex(r'snssdk\d
*://live
\?room_id
=(\d
+)', webpage, 'room ID
', default=None)
1161 uploader = uploader or traverse_obj(
1162 data, ('LiveRoom
', 'liveRoomUserInfo
', 'user
', 'uniqueId
'),
1163 ('UserModule
', 'users
', ..., 'uniqueId
'), get_all=False, expected_type=str)
1166 raise UserNotLive(video_id=uploader)
1169 live_info = self._call_api(
1170 'https
://webcast
.tiktok
.com
/webcast
/room
/info
', 'room_id
', room_id, uploader, key='data
')
1172 get_quality = qualities(('SD1
', 'ld
', 'SD2
', 'sd
', 'HD1
', 'hd
', 'FULL_HD1
', 'uhd
', 'ORIGION
', 'origin
'))
1173 parse_inner = lambda x: self._parse_json(x, None)
1175 for quality, stream in traverse_obj(live_info, (
1176 'stream_url
', 'live_core_sdk_data
', 'pull_data
', 'stream_data
',
1177 {parse_inner}, 'data
', {dict}), default={}).items():
1179 sdk_params = traverse_obj(stream, ('main
', 'sdk_params
', {parse_inner}, {
1180 'vcodec
': ('VCodec
', {str}),
1181 'tbr
': ('vbitrate
', {lambda x: int_or_none(x, 1000)}),
1182 'resolution
': ('resolution
', {lambda x: re.match(r'(?i)\d+x\d+|\d+p', x).group().lower()}),
1185 flv_url = traverse_obj(stream, ('main
', 'flv
', {url_or_none}))
1190 'format_id
': f'flv
-{quality}
',
1191 'quality
': get_quality(quality),
1195 hls_url = traverse_obj(stream, ('main
', 'hls
', {url_or_none}))
1200 'protocol
': 'm3u8_native
',
1201 'format_id
': f'hls
-{quality}
',
1202 'quality
': get_quality(quality),
1206 def get_vcodec(*keys):
1207 return traverse_obj(live_info, (
1208 'stream_url
', *keys, {parse_inner}, 'VCodec
', {str}))
1210 for stream in ('hls
', 'rtmp
'):
1211 stream_url = traverse_obj(live_info, ('stream_url
', f'{stream}_pull_url
', {url_or_none}))
1215 'ext
': 'mp4
' if stream == 'hls
' else 'flv
',
1216 'protocol
': 'm3u8_native
' if stream == 'hls
' else 'https
',
1217 'format_id
': f'{stream}
-pull
',
1218 'vcodec
': get_vcodec(f'{stream}_pull_url_params
'),
1219 'quality
': get_quality('ORIGION
'),
1222 for f_id, f_url in traverse_obj(live_info, ('stream_url
', 'flv_pull_url
', {dict}), default={}).items():
1223 if not url_or_none(f_url):
1228 'format_id
': f'flv
-{f_id}
'.lower(),
1229 'vcodec
': get_vcodec('flv_pull_url_params
', f_id),
1230 'quality
': get_quality(f_id),
1233 # If uploader is a guest on another's livestream
, primary endpoint will
not have m3u8 URLs
1234 if not traverse_obj(formats
, lambda _
, v
: v
['ext'] == 'mp4'):
1235 live_info
= merge_dicts(live_info
, self
._call
_api
(
1236 'https://www.tiktok.com/api/live/detail/', 'roomID', room_id
, uploader
, key
='LiveRoomInfo'))
1237 if url_or_none(live_info
.get('liveUrl')):
1239 'url': live_info
['liveUrl'],
1241 'protocol': 'm3u8_native',
1242 'format_id': 'hls-fallback',
1244 'quality': get_quality('origin'),
1247 uploader
= uploader
or traverse_obj(live_info
, ('ownerInfo', 'uniqueId'), ('owner', 'display_id'))
1251 'uploader': uploader
,
1252 'uploader_url': format_field(uploader
, None, self
._UPLOADER
_URL
_FORMAT
) or None,
1255 '_format_sort_fields': ('quality', 'ext'),
1256 **traverse_obj(live_info
, {
1258 'uploader_id': (('ownerInfo', 'owner'), 'id', {str_or_none}
),
1259 'creator': (('ownerInfo', 'owner'), 'nickname'),
1260 'concurrent_view_count': (('user_count', ('liveRoomStats', 'userCount')), {int_or_none}
),