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
20 srt_subtitles_timecode
,
29 class TikTokBaseIE(InfoExtractor
):
30 _APP_VERSION
= '20.1.0'
31 _MANIFEST_APP_VERSION
= '210'
34 _API_HOSTNAME
= 'api-h2.tiktokv.com'
35 _UPLOADER_URL_FORMAT
= 'https://www.tiktok.com/@%s'
36 _WEBPAGE_HOST
= 'https://www.tiktok.com/'
37 QUALITIES
= ('360p', '540p', '720p', '1080p')
39 def _call_api(self
, ep
, query
, video_id
, fatal
=True,
40 note
='Downloading API JSON', errnote
='Unable to download API page'):
43 'version_name': self
._APP
_VERSION
,
44 'version_code': self
._MANIFEST
_APP
_VERSION
,
45 'build_number': self
._APP
_VERSION
,
46 'manifest_version_code': self
._MANIFEST
_APP
_VERSION
,
47 'update_version_code': self
._MANIFEST
_APP
_VERSION
,
48 'openudid': ''.join(random
.choice('0123456789abcdef') for _
in range(16)),
49 'uuid': ''.join([random
.choice(string
.digits
) for _
in range(16)]),
50 '_rticket': int(time
.time() * 1000),
51 'ts': int(time
.time()),
52 'device_brand': 'Google',
53 'device_type': 'Pixel 4',
54 'device_platform': 'android',
55 'resolution': '1080*1920',
59 'carrier_region': 'US',
62 'app_name': self
._APP
_NAME
,
65 'timezone_name': 'America/New_York',
66 'timezone_offset': '-14400',
67 'channel': 'googleplay',
74 'cp': 'cbfhckdckkde1',
76 self
._set
_cookie
(self
._API
_HOSTNAME
, 'odin_tt', ''.join(random
.choice('0123456789abcdef') for _
in range(160)))
77 webpage_cookies
= self
._get
_cookies
(self
._WEBPAGE
_HOST
)
78 if webpage_cookies
.get('sid_tt'):
79 self
._set
_cookie
(self
._API
_HOSTNAME
, 'sid_tt', webpage_cookies
['sid_tt'].value
)
80 return self
._download
_json
(
81 'https://%s/aweme/v1/%s/' % (self
._API
_HOSTNAME
, ep
), video_id
=video_id
,
82 fatal
=fatal
, note
=note
, errnote
=errnote
, headers
={
83 'User-Agent': f
'com.ss.android.ugc.trill/{self._MANIFEST_APP_VERSION} (Linux; U; Android 10; en_US; Pixel 4; Build/QQ3A.200805.001; Cronet/58.0.2991.0)',
84 'Accept': 'application/json',
87 def _get_subtitles(self
, aweme_detail
, aweme_id
):
88 # TODO: Extract text positioning info
90 captions_info
= traverse_obj(
91 aweme_detail
, ('interaction_stickers', ..., 'auto_video_caption_info', 'auto_captions', ...), expected_type
=dict, default
=[])
92 for caption
in captions_info
:
93 caption_url
= traverse_obj(caption
, ('url', 'url_list', ...), expected_type
=url_or_none
, get_all
=False)
96 caption_json
= self
._download
_json
(
97 caption_url
, aweme_id
, note
='Downloading captions', errnote
='Unable to download captions', fatal
=False)
100 subtitles
.setdefault(caption
.get('language', 'en'), []).append({
103 f
'{i + 1}\n{srt_subtitles_timecode(line["start_time"] / 1000)} --> {srt_subtitles_timecode(line["end_time"] / 1000)}\n{line["text"]}'
104 for i
, line
in enumerate(caption_json
['utterances']) if line
.get('text'))
108 def _parse_aweme_video_app(self
, aweme_detail
):
109 aweme_id
= aweme_detail
['aweme_id']
110 video_info
= aweme_detail
['video']
112 def parse_url_key(url_key
):
113 format_id
, codec
, res
, bitrate
= self
._search
_regex
(
114 r
'v[^_]+_(?P<id>(?P<codec>[^_]+)_(?P<res>\d+p)_(?P<bitrate>\d+))', url_key
,
115 'url key', default
=(None, None, None, None), group
=('id', 'codec', 'res', 'bitrate'))
119 'format_id': format_id
,
120 'vcodec': 'h265' if codec
== 'bytevc1' else codec
,
121 'tbr': int_or_none(bitrate
, scale
=1000) or None,
122 'quality': qualities(self
.QUALITIES
)(res
),
125 known_resolutions
= {}
127 def extract_addr(addr
, add_meta
={}):
128 parsed_meta
, res
= parse_url_key(addr
.get('url_key', ''))
130 known_resolutions
.setdefault(res
, {}).setdefault('height', add_meta
.get('height'))
131 known_resolutions
[res
].setdefault('width', add_meta
.get('width'))
132 parsed_meta
.update(known_resolutions
.get(res
, {}))
133 add_meta
.setdefault('height', int_or_none(res
[:-1]))
136 'filesize': int_or_none(addr
.get('data_size')),
139 'source_preference': -2 if 'aweme/v1' in url
else -1, # Downloads from API might get blocked
140 **add_meta
, **parsed_meta
,
141 'format_note': join_nonempty(
142 add_meta
.get('format_note'), '(API)' if 'aweme/v1' in url
else None, delim
=' ')
143 } for url
in addr
.get('url_list') or []]
145 # Hack: Add direct video links first to prioritize them when removing duplicate formats
147 if video_info
.get('play_addr'):
148 formats
.extend(extract_addr(video_info
['play_addr'], {
149 'format_id': 'play_addr',
150 'format_note': 'Direct video',
151 'vcodec': 'h265' if traverse_obj(
152 video_info
, 'is_bytevc1', 'is_h265') else 'h264', # TODO: Check for "direct iOS" videos, like https://www.tiktok.com/@cookierun_dev/video/7039716639834656002
153 'width': video_info
.get('width'),
154 'height': video_info
.get('height'),
156 if video_info
.get('download_addr'):
157 formats
.extend(extract_addr(video_info
['download_addr'], {
158 'format_id': 'download_addr',
159 'format_note': 'Download video%s' % (', watermarked' if video_info
.get('has_watermark') else ''),
161 'width': video_info
.get('width'),
162 'height': video_info
.get('height'),
163 'preference': -2 if video_info
.get('has_watermark') else -1,
165 if video_info
.get('play_addr_h264'):
166 formats
.extend(extract_addr(video_info
['play_addr_h264'], {
167 'format_id': 'play_addr_h264',
168 'format_note': 'Direct video',
171 if video_info
.get('play_addr_bytevc1'):
172 formats
.extend(extract_addr(video_info
['play_addr_bytevc1'], {
173 'format_id': 'play_addr_bytevc1',
174 'format_note': 'Direct video',
178 for bitrate
in video_info
.get('bit_rate', []):
179 if bitrate
.get('play_addr'):
180 formats
.extend(extract_addr(bitrate
['play_addr'], {
181 'format_id': bitrate
.get('gear_name'),
182 'format_note': 'Playback video',
183 'tbr': try_get(bitrate
, lambda x
: x
['bit_rate'] / 1000),
184 'vcodec': 'h265' if traverse_obj(
185 bitrate
, 'is_bytevc1', 'is_h265') else 'h264',
186 'fps': bitrate
.get('FPS'),
189 self
._remove
_duplicate
_formats
(formats
)
190 auth_cookie
= self
._get
_cookies
(self
._WEBPAGE
_HOST
).get('sid_tt')
193 self
._set
_cookie
(compat_urllib_parse_urlparse(f
['url']).hostname
, 'sid_tt', auth_cookie
.value
)
194 self
._sort
_formats
(formats
, ('quality', 'codec', 'size', 'br'))
197 for cover_id
in ('cover', 'ai_dynamic_cover', 'animated_cover', 'ai_dynamic_cover_bak',
198 'origin_cover', 'dynamic_cover'):
199 cover
= video_info
.get(cover_id
)
201 for cover_url
in cover
['url_list']:
207 stats_info
= aweme_detail
.get('statistics', {})
208 author_info
= aweme_detail
.get('author', {})
209 music_info
= aweme_detail
.get('music', {})
210 user_url
= self
._UPLOADER
_URL
_FORMAT
% (traverse_obj(author_info
,
211 'sec_uid', 'id', 'uid', 'unique_id',
212 expected_type
=str_or_none
, get_all
=False))
213 labels
= traverse_obj(aweme_detail
, ('hybrid_label', ..., 'text'), expected_type
=str, default
=[])
215 contained_music_track
= traverse_obj(
216 music_info
, ('matched_song', 'title'), ('matched_pgc_sound', 'title'), expected_type
=str)
217 contained_music_author
= traverse_obj(
218 music_info
, ('matched_song', 'author'), ('matched_pgc_sound', 'author'), 'author', expected_type
=str)
220 is_generic_og_trackname
= music_info
.get('is_original_sound') and music_info
.get('title') == 'original sound - %s' % music_info
.get('owner_handle')
221 if is_generic_og_trackname
:
222 music_track
, music_author
= contained_music_track
or 'original sound', contained_music_author
224 music_track
, music_author
= music_info
.get('title'), music_info
.get('author')
228 'title': aweme_detail
['desc'],
229 'description': aweme_detail
['desc'],
230 'view_count': int_or_none(stats_info
.get('play_count')),
231 'like_count': int_or_none(stats_info
.get('digg_count')),
232 'repost_count': int_or_none(stats_info
.get('share_count')),
233 'comment_count': int_or_none(stats_info
.get('comment_count')),
234 'uploader': str_or_none(author_info
.get('unique_id')),
235 'creator': str_or_none(author_info
.get('nickname')),
236 'uploader_id': str_or_none(author_info
.get('uid')),
237 'uploader_url': user_url
,
238 'track': music_track
,
239 'album': str_or_none(music_info
.get('album')) or None,
240 'artist': music_author
,
241 'timestamp': int_or_none(aweme_detail
.get('create_time')),
243 'subtitles': self
.extract_subtitles(aweme_detail
, aweme_id
),
244 'thumbnails': thumbnails
,
245 'duration': int_or_none(traverse_obj(video_info
, 'duration', ('download_addr', 'duration')), scale
=1000),
246 'availability': self
._availability
(
247 is_private
='Private' in labels
,
248 needs_subscription
='Friends only' in labels
,
249 is_unlisted
='Followers only' in labels
)
252 def _parse_aweme_video_web(self
, aweme_detail
, webpage_url
):
253 video_info
= aweme_detail
['video']
254 author_info
= traverse_obj(aweme_detail
, 'authorInfo', 'author', expected_type
=dict, default
={})
255 music_info
= aweme_detail
.get('music') or {}
256 stats_info
= aweme_detail
.get('stats') or {}
257 user_url
= self
._UPLOADER
_URL
_FORMAT
% (traverse_obj(author_info
,
258 'secUid', 'id', 'uid', 'uniqueId',
259 expected_type
=str_or_none
, get_all
=False)
260 or aweme_detail
.get('authorSecId'))
263 play_url
= video_info
.get('playAddr')
264 width
= video_info
.get('width')
265 height
= video_info
.get('height')
266 if isinstance(play_url
, str):
268 'url': self
._proto
_relative
_url
(play_url
),
273 elif isinstance(play_url
, list):
275 'url': self
._proto
_relative
_url
(url
),
279 } for url
in traverse_obj(play_url
, (..., 'src'), expected_type
=url_or_none
, default
=[]) if url
]
281 download_url
= url_or_none(video_info
.get('downloadAddr')) or traverse_obj(video_info
, ('download', 'url'), expected_type
=url_or_none
)
284 'format_id': 'download',
285 'url': self
._proto
_relative
_url
(download_url
),
290 self
._remove
_duplicate
_formats
(formats
)
291 self
._sort
_formats
(formats
)
294 for thumbnail_name
in ('thumbnail', 'cover', 'dynamicCover', 'originCover'):
295 if aweme_detail
.get(thumbnail_name
):
297 'url': self
._proto
_relative
_url
(aweme_detail
[thumbnail_name
]),
303 'id': traverse_obj(aweme_detail
, 'id', 'awemeId', expected_type
=str_or_none
),
304 'title': aweme_detail
.get('desc'),
305 'duration': try_get(aweme_detail
, lambda x
: x
['video']['duration'], int),
306 'view_count': int_or_none(stats_info
.get('playCount')),
307 'like_count': int_or_none(stats_info
.get('diggCount')),
308 'repost_count': int_or_none(stats_info
.get('shareCount')),
309 'comment_count': int_or_none(stats_info
.get('commentCount')),
310 'timestamp': int_or_none(aweme_detail
.get('createTime')),
311 'creator': str_or_none(author_info
.get('nickname')),
312 'uploader': str_or_none(author_info
.get('uniqueId') or aweme_detail
.get('author')),
313 'uploader_id': str_or_none(author_info
.get('id') or aweme_detail
.get('authorId')),
314 'uploader_url': user_url
,
315 'track': str_or_none(music_info
.get('title')),
316 'album': str_or_none(music_info
.get('album')) or None,
317 'artist': str_or_none(music_info
.get('authorName')),
319 'thumbnails': thumbnails
,
320 'description': str_or_none(aweme_detail
.get('desc')),
322 'Referer': webpage_url
327 class TikTokIE(TikTokBaseIE
):
328 _VALID_URL
= r
'https?://www\.tiktok\.com/@[\w\.-]+/video/(?P<id>\d+)'
331 'url': 'https://www.tiktok.com/@leenabhushan/video/6748451240264420610',
332 'md5': '736bb7a466c6f0a6afeb597da1e6f5b7',
334 'id': '6748451240264420610',
336 'title': '#jassmanak #lehanga #leenabhushan',
337 'description': '#jassmanak #lehanga #leenabhushan',
341 'uploader': 'leenabhushan',
342 'uploader_id': '6691488002098119685',
343 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA_Eb4t1vodM1IuTy_cvp9CY22RAb59xqrO0Xtz9CYQJvgXaDvZxYnZYRzDWhhgJmy',
344 'creator': 'facestoriesbyleenabh',
345 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
346 'upload_date': '20191016',
347 'timestamp': 1571246252,
351 'comment_count': int,
354 'url': 'https://www.tiktok.com/@patroxofficial/video/6742501081818877190?langCountry=en',
355 'md5': '6f3cf8cdd9b28cb8363fe0a9a160695b',
357 'id': '6742501081818877190',
359 'title': 'md5:5e2a23877420bb85ce6521dbee39ba94',
360 'description': 'md5:5e2a23877420bb85ce6521dbee39ba94',
364 'uploader': 'patrox',
365 'uploader_id': '18702747',
366 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws',
368 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
369 'upload_date': '20190930',
370 'timestamp': 1569860870,
374 'comment_count': int,
377 # Banned audio, only available on the app
378 'url': 'https://www.tiktok.com/@barudakhb_/video/6984138651336838402',
380 'id': '6984138651336838402',
382 'title': 'Balas @yolaaftwsr hayu yu ? #SquadRandom_ 🔥',
383 'description': 'Balas @yolaaftwsr hayu yu ? #SquadRandom_ 🔥',
384 'uploader': 'barudakhb_',
385 'creator': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6',
386 'uploader_id': '6974687867511718913',
387 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAbhBwQC-R1iKoix6jDFsF-vBdfx2ABoDjaZrM9fX6arU3w71q3cOWgWuTXn1soZ7d',
388 'track': 'Boka Dance',
389 'artist': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6',
390 'timestamp': 1626121503,
392 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
393 'upload_date': '20210712',
397 'comment_count': int,
400 # Sponsored video, only available with feed workaround
401 'url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_/video/7042692929109986561',
403 'id': '7042692929109986561',
405 'title': 'Slap and Run!',
406 'description': 'Slap and Run!',
407 'uploader': 'user440922249',
408 'creator': 'Slap And Run',
409 'uploader_id': '7036055384943690754',
410 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_',
411 'track': 'Promoted Music',
412 'timestamp': 1639754738,
414 'thumbnail': r
're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
415 'upload_date': '20211217',
419 'comment_count': int,
421 'expected_warnings': ['Video not available']
423 # Auto-captions available
424 'url': 'https://www.tiktok.com/@hankgreen1/video/7047596209028074758',
425 'only_matching': True
428 def _extract_aweme_app(self
, aweme_id
):
430 aweme_detail
= self
._call
_api
('aweme/detail', {'aweme_id': aweme_id}
, aweme_id
,
431 note
='Downloading video details', errnote
='Unable to download video details').get('aweme_detail')
433 raise ExtractorError('Video not available', video_id
=aweme_id
)
434 except ExtractorError
as e
:
435 self
.report_warning(f
'{e}; Retrying with feed workaround')
436 feed_list
= self
._call
_api
('feed', {'aweme_id': aweme_id}
, aweme_id
,
437 note
='Downloading video feed', errnote
='Unable to download video feed').get('aweme_list') or []
438 aweme_detail
= next((aweme
for aweme
in feed_list
if str(aweme
.get('aweme_id')) == aweme_id
), None)
440 raise ExtractorError('Unable to find video in feed', video_id
=aweme_id
)
441 return self
._parse
_aweme
_video
_app
(aweme_detail
)
443 def _real_extract(self
, url
):
444 video_id
= self
._match
_id
(url
)
447 return self
._extract
_aweme
_app
(video_id
)
448 except ExtractorError
as e
:
449 self
.report_warning(f
'{e}; Retrying with webpage')
451 # If we only call once, we get a 403 when downlaoding the video.
452 self
._download
_webpage
(url
, video_id
)
453 webpage
= self
._download
_webpage
(url
, video_id
, note
='Downloading video webpage')
454 next_json
= self
._search
_regex
(
455 r
'id=\"__NEXT_DATA__\"\s+type=\"application\/json\"\s*[^>]+>\s*(?P<next_data>[^<]+)',
456 webpage
, 'next data', group
='next_data', default
=None)
459 next_data
= self
._parse
_json
(next_json
, video_id
)
460 status
= traverse_obj(next_data
, ('props', 'pageProps', 'statusCode'), expected_type
=int) or 0
461 video_data
= traverse_obj(next_data
, ('props', 'pageProps', 'itemInfo', 'itemStruct'), expected_type
=dict)
463 sigi_json
= self
._search
_regex
(
464 r
'>\s*window\[[\'"]SIGI_STATE[\'"]\
]\s
*=\s
*(?P
<sigi_state
>{.+}
);',
465 webpage, 'sigi data
', group='sigi_state
')
466 sigi_data = self._parse_json(sigi_json, video_id)
467 status = traverse_obj(sigi_data, ('VideoPage
', 'statusCode
'), expected_type=int) or 0
468 video_data = traverse_obj(sigi_data, ('ItemModule
', video_id), expected_type=dict)
471 return self._parse_aweme_video_web(video_data, url)
472 elif status == 10216:
473 raise ExtractorError('This video
is private
', expected=True)
474 raise ExtractorError('Video
not available
', video_id=video_id)
477 class TikTokUserIE(TikTokBaseIE):
478 IE_NAME = 'tiktok
:user
'
479 _VALID_URL = r'https?
://(?
:www\
.)?tiktok\
.com
/@(?P
<id>[\w\
.-]+)/?
(?
:$|
[#?])'
481 'url': 'https://tiktok.com/@corgibobaa?lang=en',
482 'playlist_mincount': 45,
484 'id': '6935371178089399301',
485 'title': 'corgibobaa',
486 'thumbnail': r
're:https://.+_1080x1080\.webp'
488 'expected_warnings': ['Retrying']
490 'url': 'https://www.tiktok.com/@meme',
491 'playlist_mincount': 593,
493 'id': '79005827461758976',
495 'thumbnail': r
're:https://.+_1080x1080\.webp'
497 'expected_warnings': ['Retrying']
500 r
''' # TODO: Fix by adding _signature to api_url
501 def _entries(self, webpage, user_id, username):
502 secuid = self._search_regex(r'\"secUid\":\"(?P<secUid>[^\"]+)', webpage, username)
503 verifyfp_cookie = self._get_cookies('https://www.tiktok.com').get('s_v_web_id')
504 if not verifyfp_cookie:
505 raise ExtractorError('Improper cookies (missing s_v_web_id).', expected=True)
506 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='
508 for page in itertools.count():
509 data_json = self._download_json(api_url + cursor, username, note='Downloading Page %d' % page)
510 for video in data_json.get('itemList', []):
511 video_id = video['id']
512 video_url = f'https://www.tiktok.com/@{user_id}/video/{video_id}'
513 yield self._url_result(video_url, 'TikTok', video_id, str_or_none(video.get('desc')))
514 if not data_json.get('hasMore'):
516 cursor = data_json['cursor']
519 def _video_entries_api(self
, webpage
, user_id
, username
):
525 'retry_type': 'no_retry',
526 '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.
529 max_retries
= self
.get_param('extractor_retries', 3)
530 for page
in itertools
.count(1):
531 for retries
in itertools
.count():
533 post_list
= self
._call
_api
('aweme/post', query
, username
,
534 note
='Downloading user video list page %d%s' % (page
, f
' (attempt {retries})' if retries
!= 0 else ''),
535 errnote
='Unable to download user video list')
536 except ExtractorError
as e
:
537 if isinstance(e
.cause
, json
.JSONDecodeError
) and e
.cause
.pos
== 0 and retries
!= max_retries
:
538 self
.report_warning('%s. Retrying...' % str(e
.cause
or e
.msg
))
542 yield from post_list
.get('aweme_list', [])
543 if not post_list
.get('has_more'):
545 query
['max_cursor'] = post_list
['max_cursor']
547 def _entries_api(self
, user_id
, videos
):
550 **self
._parse
_aweme
_video
_app
(video
),
551 'extractor_key': TikTokIE
.ie_key(),
552 'extractor': 'TikTok',
553 'webpage_url': f
'https://tiktok.com/@{user_id}/video/{video["aweme_id"]}',
556 def _real_extract(self
, url
):
557 user_name
= self
._match
_id
(url
)
558 webpage
= self
._download
_webpage
(url
, user_name
, headers
={
559 'User-Agent': 'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)'
561 user_id
= self
._html
_search
_regex
(r
'snssdk\d*://user/profile/(\d+)', webpage
, 'user ID')
563 videos
= LazyList(self
._video
_entries
_api
(webpage
, user_id
, user_name
))
564 thumbnail
= traverse_obj(videos
, (0, 'author', 'avatar_larger', 'url_list', 0))
566 return self
.playlist_result(self
._entries
_api
(user_id
, videos
), user_id
, user_name
, thumbnail
=thumbnail
)
569 class TikTokBaseListIE(TikTokBaseIE
):
570 def _entries(self
, list_id
, display_id
):
572 self
._QUERY
_NAME
: list_id
,
576 'device_id': ''.join(random
.choice(string
.digits
) for i
in range(19))
579 max_retries
= self
.get_param('extractor_retries', 3)
580 for page
in itertools
.count(1):
581 for retries
in itertools
.count():
583 post_list
= self
._call
_api
(self
._API
_ENDPOINT
, query
, display_id
,
584 note
='Downloading video list page %d%s' % (page
, f
' (attempt {retries})' if retries
!= 0 else ''),
585 errnote
='Unable to download video list')
586 except ExtractorError
as e
:
587 if isinstance(e
.cause
, json
.JSONDecodeError
) and e
.cause
.pos
== 0 and retries
!= max_retries
:
588 self
.report_warning('%s. Retrying...' % str(e
.cause
or e
.msg
))
592 for video
in post_list
.get('aweme_list', []):
594 **self
._parse
_aweme
_video
_app
(video
),
595 'extractor_key': TikTokIE
.ie_key(),
596 'extractor': 'TikTok',
597 'webpage_url': f
'https://tiktok.com/@_/video/{video["aweme_id"]}',
599 if not post_list
.get('has_more'):
601 query
['cursor'] = post_list
['cursor']
603 def _real_extract(self
, url
):
604 list_id
= self
._match
_id
(url
)
605 return self
.playlist_result(self
._entries
(list_id
, list_id
), list_id
)
608 class TikTokSoundIE(TikTokBaseListIE
):
609 IE_NAME
= 'tiktok:sound'
610 _VALID_URL
= r
'https?://(?:www\.)?tiktok\.com/music/[\w\.-]+-(?P<id>[\d]+)[/?#&]?'
611 _QUERY_NAME
= 'music_id'
612 _API_ENDPOINT
= 'music/aweme'
614 'url': 'https://www.tiktok.com/music/Build-a-Btch-6956990112127585029?lang=en',
615 'playlist_mincount': 100,
617 'id': '6956990112127585029'
619 'expected_warnings': ['Retrying']
621 # Actual entries are less than listed video count
622 'url': 'https://www.tiktok.com/music/jiefei-soap-remix-7036843036118469381',
623 'playlist_mincount': 2182,
625 'id': '7036843036118469381'
627 'expected_warnings': ['Retrying']
631 class TikTokEffectIE(TikTokBaseListIE
):
632 IE_NAME
= 'tiktok:effect'
633 _VALID_URL
= r
'https?://(?:www\.)?tiktok\.com/sticker/[\w\.-]+-(?P<id>[\d]+)[/?#&]?'
634 _QUERY_NAME
= 'sticker_id'
635 _API_ENDPOINT
= 'sticker/aweme'
637 'url': 'https://www.tiktok.com/sticker/MATERIAL-GWOOORL-1258156',
638 'playlist_mincount': 100,
642 'expected_warnings': ['Retrying']
644 # Different entries between mobile and web, depending on region
645 'url': 'https://www.tiktok.com/sticker/Elf-Friend-479565',
646 'only_matching': True
650 class TikTokTagIE(TikTokBaseListIE
):
651 IE_NAME
= 'tiktok:tag'
652 _VALID_URL
= r
'https?://(?:www\.)?tiktok\.com/tag/(?P<id>[^/?#&]+)'
653 _QUERY_NAME
= 'ch_id'
654 _API_ENDPOINT
= 'challenge/aweme'
656 'url': 'https://tiktok.com/tag/hello2018',
657 'playlist_mincount': 39,
660 'title': 'hello2018',
662 'expected_warnings': ['Retrying']
664 'url': 'https://tiktok.com/tag/fypシ?is_copy_url=0&is_from_webapp=v1',
665 'only_matching': True
668 def _real_extract(self
, url
):
669 display_id
= self
._match
_id
(url
)
670 webpage
= self
._download
_webpage
(url
, display_id
, headers
={
671 'User-Agent': 'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)'
673 tag_id
= self
._html
_search
_regex
(r
'snssdk\d*://challenge/detail/(\d+)', webpage
, 'tag ID')
674 return self
.playlist_result(self
._entries
(tag_id
, display_id
), tag_id
, display_id
)
677 class DouyinIE(TikTokIE
):
678 _VALID_URL
= r
'https?://(?:www\.)?douyin\.com/video/(?P<id>[0-9]+)'
680 'url': 'https://www.douyin.com/video/6961737553342991651',
681 'md5': '10523312c8b8100f353620ac9dc8f067',
683 'id': '6961737553342991651',
685 'title': '#杨超越 小小水手带你去远航❤️',
687 'upload_date': '20210513',
688 'timestamp': 1620905839,
689 'uploader_id': '110403406559',
693 'comment_count': int,
696 'url': 'https://www.douyin.com/video/6982497745948921092',
697 'md5': 'd78408c984b9b5102904cf6b6bc2d712',
699 'id': '6982497745948921092',
701 'title': '这个夏日和小羊@杨超越 一起遇见白色幻想',
702 'uploader': '杨超越工作室',
703 'upload_date': '20210708',
704 'timestamp': 1625739481,
705 'uploader_id': '408654318141572',
709 'comment_count': int,
712 'url': 'https://www.douyin.com/video/6953975910773099811',
713 'md5': '72e882e24f75064c218b76c8b713c185',
715 'id': '6953975910773099811',
717 'title': '#一起看海 出现在你的夏日里',
719 'upload_date': '20210422',
720 'timestamp': 1619098692,
721 'uploader_id': '110403406559',
725 'comment_count': int,
728 'url': 'https://www.douyin.com/video/6950251282489675042',
729 'md5': 'b4db86aec367ef810ddd38b1737d2fed',
731 'id': '6950251282489675042',
733 'title': '哈哈哈,成功了哈哈哈哈哈哈',
735 'upload_date': '20210412',
736 'timestamp': 1618231483,
737 'uploader_id': '110403406559',
741 'comment_count': int,
744 'url': 'https://www.douyin.com/video/6963263655114722595',
745 'md5': '1abe1c477d05ee62efb40bf2329957cf',
747 'id': '6963263655114722595',
749 'title': '#哪个爱豆的105度最甜 换个角度看看我哈哈',
751 'upload_date': '20210517',
752 'timestamp': 1621261163,
753 'uploader_id': '110403406559',
757 'comment_count': int,
760 _APP_VERSION
= '9.6.0'
761 _MANIFEST_APP_VERSION
= '960'
764 _API_HOSTNAME
= 'aweme.snssdk.com'
765 _UPLOADER_URL_FORMAT
= 'https://www.douyin.com/user/%s'
766 _WEBPAGE_HOST
= 'https://www.douyin.com/'
768 def _real_extract(self
, url
):
769 video_id
= self
._match
_id
(url
)
772 return self
._extract
_aweme
_app
(video_id
)
773 except ExtractorError
as e
:
774 self
.report_warning(f
'{e}; Retrying with webpage')
776 webpage
= self
._download
_webpage
(url
, video_id
)
777 render_data_json
= self
._search
_regex
(
778 r
'<script [^>]*\bid=[\'"]RENDER_DATA[\'"][^
>]*>(%7B
.+%7D
)</script
>',
779 webpage, 'render data
', default=None)
780 if not render_data_json:
781 # TODO: Run verification challenge code to generate signature cookies
782 raise ExtractorError('Fresh
cookies (not necessarily logged
in) are needed
')
784 render_data = self._parse_json(
785 render_data_json, video_id, transform_source=compat_urllib_parse_unquote)
786 return self._parse_aweme_video_web(
787 traverse_obj(render_data, (..., 'aweme
', 'detail
'), get_all=False), url)