from ..utils import (
ExtractorError,
int_or_none,
+ join_nonempty,
str_or_none,
traverse_obj,
try_get,
_MANIFEST_APP_VERSION = '291'
_APP_NAME = 'trill'
_AID = 1180
- _API_HOSTNAME = 'api-t2.tiktokv.com'
+ _API_HOSTNAME = 'api-h2.tiktokv.com'
_UPLOADER_URL_FORMAT = 'https://www.tiktok.com/@%s'
+ _WEBPAGE_HOST = 'https://www.tiktok.com/'
QUALITIES = ('360p', '540p', '720p')
def _call_api(self, ep, query, video_id, fatal=True,
'build_number': self._APP_VERSION,
'manifest_version_code': self._MANIFEST_APP_VERSION,
'update_version_code': self._MANIFEST_APP_VERSION,
- 'openudid': ''.join(random.choice('0123456789abcdef') for i in range(16)),
- 'uuid': ''.join([random.choice(string.digits) for num in range(16)]),
+ 'openudid': ''.join(random.choice('0123456789abcdef') for _ in range(16)),
+ 'uuid': ''.join([random.choice(string.digits) for _ in range(16)]),
'_rticket': int(time.time() * 1000),
'ts': int(time.time()),
'device_brand': 'Google',
'as': 'a1qwert123',
'cp': 'cbfhckdckkde1',
}
- self._set_cookie(self._API_HOSTNAME, 'odin_tt', ''.join(random.choice('0123456789abcdef') for i in range(160)))
+ self._set_cookie(self._API_HOSTNAME, 'odin_tt', ''.join(random.choice('0123456789abcdef') for _ in range(160)))
+ webpage_cookies = self._get_cookies(self._WEBPAGE_HOST)
+ if webpage_cookies.get('sid_tt'):
+ self._set_cookie(self._API_HOSTNAME, 'sid_tt', webpage_cookies['sid_tt'].value)
return self._download_json(
'https://%s/aweme/v1/%s/' % (self._API_HOSTNAME, ep), video_id=video_id,
fatal=fatal, note=note, errnote=errnote, headers={
'acodec': 'aac',
'source_preference': -2 if 'aweme/v1' in url else -1, # Downloads from API might get blocked
**add_meta, **parsed_meta,
- 'format_note': ' '.join(filter(None, (
- add_meta.get('format_note'), '(API)' if 'aweme/v1' in url else '')))
+ 'format_note': join_nonempty(
+ add_meta.get('format_note'), '(API)' if 'aweme/v1' in url else None, delim=' ')
} for url in addr.get('url_list') or []]
# Hack: Add direct video links first to prioritize them when removing duplicate formats
user_url = self._UPLOADER_URL_FORMAT % (traverse_obj(author_info,
'sec_uid', 'id', 'uid', 'unique_id',
expected_type=str_or_none, get_all=False))
+ labels = traverse_obj(aweme_detail, ('hybrid_label', ..., 'text'), expected_type=str, default=[])
contained_music_track = traverse_obj(
music_info, ('matched_song', 'title'), ('matched_pgc_sound', 'title'), expected_type=str)
'timestamp': int_or_none(aweme_detail.get('create_time')),
'formats': formats,
'thumbnails': thumbnails,
- 'duration': int_or_none(traverse_obj(video_info, 'duration', ('download_addr', 'duration')), scale=1000)
+ 'duration': int_or_none(traverse_obj(video_info, 'duration', ('download_addr', 'duration')), scale=1000),
+ 'availability': self._availability(
+ is_private='Private' in labels,
+ needs_subscription='Friends only' in labels,
+ is_unlisted='Followers only' in labels)
}
- def _parse_aweme_video_web(self, aweme_detail, webpage, url):
+ def _parse_aweme_video_web(self, aweme_detail, webpage_url):
video_info = aweme_detail['video']
author_info = traverse_obj(aweme_detail, 'author', 'authorInfo', default={})
music_info = aweme_detail.get('music') or {}
'thumbnails': thumbnails,
'description': str_or_none(aweme_detail.get('desc')),
'http_headers': {
- 'Referer': url
+ 'Referer': webpage_url
}
}
_TESTS = [{
'url': 'https://www.tiktok.com/@leenabhushan/video/6748451240264420610',
- 'md5': '34a7543afd5a151b0840ba6736fb633b',
+ 'md5': '736bb7a466c6f0a6afeb597da1e6f5b7',
'info_dict': {
'id': '6748451240264420610',
'ext': 'mp4',
'title': '#jassmanak #lehanga #leenabhushan',
'description': '#jassmanak #lehanga #leenabhushan',
'duration': 13,
- 'height': 1280,
- 'width': 720,
+ 'height': 1024,
+ 'width': 576,
'uploader': 'leenabhushan',
'uploader_id': '6691488002098119685',
- 'uploader_url': 'https://www.tiktok.com/@leenabhushan',
+ 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA_Eb4t1vodM1IuTy_cvp9CY22RAb59xqrO0Xtz9CYQJvgXaDvZxYnZYRzDWhhgJmy',
'creator': 'facestoriesbyleenabh',
'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
'upload_date': '20191016',
}
}, {
'url': 'https://www.tiktok.com/@patroxofficial/video/6742501081818877190?langCountry=en',
- 'md5': '06b9800d47d5fe51a19e322dd86e61c9',
+ 'md5': '6f3cf8cdd9b28cb8363fe0a9a160695b',
'info_dict': {
'id': '6742501081818877190',
'ext': 'mp4',
'width': 540,
'uploader': 'patrox',
'uploader_id': '18702747',
- 'uploader_url': 'https://www.tiktok.com/@patrox',
+ 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws',
'creator': 'patroX',
'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
'upload_date': '20190930',
}]
def _extract_aweme_app(self, aweme_id):
- aweme_detail = self._call_api('aweme/detail', {'aweme_id': aweme_id}, aweme_id,
- note='Downloading video details', errnote='Unable to download video details')['aweme_detail']
+ try:
+ aweme_detail = self._call_api('aweme/detail', {'aweme_id': aweme_id}, aweme_id,
+ note='Downloading video details', errnote='Unable to download video details').get('aweme_detail')
+ if not aweme_detail:
+ raise ExtractorError('Video not available', video_id=aweme_id)
+ except ExtractorError as e:
+ self.report_warning(f'{e}; Retrying with feed workaround')
+ feed_list = self._call_api('feed', {'aweme_id': aweme_id}, aweme_id,
+ note='Downloading video feed', errnote='Unable to download video feed').get('aweme_list') or []
+ aweme_detail = next(aweme for aweme in feed_list if str(aweme.get('aweme_id')) == aweme_id)
+ if not aweme_detail:
+ raise ExtractorError('Unable to find video in feed', video_id=aweme_id)
return self._parse_aweme_video_app(aweme_detail)
def _real_extract(self, url):
# Chech statusCode for success
status = props_data.get('pageProps').get('statusCode')
if status == 0:
- return self._parse_aweme_video_web(props_data['pageProps']['itemInfo']['itemStruct'], webpage, url)
+ return self._parse_aweme_video_web(props_data['pageProps']['itemInfo']['itemStruct'], url)
elif status == 10216:
raise ExtractorError('This video is private', expected=True)
'playlist_mincount': 45,
'info_dict': {
'id': '6935371178089399301',
+ 'title': 'corgibobaa',
},
+ 'expected_warnings': ['Retrying']
}, {
'url': 'https://www.tiktok.com/@meme',
'playlist_mincount': 593,
'info_dict': {
'id': '79005827461758976',
+ 'title': 'meme',
},
+ 'expected_warnings': ['Retrying']
}]
r''' # TODO: Fix by adding _signature to api_url
'max_cursor': 0,
'min_cursor': 0,
'retry_type': 'no_retry',
- 'device_id': ''.join(random.choice(string.digits) for i in range(19)), # Some endpoints don't like randomized device_id, so it isn't directly set in _call_api.
+ '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.
}
max_retries = self.get_param('extractor_retries', 3)
break
for video in post_list.get('aweme_list', []):
yield {
- **self._parse_aweme_video(video),
- 'ie_key': TikTokIE.ie_key(),
+ **self._parse_aweme_video_app(video),
+ 'extractor_key': TikTokIE.ie_key(),
'extractor': 'TikTok',
+ 'webpage_url': f'https://tiktok.com/@{user_id}/video/{video["aweme_id"]}',
}
if not post_list.get('has_more'):
break
query['max_cursor'] = post_list['max_cursor']
def _real_extract(self, url):
- user_id = self._match_id(url)
- webpage = self._download_webpage(url, user_id, headers={
+ user_name = self._match_id(url)
+ webpage = self._download_webpage(url, user_name, headers={
+ 'User-Agent': 'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)'
+ })
+ user_id = self._html_search_regex(r'snssdk\d*://user/profile/(\d+)', webpage, 'user ID')
+ return self.playlist_result(self._entries_api(webpage, user_id, user_name), user_id, user_name)
+
+
+class TikTokBaseListIE(TikTokBaseIE):
+ def _entries(self, list_id, display_id):
+ query = {
+ self._QUERY_NAME: list_id,
+ 'cursor': 0,
+ 'count': 20,
+ 'type': 5,
+ 'device_id': ''.join(random.choice(string.digits) for i in range(19))
+ }
+
+ max_retries = self.get_param('extractor_retries', 3)
+ for page in itertools.count(1):
+ for retries in itertools.count():
+ try:
+ post_list = self._call_api(self._API_ENDPOINT, query, display_id,
+ note='Downloading video list page %d%s' % (page, f' (attempt {retries})' if retries != 0 else ''),
+ errnote='Unable to download video list')
+ except ExtractorError as e:
+ if isinstance(e.cause, json.JSONDecodeError) and e.cause.pos == 0 and retries != max_retries:
+ self.report_warning('%s. Retrying...' % str(e.cause or e.msg))
+ continue
+ raise
+ break
+ for video in post_list.get('aweme_list', []):
+ yield {
+ **self._parse_aweme_video_app(video),
+ 'extractor_key': TikTokIE.ie_key(),
+ 'extractor': 'TikTok',
+ 'webpage_url': f'https://tiktok.com/@_/video/{video["aweme_id"]}',
+ }
+ if not post_list.get('has_more'):
+ break
+ query['cursor'] = post_list['cursor']
+
+ def _real_extract(self, url):
+ list_id = self._match_id(url)
+ return self.playlist_result(self._entries(list_id, list_id), list_id)
+
+
+class TikTokSoundIE(TikTokBaseListIE):
+ IE_NAME = 'tiktok:sound'
+ _VALID_URL = r'https?://(?:www\.)?tiktok\.com/music/[\w\.-]+-(?P<id>[\d]+)[/?#&]?'
+ _QUERY_NAME = 'music_id'
+ _API_ENDPOINT = 'music/aweme'
+ _TESTS = [{
+ 'url': 'https://www.tiktok.com/music/Build-a-Btch-6956990112127585029?lang=en',
+ 'playlist_mincount': 100,
+ 'info_dict': {
+ 'id': '6956990112127585029'
+ },
+ 'expected_warnings': ['Retrying']
+ }, {
+ # Actual entries are less than listed video count
+ 'url': 'https://www.tiktok.com/music/jiefei-soap-remix-7036843036118469381',
+ 'playlist_mincount': 2182,
+ 'info_dict': {
+ 'id': '7036843036118469381'
+ },
+ 'expected_warnings': ['Retrying']
+ }]
+
+
+class TikTokEffectIE(TikTokBaseListIE):
+ IE_NAME = 'tiktok:effect'
+ _VALID_URL = r'https?://(?:www\.)?tiktok\.com/sticker/[\w\.-]+-(?P<id>[\d]+)[/?#&]?'
+ _QUERY_NAME = 'sticker_id'
+ _API_ENDPOINT = 'sticker/aweme'
+ _TESTS = [{
+ 'url': 'https://www.tiktok.com/sticker/MATERIAL-GWOOORL-1258156',
+ 'playlist_mincount': 100,
+ 'info_dict': {
+ 'id': '1258156',
+ },
+ 'expected_warnings': ['Retrying']
+ }, {
+ # Different entries between mobile and web, depending on region
+ 'url': 'https://www.tiktok.com/sticker/Elf-Friend-479565',
+ 'only_matching': True
+ }]
+
+
+class TikTokTagIE(TikTokBaseListIE):
+ IE_NAME = 'tiktok:tag'
+ _VALID_URL = r'https?://(?:www\.)?tiktok\.com/tag/(?P<id>[^/?#&]+)'
+ _QUERY_NAME = 'ch_id'
+ _API_ENDPOINT = 'challenge/aweme'
+ _TESTS = [{
+ 'url': 'https://tiktok.com/tag/hello2018',
+ 'playlist_mincount': 39,
+ 'info_dict': {
+ 'id': '46294678',
+ 'title': 'hello2018',
+ },
+ 'expected_warnings': ['Retrying']
+ }, {
+ 'url': 'https://tiktok.com/tag/fypシ?is_copy_url=0&is_from_webapp=v1',
+ 'only_matching': True
+ }]
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id, headers={
'User-Agent': 'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)'
})
- own_id = self._html_search_regex(r'snssdk\d*://user/profile/(\d+)', webpage, 'user ID')
- return self.playlist_result(self._entries_api(webpage, own_id, user_id), user_id)
+ tag_id = self._html_search_regex(r'snssdk\d*://challenge/detail/(\d+)', webpage, 'tag ID')
+ return self.playlist_result(self._entries(tag_id, display_id), tag_id, display_id)
class DouyinIE(TikTokIE):
_AID = 1128
_API_HOSTNAME = 'aweme.snssdk.com'
_UPLOADER_URL_FORMAT = 'https://www.douyin.com/user/%s'
+ _WEBPAGE_HOST = 'https://www.douyin.com/'
def _real_extract(self, url):
video_id = self._match_id(url)
render_data = self._parse_json(
render_data_json, video_id, transform_source=compat_urllib_parse_unquote)
return self._parse_aweme_video_web(
- traverse_obj(render_data, (..., 'aweme', 'detail'), get_all=False), webpage, url)
+ traverse_obj(render_data, (..., 'aweme', 'detail'), get_all=False), url)
projects / yt-dlp.git / blobdiff