]>
Commit | Line | Data |
---|---|---|
f7f18f90 | 1 | import itertools |
b801cd71 | 2 | import json |
bd9ff55b M |
3 | import random |
4 | import string | |
5 | import time | |
1ead840d KS |
6 | |
7 | from .common import InfoExtractor | |
b801cd71 | 8 | from ..compat import compat_urllib_parse_unquote, compat_urllib_parse_urlparse |
1ead840d | 9 | from ..utils import ( |
ce18a19b | 10 | ExtractorError, |
88afe056 | 11 | HEADRequest, |
b801cd71 | 12 | LazyList, |
11e1c2e3 | 13 | UnsupportedError, |
933ed882 | 14 | UserNotLive, |
a39a7ba8 | 15 | get_element_by_id, |
ff91cf74 | 16 | get_first, |
1ead840d | 17 | int_or_none, |
34921b43 | 18 | join_nonempty, |
b801cd71 | 19 | qualities, |
ba723997 | 20 | remove_start, |
e0585e65 | 21 | srt_subtitles_timecode, |
1ead840d | 22 | str_or_none, |
bd9ff55b M |
23 | traverse_obj, |
24 | try_get, | |
943d5ab1 | 25 | url_or_none, |
1ead840d KS |
26 | ) |
27 | ||
28 | ||
0fd6661e | 29 | class TikTokBaseIE(InfoExtractor): |
f7c5a5e9 | 30 | _APP_VERSIONS = [('26.1.3', '260103'), ('26.1.2', '260102'), ('26.1.1', '260101'), ('25.6.2', '250602')] |
046cab39 | 31 | _WORKING_APP_VERSION = None |
943d5ab1 M |
32 | _APP_NAME = 'trill' |
33 | _AID = 1180 | |
943d5ab1 | 34 | _UPLOADER_URL_FORMAT = 'https://www.tiktok.com/@%s' |
53dad39e | 35 | _WEBPAGE_HOST = 'https://www.tiktok.com/' |
be1f331f | 36 | QUALITIES = ('360p', '540p', '720p', '1080p') |
ce18a19b | 37 | |
c4cbd3be | 38 | @property |
39 | def _API_HOSTNAME(self): | |
40 | return self._configuration_arg( | |
41 | 'api_hostname', ['api16-normal-c-useast1a.tiktokv.com'], ie_key=TikTokIE)[0] | |
42 | ||
b801cd71 | 43 | @staticmethod |
44 | def _create_url(user_id, video_id): | |
45 | return f'https://www.tiktok.com/@{user_id or "_"}/video/{video_id}' | |
46 | ||
a39a7ba8 | 47 | def _get_sigi_state(self, webpage, display_id): |
48 | return self._parse_json(get_element_by_id( | |
49 | 'SIGI_STATE|sigi-persisted-data', webpage, escape_value=False), display_id) | |
50 | ||
046cab39 M |
51 | def _call_api_impl(self, ep, query, manifest_app_version, video_id, fatal=True, |
52 | note='Downloading API JSON', errnote='Unable to download API page'): | |
efa944f4 | 53 | self._set_cookie(self._API_HOSTNAME, 'odin_tt', ''.join(random.choices('0123456789abcdef', k=160))) |
046cab39 M |
54 | webpage_cookies = self._get_cookies(self._WEBPAGE_HOST) |
55 | if webpage_cookies.get('sid_tt'): | |
56 | self._set_cookie(self._API_HOSTNAME, 'sid_tt', webpage_cookies['sid_tt'].value) | |
57 | return self._download_json( | |
58 | 'https://%s/aweme/v1/%s/' % (self._API_HOSTNAME, ep), video_id=video_id, | |
59 | fatal=fatal, note=note, errnote=errnote, headers={ | |
ba723997 | 60 | 'User-Agent': f'com.ss.android.ugc.{self._APP_NAME}/{manifest_app_version} (Linux; U; Android 10; en_US; Pixel 4; Build/QQ3A.200805.001; Cronet/58.0.2991.0)', |
046cab39 M |
61 | 'Accept': 'application/json', |
62 | }, query=query) | |
63 | ||
64 | def _build_api_query(self, query, app_version, manifest_app_version): | |
65 | return { | |
0fd6661e | 66 | **query, |
046cab39 M |
67 | 'version_name': app_version, |
68 | 'version_code': manifest_app_version, | |
69 | 'build_number': app_version, | |
70 | 'manifest_version_code': manifest_app_version, | |
71 | 'update_version_code': manifest_app_version, | |
efa944f4 AM |
72 | 'openudid': ''.join(random.choices('0123456789abcdef', k=16)), |
73 | 'uuid': ''.join(random.choices(string.digits, k=16)), | |
bd9ff55b M |
74 | '_rticket': int(time.time() * 1000), |
75 | 'ts': int(time.time()), | |
76 | 'device_brand': 'Google', | |
77 | 'device_type': 'Pixel 4', | |
78 | 'device_platform': 'android', | |
79 | 'resolution': '1080*1920', | |
80 | 'dpi': 420, | |
81 | 'os_version': '10', | |
82 | 'os_api': '29', | |
83 | 'carrier_region': 'US', | |
84 | 'sys_region': 'US', | |
85 | 'region': 'US', | |
943d5ab1 | 86 | 'app_name': self._APP_NAME, |
bd9ff55b M |
87 | 'app_language': 'en', |
88 | 'language': 'en', | |
89 | 'timezone_name': 'America/New_York', | |
90 | 'timezone_offset': '-14400', | |
91 | 'channel': 'googleplay', | |
92 | 'ac': 'wifi', | |
93 | 'mcc_mnc': '310260', | |
94 | 'is_my_cn': 0, | |
943d5ab1 | 95 | 'aid': self._AID, |
bd9ff55b M |
96 | 'ssmix': 'a', |
97 | 'as': 'a1qwert123', | |
98 | 'cp': 'cbfhckdckkde1', | |
99 | } | |
046cab39 M |
100 | |
101 | def _call_api(self, ep, query, video_id, fatal=True, | |
102 | note='Downloading API JSON', errnote='Unable to download API page'): | |
103 | if not self._WORKING_APP_VERSION: | |
104 | app_version = self._configuration_arg('app_version', [''], ie_key=TikTokIE.ie_key())[0] | |
105 | manifest_app_version = self._configuration_arg('manifest_app_version', [''], ie_key=TikTokIE.ie_key())[0] | |
106 | if app_version and manifest_app_version: | |
107 | self._WORKING_APP_VERSION = (app_version, manifest_app_version) | |
108 | self.write_debug('Imported app version combo from extractor arguments') | |
109 | elif app_version or manifest_app_version: | |
110 | self.report_warning('Only one of the two required version params are passed as extractor arguments', only_once=True) | |
111 | ||
112 | if self._WORKING_APP_VERSION: | |
113 | app_version, manifest_app_version = self._WORKING_APP_VERSION | |
114 | real_query = self._build_api_query(query, app_version, manifest_app_version) | |
115 | return self._call_api_impl(ep, real_query, manifest_app_version, video_id, fatal, note, errnote) | |
116 | ||
117 | for count, (app_version, manifest_app_version) in enumerate(self._APP_VERSIONS, start=1): | |
118 | real_query = self._build_api_query(query, app_version, manifest_app_version) | |
119 | try: | |
120 | res = self._call_api_impl(ep, real_query, manifest_app_version, video_id, fatal, note, errnote) | |
121 | self._WORKING_APP_VERSION = (app_version, manifest_app_version) | |
122 | return res | |
123 | except ExtractorError as e: | |
124 | if isinstance(e.cause, json.JSONDecodeError) and e.cause.pos == 0: | |
125 | if count == len(self._APP_VERSIONS): | |
126 | if fatal: | |
127 | raise e | |
128 | else: | |
129 | self.report_warning(str(e.cause or e.msg)) | |
130 | return | |
131 | self.report_warning('%s. Retrying... (attempt %s of %s)' % (str(e.cause or e.msg), count, len(self._APP_VERSIONS))) | |
132 | continue | |
133 | raise e | |
0fd6661e | 134 | |
ba723997 | 135 | def _extract_aweme_app(self, aweme_id): |
136 | feed_list = self._call_api( | |
137 | 'feed', {'aweme_id': aweme_id}, aweme_id, note='Downloading video feed', | |
138 | errnote='Unable to download video feed').get('aweme_list') or [] | |
139 | aweme_detail = next((aweme for aweme in feed_list if str(aweme.get('aweme_id')) == aweme_id), None) | |
140 | if not aweme_detail: | |
141 | raise ExtractorError('Unable to find video in feed', video_id=aweme_id) | |
142 | return self._parse_aweme_video_app(aweme_detail) | |
143 | ||
e0585e65 M |
144 | def _get_subtitles(self, aweme_detail, aweme_id): |
145 | # TODO: Extract text positioning info | |
146 | subtitles = {} | |
ba723997 | 147 | # aweme/detail endpoint subs |
e0585e65 | 148 | captions_info = traverse_obj( |
ba723997 | 149 | aweme_detail, ('interaction_stickers', ..., 'auto_video_caption_info', 'auto_captions', ...), expected_type=dict) |
e0585e65 M |
150 | for caption in captions_info: |
151 | caption_url = traverse_obj(caption, ('url', 'url_list', ...), expected_type=url_or_none, get_all=False) | |
152 | if not caption_url: | |
153 | continue | |
154 | caption_json = self._download_json( | |
155 | caption_url, aweme_id, note='Downloading captions', errnote='Unable to download captions', fatal=False) | |
156 | if not caption_json: | |
157 | continue | |
158 | subtitles.setdefault(caption.get('language', 'en'), []).append({ | |
159 | 'ext': 'srt', | |
160 | 'data': '\n\n'.join( | |
161 | f'{i + 1}\n{srt_subtitles_timecode(line["start_time"] / 1000)} --> {srt_subtitles_timecode(line["end_time"] / 1000)}\n{line["text"]}' | |
162 | for i, line in enumerate(caption_json['utterances']) if line.get('text')) | |
163 | }) | |
ba723997 | 164 | # feed endpoint subs |
165 | if not subtitles: | |
166 | for caption in traverse_obj(aweme_detail, ('video', 'cla_info', 'caption_infos', ...), expected_type=dict): | |
167 | if not caption.get('url'): | |
168 | continue | |
169 | subtitles.setdefault(caption.get('lang') or 'en', []).append({ | |
170 | 'ext': remove_start(caption.get('caption_format'), 'web'), | |
171 | 'url': caption['url'], | |
172 | }) | |
173 | # webpage subs | |
174 | if not subtitles: | |
175 | for caption in traverse_obj(aweme_detail, ('video', 'subtitleInfos', ...), expected_type=dict): | |
176 | if not caption.get('Url'): | |
177 | continue | |
178 | subtitles.setdefault(caption.get('LanguageCodeName') or 'en', []).append({ | |
179 | 'ext': remove_start(caption.get('Format'), 'web'), | |
180 | 'url': caption['Url'], | |
181 | }) | |
e0585e65 M |
182 | return subtitles |
183 | ||
943d5ab1 | 184 | def _parse_aweme_video_app(self, aweme_detail): |
0fd6661e | 185 | aweme_id = aweme_detail['aweme_id'] |
bd9ff55b M |
186 | video_info = aweme_detail['video'] |
187 | ||
188 | def parse_url_key(url_key): | |
189 | format_id, codec, res, bitrate = self._search_regex( | |
190 | r'v[^_]+_(?P<id>(?P<codec>[^_]+)_(?P<res>\d+p)_(?P<bitrate>\d+))', url_key, | |
191 | 'url key', default=(None, None, None, None), group=('id', 'codec', 'res', 'bitrate')) | |
192 | if not format_id: | |
193 | return {}, None | |
194 | return { | |
195 | 'format_id': format_id, | |
196 | 'vcodec': 'h265' if codec == 'bytevc1' else codec, | |
197 | 'tbr': int_or_none(bitrate, scale=1000) or None, | |
198 | 'quality': qualities(self.QUALITIES)(res), | |
199 | }, res | |
200 | ||
201 | known_resolutions = {} | |
202 | ||
203 | def extract_addr(addr, add_meta={}): | |
204 | parsed_meta, res = parse_url_key(addr.get('url_key', '')) | |
205 | if res: | |
206 | known_resolutions.setdefault(res, {}).setdefault('height', add_meta.get('height')) | |
207 | known_resolutions[res].setdefault('width', add_meta.get('width')) | |
208 | parsed_meta.update(known_resolutions.get(res, {})) | |
209 | add_meta.setdefault('height', int_or_none(res[:-1])) | |
210 | return [{ | |
211 | 'url': url, | |
212 | 'filesize': int_or_none(addr.get('data_size')), | |
213 | 'ext': 'mp4', | |
214 | 'acodec': 'aac', | |
0fd6661e M |
215 | 'source_preference': -2 if 'aweme/v1' in url else -1, # Downloads from API might get blocked |
216 | **add_meta, **parsed_meta, | |
34921b43 | 217 | 'format_note': join_nonempty( |
218 | add_meta.get('format_note'), '(API)' if 'aweme/v1' in url else None, delim=' ') | |
bd9ff55b M |
219 | } for url in addr.get('url_list') or []] |
220 | ||
221 | # Hack: Add direct video links first to prioritize them when removing duplicate formats | |
222 | formats = [] | |
223 | if video_info.get('play_addr'): | |
224 | formats.extend(extract_addr(video_info['play_addr'], { | |
225 | 'format_id': 'play_addr', | |
226 | 'format_note': 'Direct video', | |
227 | 'vcodec': 'h265' if traverse_obj( | |
be1f331f | 228 | video_info, 'is_bytevc1', 'is_h265') else 'h264', # TODO: Check for "direct iOS" videos, like https://www.tiktok.com/@cookierun_dev/video/7039716639834656002 |
bd9ff55b M |
229 | 'width': video_info.get('width'), |
230 | 'height': video_info.get('height'), | |
231 | })) | |
232 | if video_info.get('download_addr'): | |
233 | formats.extend(extract_addr(video_info['download_addr'], { | |
234 | 'format_id': 'download_addr', | |
235 | 'format_note': 'Download video%s' % (', watermarked' if video_info.get('has_watermark') else ''), | |
236 | 'vcodec': 'h264', | |
237 | 'width': video_info.get('width'), | |
238 | 'height': video_info.get('height'), | |
0fd6661e | 239 | 'preference': -2 if video_info.get('has_watermark') else -1, |
bd9ff55b M |
240 | })) |
241 | if video_info.get('play_addr_h264'): | |
242 | formats.extend(extract_addr(video_info['play_addr_h264'], { | |
243 | 'format_id': 'play_addr_h264', | |
244 | 'format_note': 'Direct video', | |
245 | 'vcodec': 'h264', | |
246 | })) | |
247 | if video_info.get('play_addr_bytevc1'): | |
248 | formats.extend(extract_addr(video_info['play_addr_bytevc1'], { | |
249 | 'format_id': 'play_addr_bytevc1', | |
250 | 'format_note': 'Direct video', | |
251 | 'vcodec': 'h265', | |
252 | })) | |
253 | ||
254 | for bitrate in video_info.get('bit_rate', []): | |
255 | if bitrate.get('play_addr'): | |
256 | formats.extend(extract_addr(bitrate['play_addr'], { | |
257 | 'format_id': bitrate.get('gear_name'), | |
258 | 'format_note': 'Playback video', | |
259 | 'tbr': try_get(bitrate, lambda x: x['bit_rate'] / 1000), | |
260 | 'vcodec': 'h265' if traverse_obj( | |
261 | bitrate, 'is_bytevc1', 'is_h265') else 'h264', | |
943d5ab1 | 262 | 'fps': bitrate.get('FPS'), |
bd9ff55b M |
263 | })) |
264 | ||
265 | self._remove_duplicate_formats(formats) | |
6134fbeb M |
266 | auth_cookie = self._get_cookies(self._WEBPAGE_HOST).get('sid_tt') |
267 | if auth_cookie: | |
268 | for f in formats: | |
be1f331f | 269 | self._set_cookie(compat_urllib_parse_urlparse(f['url']).hostname, 'sid_tt', auth_cookie.value) |
bd9ff55b M |
270 | |
271 | thumbnails = [] | |
272 | for cover_id in ('cover', 'ai_dynamic_cover', 'animated_cover', 'ai_dynamic_cover_bak', | |
273 | 'origin_cover', 'dynamic_cover'): | |
274 | cover = video_info.get(cover_id) | |
275 | if cover: | |
276 | for cover_url in cover['url_list']: | |
277 | thumbnails.append({ | |
278 | 'id': cover_id, | |
279 | 'url': cover_url, | |
280 | }) | |
281 | ||
282 | stats_info = aweme_detail.get('statistics', {}) | |
283 | author_info = aweme_detail.get('author', {}) | |
284 | music_info = aweme_detail.get('music', {}) | |
943d5ab1 M |
285 | user_url = self._UPLOADER_URL_FORMAT % (traverse_obj(author_info, |
286 | 'sec_uid', 'id', 'uid', 'unique_id', | |
287 | expected_type=str_or_none, get_all=False)) | |
6839ae1f | 288 | labels = traverse_obj(aweme_detail, ('hybrid_label', ..., 'text'), expected_type=str) |
bd9ff55b M |
289 | |
290 | contained_music_track = traverse_obj( | |
291 | music_info, ('matched_song', 'title'), ('matched_pgc_sound', 'title'), expected_type=str) | |
292 | contained_music_author = traverse_obj( | |
293 | music_info, ('matched_song', 'author'), ('matched_pgc_sound', 'author'), 'author', expected_type=str) | |
294 | ||
295 | is_generic_og_trackname = music_info.get('is_original_sound') and music_info.get('title') == 'original sound - %s' % music_info.get('owner_handle') | |
296 | if is_generic_og_trackname: | |
297 | music_track, music_author = contained_music_track or 'original sound', contained_music_author | |
298 | else: | |
299 | music_track, music_author = music_info.get('title'), music_info.get('author') | |
300 | ||
301 | return { | |
302 | 'id': aweme_id, | |
a39a7ba8 | 303 | 'extractor_key': TikTokIE.ie_key(), |
304 | 'extractor': TikTokIE.IE_NAME, | |
305 | 'webpage_url': self._create_url(author_info.get('uid'), aweme_id), | |
5fa3c9a8 | 306 | 'title': aweme_detail.get('desc'), |
a44ca5a4 | 307 | 'description': aweme_detail.get('desc'), |
bd9ff55b M |
308 | 'view_count': int_or_none(stats_info.get('play_count')), |
309 | 'like_count': int_or_none(stats_info.get('digg_count')), | |
310 | 'repost_count': int_or_none(stats_info.get('share_count')), | |
311 | 'comment_count': int_or_none(stats_info.get('comment_count')), | |
312 | 'uploader': str_or_none(author_info.get('unique_id')), | |
943d5ab1 | 313 | 'creator': str_or_none(author_info.get('nickname')), |
bd9ff55b | 314 | 'uploader_id': str_or_none(author_info.get('uid')), |
943d5ab1 | 315 | 'uploader_url': user_url, |
bd9ff55b M |
316 | 'track': music_track, |
317 | 'album': str_or_none(music_info.get('album')) or None, | |
f7c5a5e9 | 318 | 'artist': music_author or None, |
bd9ff55b M |
319 | 'timestamp': int_or_none(aweme_detail.get('create_time')), |
320 | 'formats': formats, | |
e0585e65 | 321 | 'subtitles': self.extract_subtitles(aweme_detail, aweme_id), |
bd9ff55b | 322 | 'thumbnails': thumbnails, |
53dad39e M |
323 | 'duration': int_or_none(traverse_obj(video_info, 'duration', ('download_addr', 'duration')), scale=1000), |
324 | 'availability': self._availability( | |
325 | is_private='Private' in labels, | |
326 | needs_subscription='Friends only' in labels, | |
9f14daf2 | 327 | is_unlisted='Followers only' in labels), |
328 | '_format_sort_fields': ('quality', 'codec', 'size', 'br'), | |
bd9ff55b M |
329 | } |
330 | ||
0481e266 | 331 | def _parse_aweme_video_web(self, aweme_detail, webpage_url): |
943d5ab1 | 332 | video_info = aweme_detail['video'] |
11aa91a1 | 333 | author_info = traverse_obj(aweme_detail, 'authorInfo', 'author', expected_type=dict, default={}) |
943d5ab1 M |
334 | music_info = aweme_detail.get('music') or {} |
335 | stats_info = aweme_detail.get('stats') or {} | |
336 | user_url = self._UPLOADER_URL_FORMAT % (traverse_obj(author_info, | |
337 | 'secUid', 'id', 'uid', 'uniqueId', | |
11aa91a1 M |
338 | expected_type=str_or_none, get_all=False) |
339 | or aweme_detail.get('authorSecId')) | |
943d5ab1 M |
340 | |
341 | formats = [] | |
342 | play_url = video_info.get('playAddr') | |
343 | width = video_info.get('width') | |
344 | height = video_info.get('height') | |
345 | if isinstance(play_url, str): | |
346 | formats = [{ | |
347 | 'url': self._proto_relative_url(play_url), | |
348 | 'ext': 'mp4', | |
349 | 'width': width, | |
350 | 'height': height, | |
351 | }] | |
352 | elif isinstance(play_url, list): | |
353 | formats = [{ | |
354 | 'url': self._proto_relative_url(url), | |
355 | 'ext': 'mp4', | |
356 | 'width': width, | |
357 | 'height': height, | |
6839ae1f | 358 | } for url in traverse_obj(play_url, (..., 'src'), expected_type=url_or_none) if url] |
943d5ab1 M |
359 | |
360 | download_url = url_or_none(video_info.get('downloadAddr')) or traverse_obj(video_info, ('download', 'url'), expected_type=url_or_none) | |
361 | if download_url: | |
362 | formats.append({ | |
363 | 'format_id': 'download', | |
364 | 'url': self._proto_relative_url(download_url), | |
365 | 'ext': 'mp4', | |
366 | 'width': width, | |
367 | 'height': height, | |
368 | }) | |
369 | self._remove_duplicate_formats(formats) | |
943d5ab1 M |
370 | |
371 | thumbnails = [] | |
372 | for thumbnail_name in ('thumbnail', 'cover', 'dynamicCover', 'originCover'): | |
373 | if aweme_detail.get(thumbnail_name): | |
374 | thumbnails = [{ | |
375 | 'url': self._proto_relative_url(aweme_detail[thumbnail_name]), | |
376 | 'width': width, | |
377 | 'height': height | |
378 | }] | |
379 | ||
380 | return { | |
381 | 'id': traverse_obj(aweme_detail, 'id', 'awemeId', expected_type=str_or_none), | |
382 | 'title': aweme_detail.get('desc'), | |
383 | 'duration': try_get(aweme_detail, lambda x: x['video']['duration'], int), | |
384 | 'view_count': int_or_none(stats_info.get('playCount')), | |
385 | 'like_count': int_or_none(stats_info.get('diggCount')), | |
386 | 'repost_count': int_or_none(stats_info.get('shareCount')), | |
387 | 'comment_count': int_or_none(stats_info.get('commentCount')), | |
388 | 'timestamp': int_or_none(aweme_detail.get('createTime')), | |
389 | 'creator': str_or_none(author_info.get('nickname')), | |
11aa91a1 | 390 | 'uploader': str_or_none(author_info.get('uniqueId') or aweme_detail.get('author')), |
ba723997 | 391 | 'uploader_id': str_or_none(traverse_obj(author_info, 'id', 'uid', 'authorId')), |
943d5ab1 M |
392 | 'uploader_url': user_url, |
393 | 'track': str_or_none(music_info.get('title')), | |
394 | 'album': str_or_none(music_info.get('album')) or None, | |
395 | 'artist': str_or_none(music_info.get('authorName')), | |
396 | 'formats': formats, | |
397 | 'thumbnails': thumbnails, | |
398 | 'description': str_or_none(aweme_detail.get('desc')), | |
399 | 'http_headers': { | |
0481e266 | 400 | 'Referer': webpage_url |
943d5ab1 M |
401 | } |
402 | } | |
403 | ||
0fd6661e M |
404 | |
405 | class TikTokIE(TikTokBaseIE): | |
c4cbd3be | 406 | _VALID_URL = r'https?://www\.tiktok\.com/(?:embed|@(?P<user_id>[\w\.-]+)?/video)/(?P<id>\d+)' |
bfd973ec | 407 | _EMBED_REGEX = [rf'<(?:script|iframe)[^>]+\bsrc=(["\'])(?P<url>{_VALID_URL})'] |
0fd6661e M |
408 | |
409 | _TESTS = [{ | |
410 | 'url': 'https://www.tiktok.com/@leenabhushan/video/6748451240264420610', | |
0481e266 | 411 | 'md5': '736bb7a466c6f0a6afeb597da1e6f5b7', |
0fd6661e M |
412 | 'info_dict': { |
413 | 'id': '6748451240264420610', | |
414 | 'ext': 'mp4', | |
415 | 'title': '#jassmanak #lehanga #leenabhushan', | |
416 | 'description': '#jassmanak #lehanga #leenabhushan', | |
417 | 'duration': 13, | |
0481e266 | 418 | 'height': 1024, |
419 | 'width': 576, | |
0fd6661e M |
420 | 'uploader': 'leenabhushan', |
421 | 'uploader_id': '6691488002098119685', | |
0481e266 | 422 | 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA_Eb4t1vodM1IuTy_cvp9CY22RAb59xqrO0Xtz9CYQJvgXaDvZxYnZYRzDWhhgJmy', |
0fd6661e M |
423 | 'creator': 'facestoriesbyleenabh', |
424 | 'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?', | |
425 | 'upload_date': '20191016', | |
426 | 'timestamp': 1571246252, | |
427 | 'view_count': int, | |
428 | 'like_count': int, | |
429 | 'repost_count': int, | |
430 | 'comment_count': int, | |
a44ca5a4 | 431 | 'artist': 'Ysrbeats', |
432 | 'album': 'Lehanga', | |
433 | 'track': 'Lehanga', | |
0fd6661e M |
434 | } |
435 | }, { | |
436 | 'url': 'https://www.tiktok.com/@patroxofficial/video/6742501081818877190?langCountry=en', | |
0481e266 | 437 | 'md5': '6f3cf8cdd9b28cb8363fe0a9a160695b', |
0fd6661e M |
438 | 'info_dict': { |
439 | 'id': '6742501081818877190', | |
440 | 'ext': 'mp4', | |
441 | 'title': 'md5:5e2a23877420bb85ce6521dbee39ba94', | |
442 | 'description': 'md5:5e2a23877420bb85ce6521dbee39ba94', | |
443 | 'duration': 27, | |
444 | 'height': 960, | |
445 | 'width': 540, | |
446 | 'uploader': 'patrox', | |
447 | 'uploader_id': '18702747', | |
0481e266 | 448 | 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws', |
0fd6661e M |
449 | 'creator': 'patroX', |
450 | 'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?', | |
451 | 'upload_date': '20190930', | |
452 | 'timestamp': 1569860870, | |
453 | 'view_count': int, | |
454 | 'like_count': int, | |
455 | 'repost_count': int, | |
456 | 'comment_count': int, | |
a44ca5a4 | 457 | 'artist': 'Evan Todd, Jessica Keenan Wynn, Alice Lee, Barrett Wilbert Weed & Jon Eidson', |
458 | 'track': 'Big Fun', | |
0fd6661e M |
459 | } |
460 | }, { | |
96f13f01 M |
461 | # Banned audio, only available on the app |
462 | 'url': 'https://www.tiktok.com/@barudakhb_/video/6984138651336838402', | |
463 | 'info_dict': { | |
464 | 'id': '6984138651336838402', | |
465 | 'ext': 'mp4', | |
466 | 'title': 'Balas @yolaaftwsr hayu yu ? #SquadRandom_ 🔥', | |
467 | 'description': 'Balas @yolaaftwsr hayu yu ? #SquadRandom_ 🔥', | |
468 | 'uploader': 'barudakhb_', | |
469 | 'creator': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6', | |
470 | 'uploader_id': '6974687867511718913', | |
471 | 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAbhBwQC-R1iKoix6jDFsF-vBdfx2ABoDjaZrM9fX6arU3w71q3cOWgWuTXn1soZ7d', | |
472 | 'track': 'Boka Dance', | |
473 | 'artist': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6', | |
474 | 'timestamp': 1626121503, | |
475 | 'duration': 18, | |
476 | 'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?', | |
477 | 'upload_date': '20210712', | |
478 | 'view_count': int, | |
479 | 'like_count': int, | |
480 | 'repost_count': int, | |
481 | 'comment_count': int, | |
482 | } | |
483 | }, { | |
484 | # Sponsored video, only available with feed workaround | |
485 | 'url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_/video/7042692929109986561', | |
486 | 'info_dict': { | |
487 | 'id': '7042692929109986561', | |
488 | 'ext': 'mp4', | |
489 | 'title': 'Slap and Run!', | |
490 | 'description': 'Slap and Run!', | |
491 | 'uploader': 'user440922249', | |
492 | 'creator': 'Slap And Run', | |
493 | 'uploader_id': '7036055384943690754', | |
494 | 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_', | |
495 | 'track': 'Promoted Music', | |
496 | 'timestamp': 1639754738, | |
497 | 'duration': 30, | |
498 | 'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?', | |
499 | 'upload_date': '20211217', | |
500 | 'view_count': int, | |
501 | 'like_count': int, | |
502 | 'repost_count': int, | |
503 | 'comment_count': int, | |
504 | }, | |
a39a7ba8 | 505 | 'expected_warnings': ['trying with webpage', 'Unable to find video in feed'] |
5fa3c9a8 HTL |
506 | }, { |
507 | # Video without title and description | |
508 | 'url': 'https://www.tiktok.com/@pokemonlife22/video/7059698374567611694', | |
509 | 'info_dict': { | |
510 | 'id': '7059698374567611694', | |
511 | 'ext': 'mp4', | |
b801cd71 | 512 | 'title': 'TikTok video #7059698374567611694', |
5fa3c9a8 HTL |
513 | 'description': '', |
514 | 'uploader': 'pokemonlife22', | |
515 | 'creator': 'Pokemon', | |
516 | 'uploader_id': '6820838815978423302', | |
517 | 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA0tF1nBwQVVMyrGu3CqttkNgM68Do1OXUFuCY0CRQk8fEtSVDj89HqoqvbSTmUP2W', | |
518 | 'track': 'original sound', | |
519 | 'timestamp': 1643714123, | |
520 | 'duration': 6, | |
521 | 'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?', | |
522 | 'upload_date': '20220201', | |
523 | 'artist': 'Pokemon', | |
524 | 'view_count': int, | |
525 | 'like_count': int, | |
526 | 'repost_count': int, | |
527 | 'comment_count': int, | |
528 | }, | |
a39a7ba8 | 529 | }, { |
530 | # hydration JSON is sent in a <script> element | |
531 | 'url': 'https://www.tiktok.com/@denidil6/video/7065799023130643713', | |
532 | 'info_dict': { | |
533 | 'id': '7065799023130643713', | |
534 | 'ext': 'mp4', | |
535 | 'title': '#denidil#денидил', | |
536 | 'description': '#denidil#денидил', | |
537 | 'uploader': 'denidil6', | |
538 | 'uploader_id': '7046664115636405250', | |
539 | 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAsvMSzFdQ4ikl3uR2TEJwMBbB2yZh2Zxwhx-WCo3rbDpAharE3GQCrFuJArI3C8QJ', | |
540 | 'artist': 'Holocron Music', | |
541 | 'album': 'Wolf Sounds (1 Hour) Enjoy the Company of the Animal That Is the Majestic King of the Night', | |
542 | 'track': 'Wolf Sounds (1 Hour) Enjoy the Company of the Animal That Is the Majestic King of the Night', | |
543 | 'timestamp': 1645134536, | |
544 | 'duration': 26, | |
545 | 'upload_date': '20220217', | |
546 | 'view_count': int, | |
547 | 'like_count': int, | |
548 | 'repost_count': int, | |
549 | 'comment_count': int, | |
550 | }, | |
f7c5a5e9 | 551 | 'skip': 'This video is unavailable', |
e0585e65 M |
552 | }, { |
553 | # Auto-captions available | |
554 | 'url': 'https://www.tiktok.com/@hankgreen1/video/7047596209028074758', | |
555 | 'only_matching': True | |
0fd6661e M |
556 | }] |
557 | ||
ce18a19b | 558 | def _real_extract(self, url): |
b801cd71 | 559 | video_id, user_id = self._match_valid_url(url).group('id', 'user_id') |
bd9ff55b M |
560 | try: |
561 | return self._extract_aweme_app(video_id) | |
562 | except ExtractorError as e: | |
a39a7ba8 | 563 | self.report_warning(f'{e}; trying with webpage') |
bd9ff55b | 564 | |
a39a7ba8 | 565 | url = self._create_url(user_id, video_id) |
566 | webpage = self._download_webpage(url, video_id, headers={'User-Agent': 'User-Agent:Mozilla/5.0'}) | |
135dfa2c | 567 | next_data = self._search_nextjs_data(webpage, video_id, default='{}') |
135dfa2c | 568 | if next_data: |
11aa91a1 M |
569 | status = traverse_obj(next_data, ('props', 'pageProps', 'statusCode'), expected_type=int) or 0 |
570 | video_data = traverse_obj(next_data, ('props', 'pageProps', 'itemInfo', 'itemStruct'), expected_type=dict) | |
571 | else: | |
a39a7ba8 | 572 | sigi_data = self._get_sigi_state(webpage, video_id) |
11aa91a1 M |
573 | status = traverse_obj(sigi_data, ('VideoPage', 'statusCode'), expected_type=int) or 0 |
574 | video_data = traverse_obj(sigi_data, ('ItemModule', video_id), expected_type=dict) | |
575 | ||
1418a043 | 576 | if status == 0: |
11aa91a1 | 577 | return self._parse_aweme_video_web(video_data, url) |
1418a043 | 578 | elif status == 10216: |
579 | raise ExtractorError('This video is private', expected=True) | |
6fb11ca8 | 580 | raise ExtractorError('Video not available', video_id=video_id) |
f7f18f90 A |
581 | |
582 | ||
0fd6661e | 583 | class TikTokUserIE(TikTokBaseIE): |
f7f18f90 | 584 | IE_NAME = 'tiktok:user' |
0fd6661e | 585 | _VALID_URL = r'https?://(?:www\.)?tiktok\.com/@(?P<id>[\w\.-]+)/?(?:$|[#?])' |
f7c5a5e9 | 586 | _WORKING = False |
f7f18f90 | 587 | _TESTS = [{ |
526d74ec | 588 | 'url': 'https://tiktok.com/@corgibobaa?lang=en', |
f7f18f90 A |
589 | 'playlist_mincount': 45, |
590 | 'info_dict': { | |
591 | 'id': '6935371178089399301', | |
0481e266 | 592 | 'title': 'corgibobaa', |
b3187433 | 593 | 'thumbnail': r're:https://.+_1080x1080\.webp' |
f7f18f90 | 594 | }, |
0481e266 | 595 | 'expected_warnings': ['Retrying'] |
5fa3c9a8 HTL |
596 | }, { |
597 | 'url': 'https://www.tiktok.com/@6820838815978423302', | |
598 | 'playlist_mincount': 5, | |
599 | 'info_dict': { | |
600 | 'id': '6820838815978423302', | |
601 | 'title': '6820838815978423302', | |
602 | 'thumbnail': r're:https://.+_1080x1080\.webp' | |
603 | }, | |
604 | 'expected_warnings': ['Retrying'] | |
f7f18f90 A |
605 | }, { |
606 | 'url': 'https://www.tiktok.com/@meme', | |
607 | 'playlist_mincount': 593, | |
608 | 'info_dict': { | |
609 | 'id': '79005827461758976', | |
0481e266 | 610 | 'title': 'meme', |
b3187433 | 611 | 'thumbnail': r're:https://.+_1080x1080\.webp' |
f7f18f90 | 612 | }, |
0481e266 | 613 | 'expected_warnings': ['Retrying'] |
f7f18f90 A |
614 | }] |
615 | ||
0fd6661e M |
616 | r''' # TODO: Fix by adding _signature to api_url |
617 | def _entries(self, webpage, user_id, username): | |
618 | secuid = self._search_regex(r'\"secUid\":\"(?P<secUid>[^\"]+)', webpage, username) | |
f7f18f90 A |
619 | verifyfp_cookie = self._get_cookies('https://www.tiktok.com').get('s_v_web_id') |
620 | if not verifyfp_cookie: | |
621 | raise ExtractorError('Improper cookies (missing s_v_web_id).', expected=True) | |
622 | 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=' | |
623 | cursor = '0' | |
624 | for page in itertools.count(): | |
0fd6661e | 625 | data_json = self._download_json(api_url + cursor, username, note='Downloading Page %d' % page) |
f7f18f90 A |
626 | for video in data_json.get('itemList', []): |
627 | video_id = video['id'] | |
628 | video_url = f'https://www.tiktok.com/@{user_id}/video/{video_id}' | |
bd9ff55b | 629 | yield self._url_result(video_url, 'TikTok', video_id, str_or_none(video.get('desc'))) |
526d74ec | 630 | if not data_json.get('hasMore'): |
f7f18f90 A |
631 | break |
632 | cursor = data_json['cursor'] | |
0fd6661e M |
633 | ''' |
634 | ||
b3187433 | 635 | def _video_entries_api(self, webpage, user_id, username): |
0fd6661e M |
636 | query = { |
637 | 'user_id': user_id, | |
638 | 'count': 21, | |
639 | 'max_cursor': 0, | |
640 | 'min_cursor': 0, | |
641 | 'retry_type': 'no_retry', | |
efa944f4 | 642 | '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. |
0fd6661e M |
643 | } |
644 | ||
0fd6661e | 645 | for page in itertools.count(1): |
be5c1ae8 | 646 | for retry in self.RetryManager(): |
0fd6661e | 647 | try: |
be5c1ae8 | 648 | post_list = self._call_api( |
649 | 'aweme/post', query, username, note=f'Downloading user video list page {page}', | |
650 | errnote='Unable to download user video list') | |
0fd6661e | 651 | except ExtractorError as e: |
be5c1ae8 | 652 | if isinstance(e.cause, json.JSONDecodeError) and e.cause.pos == 0: |
653 | retry.error = e | |
0fd6661e M |
654 | continue |
655 | raise | |
b3187433 | 656 | yield from post_list.get('aweme_list', []) |
0fd6661e M |
657 | if not post_list.get('has_more'): |
658 | break | |
659 | query['max_cursor'] = post_list['max_cursor'] | |
f7f18f90 | 660 | |
b3187433 | 661 | def _entries_api(self, user_id, videos): |
662 | for video in videos: | |
663 | yield { | |
664 | **self._parse_aweme_video_app(video), | |
665 | 'extractor_key': TikTokIE.ie_key(), | |
666 | 'extractor': 'TikTok', | |
667 | 'webpage_url': f'https://tiktok.com/@{user_id}/video/{video["aweme_id"]}', | |
668 | } | |
669 | ||
f7f18f90 | 670 | def _real_extract(self, url): |
0481e266 | 671 | user_name = self._match_id(url) |
672 | webpage = self._download_webpage(url, user_name, headers={ | |
0fd6661e M |
673 | 'User-Agent': 'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)' |
674 | }) | |
5fa3c9a8 | 675 | user_id = self._html_search_regex(r'snssdk\d*://user/profile/(\d+)', webpage, 'user ID', default=None) or user_name |
b3187433 | 676 | |
677 | videos = LazyList(self._video_entries_api(webpage, user_id, user_name)) | |
678 | thumbnail = traverse_obj(videos, (0, 'author', 'avatar_larger', 'url_list', 0)) | |
679 | ||
680 | return self.playlist_result(self._entries_api(user_id, videos), user_id, user_name, thumbnail=thumbnail) | |
943d5ab1 M |
681 | |
682 | ||
6368e2e6 | 683 | class TikTokBaseListIE(TikTokBaseIE): # XXX: Conventionally, base classes should end with BaseIE/InfoExtractor |
8126298c M |
684 | def _entries(self, list_id, display_id): |
685 | query = { | |
686 | self._QUERY_NAME: list_id, | |
687 | 'cursor': 0, | |
688 | 'count': 20, | |
689 | 'type': 5, | |
efa944f4 | 690 | 'device_id': ''.join(random.choices(string.digits, k=19)) |
8126298c M |
691 | } |
692 | ||
8126298c | 693 | for page in itertools.count(1): |
be5c1ae8 | 694 | for retry in self.RetryManager(): |
8126298c | 695 | try: |
be5c1ae8 | 696 | post_list = self._call_api( |
697 | self._API_ENDPOINT, query, display_id, note=f'Downloading video list page {page}', | |
698 | errnote='Unable to download video list') | |
8126298c | 699 | except ExtractorError as e: |
be5c1ae8 | 700 | if isinstance(e.cause, json.JSONDecodeError) and e.cause.pos == 0: |
701 | retry.error = e | |
8126298c M |
702 | continue |
703 | raise | |
8126298c M |
704 | for video in post_list.get('aweme_list', []): |
705 | yield { | |
706 | **self._parse_aweme_video_app(video), | |
0b77924a | 707 | 'extractor_key': TikTokIE.ie_key(), |
8126298c M |
708 | 'extractor': 'TikTok', |
709 | 'webpage_url': f'https://tiktok.com/@_/video/{video["aweme_id"]}', | |
710 | } | |
711 | if not post_list.get('has_more'): | |
712 | break | |
713 | query['cursor'] = post_list['cursor'] | |
714 | ||
715 | def _real_extract(self, url): | |
716 | list_id = self._match_id(url) | |
717 | return self.playlist_result(self._entries(list_id, list_id), list_id) | |
718 | ||
719 | ||
720 | class TikTokSoundIE(TikTokBaseListIE): | |
721 | IE_NAME = 'tiktok:sound' | |
722 | _VALID_URL = r'https?://(?:www\.)?tiktok\.com/music/[\w\.-]+-(?P<id>[\d]+)[/?#&]?' | |
f7c5a5e9 | 723 | _WORKING = False |
8126298c M |
724 | _QUERY_NAME = 'music_id' |
725 | _API_ENDPOINT = 'music/aweme' | |
726 | _TESTS = [{ | |
727 | 'url': 'https://www.tiktok.com/music/Build-a-Btch-6956990112127585029?lang=en', | |
728 | 'playlist_mincount': 100, | |
729 | 'info_dict': { | |
730 | 'id': '6956990112127585029' | |
731 | }, | |
732 | 'expected_warnings': ['Retrying'] | |
733 | }, { | |
734 | # Actual entries are less than listed video count | |
735 | 'url': 'https://www.tiktok.com/music/jiefei-soap-remix-7036843036118469381', | |
736 | 'playlist_mincount': 2182, | |
737 | 'info_dict': { | |
738 | 'id': '7036843036118469381' | |
739 | }, | |
740 | 'expected_warnings': ['Retrying'] | |
741 | }] | |
742 | ||
743 | ||
744 | class TikTokEffectIE(TikTokBaseListIE): | |
745 | IE_NAME = 'tiktok:effect' | |
746 | _VALID_URL = r'https?://(?:www\.)?tiktok\.com/sticker/[\w\.-]+-(?P<id>[\d]+)[/?#&]?' | |
f7c5a5e9 | 747 | _WORKING = False |
8126298c M |
748 | _QUERY_NAME = 'sticker_id' |
749 | _API_ENDPOINT = 'sticker/aweme' | |
750 | _TESTS = [{ | |
751 | 'url': 'https://www.tiktok.com/sticker/MATERIAL-GWOOORL-1258156', | |
752 | 'playlist_mincount': 100, | |
753 | 'info_dict': { | |
754 | 'id': '1258156', | |
755 | }, | |
756 | 'expected_warnings': ['Retrying'] | |
757 | }, { | |
758 | # Different entries between mobile and web, depending on region | |
759 | 'url': 'https://www.tiktok.com/sticker/Elf-Friend-479565', | |
760 | 'only_matching': True | |
761 | }] | |
762 | ||
763 | ||
764 | class TikTokTagIE(TikTokBaseListIE): | |
765 | IE_NAME = 'tiktok:tag' | |
766 | _VALID_URL = r'https?://(?:www\.)?tiktok\.com/tag/(?P<id>[^/?#&]+)' | |
f7c5a5e9 | 767 | _WORKING = False |
8126298c M |
768 | _QUERY_NAME = 'ch_id' |
769 | _API_ENDPOINT = 'challenge/aweme' | |
770 | _TESTS = [{ | |
771 | 'url': 'https://tiktok.com/tag/hello2018', | |
772 | 'playlist_mincount': 39, | |
773 | 'info_dict': { | |
774 | 'id': '46294678', | |
775 | 'title': 'hello2018', | |
776 | }, | |
777 | 'expected_warnings': ['Retrying'] | |
778 | }, { | |
779 | 'url': 'https://tiktok.com/tag/fypシ?is_copy_url=0&is_from_webapp=v1', | |
780 | 'only_matching': True | |
781 | }] | |
782 | ||
783 | def _real_extract(self, url): | |
784 | display_id = self._match_id(url) | |
785 | webpage = self._download_webpage(url, display_id, headers={ | |
786 | 'User-Agent': 'facebookexternalhit/1.1 (+http://www.facebook.com/externalhit_uatext.php)' | |
787 | }) | |
788 | tag_id = self._html_search_regex(r'snssdk\d*://challenge/detail/(\d+)', webpage, 'tag ID') | |
789 | return self.playlist_result(self._entries(tag_id, display_id), tag_id, display_id) | |
790 | ||
791 | ||
ba723997 | 792 | class DouyinIE(TikTokBaseIE): |
943d5ab1 M |
793 | _VALID_URL = r'https?://(?:www\.)?douyin\.com/video/(?P<id>[0-9]+)' |
794 | _TESTS = [{ | |
795 | 'url': 'https://www.douyin.com/video/6961737553342991651', | |
ba723997 | 796 | 'md5': 'a97db7e3e67eb57bf40735c022ffa228', |
943d5ab1 M |
797 | 'info_dict': { |
798 | 'id': '6961737553342991651', | |
799 | 'ext': 'mp4', | |
800 | 'title': '#杨超越 小小水手带你去远航❤️', | |
ba723997 | 801 | 'description': '#杨超越 小小水手带你去远航❤️', |
943d5ab1 | 802 | 'uploader_id': '110403406559', |
ba723997 | 803 | 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', |
804 | 'creator': '杨超越', | |
805 | 'duration': 19782, | |
806 | 'timestamp': 1620905839, | |
807 | 'upload_date': '20210513', | |
808 | 'track': '@杨超越创作的原声', | |
943d5ab1 M |
809 | 'view_count': int, |
810 | 'like_count': int, | |
811 | 'repost_count': int, | |
812 | 'comment_count': int, | |
ba723997 | 813 | }, |
943d5ab1 M |
814 | }, { |
815 | 'url': 'https://www.douyin.com/video/6982497745948921092', | |
ba723997 | 816 | 'md5': '34a87ebff3833357733da3fe17e37c0e', |
943d5ab1 M |
817 | 'info_dict': { |
818 | 'id': '6982497745948921092', | |
819 | 'ext': 'mp4', | |
820 | 'title': '这个夏日和小羊@杨超越 一起遇见白色幻想', | |
ba723997 | 821 | 'description': '这个夏日和小羊@杨超越 一起遇见白色幻想', |
943d5ab1 | 822 | 'uploader_id': '408654318141572', |
ba723997 | 823 | 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAZJpnglcjW2f_CMVcnqA_6oVBXKWMpH0F8LIHuUu8-lA', |
824 | 'creator': '杨超越工作室', | |
825 | 'duration': 42608, | |
826 | 'timestamp': 1625739481, | |
827 | 'upload_date': '20210708', | |
828 | 'track': '@杨超越工作室创作的原声', | |
943d5ab1 M |
829 | 'view_count': int, |
830 | 'like_count': int, | |
831 | 'repost_count': int, | |
832 | 'comment_count': int, | |
ba723997 | 833 | }, |
943d5ab1 M |
834 | }, { |
835 | 'url': 'https://www.douyin.com/video/6953975910773099811', | |
ba723997 | 836 | 'md5': 'dde3302460f19db59c47060ff013b902', |
943d5ab1 M |
837 | 'info_dict': { |
838 | 'id': '6953975910773099811', | |
839 | 'ext': 'mp4', | |
840 | 'title': '#一起看海 出现在你的夏日里', | |
ba723997 | 841 | 'description': '#一起看海 出现在你的夏日里', |
943d5ab1 | 842 | 'uploader_id': '110403406559', |
ba723997 | 843 | 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', |
844 | 'creator': '杨超越', | |
845 | 'duration': 17228, | |
846 | 'timestamp': 1619098692, | |
847 | 'upload_date': '20210422', | |
848 | 'track': '@杨超越创作的原声', | |
943d5ab1 M |
849 | 'view_count': int, |
850 | 'like_count': int, | |
851 | 'repost_count': int, | |
852 | 'comment_count': int, | |
ba723997 | 853 | }, |
943d5ab1 M |
854 | }, { |
855 | 'url': 'https://www.douyin.com/video/6950251282489675042', | |
856 | 'md5': 'b4db86aec367ef810ddd38b1737d2fed', | |
857 | 'info_dict': { | |
858 | 'id': '6950251282489675042', | |
859 | 'ext': 'mp4', | |
860 | 'title': '哈哈哈,成功了哈哈哈哈哈哈', | |
861 | 'uploader': '杨超越', | |
862 | 'upload_date': '20210412', | |
863 | 'timestamp': 1618231483, | |
864 | 'uploader_id': '110403406559', | |
865 | 'view_count': int, | |
866 | 'like_count': int, | |
867 | 'repost_count': int, | |
868 | 'comment_count': int, | |
ba723997 | 869 | }, |
870 | 'skip': 'No longer available', | |
943d5ab1 M |
871 | }, { |
872 | 'url': 'https://www.douyin.com/video/6963263655114722595', | |
ba723997 | 873 | 'md5': 'cf9f11f0ec45d131445ec2f06766e122', |
943d5ab1 M |
874 | 'info_dict': { |
875 | 'id': '6963263655114722595', | |
876 | 'ext': 'mp4', | |
877 | 'title': '#哪个爱豆的105度最甜 换个角度看看我哈哈', | |
ba723997 | 878 | 'description': '#哪个爱豆的105度最甜 换个角度看看我哈哈', |
943d5ab1 | 879 | 'uploader_id': '110403406559', |
ba723997 | 880 | 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', |
881 | 'creator': '杨超越', | |
882 | 'duration': 15115, | |
883 | 'timestamp': 1621261163, | |
884 | 'upload_date': '20210517', | |
885 | 'track': '@杨超越创作的原声', | |
943d5ab1 M |
886 | 'view_count': int, |
887 | 'like_count': int, | |
888 | 'repost_count': int, | |
889 | 'comment_count': int, | |
ba723997 | 890 | }, |
943d5ab1 | 891 | }] |
ba723997 | 892 | _APP_VERSIONS = [('23.3.0', '230300')] |
943d5ab1 M |
893 | _APP_NAME = 'aweme' |
894 | _AID = 1128 | |
895 | _API_HOSTNAME = 'aweme.snssdk.com' | |
896 | _UPLOADER_URL_FORMAT = 'https://www.douyin.com/user/%s' | |
53dad39e | 897 | _WEBPAGE_HOST = 'https://www.douyin.com/' |
943d5ab1 M |
898 | |
899 | def _real_extract(self, url): | |
900 | video_id = self._match_id(url) | |
901 | ||
902 | try: | |
903 | return self._extract_aweme_app(video_id) | |
904 | except ExtractorError as e: | |
ba723997 | 905 | e.expected = True |
906 | self.to_screen(f'{e}; trying with webpage') | |
943d5ab1 M |
907 | |
908 | webpage = self._download_webpage(url, video_id) | |
909 | render_data_json = self._search_regex( | |
910 | r'<script [^>]*\bid=[\'"]RENDER_DATA[\'"][^>]*>(%7B.+%7D)</script>', | |
911 | webpage, 'render data', default=None) | |
912 | if not render_data_json: | |
913 | # TODO: Run verification challenge code to generate signature cookies | |
ba723997 | 914 | cookies = self._get_cookies(self._WEBPAGE_HOST) |
915 | expected = not cookies.get('s_v_web_id') or not cookies.get('ttwid') | |
916 | raise ExtractorError( | |
917 | 'Fresh cookies (not necessarily logged in) are needed', expected=expected) | |
943d5ab1 M |
918 | |
919 | render_data = self._parse_json( | |
920 | render_data_json, video_id, transform_source=compat_urllib_parse_unquote) | |
ff91cf74 | 921 | return self._parse_aweme_video_web(get_first(render_data, ('aweme', 'detail')), url) |
88afe056 | 922 | |
923 | ||
49895f06 | 924 | class TikTokVMIE(InfoExtractor): |
ba723997 | 925 | _VALID_URL = r'https?://(?:(?:vm|vt)\.tiktok\.com|(?:www\.)tiktok\.com/t)/(?P<id>\w+)' |
88afe056 | 926 | IE_NAME = 'vm.tiktok' |
927 | ||
49895f06 | 928 | _TESTS = [{ |
ba723997 | 929 | 'url': 'https://www.tiktok.com/t/ZTRC5xgJp', |
49895f06 | 930 | 'info_dict': { |
ba723997 | 931 | 'id': '7170520270497680683', |
49895f06 | 932 | 'ext': 'mp4', |
ba723997 | 933 | 'title': 'md5:c64f6152330c2efe98093ccc8597871c', |
934 | 'uploader_id': '6687535061741700102', | |
935 | 'upload_date': '20221127', | |
49895f06 | 936 | 'view_count': int, |
ba723997 | 937 | 'like_count': int, |
49895f06 | 938 | 'comment_count': int, |
ba723997 | 939 | 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAObqu3WCTXxmw2xwZ3iLEHnEecEIw7ks6rxWqOqOhaPja9BI7gqUQnjw8_5FSoDXX', |
940 | 'album': 'Wave of Mutilation: Best of Pixies', | |
941 | 'thumbnail': r're:https://.+\.webp.*', | |
942 | 'duration': 5, | |
943 | 'timestamp': 1669516858, | |
49895f06 | 944 | 'repost_count': int, |
ba723997 | 945 | 'artist': 'Pixies', |
946 | 'track': 'Where Is My Mind?', | |
947 | 'description': 'md5:c64f6152330c2efe98093ccc8597871c', | |
948 | 'uploader': 'sigmachaddeus', | |
949 | 'creator': 'SigmaChad', | |
950 | }, | |
951 | }, { | |
c4cbd3be | 952 | 'url': 'https://vm.tiktok.com/ZTR45GpSF/', |
953 | 'info_dict': { | |
954 | 'id': '7106798200794926362', | |
955 | 'ext': 'mp4', | |
956 | 'title': 'md5:edc3e7ea587847f8537468f2fe51d074', | |
957 | 'uploader_id': '6997695878846268418', | |
958 | 'upload_date': '20220608', | |
959 | 'view_count': int, | |
960 | 'like_count': int, | |
961 | 'comment_count': int, | |
962 | 'thumbnail': r're:https://.+\.webp.*', | |
963 | 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAdZ_NcPPgMneaGrW0hN8O_J_bwLshwNNERRF5DxOw2HKIzk0kdlLrR8RkVl1ksrMO', | |
964 | 'duration': 29, | |
965 | 'timestamp': 1654680400, | |
966 | 'repost_count': int, | |
967 | 'artist': 'Akihitoko', | |
968 | 'track': 'original sound', | |
969 | 'description': 'md5:edc3e7ea587847f8537468f2fe51d074', | |
970 | 'uploader': 'akihitoko1', | |
971 | 'creator': 'Akihitoko', | |
972 | }, | |
49895f06 | 973 | }, { |
974 | 'url': 'https://vt.tiktok.com/ZSe4FqkKd', | |
975 | 'only_matching': True, | |
976 | }] | |
977 | ||
88afe056 | 978 | def _real_extract(self, url): |
11e1c2e3 | 979 | new_url = self._request_webpage( |
980 | HEADRequest(url), self._match_id(url), headers={'User-Agent': 'facebookexternalhit/1.1'}).geturl() | |
981 | if self.suitable(new_url): # Prevent infinite loop in case redirect fails | |
982 | raise UnsupportedError(new_url) | |
983 | return self.url_result(new_url) | |
933ed882 JC |
984 | |
985 | ||
986 | class TikTokLiveIE(InfoExtractor): | |
987 | _VALID_URL = r'https?://(?:www\.)?tiktok\.com/@(?P<id>[\w\.-]+)/live' | |
988 | IE_NAME = 'tiktok:live' | |
989 | ||
990 | _TESTS = [{ | |
991 | 'url': 'https://www.tiktok.com/@iris04201/live', | |
992 | 'only_matching': True, | |
993 | }] | |
994 | ||
995 | def _real_extract(self, url): | |
996 | uploader = self._match_id(url) | |
997 | webpage = self._download_webpage(url, uploader, headers={'User-Agent': 'User-Agent:Mozilla/5.0'}) | |
998 | room_id = self._html_search_regex(r'snssdk\d*://live\?room_id=(\d+)', webpage, 'room ID', default=None) | |
999 | if not room_id: | |
1000 | raise UserNotLive(video_id=uploader) | |
1001 | live_info = traverse_obj(self._download_json( | |
1002 | 'https://www.tiktok.com/api/live/detail/', room_id, query={ | |
1003 | 'aid': '1988', | |
1004 | 'roomID': room_id, | |
1005 | }), 'LiveRoomInfo', expected_type=dict, default={}) | |
1006 | ||
1007 | if 'status' not in live_info: | |
1008 | raise ExtractorError('Unexpected response from TikTok API') | |
1009 | # status = 2 if live else 4 | |
1010 | if not int_or_none(live_info['status']) == 2: | |
1011 | raise UserNotLive(video_id=uploader) | |
1012 | ||
1013 | return { | |
1014 | 'id': room_id, | |
1015 | 'title': live_info.get('title') or self._html_search_meta(['og:title', 'twitter:title'], webpage, default=''), | |
1016 | 'uploader': uploader, | |
1017 | 'uploader_id': traverse_obj(live_info, ('ownerInfo', 'id')), | |
1018 | 'creator': traverse_obj(live_info, ('ownerInfo', 'nickname')), | |
1019 | 'concurrent_view_count': traverse_obj(live_info, ('liveRoomStats', 'userCount'), expected_type=int), | |
1020 | 'formats': self._extract_m3u8_formats(live_info['liveUrl'], room_id, 'mp4', live=True), | |
1021 | 'is_live': True, | |
1022 | } |