github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[extractor/tiktok] Fix and improve metadata extraction (#6777)

Browse source 
Authored by: bashonly
This commit is contained in:
bashonly 2023-04-13 14:05:57 -05:00 committed by GitHub
parent 90c1f51206
commit 925936908a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 116 additions and 71 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

187
yt_dlp/extractor/tiktok.py
View file

@ -287,17 +287,15 @@ def extract_addr(addr, add_meta={}):
thumbnails = [] thumbnails = []
for cover_id in ('cover', 'ai_dynamic_cover', 'animated_cover', 'ai_dynamic_cover_bak', for cover_id in ('cover', 'ai_dynamic_cover', 'animated_cover', 'ai_dynamic_cover_bak',
'origin_cover', 'dynamic_cover'): 'origin_cover', 'dynamic_cover'):
cover = video_info.get(cover_id) for cover_url in traverse_obj(video_info, (cover_id, 'url_list', ...)):
if cover: thumbnails.append({
for cover_url in cover['url_list']: 'id': cover_id,
thumbnails.append({ 'url': cover_url,
'id': cover_id, })
'url': cover_url,
})
stats_info = aweme_detail.get('statistics', {}) stats_info = aweme_detail.get('statistics') or {}
author_info = aweme_detail.get('author', {}) author_info = aweme_detail.get('author') or {}
music_info = aweme_detail.get('music', {}) music_info = aweme_detail.get('music') or {}
user_url = self._UPLOADER_URL_FORMAT % (traverse_obj(author_info, user_url = self._UPLOADER_URL_FORMAT % (traverse_obj(author_info,
'sec_uid', 'id', 'uid', 'unique_id', 'sec_uid', 'id', 'uid', 'unique_id',
expected_type=str_or_none, get_all=False)) expected_type=str_or_none, get_all=False))
@ -319,20 +317,27 @@ def extract_addr(addr, add_meta={}):
'extractor_key': TikTokIE.ie_key(), 'extractor_key': TikTokIE.ie_key(),
'extractor': TikTokIE.IE_NAME, 'extractor': TikTokIE.IE_NAME,
'webpage_url': self._create_url(author_info.get('uid'), aweme_id), 'webpage_url': self._create_url(author_info.get('uid'), aweme_id),
'title': aweme_detail.get('desc'), **traverse_obj(aweme_detail, {
'description': aweme_detail.get('desc'), 'title': ('desc', {str}),
'view_count': int_or_none(stats_info.get('play_count')), 'description': ('desc', {str}),
'like_count': int_or_none(stats_info.get('digg_count')), 'timestamp': ('create_time', {int_or_none}),
'repost_count': int_or_none(stats_info.get('share_count')), }),
'comment_count': int_or_none(stats_info.get('comment_count')), **traverse_obj(stats_info, {
'uploader': str_or_none(author_info.get('unique_id')), 'view_count': 'play_count',
'creator': str_or_none(author_info.get('nickname')), 'like_count': 'digg_count',
'uploader_id': str_or_none(author_info.get('uid')), 'repost_count': 'share_count',
'comment_count': 'comment_count',
}, expected_type=int_or_none),
**traverse_obj(author_info, {
'uploader': 'unique_id',
'uploader_id': 'uid',
'creator': 'nickname',
'channel_id': 'sec_uid',
}, expected_type=str_or_none),
'uploader_url': user_url, 'uploader_url': user_url,
'track': music_track, 'track': music_track,
'album': str_or_none(music_info.get('album')) or None, 'album': str_or_none(music_info.get('album')) or None,
'artist': music_author or None, 'artist': music_author or None,
'timestamp': int_or_none(aweme_detail.get('create_time')),
'formats': formats, 'formats': formats,
'subtitles': self.extract_subtitles(aweme_detail, aweme_id), 'subtitles': self.extract_subtitles(aweme_detail, aweme_id),
'thumbnails': thumbnails, 'thumbnails': thumbnails,
@ -344,37 +349,27 @@ def extract_addr(addr, add_meta={}):
'_format_sort_fields': ('quality', 'codec', 'size', 'br'), '_format_sort_fields': ('quality', 'codec', 'size', 'br'),
} }
def _parse_aweme_video_web(self, aweme_detail, webpage_url): def _parse_aweme_video_web(self, aweme_detail, webpage_url, video_id):
video_info = aweme_detail['video'] video_info = aweme_detail['video']
author_info = traverse_obj(aweme_detail, 'authorInfo', 'author', expected_type=dict, default={}) author_info = traverse_obj(aweme_detail, 'authorInfo', 'author', expected_type=dict, default={})
music_info = aweme_detail.get('music') or {} music_info = aweme_detail.get('music') or {}
stats_info = aweme_detail.get('stats') or {} stats_info = aweme_detail.get('stats') or {}
user_url = self._UPLOADER_URL_FORMAT % (traverse_obj(author_info, channel_id = traverse_obj(author_info or aweme_detail, (('authorSecId', 'secUid'), {str}), get_all=False)
'secUid', 'id', 'uid', 'uniqueId', user_url = self._UPLOADER_URL_FORMAT % channel_id if channel_id else None
expected_type=str_or_none, get_all=False)
or aweme_detail.get('authorSecId'))
formats = [] formats = []
play_url = video_info.get('playAddr') width = int_or_none(video_info.get('width'))
width = video_info.get('width') height = int_or_none(video_info.get('height'))
height = video_info.get('height')
if isinstance(play_url, str): for play_url in traverse_obj(video_info, ('playAddr', ((..., 'src'), None), {url_or_none})):
formats = [{ formats.append({
'url': self._proto_relative_url(play_url), 'url': self._proto_relative_url(play_url),
'ext': 'mp4', 'ext': 'mp4',
'width': width, 'width': width,
'height': height, 'height': height,
}] })
elif isinstance(play_url, list):
formats = [{
'url': self._proto_relative_url(url),
'ext': 'mp4',
'width': width,
'height': height,
} for url in traverse_obj(play_url, (..., 'src'), expected_type=url_or_none) if url]
download_url = url_or_none(video_info.get('downloadAddr')) or traverse_obj(video_info, ('download', 'url'), expected_type=url_or_none) for download_url in traverse_obj(video_info, (('downloadAddr', ('download', 'url')), {url_or_none})):
if download_url:
formats.append({ formats.append({
'format_id': 'download', 'format_id': 'download',
'url': self._proto_relative_url(download_url), 'url': self._proto_relative_url(download_url),
@ -382,38 +377,48 @@ def _parse_aweme_video_web(self, aweme_detail, webpage_url):
'width': width, 'width': width,
'height': height, 'height': height,
}) })
self._remove_duplicate_formats(formats) self._remove_duplicate_formats(formats)
thumbnails = [] thumbnails = []
for thumbnail_name in ('thumbnail', 'cover', 'dynamicCover', 'originCover'): for thumb_url in traverse_obj(aweme_detail, (
if aweme_detail.get(thumbnail_name): (None, 'video'), ('thumbnail', 'cover', 'dynamicCover', 'originCover'), {url_or_none})):
thumbnails = [{ thumbnails.append({
'url': self._proto_relative_url(aweme_detail[thumbnail_name]), 'url': self._proto_relative_url(thumb_url),
'width': width, 'width': width,
'height': height 'height': height,
}] })
return { return {
'id': traverse_obj(aweme_detail, 'id', 'awemeId', expected_type=str_or_none), 'id': video_id,
'title': aweme_detail.get('desc'), **traverse_obj(aweme_detail, {
'duration': try_get(aweme_detail, lambda x: x['video']['duration'], int), 'title': ('desc', {str}),
'view_count': int_or_none(stats_info.get('playCount')), 'description': ('desc', {str}),
'like_count': int_or_none(stats_info.get('diggCount')), 'duration': ('video', 'duration', {int_or_none}),
'repost_count': int_or_none(stats_info.get('shareCount')), 'timestamp': ('createTime', {int_or_none}),
'comment_count': int_or_none(stats_info.get('commentCount')), }),
'timestamp': int_or_none(aweme_detail.get('createTime')), **traverse_obj(author_info or aweme_detail, {
'creator': str_or_none(author_info.get('nickname')), 'creator': ('nickname', {str}),
'uploader': str_or_none(author_info.get('uniqueId') or aweme_detail.get('author')), 'uploader': (('uniqueId', 'author'), {str}),
'uploader_id': str_or_none(traverse_obj(author_info, 'id', 'uid', 'authorId')), 'uploader_id': (('authorId', 'uid', 'id'), {str_or_none}),
}, get_all=False),
**traverse_obj(stats_info, {
'view_count': 'playCount',
'like_count': 'diggCount',
'repost_count': 'shareCount',
'comment_count': 'commentCount',
}, expected_type=int_or_none),
**traverse_obj(music_info, {
'track': 'title',
'album': ('album', {lambda x: x or None}),
'artist': 'authorName',
}, expected_type=str),
'channel_id': channel_id,
'uploader_url': user_url, 'uploader_url': user_url,
'track': str_or_none(music_info.get('title')),
'album': str_or_none(music_info.get('album')) or None,
'artist': str_or_none(music_info.get('authorName')),
'formats': formats, 'formats': formats,
'thumbnails': thumbnails, 'thumbnails': thumbnails,
'description': str_or_none(aweme_detail.get('desc')),
'http_headers': { 'http_headers': {
'Referer': webpage_url 'Referer': webpage_url,
} }
} }
@ -447,7 +452,8 @@ class TikTokIE(TikTokBaseIE):
'artist': 'Ysrbeats', 'artist': 'Ysrbeats',
'album': 'Lehanga', 'album': 'Lehanga',
'track': 'Lehanga', 'track': 'Lehanga',
} },
'skip': '404 Not Found',
}, { }, {
'url': 'https://www.tiktok.com/@patroxofficial/video/6742501081818877190?langCountry=en', 'url': 'https://www.tiktok.com/@patroxofficial/video/6742501081818877190?langCountry=en',
'md5': '6f3cf8cdd9b28cb8363fe0a9a160695b', 'md5': '6f3cf8cdd9b28cb8363fe0a9a160695b',
@ -462,6 +468,7 @@ class TikTokIE(TikTokBaseIE):
'uploader': 'patrox', 'uploader': 'patrox',
'uploader_id': '18702747', 'uploader_id': '18702747',
'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws',
'channel_id': 'MS4wLjABAAAAiFnldaILebi5heDoVU6bn4jBWWycX6-9U3xuNPqZ8Ws',
'creator': 'patroX', 'creator': 'patroX',
'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?', 'thumbnail': r're:^https?://[\w\/\.\-]+(~[\w\-]+\.image)?',
'upload_date': '20190930', 'upload_date': '20190930',
@ -472,7 +479,7 @@ class TikTokIE(TikTokBaseIE):
'comment_count': int, 'comment_count': int,
'artist': 'Evan Todd, Jessica Keenan Wynn, Alice Lee, Barrett Wilbert Weed & Jon Eidson', 'artist': 'Evan Todd, Jessica Keenan Wynn, Alice Lee, Barrett Wilbert Weed & Jon Eidson',
'track': 'Big Fun', 'track': 'Big Fun',
} },
}, { }, {
# Banned audio, only available on the app # Banned audio, only available on the app
'url': 'https://www.tiktok.com/@barudakhb_/video/6984138651336838402', 'url': 'https://www.tiktok.com/@barudakhb_/video/6984138651336838402',
@ -485,6 +492,7 @@ class TikTokIE(TikTokBaseIE):
'creator': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6', 'creator': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6',
'uploader_id': '6974687867511718913', 'uploader_id': '6974687867511718913',
'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAbhBwQC-R1iKoix6jDFsF-vBdfx2ABoDjaZrM9fX6arU3w71q3cOWgWuTXn1soZ7d', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAbhBwQC-R1iKoix6jDFsF-vBdfx2ABoDjaZrM9fX6arU3w71q3cOWgWuTXn1soZ7d',
'channel_id': 'MS4wLjABAAAAbhBwQC-R1iKoix6jDFsF-vBdfx2ABoDjaZrM9fX6arU3w71q3cOWgWuTXn1soZ7d',
'track': 'Boka Dance', 'track': 'Boka Dance',
'artist': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6', 'artist': 'md5:29f238c49bc0c176cb3cef1a9cea9fa6',
'timestamp': 1626121503, 'timestamp': 1626121503,
@ -495,7 +503,7 @@ class TikTokIE(TikTokBaseIE):
'like_count': int, 'like_count': int,
'repost_count': int, 'repost_count': int,
'comment_count': int, 'comment_count': int,
} },
}, { }, {
# Sponsored video, only available with feed workaround # Sponsored video, only available with feed workaround
'url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_/video/7042692929109986561', 'url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_/video/7042692929109986561',
@ -508,6 +516,7 @@ class TikTokIE(TikTokBaseIE):
'creator': 'Slap And Run', 'creator': 'Slap And Run',
'uploader_id': '7036055384943690754', 'uploader_id': '7036055384943690754',
'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_',
'channel_id': 'MS4wLjABAAAATh8Vewkn0LYM7Fo03iec3qKdeCUOcBIouRk1mkiag6h3o_pQu_dUXvZ2EZlGST7_',
'track': 'Promoted Music', 'track': 'Promoted Music',
'timestamp': 1639754738, 'timestamp': 1639754738,
'duration': 30, 'duration': 30,
@ -518,7 +527,6 @@ class TikTokIE(TikTokBaseIE):
'repost_count': int, 'repost_count': int,
'comment_count': int, 'comment_count': int,
}, },
'expected_warnings': ['trying with webpage', 'Unable to find video in feed']
}, { }, {
# Video without title and description # Video without title and description
'url': 'https://www.tiktok.com/@pokemonlife22/video/7059698374567611694', 'url': 'https://www.tiktok.com/@pokemonlife22/video/7059698374567611694',
@ -531,6 +539,7 @@ class TikTokIE(TikTokBaseIE):
'creator': 'Pokemon', 'creator': 'Pokemon',
'uploader_id': '6820838815978423302', 'uploader_id': '6820838815978423302',
'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA0tF1nBwQVVMyrGu3CqttkNgM68Do1OXUFuCY0CRQk8fEtSVDj89HqoqvbSTmUP2W', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAA0tF1nBwQVVMyrGu3CqttkNgM68Do1OXUFuCY0CRQk8fEtSVDj89HqoqvbSTmUP2W',
'channel_id': 'MS4wLjABAAAA0tF1nBwQVVMyrGu3CqttkNgM68Do1OXUFuCY0CRQk8fEtSVDj89HqoqvbSTmUP2W',
'track': 'original sound', 'track': 'original sound',
'timestamp': 1643714123, 'timestamp': 1643714123,
'duration': 6, 'duration': 6,
@ -577,6 +586,7 @@ class TikTokIE(TikTokBaseIE):
'uploader': '_le_cannibale_', 'uploader': '_le_cannibale_',
'uploader_id': '6604511138619654149', 'uploader_id': '6604511138619654149',
'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAoShJqaw_5gvy48y3azFeFcT4jeyKWbB0VVYasOCt2tTLwjNFIaDcHAM4D-QGXFOP', 'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAoShJqaw_5gvy48y3azFeFcT4jeyKWbB0VVYasOCt2tTLwjNFIaDcHAM4D-QGXFOP',
'channel_id': 'MS4wLjABAAAAoShJqaw_5gvy48y3azFeFcT4jeyKWbB0VVYasOCt2tTLwjNFIaDcHAM4D-QGXFOP',
'artist': 'nathan !', 'artist': 'nathan !',
'track': 'grahamscott canon', 'track': 'grahamscott canon',
'upload_date': '20220905', 'upload_date': '20220905',
@ -587,6 +597,33 @@ class TikTokIE(TikTokBaseIE):
'comment_count': int, 'comment_count': int,
'thumbnail': r're:^https://.+\.webp', 'thumbnail': r're:^https://.+\.webp',
}, },
}, {
# only available via web
'url': 'https://www.tiktok.com/@moxypatch/video/7206382937372134662',
'md5': '8d8c0be14127020cd9f5def4a2e6b411',
'info_dict': {
'id': '7206382937372134662',
'ext': 'mp4',
'title': 'md5:1d95c0b96560ca0e8a231af4172b2c0a',
'description': 'md5:1d95c0b96560ca0e8a231af4172b2c0a',
'creator': 'MoxyPatch',
'uploader': 'moxypatch',
'uploader_id': '7039142049363379205',
'uploader_url': 'https://www.tiktok.com/@MS4wLjABAAAAFhqKnngMHJSsifL0w1vFOP5kn3Ndo1ODp0XuIBkNMBCkALTvwILdpu12g3pTtL4V',
'channel_id': 'MS4wLjABAAAAFhqKnngMHJSsifL0w1vFOP5kn3Ndo1ODp0XuIBkNMBCkALTvwILdpu12g3pTtL4V',
'artist': 'your worst nightmare',
'track': 'original sound',
'upload_date': '20230303',
'timestamp': 1677866781,
'duration': 10,
'view_count': int,
'like_count': int,
'repost_count': int,
'comment_count': int,
'thumbnail': r're:^https://.+',
'thumbnails': 'count:3',
},
'expected_warnings': ['Unable to find video in feed'],
}, { }, {
# Auto-captions available # Auto-captions available
'url': 'https://www.tiktok.com/@hankgreen1/video/7047596209028074758', 'url': 'https://www.tiktok.com/@hankgreen1/video/7047596209028074758',
@ -612,7 +649,7 @@ def _real_extract(self, url):
video_data = traverse_obj(sigi_data, ('ItemModule', video_id), expected_type=dict) video_data = traverse_obj(sigi_data, ('ItemModule', video_id), expected_type=dict)
if status == 0: if status == 0:
return self._parse_aweme_video_web(video_data, url) return self._parse_aweme_video_web(video_data, url, video_id)
elif status == 10216: elif status == 10216:
raise ExtractorError('This video is private', expected=True) raise ExtractorError('This video is private', expected=True)
raise ExtractorError('Video not available', video_id=video_id) raise ExtractorError('Video not available', video_id=video_id)
@ -839,6 +876,7 @@ class DouyinIE(TikTokBaseIE):
'description': '#杨超越 小小水手带你去远航❤️', 'description': '#杨超越 小小水手带你去远航❤️',
'uploader_id': '110403406559', 'uploader_id': '110403406559',
'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
'channel_id': 'MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
'creator': '杨超越', 'creator': '杨超越',
'duration': 19782, 'duration': 19782,
'timestamp': 1620905839, 'timestamp': 1620905839,
@ -848,6 +886,7 @@ class DouyinIE(TikTokBaseIE):
'like_count': int, 'like_count': int,
'repost_count': int, 'repost_count': int,
'comment_count': int, 'comment_count': int,
'thumbnail': r're:https?://.+\.jpe?g',
}, },
}, { }, {
'url': 'https://www.douyin.com/video/6982497745948921092', 'url': 'https://www.douyin.com/video/6982497745948921092',
@ -859,8 +898,9 @@ class DouyinIE(TikTokBaseIE):
'description': '这个夏日和小羊@杨超越 一起遇见白色幻想', 'description': '这个夏日和小羊@杨超越 一起遇见白色幻想',
'uploader_id': '408654318141572', 'uploader_id': '408654318141572',
'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAZJpnglcjW2f_CMVcnqA_6oVBXKWMpH0F8LIHuUu8-lA', 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAZJpnglcjW2f_CMVcnqA_6oVBXKWMpH0F8LIHuUu8-lA',
'channel_id': 'MS4wLjABAAAAZJpnglcjW2f_CMVcnqA_6oVBXKWMpH0F8LIHuUu8-lA',
'creator': '杨超越工作室', 'creator': '杨超越工作室',
'duration': 42608, 'duration': 42479,
'timestamp': 1625739481, 'timestamp': 1625739481,
'upload_date': '20210708', 'upload_date': '20210708',
'track': '@杨超越工作室创作的原声', 'track': '@杨超越工作室创作的原声',
@ -868,6 +908,7 @@ class DouyinIE(TikTokBaseIE):
'like_count': int, 'like_count': int,
'repost_count': int, 'repost_count': int,
'comment_count': int, 'comment_count': int,
'thumbnail': r're:https?://.+\.jpe?g',
}, },
}, { }, {
'url': 'https://www.douyin.com/video/6953975910773099811', 'url': 'https://www.douyin.com/video/6953975910773099811',
@ -879,8 +920,9 @@ class DouyinIE(TikTokBaseIE):
'description': '#一起看海 出现在你的夏日里', 'description': '#一起看海 出现在你的夏日里',
'uploader_id': '110403406559', 'uploader_id': '110403406559',
'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
'channel_id': 'MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
'creator': '杨超越', 'creator': '杨超越',
'duration': 17228, 'duration': 17343,
'timestamp': 1619098692, 'timestamp': 1619098692,
'upload_date': '20210422', 'upload_date': '20210422',
'track': '@杨超越创作的原声', 'track': '@杨超越创作的原声',
@ -888,6 +930,7 @@ class DouyinIE(TikTokBaseIE):
'like_count': int, 'like_count': int,
'repost_count': int, 'repost_count': int,
'comment_count': int, 'comment_count': int,
'thumbnail': r're:https?://.+\.jpe?g',
}, },
}, { }, {
'url': 'https://www.douyin.com/video/6950251282489675042', 'url': 'https://www.douyin.com/video/6950251282489675042',
@ -916,6 +959,7 @@ class DouyinIE(TikTokBaseIE):
'description': '#哪个爱豆的105度最甜 换个角度看看我哈哈', 'description': '#哪个爱豆的105度最甜 换个角度看看我哈哈',
'uploader_id': '110403406559', 'uploader_id': '110403406559',
'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98', 'uploader_url': 'https://www.douyin.com/user/MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
'channel_id': 'MS4wLjABAAAAEKnfa654JAJ_N5lgZDQluwsxmY0lhfmEYNQBBkwGG98',
'creator': '杨超越', 'creator': '杨超越',
'duration': 15115, 'duration': 15115,
'timestamp': 1621261163, 'timestamp': 1621261163,
@ -925,6 +969,7 @@ class DouyinIE(TikTokBaseIE):
'like_count': int, 'like_count': int,
'repost_count': int, 'repost_count': int,
'comment_count': int, 'comment_count': int,
'thumbnail': r're:https?://.+\.jpe?g',
}, },
}] }]
_APP_VERSIONS = [('23.3.0', '230300')] _APP_VERSIONS = [('23.3.0', '230300')]
@ -956,7 +1001,7 @@ def _real_extract(self, url):
render_data = self._parse_json( render_data = self._parse_json(
render_data_json, video_id, transform_source=compat_urllib_parse_unquote) render_data_json, video_id, transform_source=compat_urllib_parse_unquote)
return self._parse_aweme_video_web(get_first(render_data, ('aweme', 'detail')), url) return self._parse_aweme_video_web(get_first(render_data, ('aweme', 'detail')), url, video_id)
class TikTokVMIE(InfoExtractor): class TikTokVMIE(InfoExtractor):