[tiktok] Fix extraction (closes #20809, closes #22838, closes #22850, closes #25987, closes #26281, closes #26411, closes #26639, closes #26776, closes #27237)

This commit is contained in:
Sergey M․ 2020-11-29 08:09:20 +07:00
parent 717d1d2d5a
commit fb626c0586
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D

View file

@ -5,6 +5,7 @@ from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_str, compat_str,
ExtractorError, ExtractorError,
float_or_none,
int_or_none, int_or_none,
str_or_none, str_or_none,
try_get, try_get,
@ -13,7 +14,7 @@ from ..utils import (
class TikTokBaseIE(InfoExtractor): class TikTokBaseIE(InfoExtractor):
def _extract_aweme(self, data): def _extract_video(self, data, video_id=None):
video = data['video'] video = data['video']
description = str_or_none(try_get(data, lambda x: x['desc'])) description = str_or_none(try_get(data, lambda x: x['desc']))
width = int_or_none(try_get(data, lambda x: video['width'])) width = int_or_none(try_get(data, lambda x: video['width']))
@ -21,12 +22,8 @@ class TikTokBaseIE(InfoExtractor):
format_urls = set() format_urls = set()
formats = [] formats = []
for format_id in ( for format_id in ('download', 'play'):
'play_addr_lowbr', 'play_addr', 'play_addr_h264', format_url = url_or_none(video.get('%sAddr' % format_id))
'download_addr'):
for format in try_get(
video, lambda x: x[format_id]['url_list'], list) or []:
format_url = url_or_none(format)
if not format_url: if not format_url:
continue continue
if format_url in format_urls: if format_url in format_urls:
@ -37,27 +34,42 @@ class TikTokBaseIE(InfoExtractor):
'ext': 'mp4', 'ext': 'mp4',
'height': height, 'height': height,
'width': width, 'width': width,
'http_headers': {
'Referer': 'https://www.tiktok.com/',
}
}) })
self._sort_formats(formats) self._sort_formats(formats)
thumbnail = url_or_none(try_get( thumbnail = url_or_none(video.get('cover'))
video, lambda x: x['cover']['url_list'][0], compat_str)) duration = float_or_none(video.get('duration'))
uploader = try_get(data, lambda x: x['author']['nickname'], compat_str)
timestamp = int_or_none(data.get('create_time'))
comment_count = int_or_none(data.get('comment_count')) or int_or_none(
try_get(data, lambda x: x['statistics']['comment_count']))
repost_count = int_or_none(try_get(
data, lambda x: x['statistics']['share_count']))
aweme_id = data['aweme_id'] uploader = try_get(data, lambda x: x['author']['nickname'], compat_str)
uploader_id = try_get(data, lambda x: x['author']['id'], compat_str)
timestamp = int_or_none(data.get('createTime'))
def stats(key):
return int_or_none(try_get(
data, lambda x: x['stats']['%sCount' % key]))
view_count = stats('play')
like_count = stats('digg')
comment_count = stats('comment')
repost_count = stats('share')
aweme_id = data.get('id') or video_id
return { return {
'id': aweme_id, 'id': aweme_id,
'title': uploader or aweme_id, 'title': uploader or aweme_id,
'description': description, 'description': description,
'thumbnail': thumbnail, 'thumbnail': thumbnail,
'duration': duration,
'uploader': uploader, 'uploader': uploader,
'uploader_id': uploader_id,
'timestamp': timestamp, 'timestamp': timestamp,
'view_count': view_count,
'like_count': like_count,
'comment_count': comment_count, 'comment_count': comment_count,
'repost_count': repost_count, 'repost_count': repost_count,
'formats': formats, 'formats': formats,
@ -65,62 +77,56 @@ class TikTokBaseIE(InfoExtractor):
class TikTokIE(TikTokBaseIE): class TikTokIE(TikTokBaseIE):
_VALID_URL = r'''(?x) _VALID_URL = r'https?://(?:www\.)?tiktok\.com/@[^/]+/video/(?P<id>\d+)'
https?://
(?:
(?:m\.)?tiktok\.com/v|
(?:www\.)?tiktok\.com/share/video
)
/(?P<id>\d+)
'''
_TESTS = [{ _TESTS = [{
'url': 'https://m.tiktok.com/v/6606727368545406213.html', 'url': 'https://www.tiktok.com/@zureeal/video/6606727368545406213',
'md5': 'd584b572e92fcd48888051f238022420', 'md5': '163ceff303bb52de60e6887fe399e6cd',
'info_dict': { 'info_dict': {
'id': '6606727368545406213', 'id': '6606727368545406213',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Zureeal', 'title': 'Zureeal',
'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay', 'description': '#bowsette#mario#cosplay#uk#lgbt#gaming#asian#bowsettecosplay',
'thumbnail': r're:^https?://.*~noop.image', 'thumbnail': r're:^https?://.*',
'duration': 15,
'uploader': 'Zureeal', 'uploader': 'Zureeal',
'uploader_id': '188294915489964032',
'timestamp': 1538248586, 'timestamp': 1538248586,
'upload_date': '20180929', 'upload_date': '20180929',
'view_count': int,
'like_count': int,
'comment_count': int, 'comment_count': int,
'repost_count': int, 'repost_count': int,
} }
}, {
'url': 'https://www.tiktok.com/share/video/6606727368545406213',
'only_matching': True,
}] }]
def _real_initialize(self):
# Setup session (will set necessary cookies)
self._request_webpage(
'https://www.tiktok.com/', None, note='Setting up session')
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage( webpage = self._download_webpage(url, video_id)
'https://m.tiktok.com/v/%s.html' % video_id, video_id)
data = self._parse_json(self._search_regex( data = self._parse_json(self._search_regex(
r'\bdata\s*=\s*({.+?})\s*;', webpage, 'data'), video_id) r'<script[^>]+\bid=["\']__NEXT_DATA__[^>]+>\s*({.+?})\s*</script',
return self._extract_aweme(data) webpage, 'data'), video_id)['props']['pageProps']['itemInfo']['itemStruct']
return self._extract_video(data, video_id)
class TikTokUserIE(TikTokBaseIE): class TikTokUserIE(TikTokBaseIE):
_VALID_URL = r'''(?x) _VALID_URL = r'https://(?:www\.)?tiktok\.com/@(?P<id>[^/?#&]+)'
https?://
(?:
(?:m\.)?tiktok\.com/h5/share/usr|
(?:www\.)?tiktok\.com/share/user
)
/(?P<id>\d+)
'''
_TESTS = [{ _TESTS = [{
'url': 'https://m.tiktok.com/h5/share/usr/188294915489964032.html', 'url': 'https://www.tiktok.com/@zureeal',
'info_dict': { 'info_dict': {
'id': '188294915489964032', 'id': '188294915489964032',
}, },
'playlist_mincount': 24, 'playlist_mincount': 24,
}, {
'url': 'https://www.tiktok.com/share/user/188294915489964032',
'only_matching': True,
}] }]
_WORKING = False
@classmethod
def suitable(cls, url):
return False if TikTokIE.suitable(url) else super(TikTokUserIE, cls).suitable(url)
def _real_extract(self, url): def _real_extract(self, url):
user_id = self._match_id(url) user_id = self._match_id(url)
@ -130,7 +136,7 @@ class TikTokUserIE(TikTokBaseIE):
entries = [] entries = []
for aweme in data['aweme_list']: for aweme in data['aweme_list']:
try: try:
entry = self._extract_aweme(aweme) entry = self._extract_video(aweme)
except ExtractorError: except ExtractorError:
continue continue
entry['extractor_key'] = TikTokIE.ie_key() entry['extractor_key'] = TikTokIE.ie_key()