PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-01-23 21:45:02 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[tiktok] fix extraction

Browse Source
This commit is contained in:
Mort Yao 2022-04-19 15:53:33 +02:00
parent db6ed38c6a
commit 1b567d0830
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 24 additions and 30 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

54
src/you_get/extractors/tiktok.py
View File

@ -5,42 +5,36 @@ __all__ = ['tiktok_download']
from ..common import * from ..common import *
def tiktok_download(url, output_dir='.', merge=True, info_only=False, **kwargs): def tiktok_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
referUrl = url.split('?')[0] while True:
headers = fake_headers m = re.match('https://([^/]+)(/.*)', url)
host = m.group(1)
if host == 'www.tiktok.com': # canonical URL reached
url = m.group(2).split('?')[0]
vid = url.split('/')[3] # should be a string of numbers
break
else:
url = get_location(url)
# trick or treat headers = {
html = get_content(url, headers=headers) 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0',
data = r1(r'<script id="__NEXT_DATA__".*?>(.*?)</script>', html) 'Accept-Encoding': 'gzip, deflate',
'Accept': '*/*',
'Connection': 'keep-alive' # important
}
html = getHttps(host, url, headers=headers)
data = r1(r'window\[\'SIGI_STATE\'\]=(.*?);window\[\'SIGI_RETRY\'\]', html)
info = json.loads(data) info = json.loads(data)
wid = info['props']['initialProps']['$wid'] downloadAddr = info['ItemModule'][vid]['video']['downloadAddr']
cookie = 'tt_webid=%s; tt_webid_v2=%s' % (wid, wid) author = info['ItemModule'][vid]['author'] # same as uniqueId
nickname = info['UserModule']['users'][author]['nickname']
title = '%s [%s]' % (nickname or author, vid)
# here's the cookie mime, ext, size = url_info(downloadAddr, headers=headers)
headers['Cookie'] = cookie
# try again
html = get_content(url, headers=headers)
data = r1(r'<script id="__NEXT_DATA__".*?>(.*?)</script>', html)
info = json.loads(data)
wid = info['props']['initialProps']['$wid']
cookie = 'tt_webid=%s; tt_webid_v2=%s' % (wid, wid)
videoData = info['props']['pageProps']['itemInfo']['itemStruct']
videoId = videoData['id']
videoUrl = videoData['video']['downloadAddr']
uniqueId = videoData['author'].get('uniqueId')
nickName = videoData['author'].get('nickname')
title = '%s [%s]' % (nickName or uniqueId, videoId)
# we also need the referer
headers['Referer'] = referUrl
mime, ext, size = url_info(videoUrl, headers=headers)
print_info(site_info, title, mime, size) print_info(site_info, title, mime, size)
if not info_only: if not info_only:
download_urls([videoUrl], title, ext, size, output_dir=output_dir, merge=merge, headers=headers) download_urls([downloadAddr], title, ext, size, output_dir=output_dir, merge=merge, headers=headers)
site_info = "TikTok.com" site_info = "TikTok.com"
download = tiktok_download download = tiktok_download