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 2020-10-25 17:02:28 +01:00
parent c271363585
commit 5d59f76a41
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 30 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
src/you_get/extractors/tiktok.py
View File

@ -5,26 +5,42 @@ __all__ = ['tiktok_download']
from ..common import *
def tiktok_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
html = get_html(url, faker=True)
referUrl = url.split('?')[0]
headers = fake_headers
# trick or treat
html = get_content(url, headers=headers)
data = r1(r'<script id="__NEXT_DATA__".*?>(.*?)</script>', html)
info = json.loads(data)
videoData = info['props']['pageProps']['videoData']
urls = videoData['itemInfos']['video']['urls']
videoId = videoData['itemInfos']['id']
uniqueId = videoData['authorInfos'].get('uniqueId')
nickName = videoData['authorInfos'].get('nickName')
wid = info['props']['initialProps']['$wid']
cookie = 'tt_webid=%s; tt_webid_v2=%s' % (wid, wid)
# here's the cookie
headers['Cookie'] = cookie
# try again
html = get_content(url, headers=headers)
data = r1(r'<script id="__NEXT_DATA__".*?>(.*?)</script>', html)
info = json.loads(data)
wid = info['props']['initialProps']['$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')
for i, videoUrl in enumerate(urls):
title = '%s [%s]' % (nickName or uniqueId, videoId)
if len(urls) > 1:
title = '%s [%s]' % (title, i)
mime, ext, size = url_info(videoUrl, headers={'Referer': url})
# we also need the referer
headers['Referer'] = referUrl
mime, ext, size = url_info(videoUrl, headers=headers)
print_info(site_info, title, mime, size)
if not info_only:
download_urls([videoUrl], title, ext, size, output_dir=output_dir, merge=merge, headers={'Referer': url})
download_urls([videoUrl], title, ext, size, output_dir=output_dir, merge=merge, headers=headers)
site_info = "TikTok.com"
download = tiktok_download