PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-02-02 16:24:00 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[tiktok] fix extraction for alternative URLs

Browse Source
This commit is contained in:
Mort Yao 2022-05-15 22:51:22 +02:00
parent c768b29153
commit e2ba3ecdb3
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 13 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
src/you_get/extractors/tiktok.py
View File

@ -5,16 +5,6 @@ __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):
while True:
m = re.match('(https?://)?([^/]+)(/.*)', url)
host = m.group(2)
if host == 'www.tiktok.com': # canonical URL reached
url = m.group(3).split('?')[0]
vid = url.split('/')[3] # should be a string of numbers
break
else:
url = get_location(url)
headers = { headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0', 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0',
'Accept-Encoding': 'gzip, deflate', 'Accept-Encoding': 'gzip, deflate',
@ -22,7 +12,20 @@ def tiktok_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
'Connection': 'keep-alive' # important 'Connection': 'keep-alive' # important
} }
m = re.match('(https?://)?([^/]+)(/.*)', url)
host = m.group(2)
if host != 'www.tiktok.com': # non-canonical URL
html = getHttps(host, url, headers=headers, gzip=False)
url = r1(r'(https://www.tiktok.com/[^?"]+)', html)
# use canonical URL
m = re.match('(https?://)?([^/]+)(/.*)', url)
host = m.group(2)
url = m.group(3).split('?')[0]
vid = url.split('/')[3] # should be a string of numbers
html = getHttps(host, url, headers=headers) html = getHttps(host, url, headers=headers)
data = r1(r'window\[\'SIGI_STATE\'\]=(.*?);window\[\'SIGI_RETRY\'\]', html) or \ data = r1(r'window\[\'SIGI_STATE\'\]=(.*?);window\[\'SIGI_RETRY\'\]', html) or \
r1(r'<script id="SIGI_STATE" type="application/json">(.*?)</script>', html) r1(r'<script id="SIGI_STATE" type="application/json">(.*?)</script>', html)
info = json.loads(data) info = json.loads(data)