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 2022-12-11 17:43:07 +01:00
parent 84db11759e
commit 7b845b34ce
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
2 changed files with 15 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

15
src/you_get/common.py
View File

@ -344,21 +344,24 @@ def undeflate(data):
# an http.client implementation of get_content() # an http.client implementation of get_content()
# because urllib does not support "Connection: keep-alive" # because urllib does not support "Connection: keep-alive"
def getHttps(host, url, headers, gzip=True, deflate=False, debuglevel=0): def getHttps(host, url, headers, debuglevel=0):
import http.client import http.client
conn = http.client.HTTPSConnection(host) conn = http.client.HTTPSConnection(host)
conn.set_debuglevel(debuglevel) conn.set_debuglevel(debuglevel)
conn.request("GET", url, headers=headers) conn.request("GET", url, headers=headers)
resp = conn.getresponse() resp = conn.getresponse()
set_cookie = resp.getheader('set-cookie')
data = resp.read() data = resp.read()
if gzip: try:
data = ungzip(data) data = ungzip(data) # gzip
if deflate: data = undeflate(data) # deflate
data = undeflate(data) except:
pass
return str(data, encoding='utf-8'), resp.getheader('set-cookie') conn.close()
return str(data, encoding='utf-8'), set_cookie
# DEPRECATED in favor of get_content() # DEPRECATED in favor of get_content()

12
src/you_get/extractors/tiktok.py
View File

@ -16,12 +16,12 @@ def tiktok_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
m = re.match('(https?://)?([^/]+)(/.*)', url) m = re.match('(https?://)?([^/]+)(/.*)', url)
host = m.group(2) host = m.group(2)
if host != 'www.tiktok.com': # non-canonical URL if host != 'www.tiktok.com': # non-canonical URL
url = get_location(url, headers=headers) vid = r1(r'/video/(\d+)', url)
m = re.match('(https?://)?([^/]+)(/.*)', url) url = 'https://www.tiktok.com/@/video/%s/' % vid
host = m.group(2) host = 'www.tiktok.com'
else:
url = m.group(3).split('?')[0] url = m.group(3).split('?')[0]
vid = url.split('/')[3] # should be a string of numbers vid = url.split('/')[3] # should be a string of numbers
html, set_cookie = getHttps(host, url, headers=headers) html, set_cookie = getHttps(host, url, headers=headers)
tt_chain_token = r1('tt_chain_token=([^;]+);', set_cookie) tt_chain_token = r1('tt_chain_token=([^;]+);', set_cookie)