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

Update douyin.py

Browse Source 
The site douyin.com changed to a more user friendly website, this is the updated extractor for that.
This commit is contained in:
Philip Xu 2021-06-22 17:51:17 -04:00 committed by GitHub
parent 3881ed3f94
commit 5445f5ecde
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 11 additions and 11 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

22
src/you_get/extractors/douyin.py
View File

@ -1,7 +1,7 @@
# coding=utf-8 # coding=utf-8
import re import re
import json from urllib.parse import unquote
from ..common import ( from ..common import (
url_size, url_size,
@ -18,17 +18,17 @@ __all__ = ['douyin_download_by_url']
def douyin_download_by_url(url, **kwargs): def douyin_download_by_url(url, **kwargs):
page_content = get_content(url, headers=fake_headers) page_content = get_content(url, headers=fake_headers)
match_rule = re.compile(r'var data = \[(.*?)\];') # The easiest way to get the title is, obviously, from <title>
video_info = json.loads(match_rule.findall(page_content)[0]) title = re.findall(r'<title.*>(.*)</title>', page_content)[0].strip()
video_url = video_info['video']['play_addr']['url_list'][0] # Remove the site name from title
# fix: https://www.douyin.com/share/video/6553248251821165832 site_name = ' - 抖音'
# if there is no title, use desc if title.endswith(site_name):
cha_list = video_info['cha_list'] title = title[:-len(site_name)]
if cha_list:
title = cha_list[0]['cha_name']
else:
title = video_info['desc']
video_format = 'mp4' video_format = 'mp4'
# The video url is url escaped, as of today, there are 4 working CDN video
# urls for the same video, I chose the shortest one.
cdn_pattern = r'(api\.amemv\.com.*PackSourceEnum_AWEME_DETAIL)'
video_url = 'https://' + unquote(re.findall(cdn_pattern, page_content)[0])
size = url_size(video_url, faker=True) size = url_size(video_url, faker=True)
print_info( print_info(
site_info='douyin.com', title=title, site_info='douyin.com', title=title,