PublicMirrors/you-get
1
0
Fork 0
mirror of https://github.com/soimort/you-get.git synced 2025-01-23 13:35:16 +03:00
Code Issues Actions Packages Projects Releases 1 Wiki Activity

[twitter] fix extraction

Browse Source
This commit is contained in:
Mort Yao 2024-10-27 23:57:56 +01:00
parent 1c9c0f3ed1
commit 5b4142dc4a
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 9 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -15,6 +15,12 @@ def extract_m3u(source):
return ['https://video.twimg.com%s' % i for i in s2] return ['https://video.twimg.com%s' % i for i in s2]
def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs): def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs):
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:88.0) Gecko/20100101 Firefox/88.0',
'Accept-Encoding': 'gzip, deflate',
'Accept': '*/*'
}
if re.match(r'https?://pbs\.twimg\.com', url): if re.match(r'https?://pbs\.twimg\.com', url):
universal_download(url, output_dir, merge=merge, info_only=info_only, **kwargs) universal_download(url, output_dir, merge=merge, info_only=info_only, **kwargs)
return return
@ -52,7 +58,7 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
photo_url = photo['url'] photo_url = photo['url']
title = item_id + '_' + photo_url.split('.')[-2].split('/')[-1] title = item_id + '_' + photo_url.split('.')[-2].split('/')[-1]
urls = [ photo_url + ':orig' ] urls = [ photo_url + ':orig' ]
size = urls_size(urls) size = urls_size(urls, headers=headers)
ext = photo_url.split('.')[-1] ext = photo_url.split('.')[-1]
print_info(site_info, title, ext, size) print_info(site_info, title, ext, size)
@ -66,12 +72,12 @@ def twitter_download(url, output_dir='.', merge=True, info_only=False, **kwargs)
variants = sorted(variants, key=lambda kv: kv.get('bitrate', 0)) variants = sorted(variants, key=lambda kv: kv.get('bitrate', 0))
title = item_id + '_' + variants[-1]['url'].split('/')[-1].split('?')[0].split('.')[0] title = item_id + '_' + variants[-1]['url'].split('/')[-1].split('?')[0].split('.')[0]
urls = [ variants[-1]['url'] ] urls = [ variants[-1]['url'] ]
size = urls_size(urls) size = urls_size(urls, headers=headers)
mime, ext = variants[-1]['content_type'], 'mp4' mime, ext = variants[-1]['content_type'], 'mp4'
print_info(site_info, title, ext, size) print_info(site_info, title, ext, size)
if not info_only: if not info_only:
download_urls(urls, title, ext, size, output_dir, merge=merge) download_urls(urls, title, ext, size, output_dir, merge=merge, headers=headers)
# TODO: should we deal with quoted tweets? # TODO: should we deal with quoted tweets?