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

[universal] fix blogger

Browse Source
This commit is contained in:
Mort Yao 2021-08-27 05:14:00 +02:00
parent 5498c377ff
commit 63fd9716a8
No known key found for this signature in database
GPG Key ID: 07DA00CB78203251
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
src/you_get/extractors/universal.py
View File

@ -70,12 +70,13 @@ def universal_download(url, output_dir='.', merge=True, info_only=False, **kwarg
'[-_][6-9]\d\dx1\d\d\d\.jpe?g', '[-_][6-9]\d\dx1\d\d\d\.jpe?g',
'[-_][6-9]\d\dx[6-9]\d\d\.jpe?g', '[-_][6-9]\d\dx[6-9]\d\d\.jpe?g',
's1600/[\w%]+\.jpe?g', # blogger 's1600/[\w%]+\.jpe?g', # blogger
'blogger\.googleusercontent\.com/img/a/\w*', # blogger
'img[6-9]\d\d/[\w%]+\.jpe?g' # oricon? 'img[6-9]\d\d/[\w%]+\.jpe?g' # oricon?
] ]
urls = [] urls = []
for i in media_exts: for i in media_exts:
urls += re.findall(r'(https?://[^ ;&"\'\\<>]+' + i + r'[^ ;&"\'\\<>]*)', page) urls += re.findall(r'(https?://[^ ;&"\'\\<>]*' + i + r'[^ ;&"\'\\<>]*)', page)
p_urls = re.findall(r'(https?%3A%2F%2F[^;&"]+' + i + r'[^;&"]*)', page) p_urls = re.findall(r'(https?%3A%2F%2F[^;&"]+' + i + r'[^;&"]*)', page)
urls += [parse.unquote(url) for url in p_urls] urls += [parse.unquote(url) for url in p_urls]