github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[blogger] move original/s0 URL code into a separate function

Browse Source
This commit is contained in:
Mike Fährmann
2025-06-12 17:03:30 +02:00
parent e0a961047c
commit 56ea27c474
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
gallery_dl/extractor/blogger.py
View File

@@ -12,6 +12,12 @@ from .common import BaseExtractor, Message
from .. import text, util from .. import text, util
def original(url):
return (util.re(r"(/|=)(?:[sw]\d+|w\d+-h\d+)(?=/|$)")
.sub(r"\1s0", url)
.replace("http:", "https:", 1))
class BloggerExtractor(BaseExtractor): class BloggerExtractor(BaseExtractor):
"""Base class for blogger extractors""" """Base class for blogger extractors"""
basecategory = "blogger" basecategory = "blogger"
@@ -32,7 +38,6 @@ class BloggerExtractor(BaseExtractor):
blog["date"] = text.parse_datetime(blog["published"]) blog["date"] = text.parse_datetime(blog["published"])
del blog["selfLink"] del blog["selfLink"]
sub = util.re(r"(/|=)(?:[sw]\d+|w\d+-h\d+)(?=/|$)").sub
findall_image = util.re( findall_image = util.re(
r'src="(https?://(?:' r'src="(https?://(?:'
r'blogger\.googleusercontent\.com/img|' r'blogger\.googleusercontent\.com/img|'
@@ -47,7 +52,7 @@ class BloggerExtractor(BaseExtractor):
files = findall_image(content) files = findall_image(content)
for idx, url in enumerate(files): for idx, url in enumerate(files):
files[idx] = sub(r"\1s0", url).replace("http:", "https:", 1) files[idx] = original(url)
if self.videos and 'id="BLOG_video-' in content: if self.videos and 'id="BLOG_video-' in content:
page = self.request(post["url"]).text page = self.request(post["url"]).text