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

remove '&' from URL patterns

Browse Source 
'/?&#' -> '/?#' and '?&#' -> '?#'

According to https://www.ietf.org/rfc/rfc3986.txt, URLs are
"organized hierarchically" by using "the slash ("/"), question
mark ("?"), and number sign ("#") characters to delimit components"
This commit is contained in:
Mike Fährmann
2020-10-22 23:12:59 +02:00
parent 1686dc1757
commit 968d3e8465
74 changed files with 158 additions and 158 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
gallery_dl/extractor/blogger.py
View File

@@ -92,7 +92,7 @@ class BloggerExtractor(Extractor):
class BloggerPostExtractor(BloggerExtractor):
"""Extractor for a single blog post"""
subcategory = "post"
pattern = BASE_PATTERN + r"(/\d{4}/\d\d/[^/?&#]+\.html)"
pattern = BASE_PATTERN + r"(/\d{4}/\d\d/[^/?#]+\.html)"
test = (
("https://julianbphotography.blogspot.com/2010/12/moon-rise.html", {
"url": "9928429fb62f712eb4de80f53625eccecc614aae",
@@ -171,7 +171,7 @@ class BloggerBlogExtractor(BloggerExtractor):
class BloggerSearchExtractor(BloggerExtractor):
"""Extractor for search resuls and labels"""
subcategory = "search"
pattern = BASE_PATTERN + r"/search(?:/?\?q=([^/?&#]+)|/label/([^/?&#]+))"
pattern = BASE_PATTERN + r"/search(?:/?\?q=([^/?#]+)|/label/([^/?#]+))"
test = (
("https://julianbphotography.blogspot.com/search?q=400mm", {
"count": "< 10"