remove '&' from URL patterns
'/?&#' -> '/?#' 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:
@@ -60,7 +60,7 @@ class InkbunnyExtractor(Extractor):
|
||||
class InkbunnyUserExtractor(InkbunnyExtractor):
|
||||
"""Extractor for inkbunny user profiles"""
|
||||
subcategory = "user"
|
||||
pattern = BASE_PATTERN + r"/(?!s/)(gallery/|scraps/)?([^/?&#]+)"
|
||||
pattern = BASE_PATTERN + r"/(?!s/)(gallery/|scraps/)?([^/?#]+)"
|
||||
test = (
|
||||
("https://inkbunny.net/soina", {
|
||||
"pattern": r"https://[\w.]+\.metapix\.net/files/full"
|
||||
|
||||
Reference in New Issue
Block a user