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:
@@ -64,7 +64,7 @@ class _8kunBoardExtractor(Extractor):
|
||||
"""Extractor for 8kun boards"""
|
||||
category = "8kun"
|
||||
subcategory = "board"
|
||||
pattern = r"(?:https?://)?8kun\.top/([^/?&#]+)/(?:index|\d+)\.html"
|
||||
pattern = r"(?:https?://)?8kun\.top/([^/?#]+)/(?:index|\d+)\.html"
|
||||
test = (
|
||||
("https://8kun.top/v/index.html", {
|
||||
"pattern": _8kunThreadExtractor.pattern,
|
||||
|
||||
Reference in New Issue
Block a user