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:
@@ -65,7 +65,7 @@ class _4chanBoardExtractor(Extractor):
|
||||
"""Extractor for 4chan boards"""
|
||||
category = "4chan"
|
||||
subcategory = "board"
|
||||
pattern = r"(?:https?://)?boards\.4chan(?:nel)?\.org/([^/?&#]+)/\d*$"
|
||||
pattern = r"(?:https?://)?boards\.4chan(?:nel)?\.org/([^/?#]+)/\d*$"
|
||||
test = ("https://boards.4channel.org/po/", {
|
||||
"pattern": _4chanThreadExtractor.pattern,
|
||||
"count": ">= 100",
|
||||
|
||||
Reference in New Issue
Block a user