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:
Mike Fährmann
2020-10-22 23:12:59 +02:00
parent 1686dc1757
commit 968d3e8465
74 changed files with 158 additions and 158 deletions

View File

@@ -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",