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

@@ -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,