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

@@ -151,7 +151,7 @@ class BehanceUserExtractor(BehanceExtractor):
"""Extractor for a user's galleries from www.behance.net"""
subcategory = "user"
categorytransfer = True
pattern = r"(?:https?://)?(?:www\.)?behance\.net/([^/?&#]+)/?$"
pattern = r"(?:https?://)?(?:www\.)?behance\.net/([^/?#]+)/?$"
test = ("https://www.behance.net/alexstrohl", {
"count": ">= 8",
"pattern": BehanceGalleryExtractor.pattern,