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

@@ -118,7 +118,7 @@ class PornhubGalleryExtractor(PornhubExtractor):
class PornhubUserExtractor(PornhubExtractor):
"""Extractor for all galleries of a pornhub user"""
subcategory = "user"
pattern = (BASE_PATTERN + r"/(users|model)/([^/?&#]+)"
pattern = (BASE_PATTERN + r"/(users|model)/([^/?#]+)"
"(?:/photos(?:/(public|private|favorites))?)?/?$")
test = (
("https://www.pornhub.com/users/flyings0l0/photos/public", {