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:
@@ -169,7 +169,7 @@ class PixnetUserExtractor(PixnetExtractor):
|
||||
"""Extractor for all sets and folders of a pixnet user"""
|
||||
subcategory = "user"
|
||||
url_fmt = "{}{}/album/list"
|
||||
pattern = BASE_PATTERN + r"()(?:/blog|/album(?:/list)?)?/?(?:$|[?&#])"
|
||||
pattern = BASE_PATTERN + r"()(?:/blog|/album(?:/list)?)?/?(?:$|[?#])"
|
||||
test = (
|
||||
("https://albertayu773.pixnet.net/"),
|
||||
("https://albertayu773.pixnet.net/blog"),
|
||||
|
||||
Reference in New Issue
Block a user