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

@@ -158,7 +158,7 @@ class HitomiTagExtractor(Extractor):
subcategory = "tag"
pattern = (r"(?:https?://)?hitomi\.la/"
r"(tag|artist|group|series|type|character)/"
r"([^/?&#]+)\.html")
r"([^/?#]+)\.html")
test = (
("https://hitomi.la/tag/screenshots-japanese.html", {
"pattern": HitomiGalleryExtractor.pattern,