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

@@ -24,7 +24,7 @@ class MangahereBase():
class MangahereChapterExtractor(MangahereBase, ChapterExtractor):
"""Extractor for manga-chapters from mangahere.cc"""
pattern = (r"(?:https?://)?(?:www\.|m\.)?mangahere\.c[co]/manga/"
r"([^/]+(?:/v0*(\d+))?/c([^/?&#]+))")
r"([^/]+(?:/v0*(\d+))?/c([^/?#]+))")
test = (
("https://www.mangahere.cc/manga/dongguo_xiaojie/c004.2/", {
"keyword": "7c98d7b50a47e6757b089aa875a53aa970cac66f",