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

@@ -45,7 +45,7 @@ class KomikcastBase():
class KomikcastChapterExtractor(KomikcastBase, ChapterExtractor):
"""Extractor for manga-chapters from komikcast.com"""
pattern = r"(?:https?://)?(?:www\.)?komikcast\.com(/chapter/[^/?&#]+/)"
pattern = r"(?:https?://)?(?:www\.)?komikcast\.com(/chapter/[^/?#]+/)"
test = (
(("https://komikcast.com/chapter/"
"apotheosis-chapter-02-2-bahasa-indonesia/"), {
@@ -81,7 +81,7 @@ class KomikcastMangaExtractor(KomikcastBase, MangaExtractor):
"""Extractor for manga from komikcast.com"""
chapterclass = KomikcastChapterExtractor
pattern = (r"(?:https?://)?(?:www\.)?komikcast\.com"
r"(/(?:komik/)?[^/?&#]+)/?$")
r"(/(?:komik/)?[^/?#]+)/?$")
test = (
("https://komikcast.com/komik/090-eko-to-issho/", {
"url": "dc798d107697d1f2309b14ca24ca9dba30c6600f",