github/gallery-dl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

remove '&' from URL patterns

Browse Source 
'/?&#' -> '/?#' 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
Download Patch File Download Diff File Expand all files Collapse all files

4
gallery_dl/extractor/mangapanda.py
View File

@@ -35,7 +35,7 @@ class MangapandaBase():
class MangapandaChapterExtractor(MangapandaBase, ChapterExtractor):
"""Extractor for manga-chapters from mangapanda.com"""
archive_fmt = "{manga}_{chapter}_{page}"
pattern = r"(?:https?://)?(?:www\.)?mangapanda\.com((/[^/?&#]+)/(\d+))"
pattern = r"(?:https?://)?(?:www\.)?mangapanda\.com((/[^/?#]+)/(\d+))"
test = ("https://www.mangapanda.com/red-storm/2", {
"url": "1f633f776e950531ba9b1e81965316458e785261",
"keyword": "b24df4b9cc36383fb6a44e06d32a3884a4dcb5fb",
@@ -96,7 +96,7 @@ class MangapandaMangaExtractor(MangapandaBase, MangaExtractor):
"""Extractor for manga from mangapanda.com"""
chapterclass = MangapandaChapterExtractor
reverse = False
pattern = r"(?:https?://)?(?:www\.)?mangapanda\.com(/[^/?&#]+)/?$"
pattern = r"(?:https?://)?(?:www\.)?mangapanda\.com(/[^/?#]+)/?$"
test = ("https://www.mangapanda.com/mushishi", {
"url": "357f965732371cac1990fee8b480f62e29141a42",
"keyword": "031b3ea085921c552de017ecbb9b906e462229c9",