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/hentai2read.py
View File

@@ -23,7 +23,7 @@ class Hentai2readBase():
class Hentai2readChapterExtractor(Hentai2readBase, ChapterExtractor):
"""Extractor for a single manga chapter from hentai2read.com"""
archive_fmt = "{chapter_id}_{page}"
pattern = r"(?:https?://)?(?:www\.)?hentai2read\.com(/[^/?&#]+/(\d+))"
pattern = r"(?:https?://)?(?:www\.)?hentai2read\.com(/[^/?#]+/(\d+))"
test = ("https://hentai2read.com/amazon_elixir/1/", {
"url": "964b942cf492b3a129d2fe2608abfc475bc99e71",
"keyword": "ff84b8f751f0e4ee37717efc4332ff1db71951d9",
@@ -63,7 +63,7 @@ class Hentai2readChapterExtractor(Hentai2readBase, ChapterExtractor):
class Hentai2readMangaExtractor(Hentai2readBase, MangaExtractor):
"""Extractor for hmanga from hentai2read.com"""
chapterclass = Hentai2readChapterExtractor
pattern = r"(?:https?://)?(?:www\.)?hentai2read\.com(/[^/?&#]+)/?$"
pattern = r"(?:https?://)?(?:www\.)?hentai2read\.com(/[^/?#]+)/?$"
test = (
("https://hentai2read.com/amazon_elixir/", {
"url": "273073752d418ec887d7f7211e42b832e8c403ba",