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/foolslide.py
View File

@@ -45,7 +45,7 @@ class FoolslideChapterExtractor(FoolslideBase, ChapterExtractor):
"""Base class for chapter extractors for FoOlSlide based sites"""
directory_fmt = ("{category}", "{manga}", "{chapter_string}")
archive_fmt = "{id}"
pattern_fmt = r"(/read/[^/?&#]+/[a-z-]+/\d+/\d+(?:/\d+)?)"
pattern_fmt = r"(/read/[^/?#]+/[a-z-]+/\d+/\d+(?:/\d+)?)"
decode = "default"
def items(self):
@@ -86,7 +86,7 @@ class FoolslideChapterExtractor(FoolslideBase, ChapterExtractor):
class FoolslideMangaExtractor(FoolslideBase, MangaExtractor):
"""Base class for manga extractors for FoOlSlide based sites"""
pattern_fmt = r"(/series/[^/?&#]+)"
pattern_fmt = r"(/series/[^/?#]+)"
def chapters(self, page):
extr = text.extract_from(page)