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/issuu.py
View File

@@ -26,7 +26,7 @@ class IssuuPublicationExtractor(IssuuBase, GalleryExtractor):
"{document[originalPublishDate]} {document[title]}")
filename_fmt = "{num:>03}.{extension}"
archive_fmt = "{document[id]}_{num}"
pattern = r"(?:https?://)?issuu\.com(/[^/?&#]+/docs/[^/?&#]+)"
pattern = r"(?:https?://)?issuu\.com(/[^/?#]+/docs/[^/?#]+)"
test = ("https://issuu.com/issuu/docs/motions-1-2019/", {
"pattern": r"https://image.isu.pub/190916155301-\w+/jpg/page_\d+.jpg",
"count" : 36,
@@ -80,7 +80,7 @@ class IssuuPublicationExtractor(IssuuBase, GalleryExtractor):
class IssuuUserExtractor(IssuuBase, Extractor):
"""Extractor for all publications of a user/publisher"""
subcategory = "user"
pattern = r"(?:https?://)?issuu\.com/([^/?&#]+)/?$"
pattern = r"(?:https?://)?issuu\.com/([^/?#]+)/?$"
test = ("https://issuu.com/issuu", {
"pattern": IssuuPublicationExtractor.pattern,
"count" : "> 25",