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:
@@ -20,7 +20,7 @@ class SlidesharePresentationExtractor(Extractor):
|
||||
filename_fmt = "{presentation}-{num:>02}.{extension}"
|
||||
archive_fmt = "{presentation}_{num}"
|
||||
pattern = (r"(?:https?://)?(?:www\.)?slideshare\.net"
|
||||
r"/(?:mobile/)?([^/?&#]+)/([^/?&#]+)")
|
||||
r"/(?:mobile/)?([^/?#]+)/([^/?#]+)")
|
||||
test = (
|
||||
(("https://www.slideshare.net"
|
||||
"/Slideshare/get-started-with-slide-share"), {
|
||||
|
||||
Reference in New Issue
Block a user