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:
Mike Fährmann
2020-10-22 23:12:59 +02:00
parent 1686dc1757
commit 968d3e8465
74 changed files with 158 additions and 158 deletions

View File

@@ -30,7 +30,7 @@ class SankakucomplexArticleExtractor(SankakucomplexExtractor):
filename_fmt = "{filename}.{extension}"
archive_fmt = "{date:%Y%m%d}_{filename}"
pattern = (r"(?:https?://)?www\.sankakucomplex\.com"
r"/(\d{4}/\d\d/\d\d/[^/?&#]+)")
r"/(\d{4}/\d\d/\d\d/[^/?#]+)")
test = (
("https://www.sankakucomplex.com/2019/05/11/twitter-cosplayers", {
"url": "4a9ecc5ae917fbce469280da5b6a482510cae84d",