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

@@ -84,7 +84,7 @@ class LivedoorExtractor(Extractor):
class LivedoorBlogExtractor(LivedoorExtractor):
"""Extractor for a user's blog on blog.livedoor.jp"""
subcategory = "blog"
pattern = r"(?:https?://)?blog\.livedoor\.jp/(\w+)/?(?:$|[?&#])"
pattern = r"(?:https?://)?blog\.livedoor\.jp/(\w+)/?(?:$|[?#])"
test = (
("http://blog.livedoor.jp/zatsu_ke/", {
"range": "1-50",