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/gfycat.py
View File

@@ -56,7 +56,7 @@ class GfycatUserExtractor(GfycatExtractor):
"""Extractor for gfycat user profiles"""
subcategory = "user"
directory_fmt = ("{category}", "{userName}")
pattern = r"(?:https?://)?gfycat\.com/@([^/?&#]+)"
pattern = r"(?:https?://)?gfycat\.com/@([^/?#]+)"
test = ("https://gfycat.com/@gretta", {
"pattern": r"https://giant\.gfycat\.com/[A-Za-z]+\.mp4",
"count": ">= 100",
@@ -70,7 +70,7 @@ class GfycatSearchExtractor(GfycatExtractor):
"""Extractor for gfycat search results"""
subcategory = "search"
directory_fmt = ("{category}", "Search", "{search}")
pattern = r"(?:https?://)?gfycat\.com/gifs/search/([^/?&#]+)"
pattern = r"(?:https?://)?gfycat\.com/gifs/search/([^/?#]+)"
test = ("https://gfycat.com/gifs/search/funny+animals", {
"pattern": r"https://\w+\.gfycat\.com/[A-Za-z]+\.mp4",
"archive": False,