From 4f7a0e5d022d38e479b0213a02315e7c9fbbbc93 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= Date: Wed, 18 Jun 2025 21:12:18 +0200 Subject: [PATCH] [arcalive] fix download URLs (#7678) https://github.com/danbooru/danbooru/pull/6041 --- gallery_dl/extractor/arcalive.py | 13 ++++++----- test/results/arcalive.py | 39 ++++++++++++++++---------------- 2 files changed, 27 insertions(+), 25 deletions(-) diff --git a/gallery_dl/extractor/arcalive.py b/gallery_dl/extractor/arcalive.py index b7181fe0..114c124f 100644 --- a/gallery_dl/extractor/arcalive.py +++ b/gallery_dl/extractor/arcalive.py @@ -74,7 +74,7 @@ class ArcalivePostExtractor(ArcaliveExtractor): if not src: continue - src = text.unescape(src.partition("?")[0]) + src, _, query = text.unescape(src).partition("?") if src[0] == "/": if src[1] == "/": url = "https:" + src.replace( @@ -85,26 +85,27 @@ class ArcalivePostExtractor(ArcaliveExtractor): url = src fallback = () + query = f"?type=orig&{query}" orig = text.extr(media, 'data-orig="', '"') if orig: path, _, ext = url.rpartition(".") if ext != orig: - fallback = (url + "?type=orig",) + fallback = (url + query,) url = path + "." + orig elif video and self.gifs: url_gif = url.rpartition(".")[0] + ".gif" if self.gifs_fallback: - fallback = (url + "?type=orig",) + fallback = (url + query,) url = url_gif else: response = self.request( - url_gif + "?type=orig", method="HEAD", fatal=False) + url_gif + query, method="HEAD", fatal=False) if response.status_code < 400: - fallback = (url + "?type=orig",) + fallback = (url + query,) url = url_gif files.append({ - "url" : url + "?type=orig", + "url" : url + query, "width" : text.parse_int(text.extr(media, 'width="', '"')), "height": text.parse_int(text.extr(media, 'height="', '"')), "_fallback": fallback, diff --git a/test/results/arcalive.py b/test/results/arcalive.py index 607f3222..6848cf89 100644 --- a/test/results/arcalive.py +++ b/test/results/arcalive.py @@ -11,7 +11,8 @@ __tests__ = ( { "#url" : "https://arca.live/b/arknights/66031722?p=1", "#class" : arcalive.ArcalivePostExtractor, - "#results": "https://ac.namu.la/20221225sac2/e06dcf8edd29c597240898a6752c74dbdd0680fc932cfd0ecc898795f1db34b5.jpg?type=orig", + "#pattern": r"https://ac.namu.la/20221225sac2/e06dcf8edd29c597240898a6752c74dbdd0680fc932cfd0ecc898795f1db34b5.jpg\?type=orig&expires=\d+&key=\w+", + "#count" : 1, "isEditable": False, "isDeletable": False, @@ -49,7 +50,7 @@ __tests__ = ( "post_url": "https://arca.live/b/arknights/66031722", "count": 1, "num": 1, - "url": "https://ac.namu.la/20221225sac2/e06dcf8edd29c597240898a6752c74dbdd0680fc932cfd0ecc898795f1db34b5.jpg?type=orig", + "url": str, "width": 3200, "height": 1440, "filename": "e06dcf8edd29c597240898a6752c74dbdd0680fc932cfd0ecc898795f1db34b5", @@ -60,17 +61,17 @@ __tests__ = ( "#url" : "https://arca.live/b/breaking/66031722", "#comment": "/b/breaking page URL", "#class" : arcalive.ArcalivePostExtractor, - "#results": "https://ac.namu.la/20221225sac2/e06dcf8edd29c597240898a6752c74dbdd0680fc932cfd0ecc898795f1db34b5.jpg?type=orig", + "#pattern": r"https://ac.namu.la/20221225sac2/e06dcf8edd29c597240898a6752c74dbdd0680fc932cfd0ecc898795f1db34b5.jpg\?type=orig", }, { "#url" : "https://arca.live/b/bluearchive/65031202", "#comment": "animated gif", "#class" : arcalive.ArcalivePostExtractor, - "#results": ( - "https://ac.namu.la/20221211sac/5ea7fbca5e49ec16beb099fc6fc991690d37552e599b1de8462533908346241e.png?type=orig", - "https://ac.namu.la/20221211sac/7f73beefc4f18a2f986bc4c6821caba706e27f4c94cb828fc16e2af1253402d9.gif?type=orig", - "https://ac.namu.la/20221211sac2/3e72f9e05ca97c0c3c0fe5f25632b06eb21ab9f211e9ea22816e16468ee241ca.png?type=orig", + "#pattern": ( + r"https://ac.namu.la/20221211sac/5ea7fbca5e49ec16beb099fc6fc991690d37552e599b1de8462533908346241e.png\?type=orig", + r"https://ac.namu.la/20221211sac/7f73beefc4f18a2f986bc4c6821caba706e27f4c94cb828fc16e2af1253402d9.gif\?type=orig", + r"https://ac.namu.la/20221211sac2/3e72f9e05ca97c0c3c0fe5f25632b06eb21ab9f211e9ea22816e16468ee241ca.png\?type=orig", ), }, @@ -78,9 +79,9 @@ __tests__ = ( "#url" : "https://arca.live/b/arknights/122263340", "#comment": "animated webp", "#class" : arcalive.ArcalivePostExtractor, - "#results": ( - "https://ac.namu.la/20241126sac/b2175d9ef4504945d3d989526120dbb6aded501ddedfba8ecc44a64e7aae9059.gif?type=orig", - "https://ac.namu.la/20241126sac/bc1f3cb388a3a2d099ab67bc09b28f0a93c2c4755152b3ef9190690a9f0a28fb.webp?type=orig", + "#pattern": ( + r"https://ac.namu.la/20241126sac/b2175d9ef4504945d3d989526120dbb6aded501ddedfba8ecc44a64e7aae9059.gif\?type=orig", + r"https://ac.namu.la/20241126sac/bc1f3cb388a3a2d099ab67bc09b28f0a93c2c4755152b3ef9190690a9f0a28fb.webp\?type=orig", ), }, @@ -89,7 +90,7 @@ __tests__ = ( "#comment": ".mp4 video", "#class" : arcalive.ArcalivePostExtractor, "#options": {"gifs": "check"}, - "#results": "https://ac.namu.la/20240926sac/16f07778a97f91b935c8a3394ead01a223d96b2a619fdb25c4628ddba88b5fad.mp4?type=orig", + "#pattern": r"https://ac.namu.la/20240926sac/16f07778a97f91b935c8a3394ead01a223d96b2a619fdb25c4628ddba88b5fad.mp4\?type=orig", }, { @@ -97,9 +98,9 @@ __tests__ = ( "#comment": "fake .mp4 GIF", "#class" : arcalive.ArcalivePostExtractor, "#options": {"gifs": True}, - "#results": "https://ac.namu.la/20240714sac/c8fcadeb0b578e5121eb7a7e8fb05984cb87c68e7a6e0481a1c8869bf0ecfd2b.gif?type=orig", + "#pattern": r"https://ac.namu.la/20240714sac/c8fcadeb0b578e5121eb7a7e8fb05984cb87c68e7a6e0481a1c8869bf0ecfd2b.gif\?type=orig", - "_fallback": ("https://ac.namu.la/20240714sac/c8fcadeb0b578e5121eb7a7e8fb05984cb87c68e7a6e0481a1c8869bf0ecfd2b.mp4?type=orig",), + "_fallback": "len:tuple:1", }, { @@ -107,14 +108,14 @@ __tests__ = ( "#comment": "fake .mp4 GIF", "#class" : arcalive.ArcalivePostExtractor, "#options": {"gifs": False}, - "#results": "https://ac.namu.la/20240714sac/c8fcadeb0b578e5121eb7a7e8fb05984cb87c68e7a6e0481a1c8869bf0ecfd2b.mp4?type=orig", + "#pattern": r"https://ac.namu.la/20240714sac/c8fcadeb0b578e5121eb7a7e8fb05984cb87c68e7a6e0481a1c8869bf0ecfd2b.mp4\?type=orig", }, { "#url" : "https://arca.live/b/arknights/49406926", "#comment": "static emoticon", "#class" : arcalive.ArcalivePostExtractor, - "#results": "https://ac.namu.la/20220428sac2/41f472adcea674aff75f15f146e81c27032bc4d6c8073bd7c19325bd1c97d335.png?type=orig", + "#pattern": r"https://ac.namu.la/20220428sac2/41f472adcea674aff75f15f146e81c27032bc4d6c8073bd7c19325bd1c97d335.png\?type=orig", }, { @@ -122,10 +123,10 @@ __tests__ = ( "#comment": "animated emoticon", "#class" : arcalive.ArcalivePostExtractor, "#options": {"emoticons": True}, - "#results": ( - "https://ac.namu.la/20221123sac2/14925c5e22ab9f17f2923ae60a39b7af0794c43e478ecaba054ab6131e57e022.png?type=orig", - "https://ac.namu.la/20221123sac2/50c385a4004bca44271a2f6133990f086cfefd29a7968514e9c14d6017d61265.png?type=orig", - "https://ac.namu.la/20221005sac2/28ebe073fffbb2b88f710c2d380b0fe6dd99a856070c4a836db57634a5371366.gif?type=orig", + "#pattern": ( + r"https://ac.namu.la/20221123sac2/14925c5e22ab9f17f2923ae60a39b7af0794c43e478ecaba054ab6131e57e022.png\?type=orig", + r"https://ac.namu.la/20221123sac2/50c385a4004bca44271a2f6133990f086cfefd29a7968514e9c14d6017d61265.png\?type=orig", + r"https://ac.namu.la/20221005sac2/28ebe073fffbb2b88f710c2d380b0fe6dd99a856070c4a836db57634a5371366.gif\?type=orig", ), },