1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
|
# -*- coding: utf-8 -*-
# Copyright 2022-2023 Mike Fährmann
#
# This program is free software; you can redistribute it and/or modify
# it under the terms of the GNU General Public License version 2 as
# published by the Free Software Foundation.
"""Extractors for https://catbox.moe/"""
from .common import GalleryExtractor, Extractor, Message
from .. import text
class CatboxAlbumExtractor(GalleryExtractor):
"""Extractor for catbox albums"""
category = "catbox"
subcategory = "album"
root = "https://catbox.moe"
filename_fmt = "{filename}.{extension}"
directory_fmt = ("{category}", "{album_name} ({album_id})")
archive_fmt = "{album_id}_{filename}"
pattern = r"(?:https?://)?(?:www\.)?catbox\.moe(/c/[^/?#]+)"
example = "https://catbox.moe/c/ID"
def metadata(self, page):
extr = text.extract_from(page)
return {
"album_id" : self.page_url.rpartition("/")[2],
"album_name" : text.unescape(extr("<h1>", "<")),
"date" : self.parse_datetime(extr(
"<p>Created ", "<"), "%B %d %Y"),
"description": text.unescape(extr("<p>", "<")),
}
def images(self, page):
return [
("https://files.catbox.moe/" + path, None)
for path in text.extract_iter(
page, ">https://files.catbox.moe/", "<")
]
class CatboxFileExtractor(Extractor):
"""Extractor for catbox files"""
category = "catbox"
subcategory = "file"
archive_fmt = "{filename}"
pattern = r"(?:https?://)?(?:files|litter|de)\.catbox\.moe/([^/?#]+)"
example = "https://files.catbox.moe/NAME.EXT"
def items(self):
url = text.ensure_http_scheme(self.url)
file = text.nameext_from_url(url, {"url": url})
yield Message.Directory, "", file
yield Message.Url, url, file
|
