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
|
# -*- coding: utf-8 -*-
# Copyright 2025 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://yourlesbians.com/"""
from .common import GalleryExtractor
from .. import text
BASE_PATTERN = r"(?:https?://)?(?:www\.)?yourlesbians\.com"
class YourlesbiansAlbumExtractor(GalleryExtractor):
category = "yourlesbians"
subcategory = "album"
root = "https://yourlesbians.com"
directory_fmt = ("{category}", "{title}")
filename_fmt = "{num:>03} {filename}.{extension}"
archive_fmt = "{title}/{num}"
pattern = BASE_PATTERN + r"(/album/([^/?#]+)/?)"
example = "https://yourlesbians.com/album/SLUG/"
def metadata(self, page):
extr = text.extract_from(page)
data = {
"album_url": extr('property="og:url" content="', '"'),
"title": text.unescape(extr(
'property="og:title" content="', '"')[:-8].rstrip()),
"album_thumbnail": extr('property="og:image" content="', '"'),
"description": extr('property="og:description" content="', '"'),
"tags": text.split_html(extr('tags-row', '</div>'))[1:],
}
if data["description"].endswith(", right after."):
data["description"] = ""
self.album = extr('class="album-inner', "</div>")
return data
def images(self, _):
results = []
for url in text.extract_iter(self.album, '<a href="', '"'):
fn, _, ext = url.rsplit("/", 2)[1].rpartition(".")
results.append((url, {
"filename" : fn,
"extension": ext,
}))
return results
|
