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
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
|
# -*- coding: utf-8 -*-
# Copyright 2019-2025 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://nsfwalbum.com/"""
from .common import GalleryExtractor
from .. import text
class NsfwalbumAlbumExtractor(GalleryExtractor):
"""Extractor for image albums on nsfwalbum.com"""
category = "nsfwalbum"
subcategory = "album"
root = "https://nsfwalbum.com"
filename_fmt = "{album_id}_{num:>03}_{id}.{extension}"
directory_fmt = ("{category}", "{album_id} {title}")
archive_fmt = "{id}"
referer = False
pattern = r"(?:https?://)?(?:www\.)?nsfwalbum\.com(/album/(\d+))"
example = "https://nsfwalbum.com/album/12345"
def __init__(self, match):
self.album_id = match[2]
GalleryExtractor.__init__(self, match)
def metadata(self, page):
extr = text.extract_from(page)
return {
"album_id": text.parse_int(self.album_id),
"title" : text.unescape(extr('<h6>', '</h6>')),
"models" : text.split_html(extr('"models"> Models:', '</div>')),
"studio" : text.remove_html(extr('"models"> Studio:', '</div>')),
}
def images(self, page):
iframe = self.root + "/iframe_image.php?id="
backend = self.root + "/backend.php"
retries = self._retries
for image_id in text.extract_iter(page, 'data-img-id="', '"'):
spirit = None
tries = 0
while tries <= retries:
try:
if not spirit:
spirit = self._annihilate(text.extract(
self.request(iframe + image_id).text,
'giraffe.annihilate("', '"')[0])
params = {"spirit": spirit, "photo": image_id}
data = self.request_json(backend, params=params)
break
except Exception:
tries += 1
else:
self.log.warning("Unable to fetch image %s", image_id)
continue
yield data[0], {
"id" : text.parse_int(image_id),
"width" : text.parse_int(data[1]),
"height": text.parse_int(data[2]),
"_http_validate": self._validate_response,
"_fallback": (f"{self.root}/imageProxy.php"
f"?photoId={image_id}&spirit={spirit}",),
}
def _validate_response(self, response):
return not response.url.endswith(
("/no_image.jpg", "/placeholder.png", "/error.jpg"))
def _annihilate(self, value, base=6):
return "".join(
chr(ord(char) ^ base)
for char in value
)
|
