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
|
# -*- coding: utf-8 -*-
# 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://hentai-cosplay-xxx.com/
(also works for hentai-img-xxx.com and porn-image.com)"""
from .common import BaseExtractor, GalleryExtractor
from .. import text
class HentaicosplaysExtractor(BaseExtractor):
basecategory = "hentaicosplays"
BASE_PATTERN = HentaicosplaysExtractor.update({
"hentaicosplay": {
"root": "https://hentai-cosplay-xxx.com",
"pattern": r"(?:\w\w\.)?hentai-cosplays?(?:-xxx)?\.com",
},
"hentaiimg": {
"root": "https://hentai-img-xxx.com",
"pattern": r"(?:\w\w\.)?hentai-img(?:-xxx)?\.com",
},
"pornimage": {
"root": "https://porn-image.com",
"pattern": r"(?:\w\w\.)?porn-images?(?:-xxx)?\.com",
},
})
class HentaicosplaysGalleryExtractor(
HentaicosplaysExtractor, GalleryExtractor):
"""Extractor for image galleries from
hentai-cosplay-xxx.com, hentai-img-xxx.com, and porn-image.com"""
directory_fmt = ("{site}", "{title}")
filename_fmt = "{filename}.{extension}"
archive_fmt = "{title}_{filename}"
pattern = rf"{BASE_PATTERN}/(?:image|story)/([\w-]+)"
example = "https://hentai-cosplay-xxx.com/image/TITLE/"
def __init__(self, match):
BaseExtractor.__init__(self, match)
self.slug = self.groups[-1]
self.page_url = f"{self.root}/story/{self.slug}/"
def _init(self):
self.session.headers["Referer"] = self.page_url
def metadata(self, page):
title = text.extr(page, "<title>", "</title>")
return {
"title": text.unescape(title.rpartition(" Story Viewer - ")[0]),
"slug" : self.slug,
"site" : self.root.partition("://")[2].rpartition(".")[0],
}
def images(self, page):
return [
(url.replace("http:", "https:", 1), None)
for url in text.extract_iter(
page, '<amp-img class="auto-style" src="', '"')
]
|
