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
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
|
# -*- coding: utf-8 -*-
# Copyright 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 Chevereto galleries"""
from .common import BaseExtractor, Message
from .. import text, util
class CheveretoExtractor(BaseExtractor):
"""Base class for chevereto extractors"""
basecategory = "chevereto"
directory_fmt = ("{category}", "{user}", "{album}",)
archive_fmt = "{id}"
def _init(self):
self.path = self.groups[-1]
def _pagination(self, url):
while True:
page = self.request(url).text
for item in text.extract_iter(
page, '<div class="list-item-image ', 'image-container'):
yield text.urljoin(self.root, text.extr(
item, '<a href="', '"'))
url = text.extr(page, 'data-pagination="next" href="', '"')
if not url:
return
if url[0] == "/":
url = self.root + url
BASE_PATTERN = CheveretoExtractor.update({
"jpgfish": {
"root": "https://jpg5.su",
"pattern": r"jpe?g\d?\.(?:su|pet|fish(?:ing)?|church)",
},
"imgkiwi": {
"root": "https://img.kiwi",
"pattern": r"img\.kiwi",
},
"imagepond": {
"root": "https://imagepond.net",
"pattern": r"imagepond\.net",
},
})
class CheveretoImageExtractor(CheveretoExtractor):
"""Extractor for chevereto Images"""
subcategory = "image"
pattern = BASE_PATTERN + r"(/im(?:g|age)/[^/?#]+)"
example = "https://jpg2.su/img/TITLE.ID"
def items(self):
url = self.root + self.path
page = self.request(url).text
extr = text.extract_from(page)
url = (extr('<meta property="og:image" content="', '"') or
extr('url: "', '"'))
if not url or url.endswith("/loading.svg"):
pos = page.find(" download=")
url = text.rextract(page, 'href="', '"', pos)[0]
if not url.startswith("https://"):
url = util.decrypt_xor(
url, b"seltilovessimpcity@simpcityhatesscrapers",
fromhex=True)
image = {
"id" : self.path.rpartition(".")[2],
"url" : url,
"album": text.extr(extr("Added to <a", "/a>"), ">", "<"),
"user" : extr('username: "', '"'),
}
text.nameext_from_url(image["url"], image)
yield Message.Directory, image
yield Message.Url, image["url"], image
class CheveretoAlbumExtractor(CheveretoExtractor):
"""Extractor for chevereto Albums"""
subcategory = "album"
pattern = BASE_PATTERN + r"(/a(?:lbum)?/[^/?#]+(?:/sub)?)"
example = "https://jpg2.su/album/TITLE.ID"
def items(self):
url = self.root + self.path
data = {"_extractor": CheveretoImageExtractor}
if self.path.endswith("/sub"):
albums = self._pagination(url)
else:
albums = (url,)
for album in albums:
for image in self._pagination(album):
yield Message.Queue, image, data
class CheveretoUserExtractor(CheveretoExtractor):
"""Extractor for chevereto Users"""
subcategory = "user"
pattern = BASE_PATTERN + r"(/(?!img|image|a(?:lbum)?)[^/?#]+(?:/albums)?)"
example = "https://jpg2.su/USER"
def items(self):
url = self.root + self.path
if self.path.endswith("/albums"):
data = {"_extractor": CheveretoAlbumExtractor}
else:
data = {"_extractor": CheveretoImageExtractor}
for url in self._pagination(url):
yield Message.Queue, url, data
|
