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
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
|
# -*- coding: utf-8 -*-
# Copyright 2023-2025 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 Shimmie2 instances"""
from .common import BaseExtractor, Message
from .. import text
class Shimmie2Extractor(BaseExtractor):
"""Base class for shimmie2 extractors"""
basecategory = "shimmie2"
filename_fmt = "{category}_{id}{md5:?_//}.{extension}"
archive_fmt = "{id}"
def _init(self):
if cookies := self.config_instance("cookies"):
domain = self.root.rpartition("/")[2]
self.cookies_update_dict(cookies, domain=domain)
if file_url := self.config_instance("file_url"):
self.file_url_fmt = file_url
def items(self):
data = self.metadata()
for post in self.posts():
post["id"] = text.parse_int(post["id"])
post["width"] = text.parse_int(post["width"])
post["height"] = text.parse_int(post["height"])
post["tags"] = text.unquote(post["tags"])
post.update(data)
url = post["file_url"]
if "/index.php?" in url:
post["filename"], _, post["extension"] = \
url.rpartition("/")[2].rpartition(".")
else:
text.nameext_from_url(url, post)
yield Message.Directory, post
yield Message.Url, url, post
def metadata(self):
"""Return general metadata"""
return ()
def posts(self):
"""Return an iterable containing data of all relevant posts"""
return ()
def _quote_type(self, page):
"""Return quoting character used in 'page' (' or ")"""
try:
return page[page.index("<link rel=")+10]
except Exception:
return "'"
BASE_PATTERN = Shimmie2Extractor.update({
"cavemanon": {
"root": "https://booru.cavemanon.xyz",
"pattern": r"booru\.cavemanon\.xyz",
"file_url": "{0}/index.php?q=image/{2}.{4}",
},
"rule34hentai": {
"root": "https://rule34hentai.net",
"pattern": r"rule34hentai\.net",
},
"vidyapics": {
"root": "https://vidya.pics",
"pattern": r"vidya\.pics",
},
"nozrip": {
"root": "https://noz.rip/booru",
"base": "https://noz.rip",
"pattern": r"noz\.rip/booru",
},
}) + r"/(?:index\.php\?q=/?)?"
class Shimmie2TagExtractor(Shimmie2Extractor):
"""Extractor for shimmie2 posts by tag search"""
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
file_url_fmt = "{}/_images/{}/{}%20-%20{}.{}"
pattern = BASE_PATTERN + r"post/list/([^/?#]+)(?:/(\d+))?"
example = "https://vidya.pics/post/list/TAG/1"
def metadata(self):
self.tags = text.unquote(self.groups[-2])
return {"search_tags": self.tags}
def posts(self):
pnum = text.parse_int(self.groups[-1], 1)
file_url_fmt = self.file_url_fmt.format
init = True
mime = ""
while True:
url = f"{self.root}/post/list/{self.tags}/{pnum}"
page = self.request(url).text
extr = text.extract_from(page)
if init:
init = False
quote = self._quote_type(page)
has_mime = (" data-mime=" in page)
has_pid = (" data-post-id=" in page)
while True:
if has_mime:
mime = extr(" data-mime="+quote, quote)
if has_pid:
pid = extr(" data-post-id="+quote, quote)
else:
pid = extr(" href='/post/view/", quote)
if not pid:
break
data = extr("title="+quote, quote).split(" // ")
tags = data[0]
dimensions = data[1]
size = data[2]
width, _, height = dimensions.partition("x")
md5 = extr("/_thumbs/", "/")
yield {
"file_url": file_url_fmt(
self.root, md5, pid, text.quote(tags),
mime.rpartition("/")[2] if mime else "jpg"),
"id": pid,
"md5": md5,
"tags": tags,
"width": width,
"height": height,
"size": text.parse_bytes(size[:-1]),
}
pnum += 1
if not extr(">Next<", ">"):
if not extr(f"/{pnum}'>{pnum}<", ">"):
return
class Shimmie2PostExtractor(Shimmie2Extractor):
"""Extractor for single shimmie2 posts"""
subcategory = "post"
pattern = BASE_PATTERN + r"post/view/(\d+)"
example = "https://vidya.pics/post/view/12345"
def posts(self):
post_id = self.groups[-1]
url = f"{self.root}/post/view/{post_id}"
page = self.request(url).text
extr = text.extract_from(page)
base = self.config_instance("base", self.root)
qt = self._quote_type(page)
post = {
"id" : post_id,
"tags" : extr(": ", "<").partition(" - ")[0].rstrip(")"),
"md5" : extr("/_thumbs/", "/"),
"file_url": base + (
extr(f"id={qt}main_image{qt} src={qt}", qt) or
extr("<source src="+qt, qt)).lstrip("."),
"width" : extr("data-width=", " ").strip("\"'"),
"height" : extr("data-height=", ">").partition(
" ")[0].strip("\"'"),
"size" : 0,
}
if not post["md5"]:
post["md5"] = text.extr(post["file_url"], "/_images/", "/")
return (post,)
|
