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
|
# -*- 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://sizebooru.com/"""
from .booru import BooruExtractor
from .. import text
BASE_PATTERN = r"(?:https?://)?(?:www\.)?sizebooru\.com"
class SizebooruExtractor(BooruExtractor):
"""Base class for sizebooru extractors"""
category = "sizebooru"
root = "https://sizebooru.com"
filename_fmt = "{id}.{extension}"
archive_fmt = "{id}"
page_start = 1
request_interval = (0.5, 1.5)
def _init(self):
if self.config("metadata", False):
self._prepare = self._prepare_metadata
def _file_url(self, post):
post["file_url"] = url = f"{self.root}/Picture/{post['id']}"
return url
def _prepare(self, post):
post_id = post["id"]
post["id"] = text.parse_int(post_id)
post["filename"] = post_id
if not post["extension"]:
post["extension"] = "jpg"
def _prepare_metadata(self, post):
post_id = post["id"]
url = f"{self.root}/Details/{post_id}"
extr = text.extract_from(self.request(url).text)
post.update({
"id" : text.parse_int(post_id),
"date" : self.parse_datetime(
extr("<b>Posted Date:</b> ", "<"), "%m/%d/%Y"),
"date_approved": self.parse_datetime(
extr("<b>Approved Date:</b> ", "<"), "%m/%d/%Y"),
"approver" : text.remove_html(extr("<b>Approved By:</b>", "</")),
"uploader" : text.remove_html(extr("<b>Posted By:</b>", "</")),
"artist" : None
if (artist := extr("<b>Artist:</b> ", "</")) == "N/A" else # noqa: E131 E501
text.remove_html(artist), # noqa: E131
"views" : text.parse_int(extr("<b>Views:</b>", "<")),
"source" : text.extr(extr(
"<b>Source Link:</b>", "</"), ' href="', '"') or None,
"tags" : text.split_html(extr(
"<h6>Related Tags</h6>", "</ul>")),
"favorite" : text.split_html(extr(
"<h6>Favorited By</h6>", "</ul>")),
})
post["filename"], _, ext = extr('" alt="', '"').rpartition(".")
if not post["extension"]:
post["extension"] = ext.lower()
return post
def _pagination(self, url, callback=None):
params = {
"pageNo" : self.page_start,
"pageSize": self.per_page,
}
page = self.request(url, params=params).text
if callback is not None:
callback(page)
while True:
thumb = None
for thumb in text.extract_iter(
page, '<a href="/Details/', ';base64'):
yield {
"id" : thumb[:thumb.find('"')],
"extension": thumb[thumb.rfind("/")+1:],
}
if "disabled" in text.extr(page, 'area-label="Next"', ">") or \
thumb is None:
return
params["pageNo"] += 1
page = self.request(url, params=params).text
class SizebooruPostExtractor(SizebooruExtractor):
"""Extractor for sizebooru posts"""
subcategory = "post"
pattern = BASE_PATTERN + r"/Details/(\d+)"
example = "https://sizebooru.com/Details/12345"
def posts(self):
return ({"id": self.groups[0], "extension": None},)
class SizebooruTagExtractor(SizebooruExtractor):
"""Extractor for sizebooru tag searches"""
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
pattern = BASE_PATTERN + r"/Search/([^/?#]+)"
example = "https://sizebooru.com/Search/TAG"
def posts(self):
tag = self.groups[0]
self.kwdict["search_tags"] = text.unquote(tag)
return self._pagination(f"{self.root}/Search/{tag}")
class SizebooruGalleryExtractor(SizebooruExtractor):
"""Extractor for sizebooru galleries"""
subcategory = "gallery"
directory_fmt = ("{category}", "{gallery_name} ({gallery_id})")
pattern = BASE_PATTERN + r"/Galleries/List/(\d+)"
example = "https://sizebooru.com/Galleries/List/123"
def posts(self):
gid = self.groups[0]
self.kwdict["gallery_id"] = text.parse_int(gid)
return self._pagination(
f"{self.root}/Galleries/List/{gid}", self._extract_name)
def _extract_name(self, page):
self.kwdict["gallery_name"] = text.unescape(text.extr(
page, "<title>Gallery: ", " - Size Booru<"))
class SizebooruUserExtractor(SizebooruExtractor):
"""Extractor for a sizebooru user's uploads"""
subcategory = "user"
directory_fmt = ("{category}", "Uploads {user}")
pattern = BASE_PATTERN + r"/Profile/Uploads/([^/?#]+)"
example = "https://sizebooru.com/Profile/Uploads/USER"
def posts(self):
user = self.groups[0]
self.kwdict["user"] = text.unquote(user)
return self._pagination(f"{self.root}/Profile/Uploads/{user}",)
class SizebooruFavoriteExtractor(SizebooruExtractor):
"""Extractor for a sizebooru user's favorites"""
subcategory = "favorite"
directory_fmt = ("{category}", "Favorites {user}")
pattern = BASE_PATTERN + r"/Profile/Favorites/([^/?#]+)"
example = "https://sizebooru.com/Profile/Favorites/USER"
def posts(self):
user = self.groups[0]
self.kwdict["user"] = text.unquote(user)
return self._pagination(f"{self.root}/Profile/Favorites/{user}",)
|
