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
|
# -*- coding: utf-8 -*-
# Copyright 2024-2025 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://realbooru.com/"""
from . import booru
from .. import text, util
import collections
BASE_PATTERN = r"(?:https?://)?realbooru\.com"
class RealbooruExtractor(booru.BooruExtractor):
basecategory = "booru"
category = "realbooru"
root = "https://realbooru.com"
def _parse_post(self, post_id):
url = f"{self.root}/index.php?page=post&s=view&id={post_id}"
page = self.request(url).text
extr = text.extract_from(page)
rating = extr('name="rating" content="', '"')
extr('class="container"', '>')
post = {
"id" : post_id,
"rating" : "e" if rating == "adult" else (rating or "?")[0],
"file_url" : (s := extr('src="', '"')),
"_fallback" : (extr('src="', '"'),) if s.endswith(".mp4") else (),
"created_at": extr(">Posted at ", " by "),
"uploader" : extr(">", "<"),
"score" : extr('">', "<"),
"tags" : extr('<br />', "</div>"),
"title" : extr('id="title" style="width: 100%;" value="', '"'),
"source" : extr('d="source" style="width: 100%;" value="', '"'),
}
tags_container = post["tags"]
tags = []
tags_categories = collections.defaultdict(list)
pattern = text.re(r'<a class="(?:tag-type-)?([^"]+).*?;tags=([^"&]+)')
for tag_type, tag_name in pattern.findall(tags_container):
tag = text.unescape(text.unquote(tag_name))
tags.append(tag)
tags_categories[tag_type].append(tag)
for key, value in tags_categories.items():
post["tags_" + key] = ", ".join(value)
tags.sort()
post["tags"] = ", ".join(tags)
post["md5"] = post["file_url"].rpartition("/")[2].partition(".")[0]
return post
def skip(self, num):
self.page_start += num
return num
def _prepare(self, post):
post["date"] = self.parse_datetime(post["created_at"], "%b, %d %Y")
def _pagination(self, params, begin, end):
url = self.root + "/index.php"
params["pid"] = self.page_start
while True:
page = self.request(url, params=params).text
cnt = 0
for post_id in text.extract_iter(page, begin, end):
cnt += 1
yield self._parse_post(post_id)
if cnt < self.per_page:
return
params["pid"] += self.per_page
class RealbooruTagExtractor(RealbooruExtractor):
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
archive_fmt = "t_{search_tags}_{id}"
per_page = 42
pattern = BASE_PATTERN + r"/index\.php\?page=post&s=list&tags=([^&#]*)"
example = "https://realbooru.com/index.php?page=post&s=list&tags=TAG"
def metadata(self):
self.tags = text.unquote(self.groups[0].replace("+", " "))
return {"search_tags": self.tags}
def posts(self):
return self._pagination({
"page": "post",
"s" : "list",
"tags": self.tags,
}, '<a id="p', '"')
class RealbooruFavoriteExtractor(RealbooruExtractor):
subcategory = "favorite"
directory_fmt = ("{category}", "favorites", "{favorite_id}")
archive_fmt = "f_{favorite_id}_{id}"
per_page = 50
pattern = BASE_PATTERN + r"/index\.php\?page=favorites&s=view&id=(\d+)"
example = "https://realbooru.com/index.php?page=favorites&s=view&id=12345"
def metadata(self):
return {"favorite_id": text.parse_int(self.groups[0])}
def posts(self):
return self._pagination({
"page": "favorites",
"s" : "view",
"id" : self.groups[0],
}, '" id="p', '"')
class RealbooruPoolExtractor(RealbooruExtractor):
subcategory = "pool"
directory_fmt = ("{category}", "pool", "{pool} {pool_name}")
archive_fmt = "p_{pool}_{id}"
pattern = BASE_PATTERN + r"/index\.php\?page=pool&s=show&id=(\d+)"
example = "https://realbooru.com/index.php?page=pool&s=show&id=12345"
def metadata(self):
pool_id = self.groups[0]
url = f"{self.root}/index.php?page=pool&s=show&id={pool_id}"
page = self.request(url).text
name, pos = text.extract(page, "<h4>Pool: ", "</h4>")
self.post_ids = text.extract_iter(
page, 'class="thumb" id="p', '"', pos)
return {
"pool": text.parse_int(pool_id),
"pool_name": text.unescape(name),
}
def posts(self):
return map(
self._parse_post,
util.advance(self.post_ids, self.page_start)
)
class RealbooruPostExtractor(RealbooruExtractor):
subcategory = "post"
archive_fmt = "{id}"
pattern = BASE_PATTERN + r"/index\.php\?page=post&s=view&id=(\d+)"
example = "https://realbooru.com/index.php?page=post&s=view&id=12345"
def posts(self):
return (self._parse_post(self.groups[0]),)
|
