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
|
# -*- coding: utf-8 -*-
# Copyright 2024 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://rule34.xyz/"""
from .booru import BooruExtractor
from .. import text
import collections
BASE_PATTERN = r"(?:https?://)?rule34\.xyz"
class Rule34xyzExtractor(BooruExtractor):
category = "rule34xyz"
root = "https://rule34.xyz"
root_cdn = "https://rule34xyz.b-cdn.net"
filename_fmt = "{category}_{id}.{extension}"
per_page = 60
TAG_TYPES = {
0: "general",
1: "copyright",
2: "character",
3: "artist",
}
def _init(self):
formats = self.config("format")
if formats:
if isinstance(formats, str):
formats = formats.split(",")
self.formats = formats
else:
self.formats = ("10", "40", "41", "2")
def _file_url(self, post):
post["files"] = files = {
str(link["type"]): link["url"]
for link in post.pop("imageLinks")
}
for fmt in self.formats:
if fmt in files:
break
else:
fmt = "2"
self.log.warning("%s: Requested format not available", post["id"])
post["file_url"] = url = files[fmt]
post["format_id"] = fmt
post["format"] = url.rsplit(".", 2)[1]
return url
def _prepare(self, post):
post.pop("filesPreview", None)
post.pop("tagsWithType", None)
post["date"] = text.parse_datetime(
post["created"], "%Y-%m-%dT%H:%M:%S.%f")
def _tags(self, post, _):
if post.get("tagsWithType") is None:
post.update(self._fetch_post(post["id"]))
tags = collections.defaultdict(list)
for tag in post["tagsWithType"]:
tags[tag["type"]].append(tag["value"])
types = self.TAG_TYPES
for type, values in tags.items():
post["tags_" + types[type]] = values
def _fetch_post(self, post_id):
url = "{}/api/post/{}".format(self.root, post_id)
return self.request(url).json()
def _pagination(self, endpoint, params=None):
url = "{}/api{}".format(self.root, endpoint)
if params is None:
params = {}
params["IncludeLinks"] = "true"
params["IncludeTags"] = "true"
params["OrderBy"] = "0"
params["Skip"] = self.page_start * self.per_page
params["Take"] = self.per_page
params["DisableTotal"] = "true"
threshold = self.per_page
while True:
data = self.request(url, params=params).json()
yield from data["items"]
if len(data["items"]) < threshold:
return
params["Skip"] += params["Take"]
class Rule34xyzPostExtractor(Rule34xyzExtractor):
subcategory = "post"
archive_fmt = "{id}"
pattern = BASE_PATTERN + r"/post/(\d+)"
example = "https://rule34.xyz/post/12345"
def posts(self):
return (self._fetch_post(self.groups[0]),)
class Rule34xyzPlaylistExtractor(Rule34xyzExtractor):
subcategory = "playlist"
directory_fmt = ("{category}", "{playlist_id}")
archive_fmt = "p_{playlist_id}_{id}"
pattern = BASE_PATTERN + r"/playlists/view/(\d+)"
example = "https://rule34.xyz/playlists/view/12345"
def metadata(self):
return {"playlist_id": self.groups[0]}
def posts(self):
endpoint = "/playlist-item"
params = {"PlaylistId": self.groups[0]}
return self._pagination(endpoint, params)
class Rule34xyzTagExtractor(Rule34xyzExtractor):
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
archive_fmt = "t_{search_tags}_{id}"
pattern = BASE_PATTERN + r"/([^/?#]+)$"
example = "https://rule34.xyz/TAG"
def metadata(self):
self.tags = text.unquote(self.groups[0]).replace("_", " ")
return {"search_tags": self.tags}
def posts(self):
endpoint = "/post/search"
params = {"Tag": self.tags}
return self._pagination(endpoint, params)
|
