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
|
# -*- coding: utf-8 -*-
# Copyright 2021-2025 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://rule34.us/"""
from .booru import BooruExtractor
from .. import text
import collections
class Rule34usExtractor(BooruExtractor):
category = "rule34us"
root = "https://rule34.us"
per_page = 42
def _init(self):
self._find_tags = text.re(
r'<li class="([^-"]+)-tag"[^>]*><a href="[^;"]+;q=([^"]+)').findall
def _parse_post(self, post_id):
url = f"{self.root}/index.php?r=posts/view&id={post_id}"
page = self.request(url).text
extr = text.extract_from(page)
post = {
"id" : post_id,
"tags" : text.unescape(extr(
'name="keywords" content="', '"').rstrip(", ")),
"uploader": text.extract(extr('Added by: ', '</li>'), ">", "<")[0],
"score" : text.extract(extr('Score: ', '> - <'), ">", "<")[0],
"width" : extr('Size: ', 'w'),
"height" : extr(' x ', 'h'),
"file_url": extr('<source src="', '"') or extr('<img src="', '"'),
}
url = post["file_url"]
if "//video-cdn1." in url:
post["file_url"] = url.replace("//video-cdn1.", "//video.")
post["_fallback"] = (url,)
post["md5"] = url.rpartition("/")[2].partition(".")[0]
tags = collections.defaultdict(list)
for tag_type, tag_name in self._find_tags(page):
tags[tag_type].append(text.unquote(tag_name))
for key, value in tags.items():
post["tags_" + key] = " ".join(value)
return post
class Rule34usTagExtractor(Rule34usExtractor):
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
archive_fmt = "t_{search_tags}_{id}"
pattern = r"(?:https?://)?rule34\.us/index\.php\?r=posts/index&q=([^&#]*)"
example = "https://rule34.us/index.php?r=posts/index&q=TAG"
def __init__(self, match):
Rule34usExtractor.__init__(self, match)
self.tags = text.unquote(match[1].replace("+", " "))
def metadata(self):
return {"search_tags": self.tags}
def posts(self):
url = self.root + "/index.php"
params = {
"r" : "posts/index",
"q" : self.tags,
"page": self.page_start,
}
while True:
page = self.request(url, params=params).text
cnt = 0
for post_id in text.extract_iter(page, '><a id="', '"'):
yield self._parse_post(post_id)
cnt += 1
if cnt < self.per_page:
return
if "page" in params:
del params["page"]
params["q"] = self.tags + " id:<" + post_id
class Rule34usPostExtractor(Rule34usExtractor):
subcategory = "post"
archive_fmt = "{id}"
pattern = r"(?:https?://)?rule34\.us/index\.php\?r=posts/view&id=(\d+)"
example = "https://rule34.us/index.php?r=posts/view&id=12345"
def __init__(self, match):
Rule34usExtractor.__init__(self, match)
self.post_id = match[1]
def posts(self):
return (self._parse_post(self.post_id),)
|
