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
186
187
188
189
|
# -*- coding: utf-8 -*-
# Copyright 2019-2025 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://nozomi.la/"""
from .common import Extractor, Message
from .. import text, dt
def decode_nozomi(n):
for i in range(0, len(n), 4):
yield (n[i] << 24) + (n[i+1] << 16) + (n[i+2] << 8) + n[i+3]
class NozomiExtractor(Extractor):
"""Base class for nozomi extractors"""
category = "nozomi"
root = "https://nozomi.la"
domain = "gold-usergeneratedcontent.net"
filename_fmt = "{postid} {dataid}.{extension}"
archive_fmt = "{dataid}"
def _init(self):
self.session.headers["Origin"] = self.root
def items(self):
data = self.metadata()
for post_id in map(str, self.posts()):
url = (f"https://j.{self.domain}/post"
f"/{post_id[-1]}/{post_id[-3:-1]}/{post_id}.json")
response = self.request(url, fatal=False)
if response.status_code >= 400:
self.log.warning(
"Skipping post %s ('%s %s')",
post_id, response.status_code, response.reason)
continue
post = response.json()
post["tags"] = self._list(post.get("general"))
post["artist"] = self._list(post.get("artist"))
post["copyright"] = self._list(post.get("copyright"))
post["character"] = self._list(post.get("character"))
try:
post["date"] = dt.parse_iso(post["date"] + ":00")
except Exception:
post["date"] = dt.NONE
post.update(data)
images = post["imageurls"]
for key in ("general", "imageurl", "imageurls"):
if key in post:
del post[key]
yield Message.Directory, "", post
for post["num"], image in enumerate(images, 1):
post["filename"] = post["dataid"] = did = image["dataid"]
post["is_video"] = video = \
True if image.get("is_video") else False
ext = image["type"]
if video:
subdomain = "v"
elif ext == "gif":
subdomain = "g"
else:
subdomain = "w"
ext = "webp"
post["extension"] = ext
post["url"] = url = (f"https://{subdomain}.{self.domain}"
f"/{did[-1]}/{did[-3:-1]}/{did}.{ext}")
yield Message.Url, url, post
def posts(self):
url = "https://n.nozomi.la" + self.nozomi
offset = (text.parse_int(self.pnum, 1) - 1) * 256
while True:
headers = {"Range": f"bytes={offset}-{offset + 255}"}
response = self.request(url, headers=headers)
yield from decode_nozomi(response.content)
offset += 256
cr = response.headers.get("Content-Range", "").rpartition("/")[2]
if text.parse_int(cr, offset) <= offset:
return
def metadata(self):
return {}
def _list(self, src):
return [x["tagname_display"] for x in src] if src else ()
class NozomiPostExtractor(NozomiExtractor):
"""Extractor for individual posts on nozomi.la"""
subcategory = "post"
pattern = r"(?:https?://)?nozomi\.la/post/(\d+)"
example = "https://nozomi.la/post/12345.html"
def __init__(self, match):
NozomiExtractor.__init__(self, match)
self.post_id = match[1]
def posts(self):
return (self.post_id,)
class NozomiIndexExtractor(NozomiExtractor):
"""Extractor for the nozomi.la index"""
subcategory = "index"
pattern = (r"(?:https?://)?nozomi\.la/"
r"(?:(index(?:-Popular)?)-(\d+)\.html)?(?:$|#|\?)")
example = "https://nozomi.la/index-1.html"
def __init__(self, match):
NozomiExtractor.__init__(self, match)
index, self.pnum = match.groups()
self.nozomi = f"/{index or 'index'}.nozomi"
class NozomiTagExtractor(NozomiExtractor):
"""Extractor for posts from tag searches on nozomi.la"""
subcategory = "tag"
directory_fmt = ("{category}", "{search_tags}")
archive_fmt = "t_{search_tags}_{dataid}"
pattern = r"(?:https?://)?nozomi\.la/tag/([^/?#]+)-(\d+)\."
example = "https://nozomi.la/tag/TAG-1.html"
def __init__(self, match):
NozomiExtractor.__init__(self, match)
tags, self.pnum = match.groups()
self.tags = text.unquote(tags)
self.nozomi = f"/nozomi/{self.tags}.nozomi"
def metadata(self):
return {"search_tags": self.tags}
class NozomiSearchExtractor(NozomiExtractor):
"""Extractor for search results on nozomi.la"""
subcategory = "search"
directory_fmt = ("{category}", "{search_tags:J }")
archive_fmt = "t_{search_tags}_{dataid}"
pattern = r"(?:https?://)?nozomi\.la/search\.html\?q=([^&#]+)"
example = "https://nozomi.la/search.html?q=QUERY"
def __init__(self, match):
NozomiExtractor.__init__(self, match)
self.tags = text.unquote(match[1]).split()
def metadata(self):
return {"search_tags": self.tags}
def posts(self):
result = None
positive = []
negative = []
def nozomi(path):
url = f"https://j.{self.domain}/{path}.nozomi"
return decode_nozomi(self.request(url).content)
for tag in self.tags:
(negative if tag[0] == "-" else positive).append(
text.quote(tag.replace("/", "")))
for tag in positive:
ids = nozomi("nozomi/" + tag)
if result is None:
result = set(ids)
else:
result.intersection_update(ids)
if result is None:
result = set(nozomi("index"))
for tag in negative:
result.difference_update(nozomi("nozomi/" + tag[1:]))
return sorted(result, reverse=True) if result else ()
|
