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
|
# -*- coding: utf-8 -*-
# Copyright 2015-2023 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://nhentai.net/"""
from .common import GalleryExtractor, Extractor, Message
from .. import text, util
import collections
class NhentaiGalleryExtractor(GalleryExtractor):
"""Extractor for image galleries from nhentai.net"""
category = "nhentai"
root = "https://nhentai.net"
pattern = r"(?:https?://)?nhentai\.net/g/(\d+)"
example = "https://nhentai.net/g/12345/"
def __init__(self, match):
url = self.root + "/api/gallery/" + match.group(1)
GalleryExtractor.__init__(self, match, url)
def metadata(self, page):
self.data = data = util.json_loads(page)
title_en = data["title"].get("english", "")
title_ja = data["title"].get("japanese", "")
info = collections.defaultdict(list)
for tag in data["tags"]:
info[tag["type"]].append(tag["name"])
language = ""
for language in info["language"]:
if language != "translated":
language = language.capitalize()
break
return {
"title" : title_en or title_ja,
"title_en" : title_en,
"title_ja" : title_ja,
"gallery_id": data["id"],
"media_id" : text.parse_int(data["media_id"]),
"date" : data["upload_date"],
"scanlator" : data["scanlator"],
"artist" : info["artist"],
"group" : info["group"],
"parody" : info["parody"],
"characters": info["character"],
"tags" : info["tag"],
"type" : info["category"][0] if info["category"] else "",
"lang" : util.language_to_code(language),
"language" : language,
}
def images(self, _):
ufmt = ("https://i.nhentai.net/galleries/" +
self.data["media_id"] + "/{}.{}")
extdict = {"j": "jpg", "p": "png", "g": "gif"}
return [
(ufmt.format(num, extdict.get(img["t"], "jpg")), {
"width": img["w"], "height": img["h"],
})
for num, img in enumerate(self.data["images"]["pages"], 1)
]
class NhentaiExtractor(Extractor):
"""Base class for nhentai extractors"""
category = "nhentai"
root = "https://nhentai.net"
def __init__(self, match):
Extractor.__init__(self, match)
self.path, self.query = match.groups()
def items(self):
data = {"_extractor": NhentaiGalleryExtractor}
for gallery_id in self._pagination():
url = "{}/g/{}/".format(self.root, gallery_id)
yield Message.Queue, url, data
def _pagination(self):
url = self.root + self.path
params = text.parse_query(self.query)
params["page"] = text.parse_int(params.get("page"), 1)
while True:
page = self.request(url, params=params).text
yield from text.extract_iter(page, 'href="/g/', '/')
if 'class="next"' not in page:
return
params["page"] += 1
class NhentaiTagExtractor(NhentaiExtractor):
"""Extractor for nhentai tag searches"""
subcategory = "tag"
pattern = (r"(?:https?://)?nhentai\.net("
r"/(?:artist|category|character|group|language|parody|tag)"
r"/[^/?#]+(?:/popular[^/?#]*)?/?)(?:\?([^#]+))?")
example = "https://nhentai.net/tag/TAG/"
class NhentaiSearchExtractor(NhentaiExtractor):
"""Extractor for nhentai search results"""
subcategory = "search"
pattern = r"(?:https?://)?nhentai\.net(/search/?)\?([^#]+)"
example = "https://nhentai.net/search/?q=QUERY"
class NhentaiFavoriteExtractor(NhentaiExtractor):
"""Extractor for nhentai favorites"""
subcategory = "favorite"
pattern = r"(?:https?://)?nhentai\.net(/favorites/?)(?:\?([^#]+))?"
example = "https://nhentai.net/favorites/"
|
