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
|
# -*- coding: utf-8 -*-
# Copyright 2020-2025 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://hentaihand.com/"""
from .common import GalleryExtractor, Extractor, Message
from .. import text, util
class HentaihandGalleryExtractor(GalleryExtractor):
"""Extractor for image galleries on hentaihand.com"""
category = "hentaihand"
root = "https://hentaihand.com"
pattern = r"(?:https?://)?(?:www\.)?hentaihand\.com/\w+/comic/([\w-]+)"
example = "https://hentaihand.com/en/comic/TITLE"
def __init__(self, match):
self.slug = match[1]
url = f"{self.root}/api/comics/{self.slug}"
GalleryExtractor.__init__(self, match, url)
def metadata(self, page):
info = util.json_loads(page)
data = {
"gallery_id" : text.parse_int(info["id"]),
"title" : info["title"],
"title_alt" : info["alternative_title"],
"slug" : self.slug,
"type" : info["category"]["name"],
"language" : info["language"]["name"],
"lang" : util.language_to_code(info["language"]["name"]),
"tags" : [t["slug"] for t in info["tags"]],
"date" : self.parse_datetime_iso(info["uploaded_at"]),
}
for key in ("artists", "authors", "groups", "characters",
"relationships", "parodies"):
data[key] = [v["name"] for v in info[key]]
return data
def images(self, _):
info = self.request_json(self.page_url + "/images")
return [(img["source_url"], img) for img in info["images"]]
class HentaihandTagExtractor(Extractor):
"""Extractor for tag searches on hentaihand.com"""
category = "hentaihand"
subcategory = "tag"
root = "https://hentaihand.com"
pattern = (r"(?i)(?:https?://)?(?:www\.)?hentaihand\.com"
r"/\w+/(parody|character|tag|artist|group|language"
r"|category|relationship)/([^/?#]+)")
example = "https://hentaihand.com/en/tag/TAG"
def __init__(self, match):
Extractor.__init__(self, match)
self.type, self.key = match.groups()
def items(self):
if self.type[-1] == "y":
tpl = self.type[:-1] + "ies"
else:
tpl = self.type + "s"
url = f"{self.root}/api/{tpl}/{self.key}"
tid = self.request_json(url, notfound=self.type)["id"]
url = self.root + "/api/comics"
params = {
"per_page": "18",
tpl : tid,
"page" : 1,
"q" : "",
"sort" : "uploaded_at",
"order" : "desc",
"duration": "day",
}
while True:
info = self.request_json(url, params=params)
for gallery in info["data"]:
gurl = f"{self.root}/en/comic/{gallery['slug']}"
gallery["_extractor"] = HentaihandGalleryExtractor
yield Message.Queue, gurl, gallery
if params["page"] >= info["last_page"]:
return
params["page"] += 1
|
