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
|
# -*- 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://hitomi.la/"""
from .common import GalleryExtractor, Extractor, Message
from .nozomi import decode_nozomi
from ..cache import memcache
from .. import text, util
import string
import re
class HitomiGalleryExtractor(GalleryExtractor):
"""Extractor for image galleries from hitomi.la"""
category = "hitomi"
root = "https://hitomi.la"
pattern = (r"(?:https?://)?hitomi\.la"
r"/(?:manga|doujinshi|cg|gamecg|imageset|galleries|reader)"
r"/(?:[^/?#]+-)?(\d+)")
example = "https://hitomi.la/manga/TITLE-867789.html"
def __init__(self, match):
self.gid = match.group(1)
url = "https://ltn.hitomi.la/galleries/{}.js".format(self.gid)
GalleryExtractor.__init__(self, match, url)
def _init(self):
self.session.headers["Referer"] = "{}/reader/{}.html".format(
self.root, self.gid)
def metadata(self, page):
self.info = info = util.json_loads(page.partition("=")[2])
iget = info.get
language = iget("language")
if language:
language = language.capitalize()
date = iget("date")
if date:
date += ":00"
tags = []
for tinfo in iget("tags") or ():
tag = string.capwords(tinfo["tag"])
if tinfo.get("female"):
tag += " ♀"
elif tinfo.get("male"):
tag += " ♂"
tags.append(tag)
return {
"gallery_id": text.parse_int(info["id"]),
"title" : info["title"],
"title_jpn" : info.get("japanese_title") or "",
"type" : info["type"].capitalize(),
"language" : language,
"lang" : util.language_to_code(language),
"date" : text.parse_datetime(date, "%Y-%m-%d %H:%M:%S%z"),
"tags" : tags,
"artist" : [o["artist"] for o in iget("artists") or ()],
"group" : [o["group"] for o in iget("groups") or ()],
"parody" : [o["parody"] for o in iget("parodys") or ()],
"characters": [o["character"] for o in iget("characters") or ()]
}
def images(self, _):
# see https://ltn.hitomi.la/gg.js
gg_m, gg_b, gg_default = _parse_gg(self)
fmt = self.config("format") or "webp"
if fmt == "original":
subdomain, path, ext, check = "b", "images", None, False
else:
subdomain, path, ext, check = "a", fmt, fmt, (fmt != "webp")
result = []
for image in self.info["files"]:
if check:
if image.get("has" + fmt):
path = ext = fmt
else:
path = ext = "webp"
ihash = image["hash"]
idata = text.nameext_from_url(image["name"])
idata["extension_original"] = idata["extension"]
if ext:
idata["extension"] = ext
# see https://ltn.hitomi.la/common.js
inum = int(ihash[-1] + ihash[-3:-1], 16)
url = "https://{}{}.hitomi.la/{}/{}/{}/{}.{}".format(
chr(97 + gg_m.get(inum, gg_default)),
subdomain, path, gg_b, inum, ihash, idata["extension"],
)
result.append((url, idata))
return result
class HitomiTagExtractor(Extractor):
"""Extractor for galleries from tag searches on hitomi.la"""
category = "hitomi"
subcategory = "tag"
root = "https://hitomi.la"
pattern = (r"(?:https?://)?hitomi\.la/"
r"(tag|artist|group|series|type|character)/"
r"([^/?#]+)\.html")
example = "https://hitomi.la/tag/TAG-LANG.html"
def __init__(self, match):
Extractor.__init__(self, match)
self.type, self.tag = match.groups()
tag, _, num = self.tag.rpartition("-")
if num.isdecimal():
self.tag = tag
def items(self):
data = {"_extractor": HitomiGalleryExtractor}
nozomi_url = "https://ltn.hitomi.la/{}/{}.nozomi".format(
self.type, self.tag)
headers = {
"Origin": self.root,
"Cache-Control": "max-age=0",
}
offset = 0
total = None
while True:
headers["Referer"] = "{}/{}/{}.html?page={}".format(
self.root, self.type, self.tag, offset // 100 + 1)
headers["Range"] = "bytes={}-{}".format(offset, offset+99)
response = self.request(nozomi_url, headers=headers)
for gallery_id in decode_nozomi(response.content):
gallery_url = "{}/galleries/{}.html".format(
self.root, gallery_id)
yield Message.Queue, gallery_url, data
offset += 100
if total is None:
total = text.parse_int(
response.headers["content-range"].rpartition("/")[2])
if offset >= total:
return
@memcache(maxage=1800)
def _parse_gg(extr):
page = extr.request("https://ltn.hitomi.la/gg.js").text
m = {}
keys = []
for match in re.finditer(
r"case\s+(\d+):(?:\s*o\s*=\s*(\d+))?", page):
key, value = match.groups()
keys.append(int(key))
if value:
value = int(value)
for key in keys:
m[key] = value
keys.clear()
for match in re.finditer(
r"if\s+\(g\s*===?\s*(\d+)\)[\s{]*o\s*=\s*(\d+)", page):
m[int(match.group(1))] = int(match.group(2))
d = re.search(r"(?:var\s|default:)\s*o\s*=\s*(\d+)", page)
b = re.search(r"b:\s*[\"'](.+)[\"']", page)
return m, b.group(1).strip("/"), int(d.group(1)) if d else 1
|
