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
|
# -*- coding: utf-8 -*-
# Copyright 2020 Jake Mannens
# 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://www.mangakakalot.gg/ and mirror sites"""
from .common import BaseExtractor, ChapterExtractor, MangaExtractor, Message
from .. import text, util, exception
class ManganeloExtractor(BaseExtractor):
basecategory = "manganelo"
BASE_PATTERN = ManganeloExtractor.update({
"nelomanga": {
"root" : "https://www.nelomanga.net",
"pattern": r"(?:www\.)?nelomanga\.net",
},
"natomanga": {
"root" : "https://www.natomanga.com",
"pattern": r"(?:www\.)?natomanga\.com",
},
"manganato": {
"root" : "https://www.manganato.gg",
"pattern": r"(?:www\.)?manganato\.gg",
},
"mangakakalot": {
"root" : "https://www.mangakakalot.gg",
"pattern": r"(?:www\.)?mangakakalot\.gg",
},
})
class ManganeloChapterExtractor(ManganeloExtractor, ChapterExtractor):
"""Extractor for manganelo manga chapters"""
pattern = BASE_PATTERN + r"(/manga/[^/?#]+/chapter-[^/?#]+)"
example = "https://www.mangakakalot.gg/manga/MANGA_NAME/chapter-123"
def __init__(self, match):
ManganeloExtractor.__init__(self, match)
self.page_url = self.root + self.groups[-1]
def metadata(self, page):
extr = text.extract_from(page)
data = {
"date" : self.parse_datetime_iso(extr(
'"datePublished": "', '"')[:19]),
"date_updated": self.parse_datetime_iso(extr(
'"dateModified": "', '"')[:19]),
"manga_id" : text.parse_int(extr("comic_id =", ";")),
"chapter_id" : text.parse_int(extr("chapter_id =", ";")),
"manga" : extr("comic_name =", ";").strip('" '),
"lang" : "en",
"language" : "English",
}
chapter_name = extr("chapter_name =", ";").strip('" ')
chapter, sep, minor = chapter_name.rpartition(" ")[2].partition(".")
data["chapter"] = text.parse_int(chapter)
data["chapter_minor"] = sep + minor
data["author"] = extr(". Author:", " already has ").strip()
return data
def images(self, page):
extr = text.extract_from(page)
cdns = util.json_loads(extr("var cdns =", ";"))[0]
imgs = util.json_loads(extr("var chapterImages =", ";"))
if cdns[-1] != "/":
cdns += "/"
return [
(cdns + path, None)
for path in imgs
]
class ManganeloMangaExtractor(ManganeloExtractor, MangaExtractor):
"""Extractor for manganelo manga"""
chapterclass = ManganeloChapterExtractor
pattern = BASE_PATTERN + r"(/manga/[^/?#]+)$"
example = "https://www.mangakakalot.gg/manga/MANGA_NAME"
def __init__(self, match):
ManganeloExtractor.__init__(self, match)
self.page_url = self.root + self.groups[-1]
def chapters(self, page):
extr = text.extract_from(page)
manga = text.unescape(extr("<h1>", "<"))
author = text.remove_html(extr("<li>Author(s) :", "</a>"))
status = extr("<li>Status :", "<").strip()
update = self.parse_datetime(extr(
"<li>Last updated :", "<").strip(), "%b-%d-%Y %I:%M:%S %p")
tags = text.split_html(extr(">Genres :", "</li>"))[::2]
results = []
for chapter in text.extract_iter(page, '<div class="row">', '</div>'):
url, pos = text.extract(chapter, '<a href="', '"')
title, pos = text.extract(chapter, '>', '</a>', pos)
date, pos = text.extract(chapter, '<span title="', '"', pos)
chapter, sep, minor = url.rpartition("/chapter-")[2].partition("-")
if url[0] == "/":
url = self.root + url
results.append((url, {
"manga" : manga,
"author" : author,
"status" : status,
"tags" : tags,
"date_updated": update,
"chapter" : text.parse_int(chapter),
"chapter_minor": (sep and ".") + minor,
"title" : title.partition(": ")[2],
"date" : self.parse_datetime(date, "%b-%d-%Y %H:%M"),
"lang" : "en",
"language": "English",
}))
return results
class ManganeloBookmarkExtractor(ManganeloExtractor):
"""Extractor for manganelo bookmarks"""
subcategory = "bookmark"
pattern = BASE_PATTERN + r"/bookmark"
example = "https://www.mangakakalot.gg/bookmark"
def items(self):
data = {"_extractor": ManganeloMangaExtractor}
url = self.root + "/bookmark"
params = {"page": 1}
response = self.request(url, params=params)
if response.history:
raise exception.AuthRequired(
"authenticated cookies", "your bookmarks")
page = response.text
last = text.parse_int(text.extr(page, ">Last(", ")"))
while True:
for bookmark in text.extract_iter(
page, 'class="user-bookmark-item ', '</a>'):
yield Message.Queue, text.extr(bookmark, ' href="', '"'), data
if params["page"] >= last:
break
params["page"] += 1
page = self.request(url, params=params).text
|
