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
|
# -*- coding: utf-8 -*-
# Copyright 2016-2023 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 FoOlSlide based sites"""
from .common import BaseExtractor, Message
from .. import text, util
class FoolslideExtractor(BaseExtractor):
"""Base class for FoOlSlide extractors"""
basecategory = "foolslide"
def __init__(self, match):
BaseExtractor.__init__(self, match)
self.gallery_url = self.root + match.group(match.lastindex)
def request(self, url):
return BaseExtractor.request(
self, url, encoding="utf-8", method="POST", data={"adult": "true"})
@staticmethod
def parse_chapter_url(url, data):
info = url.partition("/read/")[2].rstrip("/").split("/")
lang = info[1].partition("-")[0]
data["lang"] = lang
data["language"] = util.code_to_language(lang)
data["volume"] = text.parse_int(info[2])
data["chapter"] = text.parse_int(info[3])
data["chapter_minor"] = "." + info[4] if len(info) >= 5 else ""
data["title"] = data["chapter_string"].partition(":")[2].strip()
return data
BASE_PATTERN = FoolslideExtractor.update({
"powermanga": {
"root": "https://read.powermanga.org",
"pattern": r"read(?:er)?\.powermanga\.org",
},
"sensescans": {
"root": "https://sensescans.com/reader",
"pattern": r"(?:(?:www\.)?sensescans\.com/reader"
r"|reader\.sensescans\.com)",
},
})
class FoolslideChapterExtractor(FoolslideExtractor):
"""Base class for chapter extractors for FoOlSlide based sites"""
subcategory = "chapter"
directory_fmt = ("{category}", "{manga}", "{chapter_string}")
filename_fmt = (
"{manga}_c{chapter:>03}{chapter_minor:?//}_{page:>03}.{extension}")
archive_fmt = "{id}"
pattern = BASE_PATTERN + r"(/read/[^/?#]+/[a-z-]+/\d+/\d+(?:/\d+)?)"
test = (
(("https://read.powermanga.org"
"/read/one_piece_digital_colour_comics/en/0/75/"), {
"url": "854c5817f8f767e1bccd05fa9d58ffb5a4b09384",
"keyword": "a60c42f2634b7387899299d411ff494ed0ad6dbe",
}),
("https://sensescans.com/reader/read/ao_no_orchestra/en/0/26/", {
"url": "bbd428dc578f5055e9f86ad635b510386cd317cd",
"keyword": "083ef6f8831c84127fe4096fa340a249be9d1424",
}),
("https://reader.sensescans.com/read/ao_no_orchestra/en/0/26/"),
)
def items(self):
page = self.request(self.gallery_url).text
data = self.metadata(page)
imgs = self.images(page)
data["count"] = len(imgs)
data["chapter_id"] = text.parse_int(imgs[0]["chapter_id"])
yield Message.Directory, data
enum = util.enumerate_reversed if self.config(
"page-reverse") else enumerate
for data["page"], image in enum(imgs, 1):
try:
url = image["url"]
del image["url"]
del image["chapter_id"]
del image["thumb_url"]
except KeyError:
pass
for key in ("height", "id", "size", "width"):
image[key] = text.parse_int(image[key])
data.update(image)
text.nameext_from_url(data["filename"], data)
yield Message.Url, url, data
def metadata(self, page):
extr = text.extract_from(page)
extr('<h1 class="tbtitle dnone">', '')
return self.parse_chapter_url(self.gallery_url, {
"manga" : text.unescape(extr('title="', '"')).strip(),
"chapter_string": text.unescape(extr('title="', '"')),
})
def images(self, page):
return util.json_loads(text.extr(page, "var pages = ", ";"))
class FoolslideMangaExtractor(FoolslideExtractor):
"""Base class for manga extractors for FoOlSlide based sites"""
subcategory = "manga"
categorytransfer = True
pattern = BASE_PATTERN + r"(/series/[^/?#]+)"
test = (
(("https://read.powermanga.org"
"/series/one_piece_digital_colour_comics/"), {
"count": ">= 1",
"keyword": {
"chapter": int,
"chapter_minor": str,
"chapter_string": str,
"group": "PowerManga",
"lang": "en",
"language": "English",
"manga": "One Piece Digital Colour Comics",
"title": str,
"volume": int,
},
}),
("https://sensescans.com/reader/series/yotsubato/", {
"count": ">= 3",
}),
)
def items(self):
page = self.request(self.gallery_url).text
chapters = self.chapters(page)
if not self.config("chapter-reverse", False):
chapters.reverse()
for chapter, data in chapters:
data["_extractor"] = FoolslideChapterExtractor
yield Message.Queue, chapter, data
def chapters(self, page):
extr = text.extract_from(page)
manga = text.unescape(extr('<h1 class="title">', '</h1>')).strip()
author = extr('<b>Author</b>: ', '<br')
artist = extr('<b>Artist</b>: ', '<br')
results = []
while True:
url = extr('<div class="title"><a href="', '"')
if not url:
return results
results.append((url, self.parse_chapter_url(url, {
"manga": manga, "author": author, "artist": artist,
"chapter_string": extr('title="', '"'),
"group" : extr('title="', '"'),
})))
|
