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
|
# -*- coding: utf-8 -*-
# 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://tcbscans.com/"""
from .common import ChapterExtractor, MangaExtractor
from .. import text
BASE_PATTERN = r"(?:https?://)?(?:tcbscans|onepiecechapters)\.com"
class TcbscansChapterExtractor(ChapterExtractor):
category = "tcbscans"
root = "https://tcbscans.com"
pattern = BASE_PATTERN + r"(/chapters/\d+/[^/?#]+)"
test = (
(("https://tcbscans.com"
"/chapters/4708/chainsaw-man-chapter-108"), {
"pattern": (r"https://cdn\.[^/]+"
r"/(file|attachments/[^/]+)/[^/]+/[^.]+\.\w+"),
"count" : 17,
"keyword": {
"manga": "Chainsaw Man",
"chapter": 108,
"chapter_minor": "",
"lang": "en",
"language": "English",
},
}),
("https://onepiecechapters.com/chapters/4716/one-piece-chapter-1065", {
"pattern": (r"https://cdn\.[^/]+"
r"/(file|attachments/[^/]+)/[^/]+/[^.]+\.\w+"),
"count" : 18,
"keyword": {
"manga": "One Piece",
"chapter": 1065,
"chapter_minor": "",
"lang": "en",
"language": "English",
},
}),
(("https://onepiecechapters.com/"
"chapters/44/ace-novel-manga-adaptation-chapter-1")),
)
def images(self, page):
return [
(url, None)
for url in text.extract_iter(
page, '<img class="fixed-ratio-content" src="', '"')
]
def metadata(self, page):
manga, _, chapter = text.extr(
page, 'font-bold mt-8">', "</h1>").rpartition(" - Chapter ")
chapter, sep, minor = chapter.partition(".")
return {
"manga": text.unescape(manga),
"chapter": text.parse_int(chapter),
"chapter_minor": sep + minor,
"lang": "en", "language": "English",
}
class TcbscansMangaExtractor(MangaExtractor):
category = "tcbscans"
root = "https://tcbscans.com"
chapterclass = TcbscansChapterExtractor
pattern = BASE_PATTERN + r"(/mangas/\d+/[^/?#]+)"
test = (
("https://tcbscans.com/mangas/13/chainsaw-man", {
"pattern": TcbscansChapterExtractor.pattern,
"range" : "1-50",
"count" : 50,
}),
("https://onepiecechapters.com/mangas/4/jujutsu-kaisen", {
"pattern": TcbscansChapterExtractor.pattern,
"range" : "1-50",
"count" : 50,
}),
("https://onepiecechapters.com/mangas/15/hunter-x-hunter"),
)
def chapters(self, page):
data = {
"manga": text.unescape(text.extr(
page, 'class="my-3 font-bold text-3xl">', "</h1>")),
"lang": "en", "language": "English",
}
results = []
page = text.extr(page, 'class="col-span-2"', 'class="order-1')
for chapter in text.extract_iter(page, "<a", "</a>"):
url = text.extr(chapter, 'href="', '"')
data["title"] = text.unescape(text.extr(
chapter, 'text-gray-500">', "</div>"))
chapter = text.extr(
chapter, 'font-bold">', "</div>").rpartition(" Chapter ")[2]
chapter, sep, minor = chapter.partition(".")
data["chapter"] = text.parse_int(chapter)
data["chapter_minor"] = sep + minor
results.append((self.root + url, data.copy()))
return results
|
