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
|
# -*- 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://rawkuma.net/"""
from .common import MangaExtractor, ChapterExtractor
from .. import text
BASE_PATTERN = r"(?:https?://)?rawkuma\.(?:net|com)"
class RawkumaBase():
"""Base class for rawkuma extractors"""
category = "rawkuma"
root = "https://rawkuma.net"
class RawkumaChapterExtractor(RawkumaBase, ChapterExtractor):
"""Extractor for manga chapters from rawkuma.net"""
archive_fmt = "{chapter_id}_{page}"
pattern = rf"{BASE_PATTERN}(/manga/[^/?#]+/chapter-\d+(?:.\d+)?\.(\d+))"
example = "https://rawkuma.net/manga/7TITLE/chapter-123.321"
def __init__(self, match):
url = f"{self.root}/{match[1]}/"
ChapterExtractor.__init__(self, match, url)
def metadata(self, page):
manga, _, chapter = text.extr(
page, '<title>', "<").rpartition(" Chapter ")
chapter, sep, minor = chapter.partition(" – ")[0].partition(".")
return {
"manga" : text.unescape(manga),
"manga_id" : text.parse_int(text.extr(page, "manga_id=", "&")),
"chapter" : text.parse_int(chapter),
"chapter_minor": sep + minor,
"chapter_id" : text.parse_int(self.groups[-1]),
# "title" : text.unescape(title),
"date" : self.parse_datetime_iso(text.extr(
page, 'datetime="', '"')),
"lang" : "ja",
"language" : "Japanese",
}
def images(self, page):
return [(url, None) for url in text.extract_iter(
page, "<img src='", "'")]
class RawkumaMangaExtractor(RawkumaBase, MangaExtractor):
"""Extractor for manga from rawkuma.net"""
chapterclass = RawkumaChapterExtractor
pattern = rf"{BASE_PATTERN}/manga/([^/?#]+)"
example = "https://rawkuma.net/manga/TITLE/"
def __init__(self, match):
url = f"{self.root}/manga/{match[1]}/"
MangaExtractor.__init__(self, match, url)
def chapters(self, page):
manga = text.unescape(text.extr(page, "<title>", " – "))
manga_id = text.parse_int(text.extr(page, "manga_id=", "&"))
url = f"{self.root}/wp-admin/admin-ajax.php"
params = {
"manga_id": manga_id,
"page" : "1",
"action" : "chapter_list",
}
headers = {
"HX-Request" : "true",
"HX-Trigger" : "chapter-list",
"HX-Target" : "chapter-list",
"HX-Current-URL": self.page_url,
"Sec-Fetch-Dest": "empty",
"Sec-Fetch-Mode": "cors",
"Sec-Fetch-Site": "same-origin",
}
html = self.request(url, params=params, headers=headers).text
results = []
for url in text.extract_iter(html, '<a href="', '"'):
info = url[url.rfind("-")+1:-1]
chapter, _, chapter_id = info.rpartition(".")
chapter, sep, minor = chapter.partition(".")
results.append((url, {
"manga" : manga,
"manga_id" : manga_id,
"chapter" : text.parse_int(chapter),
"chapter-minor": sep + minor,
"chapter_id" : text.parse_int(chapter_id),
}))
return results
|
