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
|
# -*- coding: utf-8 -*-
# Copyright 2018-2023 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://komikcast.cz/"""
from .common import ChapterExtractor, MangaExtractor
from .. import text
import re
BASE_PATTERN = r"(?:https?://)?(?:www\.)?komikcast\.(?:cz|lol|site|mo?e|com)"
class KomikcastBase():
"""Base class for komikcast extractors"""
category = "komikcast"
root = "https://komikcast.cz"
@staticmethod
def parse_chapter_string(chapter_string, data=None):
"""Parse 'chapter_string' value and add its info to 'data'"""
if not data:
data = {}
match = re.match(
r"(?:(.*) Chapter )?0*(\d+)([^ ]*)(?: (?:- )?(.+))?",
text.unescape(chapter_string),
)
manga, chapter, data["chapter_minor"], title = match.groups()
if manga:
data["manga"] = manga.partition(" Chapter ")[0]
if title and not title.lower().startswith("bahasa indonesia"):
data["title"] = title.strip()
else:
data["title"] = ""
data["chapter"] = text.parse_int(chapter)
data["lang"] = "id"
data["language"] = "Indonesian"
return data
class KomikcastChapterExtractor(KomikcastBase, ChapterExtractor):
"""Extractor for komikcast manga chapters"""
pattern = BASE_PATTERN + r"(/chapter/[^/?#]+/)"
example = "https://komikcast.cz/chapter/TITLE/"
def metadata(self, page):
info = text.extr(page, "<title>", " - Komikcast<")
return self.parse_chapter_string(info)
@staticmethod
def images(page):
readerarea = text.extr(
page, '<div class="main-reading-area', '</div')
return [
(text.unescape(url), None)
for url in re.findall(r"<img[^>]* src=[\"']([^\"']+)", readerarea)
]
class KomikcastMangaExtractor(KomikcastBase, MangaExtractor):
"""Extractor for komikcast manga"""
chapterclass = KomikcastChapterExtractor
pattern = BASE_PATTERN + r"(/(?:komik/)?[^/?#]+)/?$"
example = "https://komikcast.cz/komik/TITLE"
def chapters(self, page):
results = []
data = self.metadata(page)
for item in text.extract_iter(
page, '<a class="chapter-link-item" href="', '</a'):
url, _, chapter = item.rpartition('">Chapter')
chapter, sep, minor = chapter.strip().partition(".")
data["chapter"] = text.parse_int(chapter)
data["chapter_minor"] = sep + minor
results.append((url, data.copy()))
return results
@staticmethod
def metadata(page):
"""Return a dict with general metadata"""
manga , pos = text.extract(page, "<title>" , " - Komikcast<")
genres, pos = text.extract(
page, 'class="komik_info-content-genre">', "</span>", pos)
author, pos = text.extract(page, ">Author:", "</span>", pos)
mtype , pos = text.extract(page, ">Type:" , "</span>", pos)
return {
"manga": text.unescape(manga),
"genres": text.split_html(genres),
"author": text.remove_html(author),
"type": text.remove_html(mtype),
}
|
