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
|
# -*- coding: utf-8 -*-
# Copyright 2016-2022 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://readcomiconline.li/"""
from .common import Extractor, ChapterExtractor, MangaExtractor
from .. import text, exception
import binascii
import re
BASE_PATTERN = r"(?i)(?:https?://)?(?:www\.)?readcomiconline\.(?:li|to)"
class ReadcomiconlineBase():
"""Base class for readcomiconline extractors"""
category = "readcomiconline"
directory_fmt = ("{category}", "{comic}", "{issue:>03}")
filename_fmt = "{comic}_{issue:>03}_{page:>03}.{extension}"
archive_fmt = "{issue_id}_{page}"
root = "https://readcomiconline.li"
browser = "firefox"
def request(self, url, **kwargs):
"""Detect and handle redirects to CAPTCHA pages"""
while True:
response = Extractor.request(self, url, **kwargs)
if not response.history or "/AreYouHuman" not in response.url:
return response
if self.config("captcha", "stop") == "wait":
self.log.warning(
"Redirect to \n%s\nVisit this URL in your browser, solve "
"the CAPTCHA, and press ENTER to continue", response.url)
try:
input()
except (EOFError, OSError):
pass
else:
raise exception.StopExtraction(
"Redirect to \n%s\nVisit this URL in your browser and "
"solve the CAPTCHA to continue", response.url)
class ReadcomiconlineIssueExtractor(ReadcomiconlineBase, ChapterExtractor):
"""Extractor for comic-issues from readcomiconline.li"""
subcategory = "issue"
pattern = BASE_PATTERN + r"(/Comic/[^/?#]+/[^/?#]+\?)([^#]+)"
test = ("https://readcomiconline.li/Comic/W-i-t-c-h/Issue-130?id=22289", {
"url": "30d29c5afc65043bfd384c010257ec2d0ecbafa6",
"keyword": "2d9ec81ce1b11fac06ebf96ce33cdbfca0e85eb5",
})
def __init__(self, match):
ChapterExtractor.__init__(self, match)
params = text.parse_query(match.group(2))
quality = self.config("quality")
if quality is None or quality == "auto":
if "quality" not in params:
params["quality"] = "hq"
else:
params["quality"] = str(quality)
self.gallery_url += "&".join(k + "=" + v for k, v in params.items())
self.issue_id = params.get("id")
def metadata(self, page):
comic, pos = text.extract(page, " - Read\r\n ", "\r\n")
iinfo, pos = text.extract(page, " ", "\r\n", pos)
match = re.match(r"(?:Issue )?#(\d+)|(.+)", iinfo)
return {
"comic": comic,
"issue": match.group(1) or match.group(2),
"issue_id": text.parse_int(self.issue_id),
"lang": "en",
"language": "English",
}
def images(self, page):
return [
(beau(url), None)
for url in text.extract_iter(
page, 'lstImages.push("', '"'
)
]
class ReadcomiconlineComicExtractor(ReadcomiconlineBase, MangaExtractor):
"""Extractor for comics from readcomiconline.li"""
chapterclass = ReadcomiconlineIssueExtractor
subcategory = "comic"
pattern = BASE_PATTERN + r"(/Comic/[^/?#]+/?)$"
test = (
("https://readcomiconline.li/Comic/W-i-t-c-h", {
"url": "74eb8b9504b4084fcc9367b341300b2c52260918",
"keyword": "3986248e4458fa44a201ec073c3684917f48ee0c",
}),
("https://readcomiconline.to/Comic/Bazooka-Jules", {
"url": "2f66a467a772df4d4592e97a059ddbc3e8991799",
"keyword": "f5ba5246cd787bb750924d9690cb1549199bd516",
}),
)
def chapters(self, page):
results = []
comic, pos = text.extract(page, ' class="barTitle">', '<')
page , pos = text.extract(page, ' class="listing">', '</table>', pos)
comic = comic.rpartition("information")[0].strip()
needle = ' title="Read {} '.format(comic)
comic = text.unescape(comic)
for item in text.extract_iter(page, ' href="', ' comic online '):
url, _, issue = item.partition(needle)
url = url.rpartition('"')[0]
if issue.startswith('Issue #'):
issue = issue[7:]
results.append((self.root + url, {
"comic": comic, "issue": issue,
"issue_id": text.parse_int(url.rpartition("=")[2]),
"lang": "en", "language": "English",
}))
return results
def beau(url):
"""https://readcomiconline.li/Scripts/rguard.min.js?v=1.1"""
if url.startswith("https"):
return url
containsS0 = "=s0" in url
url = url[:-3 if containsS0 else -6]
url = url[4:22] + url[25:]
url = url[0:-6] + url[-2:]
url = binascii.a2b_base64(url).decode()
url = url[0:13] + url[17:]
url = url[0:-2] + ("=s0" if containsS0 else "=s1600")
return "https://2.bp.blogspot.com/" + url
|
