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
|
# -*- coding: utf-8 -*-
# Copyright 2019-2025 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 http://www.keenspot.com/"""
from .common import Extractor, Message
from .. import text
class KeenspotComicExtractor(Extractor):
"""Extractor for webcomics from keenspot.com"""
category = "keenspot"
subcategory = "comic"
directory_fmt = ("{category}", "{comic}")
filename_fmt = "{filename}.{extension}"
archive_fmt = "{comic}_{filename}"
pattern = r"(?:https?://)?(?!www\.|forums\.)([\w-]+)\.keenspot\.com(/.+)?"
example = "http://COMIC.keenspot.com/"
def __init__(self, match):
Extractor.__init__(self, match)
self.comic = match[1].lower()
self.path = match[2]
self.root = "http://" + self.comic + ".keenspot.com"
self._needle = ""
self._image = 'class="ksc"'
self._next = self._next_needle
def items(self):
data = {"comic": self.comic}
yield Message.Directory, data
with self.request(self.root + "/") as response:
if response.history:
url = response.request.url
self.root = url[:url.index("/", 8)]
page = response.text
del response
url = self._first(page)
if self.path:
url = self.root + self.path
prev = None
ilen = len(self._image)
while url and url != prev:
prev = url
page = self.request(text.urljoin(self.root, url)).text
pos = 0
while True:
pos = page.find(self._image, pos)
if pos < 0:
break
img, pos = text.extract(page, 'src="', '"', pos + ilen)
if img.endswith(".js"):
continue
if img[0] == "/":
img = self.root + img
elif "youtube.com/" in img:
img = "ytdl:" + img
yield Message.Url, img, text.nameext_from_url(img, data)
url = self._next(page)
def _first(self, page):
if self.comic == "brawlinthefamily":
self._next = self._next_brawl
self._image = '<div id="comic">'
return "http://brawlinthefamily.keenspot.com/comic/theshowdown/"
if url := text.extr(page, '<link rel="first" href="', '"'):
if self.comic == "porcelain":
self._needle = 'id="porArchivetop_"'
else:
self._next = self._next_link
return url
pos = page.find('id="first_day1"')
if pos >= 0:
self._next = self._next_id
return text.rextr(page, 'href="', '"', pos)
pos = page.find('>FIRST PAGE<')
if pos >= 0:
if self.comic == "lastblood":
self._next = self._next_lastblood
self._image = '<div id="comic">'
else:
self._next = self._next_id
return text.rextr(page, 'href="', '"', pos)
pos = page.find('<div id="kscomicpart"')
if pos >= 0:
self._needle = '<a href="/archive.html'
return text.extract(page, 'href="', '"', pos)[0]
pos = page.find('>First Comic<') # twokinds
if pos >= 0:
self._image = '</header>'
self._needle = 'class="navarchive"'
return text.rextr(page, 'href="', '"', pos)
pos = page.find('id="flip_FirstDay"') # flipside
if pos >= 0:
self._image = 'class="flip_Pages ksc"'
self._needle = 'id="flip_ArcButton"'
return text.rextr(page, 'href="', '"', pos)
self.log.error("Unrecognized page layout")
return None
def _next_needle(self, page):
pos = page.index(self._needle) + len(self._needle)
return text.extract(page, 'href="', '"', pos)[0]
def _next_link(self, page):
return text.extr(page, '<link rel="next" href="', '"')
def _next_id(self, page):
pos = page.find('id="next_')
return text.rextr(page, 'href="', '"', pos) if pos >= 0 else None
def _next_lastblood(self, page):
pos = page.index("link rel='next'")
return text.extract(page, "href='", "'", pos)[0]
def _next_brawl(self, page):
pos = page.index("comic-nav-next")
url = text.rextr(page, 'href="', '"', pos)
return None if "?random" in url else url
|
