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
|
# SPDX-License-Identifier: MIT
# SPDX-FileCopyrightText: © 2004 Tristan Seligmann and Jonathan Jacobs
# SPDX-FileCopyrightText: © 2012 Bastian Kleineidam
# SPDX-FileCopyrightText: © 2015 Tobias Gruetzmacher
# SPDX-FileCopyrightText: © 2019 Daniel Ring
import re
from .. import util
from ..helpers import bounceStarter
from ..scraper import ParserScraper
class WLPComics(ParserScraper):
imageSearch = '//img[contains(@alt, " Comic")]'
prevSearch = '//a[contains(text(), "Previous ")]'
nextSearch = '//a[contains(text(), "Next ")]'
starter = bounceStarter
help = 'Index format: nnn'
def __init__(self, name):
super().__init__('WLP/' + name)
def namer(self, image_url, page_url):
return (page_url.rsplit('/', 1)[-1].split('.')[0] + '_' +
util.urlpathsplit(image_url)[-1])
class ChichiChan(WLPComics):
url = 'http://www.wlpcomics.com/adult/chichi/'
stripUrl = url + '%s.html'
adult = True
class ChocolateMilkMaid(WLPComics):
# Newer pages seem to be broken
stripUrl = 'http://www.wlpcomics.com/adult/cm/%s.html'
url = stripUrl % '264'
adult = True
def link_modifier(self, fromurl, tourl):
"""Bugfix for self-referencing pages..."""
if tourl == fromurl:
return re.sub(r'/(\d+)\.ht',
lambda m: '/%03i.ht' % (int(m.group(1)) - 1), tourl)
if '263.html' in fromurl and '265.html' in tourl:
return self.stripUrl % '264'
return tourl
class MaidAttack(WLPComics):
url = 'http://www.wlpcomics.com/general/maidattack/'
stripUrl = url + '%s.html'
class PeterIsTheWolfAdult(WLPComics):
stripUrl = 'http://www.peteristhewolf.com/adult/%s.html'
# navigation to newest page is broken
url = stripUrl % '427'
firstStripUrl = stripUrl % '001'
multipleImagesPerStrip = True
adult = True
endOfLife = True
def namer(self, image_url, page_url):
name = page_url.rsplit('/', 1)[-1].split('.')[0] + '_' + util.urlpathsplit(image_url)[-1]
if 'adult' in image_url:
name = name.split('.')
return name[0] + '_adult.' + name[1]
return name
def getPrevUrl(self, url, data):
# Fix loop in site navigation
if url == self.stripUrl % '194':
return self.stripUrl % '193'
return super(PeterIsTheWolfAdult, self).getPrevUrl(url, data)
class PeterIsTheWolfGeneral(WLPComics):
stripUrl = 'http://www.peteristhewolf.com/general/%s.html'
# navigation to newest page is broken
url = stripUrl % '427'
firstStripUrl = stripUrl % '001'
endOfLife = True
def getPrevUrl(self, url, data):
# Fix loops in site navigation
if url == self.stripUrl % '406':
return self.stripUrl % '405'
if url == self.stripUrl % '230':
return self.stripUrl % '229'
if url == self.stripUrl % '229':
return self.stripUrl % '228'
if url == self.stripUrl % '153':
return self.stripUrl % '152'
return super(PeterIsTheWolfGeneral, self).getPrevUrl(url, data)
class Stellar(WLPComics):
url = 'http://www.wlpcomics.com/adult/stellar/'
stripUrl = url + '%s.html'
adult = True
def link_modifier(self, fromurl, tourl):
"""Bugfix for empty page..."""
if tourl == self.url + '075.html':
return self.url + '074.html'
return tourl
|
