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
|
# 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
from re import compile, escape
from .. import util
from ..scraper import BasicScraper, ParserScraper
from ..util import tagre
from .common import WordPressNavi, WordPressScraper
class IAmArg(BasicScraper):
url = 'http://iamarg.com/'
rurl = escape(url)
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2011/05/08/05082011'
imageSearch = compile(tagre("img", "src", r'(//iamarg.com/comics/\d+-\d+-\d+[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl, after="prev"))
help = 'Index format: yyyy/mm/dd/stripname'
class ICanBarelyDraw(BasicScraper):
url = 'http://www.icanbarelydraw.com/comic/'
rurl = escape(url)
stripUrl = url + '%s'
firstStripUrl = stripUrl % '39'
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+-[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\d+)' % rurl))
help = 'Index format: number'
class IDreamOfAJeanieBottle(WordPressScraper):
url = 'http://jeaniebottle.com/'
class InternetWebcomic(WordPressNavi):
url = 'http://www.internet-webcomic.com/'
stripUrl = url + '?p=%s'
firstStripUrl = stripUrl % '30'
help = 'Index format: n'
class Inverloch(ParserScraper):
stripUrl = 'https://www.seraph-inn.com/view.php?story=inverloch&page=%s'
url = stripUrl % '763'
firstStripUrl = stripUrl % '2'
imageSearch = '//img[@class="page"]'
prevSearch = '//p[@class="comic-nav"]/a[text()=" Previous"]'
multipleImagesPerStrip = True
endOfLife = True
class IrregularWebcomic(BasicScraper):
url = 'http://www.irregularwebcomic.net/'
stripUrl = url + '%s.html'
firstStripUrl = stripUrl % '1'
imageSearch = compile(r'<img .*src="(.*comics/.*(png|jpg|gif))".*>')
prevSearch = compile(r'<a href="(/\d+\.html|/cgi-bin/comic\.pl\?comic=\d+)">Previous ')
help = 'Index format: nnn'
class IslaAukate(ParserScraper):
url = 'https://overlordcomic.com/archive/default/latest'
stripUrl = 'https://overlordcomic.com/archive/default/pages/%s'
firstStripUrl = stripUrl % '001'
imageSearch = '//div[@id="comicpage"]/img'
prevSearch = '//nav[@class="comicnav"]/a[text()="Prev"]'
def namer(self, image_url, page_url):
filename = util.urlpathsplit(image_url)[-1]
return filename.rsplit('_', 1)[0]
class IslaAukateColor(ParserScraper):
url = 'https://overlordcomic.com/archive/color/latest'
stripUrl = 'https://overlordcomic.com/archive/color/pages/%s'
firstStripUrl = stripUrl % '001'
imageSearch = '//div[@id="comicpage"]/img'
prevSearch = '//nav[@class="comicnav"]/a[text()="Prev"]'
def namer(self, image_url, page_url):
# Fix filenames of early comics
filename = util.urlpathsplit(image_url)[-1]
if filename[0].isdigit():
filename = 'Aukate' + filename
return filename.rsplit('_', 1)[0] + '.' + filename.rsplit('.', 1)[-1]
class ItsWalky(WordPressScraper):
url = 'http://www.itswalky.com/'
|
