2020-04-18 11:45:44 +00:00
|
|
|
# SPDX-License-Identifier: MIT
|
2016-10-28 22:21:41 +00:00
|
|
|
# Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs
|
2014-01-05 15:50:57 +00:00
|
|
|
# Copyright (C) 2012-2014 Bastian Kleineidam
|
2020-01-13 06:34:05 +00:00
|
|
|
# Copyright (C) 2015-2020 Tobias Gruetzmacher
|
|
|
|
# Copyright (C) 2019-2020 Daniel Ring
|
2013-04-10 16:19:11 +00:00
|
|
|
from re import compile, escape
|
2016-04-10 21:04:34 +00:00
|
|
|
|
2020-03-04 06:03:14 +00:00
|
|
|
from ..helpers import indirectStarter
|
2019-06-19 08:27:06 +00:00
|
|
|
from ..scraper import _BasicScraper, _ParserScraper
|
2012-11-20 17:53:53 +00:00
|
|
|
from ..util import tagre
|
2020-03-04 06:03:14 +00:00
|
|
|
from .common import _WordPressScraper, _WPNavi, _WPWebcomic
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2013-03-06 19:00:30 +00:00
|
|
|
class IAmArg(_BasicScraper):
|
|
|
|
url = 'http://iamarg.com/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-03-06 19:00:30 +00:00
|
|
|
stripUrl = url + '%s/'
|
|
|
|
firstStripUrl = stripUrl % '2011/05/08/05082011'
|
2015-04-15 18:43:06 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(//iamarg.com/comics/\d+-\d+-\d+[^"]+)'))
|
2013-04-10 16:19:11 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl, after="prev"))
|
2013-03-06 19:00:30 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/stripname'
|
|
|
|
|
|
|
|
|
2013-07-04 10:22:20 +00:00
|
|
|
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'
|
|
|
|
|
|
|
|
|
2016-04-01 22:14:31 +00:00
|
|
|
class IDreamOfAJeanieBottle(_WordPressScraper):
|
|
|
|
url = 'http://jeaniebottle.com/'
|
|
|
|
|
|
|
|
|
2020-03-04 06:03:14 +00:00
|
|
|
class InsignificantOtters(_WPWebcomic):
|
|
|
|
stripUrl = 'https://www.thedepthscomic.com/i-otters/%s/'
|
|
|
|
firstStripUrl = stripUrl % 'page-1'
|
|
|
|
url = firstStripUrl
|
|
|
|
imageSearch = '//div[contains(@class, "webcomic-media")]//img'
|
|
|
|
starter = indirectStarter
|
|
|
|
|
|
|
|
|
2017-05-21 23:17:05 +00:00
|
|
|
class InternetWebcomic(_WPNavi):
|
2013-12-10 18:50:21 +00:00
|
|
|
url = 'http://www.internet-webcomic.com/'
|
|
|
|
stripUrl = url + '?p=%s'
|
|
|
|
firstStripUrl = stripUrl % '30'
|
|
|
|
help = 'Index format: n'
|
|
|
|
|
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
class IrregularWebcomic(_BasicScraper):
|
|
|
|
url = 'http://www.irregularwebcomic.net/'
|
|
|
|
stripUrl = url + '%s.html'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2013-03-06 19:21:10 +00:00
|
|
|
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'
|
2016-04-01 22:14:31 +00:00
|
|
|
|
|
|
|
|
2019-06-19 08:27:06 +00:00
|
|
|
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"]'
|
|
|
|
|
2020-04-11 23:51:08 +00:00
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
filename = imageUrl.rsplit('/', 1)[-1]
|
|
|
|
return filename.rsplit('_', 1)[0] + '.' + filename.rsplit('.', 1)[-1]
|
|
|
|
|
2019-06-19 08:27:06 +00:00
|
|
|
|
|
|
|
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, imageUrl, pageUrl):
|
|
|
|
# Fix filenames of early comics
|
|
|
|
filename = imageUrl.rsplit('/', 1)[-1]
|
|
|
|
if filename[0].isdigit():
|
|
|
|
filename = 'Aukate' + filename
|
2020-04-11 23:51:08 +00:00
|
|
|
return filename.rsplit('_', 1)[0] + '.' + filename.rsplit('.', 1)[-1]
|
2019-06-19 08:27:06 +00:00
|
|
|
|
|
|
|
|
2016-04-01 22:14:31 +00:00
|
|
|
class ItsWalky(_WordPressScraper):
|
|
|
|
url = 'http://www.itswalky.com/'
|