2016-03-31 21:13:54 +00:00
|
|
|
# -*- coding: utf-8 -*-
|
2012-06-20 20:41:04 +00:00
|
|
|
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
|
2014-01-05 15:50:57 +00:00
|
|
|
# Copyright (C) 2012-2014 Bastian Kleineidam
|
2016-03-31 21:13:54 +00:00
|
|
|
# Copyright (C) 2015-2016 Tobias Gruetzmacher
|
2012-11-21 20:57:26 +00:00
|
|
|
|
2016-03-31 21:13:54 +00:00
|
|
|
from __future__ import absolute_import, division, print_function
|
2016-04-10 21:04:34 +00:00
|
|
|
|
2013-04-25 19:38:18 +00:00
|
|
|
from re import compile, escape
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2012-10-11 10:03:12 +00:00
|
|
|
from ..scraper import _BasicScraper
|
2016-03-31 21:13:54 +00:00
|
|
|
from ..helpers import indirectStarter
|
|
|
|
from ..util import tagre
|
2016-04-10 21:04:34 +00:00
|
|
|
from .common import _WordPressScraper, xpath_class
|
2016-03-31 21:13:54 +00:00
|
|
|
|
2012-11-20 17:53:53 +00:00
|
|
|
|
2016-04-10 21:04:34 +00:00
|
|
|
class Underling(_WordPressScraper):
|
2014-02-20 11:54:40 +00:00
|
|
|
url = 'http://underlingcomic.com/'
|
2016-04-10 21:04:34 +00:00
|
|
|
firstStripUrl = url + 'page-one/'
|
|
|
|
prevSearch = '//a[%s]' % xpath_class('navi-prev')
|
2014-02-20 11:54:40 +00:00
|
|
|
|
2012-11-20 17:53:53 +00:00
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class Undertow(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://undertow.dreamshards.org/'
|
2012-12-04 06:02:40 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'([^"]+\.jpg)'))
|
2012-06-20 19:58:13 +00:00
|
|
|
prevSearch = compile(r'href="(.+?)".+?teynpoint')
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = compile(r'href="(.+?)".+?Most recent page')
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
|
|
|
class UnicornJelly(_BasicScraper):
|
2013-04-13 18:58:00 +00:00
|
|
|
baseUrl = 'http://unicornjelly.com/'
|
|
|
|
url = baseUrl + 'uni666.html'
|
|
|
|
stripUrl = baseUrl + 'uni%s.html'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '001'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'</TABLE>(?:<FONT COLOR="BLACK">)?<IMG SRC="(images/[^"]+)" WIDTH=')
|
|
|
|
prevSearch = compile(r'<A HREF="(uni\d{3}[bcs]?\.html)">(<FONT COLOR="BLACK">)?<IMG SRC="images/back00\.gif"')
|
|
|
|
help = 'Index format: nnn'
|
|
|
|
|
|
|
|
|
2013-04-25 19:38:18 +00:00
|
|
|
class Unsounded(_BasicScraper):
|
|
|
|
url = 'http://www.casualvillain.com/Unsounded/'
|
|
|
|
stripUrl = url + 'comic/ch%s/ch%s_%s.html'
|
|
|
|
firstStripUrl = stripUrl % ('01', '01', '01')
|
|
|
|
rurl = escape(url)
|
2013-07-18 18:39:53 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(pageart/[^"]*)'))
|
2013-04-25 19:38:18 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]*)', after='class="back'))
|
2016-04-12 21:11:39 +00:00
|
|
|
latestSearch = compile(tagre("a", "href", r'(%scomic/[^"]*)' % rurl) +
|
|
|
|
tagre("img", "src",
|
|
|
|
r"%simages/newpages\.png" % rurl))
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2013-04-25 19:38:18 +00:00
|
|
|
help = 'Index format: chapter-number'
|
|
|
|
|
|
|
|
def getIndexStripUrl(self, index):
|
|
|
|
"""Get comic strip URL from index."""
|
|
|
|
chapter, num = index.split('-')
|
|
|
|
return self.stripUrl % (chapter, chapter, num)
|
2016-05-16 21:55:41 +00:00
|
|
|
|
|
|
|
|
|
|
|
class UrgentTransformationCrisis(_WordPressScraper):
|
|
|
|
url = 'http://www.catomix.com/utc/'
|
|
|
|
firstStripUrl = url + 'comic/cover1'
|