# -*- coding: utf-8 -*- # Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2014 Bastian Kleineidam # Copyright (C) 2015-2016 Tobias Gruetzmacher from __future__ import absolute_import, division, print_function from re import compile, escape, IGNORECASE from ..scraper import _BasicScraper, _ParserScraper from ..helpers import indirectStarter from ..util import tagre from .common import (_ComicControlScraper, _TumblrScraper, _WordPressScraper, xpath_class) class TheBrads(_ParserScraper): url = 'http://bradcolbow.com/archive/' imageSearch = '//div[%s]//img' % xpath_class('entry') prevSearch = '//a[%s]' % xpath_class('prev') multipleImagesPerStrip = True class TheDevilsPanties(_BasicScraper): url = 'http://thedevilspanties.com/' stripUrl = url + 'archives/%s' firstStripUrl = stripUrl % '300' imageSearch = compile(tagre("img", "src", r'(http://origin\.thedevilspanties\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/archives/\d+)', after="Previous")) help = 'Index format: number' class TheDreamlandChronicles(_WordPressScraper): url = 'http://www.thedreamlandchronicles.com/' class TheGamerCat(_ParserScraper): url = "http://www.thegamercat.com/" stripUrl = url + "comic/%s/" firstStripUrl = stripUrl % "06102011" css = True imageSearch = '#comic img' prevSearch = '.comic-nav-previous' help = 'Index format: stripname' class TheGentlemansArmchair(_WordPressScraper): url = 'http://thegentlemansarmchair.com/' class TheLandscaper(_BasicScraper): stripUrl = 'http://landscaper.visual-assault.net/comic/%s' url = stripUrl % 'latest' firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r'(/comics/comic/comic_page/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/comic/[^"]+)') + '‹ Previous') help = 'Index format: name' class TheMelvinChronicles(_WordPressScraper): url = 'http://melvin.jeaniebottle.com/' class TheNoob(_WordPressScraper): url = 'http://thenoobcomic.com/' stripUrl = url + 'comic/%s/' firstStripUrl = stripUrl % '1' help = 'Index format: n (unpadded)' class TheOrderOfTheStick(_BasicScraper): url = 'http://www.giantitp.com/' stripUrl = url + 'comics/oots%s.html' firstStripUrl = stripUrl % '0001' imageSearch = compile(r'') prevSearch = compile(r'', IGNORECASE) prevSearch = compile(r' previous', IGNORECASE) help = 'Index format: twb or wb + n wg. twb1000' class TheWotch(_WordPressScraper): url = 'http://www.thewotch.com/' firstStripUrl = url + '?comic=enter-the-wotch' class ThisIsIndexed(_BasicScraper): url = 'http://thisisindexed.com/' rurl = escape(url) stripUrl = url + 'page/%s' imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/card[^"]+)' % rurl)) multipleImagesPerStrip = True prevSearch = compile(tagre("div", "class", "nav-previous") + tagre("a", "href", r'(%spage/\d+/)[^"]*' % rurl)) help = 'Index format: number' class ThreePanelSoul(_ComicControlScraper): url = 'http://threepanelsoul.com/' firstStripUrl = url + 'comic/a-test-comic' class ToonHole(_WordPressScraper): url = 'http://toonhole.com/' firstStripUrl = url + 'comic/toon-hole-coming-soon-2010/' def shouldSkipUrl(self, url, data): return url in (self.url + "comic/if-game-of-thrones-was-animated/",) class TracyAndTristan(_BasicScraper): url = 'http://tandt.thecomicseries.com/' rurl = escape(url) stripUrl = url + 'comics/%s' imageSearch = compile(tagre("img", "src", r'(%simages/comics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(/comics/\d+)', after="prev")) help = 'Index format: number' class TwoGuysAndGuy(_BasicScraper): url = 'http://www.twogag.com/' rurl = escape(url) stripUrl = url + 'archives/%s' firstStripUrl = stripUrl % '4' imageSearch = compile(tagre('img', 'src', r'(%scomics/\d{4}-\d{2}-\d{2}[^"]*)' % rurl)) prevSearch = compile(tagre('a', 'href', r'(%sarchives/\d+)' % rurl, after='title="Previous"')) help = 'Index format: number' adult = True class Twokinds(_ParserScraper): url = 'http://twokinds.keenspot.com/' imageSearch = ('//p[@id="cg_img"]//img', '//article/p//img') prevSearch = ('//a[@id="cg_back"]', '//a[%s]' % xpath_class('navprev')) class TwoLumps(_BasicScraper): url = 'http://www.twolumps.net/' stripUrl = url + 'd/%s.html' imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)', after="prev")) help = 'Index format: yyyymmdd'