# -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2014 Bastian Kleineidam from re import compile, escape, IGNORECASE from ..scraper import _BasicScraper, _ParserScraper from ..helpers import indirectStarter from ..util import tagre class TheBrads(_BasicScraper): url = 'http://bradcolbow.com/archive/C4/' stripUrl = url + '%s/' firstStripUrl = stripUrl % 'P125' imageSearch = compile(tagre("img", "src", r'(http://s3\.amazonaws\.com/the_brads/the-?brads[-_][^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://bradcolbow\.com/archive/C4/[^"]+)', before="prev")) multipleImagesPerStrip = True help = 'Index format: a letter and a number' class TheDevilsPanties(_BasicScraper): url = 'http://thedevilspanties.com/' stripUrl = url + 'archives/%s' firstStripUrl = stripUrl % '300' imageSearch = compile(tagre("img", "src", r'(http://cdn\.thedevilspanties\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/archives/\d+)', after="Previous")) help = 'Index format: number' class TheDreamlandChronicles(_BasicScraper): url = 'http://www.thedreamlandchronicles.com/' stripUrl = url + 'comic/%s/' firstStripUrl = stripUrl % 'page-1' rurl = escape(url) imageSearch = compile(tagre("img", "src", r'(http://www\.thedreamlandchronicles\.com/wp-content/uploads/\d+/\d+/\d+-\d+-\d+[^"]*)')) prevSearch = compile(tagre("a", "href", r'(%s[^"]*)' % rurl, after='navi-prev"')) help = 'Index format: page-n or chapter-n' @classmethod def namer(cls, imageUrl, pageUrl): """Remove trailing digit from day number.""" name = imageUrl.split('/')[-1] base, ext = name.split('.', 1) bp = base.split('-') if len(bp[2]) == 3: bp[2] = bp[2][:-1] return "%s-%s-%s.%s" % (bp[0], bp[1], bp[2], ext) 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(_BasicScraper): url = 'http://thegentlemansarmchair.com/' rurl = escape(url) stripUrl = url + 'comic/%s' firstStripUrl = stripUrl % 'dora-the-explorer/' imageSearch = compile(tagre("div", "id", r'comic') + "\s*.*\s*" + tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after='navi-prev')) textSearch = compile(r'

(.+)

') help = 'Index Format: name' class TheLandscaper(_BasicScraper): url = 'http://landscaper.visual-assault.net/comic/latest' rurl = escape(url) stripUrl = url + 'comic/%s' 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 TheNoob(_BasicScraper): url = 'http://www.thenoobcomic.com/index.php' stripUrl = url + '?pos=%s' firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r'(/headquarters/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(\?pos=\d+)', before="comic_nav_previous_button")) help = 'Index format: nnnn' class TheOrderOfTheStick(_BasicScraper): baseUrl = 'http://www.giantitp.com/' url = baseUrl + 'comics/oots0863.html' stripUrl = baseUrl + 'comics/oots%s.html' firstStripUrl = stripUrl % '0001' imageSearch = compile(r'') prevSearch = compile(r'') multipleImagesPerStrip = True prevSearch = compile(r'\d{4} -\s+\d{4}') help = 'Index format: nnn' class TheWotch(_BasicScraper): url = 'http://www.thewotch.com/' stripUrl = url + '?date=%s' firstStripUrl = stripUrl % '2002-11-21' imageSearch = compile(r"', IGNORECASE) prevSearch = compile(r' previous', IGNORECASE) help = 'Index format: twb or wb + n wg. twb1000' class TheOuterQuarter(_BasicScraper): url = 'http://theouterquarter.com/' rurl = escape(url) stripUrl = url + 'comic/%s' firstStripUrl = stripUrl % 'oq-the-first-take/4' imageSearch = compile(r'') starter = indirectStarter(url, compile(tagre("a", "href", r'([^"]+)', after='class="timestamp"'))) adult = True indirectImageSearch = compile(tagre('a', 'href', r'(%simage/\d+)' % rurl)) def getComicStrip(self, url, data): """The comic strip image is in a separate page.""" pageUrl = self.fetchUrl(url, data, self.indirectImageSearch) pageData = self.getPage(pageUrl) return super(TheThinHLine, self).getComicStrip(pageUrl, pageData) @classmethod def namer(cls, imageUrl, pageUrl): """Use page URL sequence which is apparently increasing.""" num = pageUrl.split('/')[-1] ext = imageUrl.rsplit('.', 1)[1] return "thethinhline-%s.%s" % (num, ext) class ThreePanelSoul(_BasicScraper): url = 'http://threepanelsoul.com/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2006/05/11/a-test-comic' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/mm/dd/stripname' 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