# -*- coding: utf-8 -*- # Copyright (C) 2004-2005 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 ..helpers import indirectStarter from ..scraper import _BasicScraper, _ParserScraper from ..util import tagre from .common import _WordPressScraper, WP_LATEST_SEARCH, xpath_class class EarthsongSaga(_ParserScraper): url = 'http://earthsongsaga.com/index.php' starter = indirectStarter() imageSearch = '//div[@id="comic"]//img' prevSearch = '//a[@title="Previous"]' latestSearch = '//div[@id="leftmenu"]/span[1]/a[1]' @classmethod def fetchUrls(cls, url, data, urlSearch): urls = super(EarthsongSaga, cls).fetchUrls(url, data, urlSearch) return [x.replace('earthsongsaga.com/../', 'earthsongsaga.com/') for x in urls] @classmethod def namer(cls, imageUrl, pageUrl): imgmatch = compile(r'images/vol(\d+)/ch(\d+)/(\d+)\.\w+$', IGNORECASE).search(imageUrl) if not imgmatch: imgmatch = compile(r'images/vol(\d+)/ch(\d+)/ch(\d+)cover\.\w+$', IGNORECASE).search(imageUrl) suffix = "cover" else: suffix = "" return 'vol%02d_ch%02d_%02d%s' % ( int(imgmatch.group(1)), int(imgmatch.group(2)), int(imgmatch.group(3)), suffix) class EasilyAmused(_WordPressScraper): url = 'http://www.flowerlarkstudios.com/comic/college-daze/ea01/' firstStripUrl = url latestSearch = WP_LATEST_SEARCH starter = indirectStarter() class EatLiver(_BasicScraper): url = 'http://www.eatliver.com/' rurl = escape(url) starter = indirectStarter() stripUrl = url + "i.php?n=%s" firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("link", "href", r'(%simg/\d+/[^"]+)' % rurl, before="image_src")) prevSearch = compile(tagre("a", "href", r'(i\.php\?n=\d+)') + "<< Previous") latestSearch = compile(tagre("a", "href", r'(i\.php\?n=\d+)') + tagre("img", "src", r'img/small/[^"]+') + r"\s*]+?src="([^"]*?comics/.+?)"') prevSearch = compile(r'><Previous') help = 'Index format: yyyy-mm-dd/num' class Erstwhile(_WordPressScraper): url = 'http://www.erstwhiletales.com/' prevSearch = '//a[%s]' % xpath_class('navi-prev') endOfLife = True class Eryl(_WordPressScraper): url = 'http://www.flowerlarkstudios.com/comic/prologue-migration/page-i/' firstStripUrl = url latestSearch = WP_LATEST_SEARCH starter = indirectStarter() help = 'This was known as DarkWings in previous Dosage versions' class EverybodyLovesEricRaymond(_BasicScraper): url = 'http://geekz.co.uk/lovesraymond/' stripUrl = url + 'archive/%s' firstStripUrl = stripUrl % 'slashdotted' imageSearch = compile(r'') help = 'Index format: name-of-old-comic' class EverydayBlues(_WordPressScraper): url = 'http://everydayblues.everydayblues.net/' firstStripUrl = url + '2010/02/11/sometimes/' prevSearch = '//a[%s]' % xpath_class('navi-prev') class EvilDiva(_BasicScraper): url = 'http://www.evildivacomics.com/' stripUrl = url + '?p=%s' firstStripUrl = stripUrl % '145' imageSearch = compile(r'(/comics/.+?)"') prevSearch = compile(r'http.+?com/(.+?)".+?"prev') help = 'Index format: n (unpadded)' class EvilInc(_BasicScraper): url = 'http://evil-inc.com/' stripUrl = url + 'comic/%s' firstStripUrl = stripUrl % 'monday-3' imageSearch = compile( tagre("div", "id", "comic") + r'\s*.*\s*' + # filter out the variant href tag tagre("img", "src", r'(http://i\d\.wp\.com/evil-inc\.com/wp-content/uploads/[^"]+)')) prevSearch = compile(tagre("span", "class", "mininav-prev") + tagre("a", "href", r'([^"]+)')) help = 'Index format: stripname' class Exiern(_BasicScraper): url = 'http://www.exiern.com/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2005/09/06/so-far' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/mm/dd/stripname' class ExploitationNow(_WordPressScraper): url = 'http://www.exploitationnow.com/' firstStripUrl = url + '2000-07-07/9' prevSearch = '//a[%s]' % xpath_class('navi-prev') endOfLife = True class ExtraLife(_BasicScraper): url = 'http://www.myextralife.com/' stripUrl = url + 'comic/%s/' imageSearch = compile(tagre("img", "src", r'(http://www\.myextralife\.com/wp-content/uploads/[^"]+)', before="comic")) prevSearch = compile(tagre("a", "href", r'([^"]+)', before="prev_comic")) help = 'Index format: stripname' class ExtraOrdinary(_BasicScraper): url = 'http://www.exocomics.com/' rurl = escape(url) stripUrl = url + '%s' firstStripUrl = stripUrl % '01' prevSearch = compile(tagre("a", "href", r'(%s\d+)' % rurl, before="prev")) imageSearch = compile(tagre("img", "src", r'(%scomics/comics/\d+\.[^"]+)' % rurl)) help = 'Index format: number' class EyeOfRamalach(_BasicScraper): url = 'http://theeye.katbox.net/' rurl = escape(url) stripUrl = url + 'comic/%s/' imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/[^"]+)' % rurl, after="data-webcomic-parent")) prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl, after="previous")) help = 'Index format: stripname'