# -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012 Bastian Kleineidam from re import compile, MULTILINE, IGNORECASE, sub from os.path import splitext from ..scraper import _BasicScraper from ..helpers import indirectStarter from ..util import tagre class SailorsunOrg(_BasicScraper): latestUrl = 'http://sailorsun.org/' stripUrl = latestUrl + '?p=%s' imageSearch = compile(tagre("img", "src", r'(http://sailorsun\.org/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://sailorsun\.org/\?p=\d+)', after="prev")) help = 'Index format: n (unpadded)' class SamAndFuzzy(_BasicScraper): latestUrl = 'http://www.samandfuzzy.com/' stripUrl = 'http://samandfuzzy.com/%s' imageSearch = compile(r'(/comics/.+?)" alt') prevSearch = compile(r'">]+?>') help = 'Index format: yymmdd' class SodiumEyes(_BasicScraper): latestUrl = 'http://sodiumeyes.com/' stripUrl = latestUrl + '%s/' imageSearch = compile(tagre("img", "src", r'(http://sodiumeyes\.com/comic/[^ ]+)', quote="")) prevSearch = compile(tagre("a", "href", r'(http://sodiumeyes\.com/[^"]+)', after="prev")) help = 'Index format: yyyy/mm/dd/stripname' class SpareParts(_BasicScraper): baseUrl = 'http://www.sparepartscomics.com/' latestUrl = baseUrl + 'comics/?date=20080328' stripUrl = baseUrl + 'comics/index.php?date=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.sparepartscomics\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(index\.php\?date=\d+)', quote="'") + "Previous Comic") help = 'Index format: yyyymmdd' class Stubble(_BasicScraper): latestUrl = 'http://stubblecomics.com/' stripUrl = latestUrl + '?p=%s' imageSearch = compile(tagre("img", "src", r'(http://stubblecomics\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://stubblecomics\.com/\?p=\d+)', after="navi-prev")) help = 'Index format: number' class StrawberryDeathCake(_BasicScraper): latestUrl = 'http://strawberrydeathcake.com/' stripUrl = latestUrl + 'archive/%s/' imageSearch = compile(tagre("img", "src", r'(http://strawberrydeathcake\.com/wp-content/webcomic/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://strawberrydeathcake\.com/archive/[^"]+)', after="previous")) help = 'Index format: stripname' class SuburbanTribe(_BasicScraper): latestUrl = 'http://www.pixelwhip.com/' stripUrl = latestUrl + '?p=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.pixelwhip\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.pixelwhip\.com/\?p=\d+)', after="prev")) help = 'Index format: nnnn' class SomethingPositive(_BasicScraper): latestUrl = 'http://www.somethingpositive.net/' stripUrl = latestUrl + 'sp%s.shtml' imageSearch = compile(tagre("img", "src", r'(sp\d+\.png)')) prevSearch = compile(tagre("a", "href", r'(sp\d+\.shtml)') + "(?:" + tagre("img", "src", r'images/previous\.gif') + "|Previous)") help = 'Index format: mmddyyyy' class SexyLosers(_BasicScraper): stripUrl = 'http://www.sexylosers.com/%s.html' imageSearch = compile(r'<<', IGNORECASE) help = 'Index format: nnn' starter = indirectStarter('http://www.sexylosers.com/', compile(r'SEXY LOSERS Latest SL Comic \(#\d+\)', IGNORECASE)) @classmethod def namer(cls, imageUrl, pageUrl): index = pageUrl.split('/')[-1].split('.')[0] title = imageUrl.split('/')[-1].split('.')[0] return index + '-' + title class StarCrossdDestiny(_BasicScraper): latestUrl = 'http://www.starcrossd.net/comic.html' stripUrl = 'http://www.starcrossd.net/archives/%s.html' imageSearch = compile(tagre("img", "src", r'(http://www\.starcrossd\.net/(?:ch1|strips|book2)/[^"]+)')) prevSearch = compile(r']*"[^"]*"[^>]*>prev', IGNORECASE) help = 'Index format: nnnnnnnn' @classmethod def namer(cls, imageUrl, pageUrl): if imageUrl.find('ch1') == -1: # At first all images were stored in a strips/ directory but that was changed with the introduction of book2 imageUrl = sub('(?:strips)|(?:images)','book1',imageUrl) elif not imageUrl.find('strips') == -1: imageUrl = imageUrl.replace('strips/','') directory, filename = imageUrl.split('/')[-2:] filename, extension = splitext(filename) return directory + '-' + filename class Spamusement(_BasicScraper): stripUrl = 'http://spamusement.com/index.php/comics/view/%s' imageSearch = compile(r'', IGNORECASE) help = 'Index format: n (unpadded)' starter = indirectStarter('http://spamusement.com/', prevSearch) class StrangeCandy(_BasicScraper): latestUrl = 'http://www.strangecandy.net/' stripUrl = latestUrl + 'd/%s.html' imageSearch = compile(tagre("img", "src", r'(/comics/\d+\.jpg)')) prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)') + tagre("img", "alt", "Previous comic")) help = 'Index format: yyyyddmm' class SMBC(_BasicScraper): latestUrl = 'http://www.smbc-comics.com/' stripUrl = latestUrl + 'index.php?db=comics&id=%s' imageSearch = compile(r'') prevSearch = compile(r'131,13,216,84"\n\s+href="(.+?)#comic"\n>', MULTILINE) help = 'Index format: nnnn'