# -*- 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, sub from os.path import splitext from ..scraper import _BasicScraper, _ParserScraper from ..helpers import indirectStarter, bounceStarter from ..util import tagre, getPageContent class SabrinaOnline(_BasicScraper): url = 'http://sabrina-online.com/' imageSearch = compile(tagre("a", "href", r'(strips/[^"]*)')) prevSearch = compile(tagre("a", "href", r"(\d\d\d\d-\d\d.html)") + tagre("img", "src", "b_back.gif")) help = 'Index format: n (unpadded)' adult = True multipleImagesPerStrip = True @classmethod def starter(cls): """Pick last one in a list of archive pages.""" archive = cls.url + 'archive.html' data = getPageContent(archive, cls.session) search = compile(tagre("a", "href", r"(\d\d\d\d-\d\d.html)")) archivepages = search.findall(data) return cls.url + archivepages[-1] class SafelyEndangered(_BasicScraper): url = 'http://www.safelyendangered.com/' stripUrl = url + 'comic/%s' firstStripUrl = stripUrl % 'ignored' imageSearch = compile(tagre("img", "src", r'(http://www\.safelyendangered\.com/wp-content/uploads/\d+/\d+/[^"]+\.[a-z]+).*')) prevSearch = compile(tagre("a", "href", r'([^"]+)', after="navi navi-prev")) textSearch = compile(tagre("img", "title", r'([^"]+)', before=r'http://www\.safelyendangered\.com/wp-content/uploads')) help = 'Index format: yyyy/mm/stripname' class SailorsunOrg(_BasicScraper): url = 'http://sailorsun.org/' rurl = escape(url) stripUrl = url + '?p=%s' firstStripUrl = stripUrl % '21' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev")) help = 'Index format: n (unpadded)' class SamAndFuzzy(_BasicScraper): url = 'http://www.samandfuzzy.com/' stripUrl = 'http://samandfuzzy.com/%s' firstStripUrl = stripUrl % '1' imageSearch = compile(r'(/comics/.+?)" alt') prevSearch = compile(r'"><<', IGNORECASE) help = 'Index format: nnn' starter = indirectStarter(url, 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 # XXX site has been hacked class _ShadowGirls(_BasicScraper): url = 'http://www.shadowgirlscomic.com/' stripUrl = url + 'comics/%s' firstStripUrl = stripUrl % 'book-1/chapter-1-broken-dreams/welcome' imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]*)')) prevSearch = compile(tagre("a", "href", r'([^"]*)', after='navi-prev')) help = 'Index format: custom' starter = indirectStarter(url, compile(tagre("a", "href", r'([^"]*/comics/[^"]+)'))) class Sheldon(_BasicScraper): url = 'http://www.sheldoncomics.com/' rurl = escape(url) stripUrl = url + 'archive/%s.html' firstStripUrl = stripUrl % '011130' imageSearch = compile(tagre("img", "src", r'(http://cdn\.sheldoncomics\.com/strips/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(%sarchive/\d+\.html)' % rurl, after="sidenav-prev")) help = 'Index format: yymmdd' class ShermansLagoon(_BasicScraper): url = 'http://shermanslagoon.com/' stripUrl = url + 'comics/%s' firstStripUrl = stripUrl % '/december-29-2003/' imageSearch = compile(tagre("img", "src", r'(http://safr\.kingfeatures\.com/idn/etv/zone/xml/content\.php\?file=.+?)')) prevSearch = compile(r'id="previouscomic" class="button white">]+?>') multipleImagesPerStrip = True help = 'Index format: yymmdd' class SMBC(_ParserScraper): url = 'http://www.smbc-comics.com/' rurl = escape(url) stripUrl = url + '?id=%s' firstStripUrl = stripUrl % '1' imageSearch = '//img[@id="comic"]' prevSearch = '//a[@class="prev"]' help = 'Index format: nnnn' @classmethod def namer(cls, imageUrl, pageUrl): """Remove random noise from name.""" return imageUrl.rsplit('-', 1)[-1] def shouldSkipUrl(self, url, data): """Skip promo or missing update pages.""" return url in ( self.stripUrl % '2865', self.stripUrl % '2653', self.stripUrl % '2424', self.stripUrl % '2226', self.stripUrl % '2069', self.stripUrl % '1895', self.stripUrl % '1896', self.stripUrl % '1589', ) class SnowFlakes(_BasicScraper): url = 'http://www.snowflakescomic.com/' stripUrl = url + '?id=%s&sl=%s' firstStripUrl = stripUrl % ('103', '1') endOfLife = True imageSearch = ( compile(tagre("img", "src", r'(comics/[^"]+)')), compile(tagre("img", "src", r'(http://www.snowflakescomic.com/comics/[^"]+)')), ) prevSearch = compile(tagre("a", "href", r'(/\?id=\d+\&sl=\d)', quote="") + tagre("img", "src", r'images/nav_prior-ON\.gif')) help = 'Index format: number' @classmethod def starter(cls): return cls.stripUrl % ('530', '5') def getIndexStripUrl(self, index): return self.stripUrl % (index, index[0]) @classmethod def namer(cls, imageUrl, pageUrl): """Use strip index number for image name.""" index = int(compile(r'id=(\d+)').search(pageUrl).group(1)) ext = imageUrl.rsplit('.', 1)[1] return "SnowFlakes-%d.%s" % (index, ext) def shouldSkipUrl(self, url, data): """Skip pages without images.""" return url in ( self.stripUrl % ('279', '2'), # no comic self.stripUrl % ('278', '2'), # no comic self.stripUrl % ('277', '2'), # no comic self.stripUrl % ('276', '2'), # no comic self.stripUrl % ('275', '2'), # no comic self.stripUrl % ('214', '2'), # no comic ) class SnowFlame(_BasicScraper): url = 'http://www.snowflamecomic.com/' rurl = escape(url) stripUrl = url + '?comic=snowflame-%s-%s' firstStripUrl = stripUrl % ('01', '01') imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl, after="Snow[Ff]lame ")) prevSearch = compile(tagre("span", "class", "mininav-prev") + tagre("a", "href", r'(%s\?comic=snowflame[^"]+)' % rurl)) starter = bounceStarter(url, compile(tagre("span", "class", "mininav-next") + tagre("a", "href", r'(%s\?comic=snowflame[^"]+)' % rurl))) help = 'Index format: chapter-page' def getIndexStripUrl(self, index): return self.stripUrl % tuple(index.split('-')) @classmethod def namer(cls, imageUrl, pageUrl): prefix, filename = imageUrl.rsplit('/', 1) ro = compile(r'snowflame-([^-]+)-([^-]+)') mo = ro.search(pageUrl) chapter = mo.group(1) page = mo.group(2) return "%s-%s-%s" % (chapter, page, filename) class SodiumEyes(_BasicScraper): url = 'http://sodiumeyes.com/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2007/11/08/damning-evidence' imageSearch = compile(tagre("img", "src", r'(%scomic/[^ ]+)' % rurl, quote="")) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/mm/dd/stripname' class Sorcery101(_BasicScraper): baseUrl = 'http://www.sorcery101.net/' url = baseUrl + 'sorcery-101/' rurl = escape(baseUrl) stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%ssorcery-101/[^"]+)' % rurl, after="previous-")) help = 'Index format: stripname' class SpaceTrawler(_BasicScraper): url = 'http://spacetrawler.com/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2010/01/01/spacetrawler-4' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl, after="navi-prev")) help = 'Index format: yyyy/mm/dd/stripname' class Spamusement(_BasicScraper): url = 'http://spamusement.com/' rurl = escape(url) stripUrl = url + 'index.php/comics/view/%s' imageSearch = compile(r'' % rurl, IGNORECASE) help = 'Index format: n (unpadded)' starter = indirectStarter(url, prevSearch) class SpareParts(_BasicScraper): baseUrl = 'http://www.sparepartscomics.com/' url = baseUrl + 'comics/?date=20080328' stripUrl = baseUrl + 'comics/index.php?date=%s' firstStripUrl = stripUrl % '20031022' 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 Spinnerette(_BasicScraper): url = 'http://www.spinnyverse.com/' rurl = escape(url) stripUrl = url + 'index.php?id=%s' firstStripUrl = stripUrl % '2010/02/09/02092010' imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)', after="comic")) prevSearch = compile(tagre("a", "href", r'(/index\.php\?id=[^"]+)', after="prev")) help = 'Index format: number' class SPQRBlues(_BasicScraper): url = 'http://spqrblues.com/IV/' rurl = escape(url) stripUrl = url + '?p=%s' firstStripUrl = stripUrl % '1467' imageSearch = compile(tagre("img", "src", r'(%scomics/\d+\.png)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev")) help = 'Index format: number' class StandStillStaySilent(_ParserScraper): url = 'http://www.sssscomic.com/comic.php' rurl = escape(url) stripUrl = url + '?page=%s' firstStripUrl = stripUrl % '1' imageSearch = '//img[@class="comicnormal"]' prevSearch = '//a//div[@id="navprev"]' help = 'Index Format: number' # XXX disallowed by robots.txt class _StationV3(_BasicScraper): url = 'http://www.stationv3.com/' rurl = escape(url) stripUrl = url + 'd/%s.html' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%sd/\d+\.html)' % rurl) + tagre("img", "src", r'http://www\.stationv3\.com/images/previous\.gif')) help = 'Index format: yyyymmdd' class StickyDillyBuns(_BasicScraper): url = 'http://www.stickydillybuns.com/' stripUrl = url + 'strips-sdb/%s' firstStripUrl = stripUrl % 'awesome_leading_man' imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]*/strips-sdb/[^"]+)', before="cn[id]prev")) help = 'Index format: name' class Stubble(_BasicScraper): url = 'http://stubblecomics.com/' rurl = escape(url) stripUrl = url + '?p=%s' firstStripUrl = stripUrl % '4' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="navi-prev")) help = 'Index format: number' class StuffNoOneToldMe(_BasicScraper): url = 'http://www.snotm.com/' stripUrl = url + '%s.html' firstStripUrl = stripUrl % '2010/05/01' olderHref = r"(http://www\.snotm\.com/\d+/\d+/[^']+\.html)" starter = indirectStarter(url, compile(tagre("a", "href", olderHref, quote="'"))) imageSearch = ( compile(tagre("img", "src", r'(http://i\.imgur\.com/[^"]+)') + r"(?:|
)"), compile(tagre("img", "src", r'(http://\d+\.bp\.blogspot\.com/[^"]+)') + r"(?:(?: )?|)"), compile(tagre("img", "src", r'(https://lh\d+\.googleusercontent\.com/[^"]+)') + r""), ) prevSearch = compile(tagre("a", "href", olderHref, quote="'", before="older-link")) multipleImagesPerStrip = True help = 'Index format: yyyy/mm/stripname' @classmethod def namer(cls, imageUrl, pageUrl): """Use page URL to construct meaningful image name.""" parts, year, month, stripname = pageUrl.rsplit('/', 3) stripname = stripname.rsplit('.', 1)[0] parts, imagename = imageUrl.rsplit('/', 1) return '%s-%s-%s-%s' % (year, month, stripname, imagename) def shouldSkipUrl(self, url, data): """Skip pages without images.""" return url in ( self.stripUrl % '2012/08/self-rant', # no comic self.stripUrl % '2012/06/if-you-wonder-where-ive-been', # video self.stripUrl % '2011/10/i-didnt-make-this-nor-have-anything-to', # video self.stripUrl % '2010/12/first-snotm-fans-in-sao-paulo', # no comic self.stripUrl % '2010/11/ear-infection', # no comic ) class StrawberryDeathCake(_BasicScraper): url = 'http://strawberrydeathcake.com/' rurl = escape(url) stripUrl = url + 'archive/%s/' imageSearch = compile(tagre("img", "src", r'(%swp-content/webcomic/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%sarchive/[^"]+)' % rurl, after="previous")) help = 'Index format: stripname' class StrongFemaleProtagonist(_ParserScraper): url = 'http://strongfemaleprotagonist.com/' stripUrl = url + '%s/' css = True imageSearch = 'article p:first-child img' prevSearch = 'div.nav-previous > a' help = 'Index format: issue-?/page-??' def shouldSkipUrl(self, url, data): """Skip hiatus & non-comic pages.""" return url in ( self.stripUrl % 'guest-art/tuesday', self.stripUrl % 'guest-art/friday', self.stripUrl % 'guest-art/wednesday', self.stripUrl % 'issue-5/newspaper', self.stripUrl % 'issue-5/hiatus-1', self.stripUrl % 'issue-5/hiatus-2', ) class SuburbanTribe(_BasicScraper): url = 'http://www.pixelwhip.com/' rurl = escape(url) stripUrl = url + '?p=%s' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev")) help = 'Index format: nnnn' class SomethingPositive(_BasicScraper): url = 'http://www.somethingpositive.net/' stripUrl = url + 'sp%s.shtml' imageSearch = ( compile(tagre("img", "src", r'(sp\d+\.png)')), compile(tagre("img", "src", r'(twither\.gif)')), ) prevSearch = compile(tagre("a", "href", r'(sp\d+\.shtml)') + "(?:" + tagre("img", "src", r'images/previous\.gif') + "|Previous)") help = 'Index format: mmddyyyy' class StarCrossdDestiny(_BasicScraper): baseUrl = 'http://www.starcrossd.net/' rurl = escape(baseUrl) url = baseUrl + 'comic.html' stripUrl = baseUrl + 'archives/%s.html' firstStripUrl = stripUrl % '00000001' imageSearch = compile(tagre("img", "src", r'(http://(?:www\.)?starcrossd\.net/(?:ch1|strips|book2)/[^"]+)')) prevSearch = compile(r']*"[^"]*"[^>]*>prev' % rurl, 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 # XXX disallowed by robots.txt class _StrangeCandy(_BasicScraper): url = 'http://www.strangecandy.net/' stripUrl = url + '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 SupernormalStep(_BasicScraper): url = 'http://supernormalstep.com/' rurl = escape(url) stripUrl = url + '?p=%s' firstStripUrl = stripUrl % '8' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev")) help = 'Index format: number'