# -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2013 Bastian Kleineidam from re import compile, escape from ..scraper import _BasicScraper from ..helpers import indirectStarter, bounceStarter from ..util import tagre class DailyDose(_BasicScraper): url = 'http://dailydoseofcomics.com/' starter = indirectStarter(url, compile(tagre("a", "href", r'(http://dailydoseofcomics\.com/[^"]+)', after="preview"))) stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'([^"]+)', before="align(?:none|center)")) prevSearch = compile(tagre("a", "href", r'(http://dailydoseofcomics\.com/[^"]+)', after="prev")) help = 'Index format: stripname' class DamnLol(_BasicScraper): url = 'http://www.damnlol.com/' rurl = escape(url) stripUrl = url + '%s.html' prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) imageSearch = ( compile(tagre("img", "src", r'(%si/[^"]+)' % rurl)), compile(tagre("img", "src", r'(%spics/[^"]+)' % rurl)), ) help = 'Index format: stripname-number' description = 'Funny pictures from the internet. Thousands of them.' starter = bounceStarter(url, compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="next"))) @classmethod def namer(cls, imageUrl, pageUrl): ext = imageUrl.rsplit('.', 1)[1] path = pageUrl.rsplit('/', 1)[1][:-5] stripname, number = path.rsplit('-', 1) return '%s-%s.%s' % (number, stripname, ext) class Damonk(_BasicScraper): url = 'http://www.damonk.com/' stripUrl = url + 'd/%s.html' firstStripUrl = stripUrl % '20060522' imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)') + tagre("img", "src", r'/images/previous_day\.gif')) help = 'Index format: yyyymmdd' # XXX disallowed /search by robots.txt class _DandyAndCompany(_BasicScraper): url = 'http://www.dandyandcompany.com/' stripUrl = None multipleImagesPerStrip = True imageSearch = compile(tagre("a", "href", r'(http://\d+\.bp\.blogspot\.com/[^"]+)', after="imageanchor")) prevSearch = compile(tagre("a", "href", r"([^']+)", quote="'", after="Older Posts")) help = 'Index format: none' class DangerouslyChloe(_BasicScraper): url = 'http://www.dangerouslychloe.com/' stripUrl = url + 'strips-dc/%s' firstStripUrl = stripUrl % 'chapter_1_-_that_damned_girl' imageSearch = compile(tagre("img", "src", r'([^"]*/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]*/strips-dc/[^"]+)', before="cn[id]prevt")) help = 'Index format: name' class DarkWings(_BasicScraper): url = 'http://www.flowerlarkstudios.com/dark-wings/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2008/05/31/page-i' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="navi-prev")) help = 'Index format: yyyy/mm/dd/page-nn-mm' class DasLebenIstKeinPonyhof(_BasicScraper): url = 'http://sarahburrini.com/wordpress/' rurl = escape(url) stripUrl = url + 'comic/%s/' firstStripUrl = stripUrl % 'mein-erster-webcomic' imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/\d+-\d+-\d+[^"]+)' % rurl)) multipleImagesPerStrip = True prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl, after="navi-prev")) help = 'Index format: stripname' lang = 'de' class DeadWinter(_BasicScraper): url = 'http://deadwinter.cc/' stripUrl = url + 'page/%s' firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r"(/static/page/strip/\d+[^']+)", quote="'")) prevSearch = compile(tagre("a", "href", r'(/page/\d+)') + "Previous") help = 'Index format: number' class DeathToTheExtremist(_BasicScraper): url = 'http://www.dtecomic.com/' stripUrl = url + '?n=%s' firstStripUrl = stripUrl % '1' imageSearch = compile(r'"(comics/.*?)"') prevSearch = compile(r' <.+?/aprev.gif"') help = 'Index format: nnn' class DeepFried(_BasicScraper): url = 'http://www.whatisdeepfried.com/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2001/09/16/new-world-out-of-order' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: none' class DemolitionSquad(_BasicScraper): url = 'http://www.demolitionsquad.de/' starter = indirectStarter(url, compile(tagre("a", "href", r'(no_cache/comicstrips/einzelansicht/archive/[^"]+)'))) stripUrl = url + 'comicstrips/einzelansicht/article/%s/' firstStripUrl = stripUrl % 'videospiele-hentai-master' imageSearch = compile(tagre("img", "src", r'(uploads/pics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(comicstrips/einzelansicht/article/[^"]+)') + tagre("img", "src", r'fileadmin/templates/images/button_back.gif')) help = 'Index format: stripname' lang = 'de' def prevUrlModifier(self, url): # remove CGI params return url.split('?')[0] class DerTodUndDasMaedchen(_BasicScraper): url = 'http://www.cartoontomb.de/deutsch/tod2.php' stripUrl = url + '?bild=%s.jpg' firstStripUrl = stripUrl % '00_01_01' imageSearch = compile(tagre("img", "src", r"(\.\./images/tod/teil2/[^']+)", quote="'")) prevSearch = compile(tagre("a", "href", r"(/deutsch/tod2\.php\?bild=[^']+)", quote="'") + "zurück") help = 'Index format: nn_nn_nn' lang = 'de' class DieselSweeties(_BasicScraper): url = 'http://www.dieselsweeties.com/' stripUrl = url + 'archive/%s' firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r'(/hstrips/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/archive/\d+)') + tagre("img", "src", r'(?:http://www\.dieselsweeties\.com/ximages/blackbackarrow160.png|/ximages/prev\.gif)')) help = 'Index format: n (unpadded)' @classmethod def namer(cls, imageUrl, pageUrl): index = int(imageUrl.split('/')[-1].split('.')[0]) return 'sw%02d' % (index,) class Dilbert(_BasicScraper): url = 'http://dilbert.com/' stripUrl = url + '%s/' firstStripUrl = stripUrl % '1989-04-16' starter = bounceStarter(url, compile(tagre("a", "href", r'(/\d+-\d+-\d+/)', after="STR_Next"))) prevSearch = compile(tagre("a", "href", r'(/\d+-\d+-\d+/)', after="STR_Prev")) imageSearch = compile(tagre("img", "src", r'(/dyn/str_strip/[^"]+\.strip\.zoom\.gif)')) help = 'Index format: yyyy-mm-dd' description = 'A comic featuring satirical office humor about a white-collar, micromanaged office featuring the engineer Dilbert as the title character.' @classmethod def namer(cls, imageUrl, pageUrl): ext = imageUrl.rsplit(".", 1)[1] name = pageUrl.rsplit("/", 2)[1] return "%s.%s" % (name, ext) class DMFA(_BasicScraper): url = 'http://www.missmab.com/' stripUrl = url + 'Comics/Vol_%s.php' firstStripUrl = stripUrl % '001' imageSearch = compile(tagre("img", "src", r'((?:Comics/|Vol)[^"]+)')) multipleImagesPerStrip = True prevSearch = compile(tagre("a", "href", r'((?:Comics/)?Vol[^"]+)')+ tagre("img", "src", r'(?:../)?Images/comicprev\.gif')) help = 'Index format: nnn (normally, some specials)' class DoemainOfOurOwn(_BasicScraper): url = 'http://www.doemain.com/' stripUrl = url + 'index.cgi/%s' imageSearch = compile(r"Previous Strip« Prev') help = 'Index format: nnn' class DreamKeepersPrelude(_BasicScraper): url = 'http://www.dreamkeeperscomic.com/Prelude.php' stripUrl = url + '?pg=%s' imageSearch = compile(r'(images/PreludeNew/.+?)"') prevSearch = compile(r'(Prelude.php\?pg=.+?)"') help = 'Index format: n' class DresdenCodak(_BasicScraper): url = 'http://dresdencodak.com/' rurl = escape(url) stripUrl = None firstStripUrl = url + '2007/02/08/pom/' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl) + tagre("img", "src", r"%sm_prev2?\.png" % rurl, quote="")) starter = indirectStarter(url, compile(tagre("div", "id", "preview") + tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl))) class DrFun(_BasicScraper): baseurl = 'http://www.ibiblio.org/Dave/' url = baseurl + 'ar00502.htm' stripUrl = baseurl + 'ar%s.htm' firstStripUrl = stripUrl % '00001' imageSearch = compile(tagre("a", "href", r'(Dr-Fun/df\d+/df[^"]+)')) multipleImagesPerStrip = True prevSearch = compile(tagre("a", "href", r'([^"]+)') + 'Previous Week,') help = 'Index format: nnnnn' description = 'A series of bizarre one-panel gags. Topics range from the mundane to the obscure.' class DrMcNinja(_BasicScraper): url = 'http://drmcninja.com/' rurl = escape(url) stripUrl = url + 'archives/comic/%s/' firstStripUrl = stripUrl % '0p1' imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%sarchives/comic/[^"]+)' % rurl, after="prev")) help = 'Index format: episode number and page' class Drowtales(_BasicScraper): baseurl = 'http://www.drowtales.com/' rurl = escape(baseurl) url = baseurl + 'mainarchive.php' stripUrl = url + '?sid=%s' firstStripUrl = stripUrl % '4192' imageSearch = ( compile(tagre("img", "src", r'(%smainarchive/[^"]+)' % rurl)), compile(r'background-image:url\((mainarchive/[^\)]+center\.jpg)'), ) prevSearch = compile(tagre("a", "href", r'(\?sid=\d+)', before="link_prev_top")) help = 'Index format: number' # XXX disallowed by robots.txt class _DumbingOfAge(_BasicScraper): url = 'http://www.dumbingofage.com/' rurl = escape(url) stripUrl = url + '%s/' prevSearch = compile(tagre("a", "href", r'(%s\d+/[^"]+)' % rurl, after="prev")) imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl)) help = 'Index format: yyyy/comic/book-num/seriesname/stripname'