# -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2014 Bastian Kleineidam from re import compile, escape from ..scraper import _BasicScraper from ..helpers import indirectStarter from ..util import tagre class Gaia(_BasicScraper): description = u'Gaia, a story about the nature of reality, and the answer to Lilith?s simple, meek, world-shattering question: ?Will you come along??' url = 'http://www.sandraandwoo.com/gaia/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2000/01/01/welcome-to-gaia/' imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+-[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+/)' % rurl, after="prev")) help = 'Index format: yyyy/mm/dd/number-stripname' class GaiaGerman(_BasicScraper): description = u'Gaia, eine Geschichte über das Wesen der Wirklichkeit und die Antwort auf Liliths einfache, bescheidene, welterschütternde Frage: ?Kommt ihr mit??' url = 'http://www.sandraandwoo.com/gaiade/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2000/01/01/welcome-to-gaia/' imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+-[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+/)' % rurl, after="prev")) help = 'Index format: yyyy/mm/dd/number-stripname' lang = 'de' class Galaxion(_BasicScraper): description = u'Galaxion - Life. Love. Hyperspace.' url = 'http://galaxioncomics.com/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '1-comic/the-story-so-far/the-story-so-far' imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: n-comic/book-n/chapter-n/title-nnn' class Garanos(_BasicScraper): description = u'Garanos - A dramatic fantasy webcomic with a dash of adventure, gothic horror, and romance for flavor.' baseUrl = 'http://garanos.alexheberling.com/' rurl = escape(baseUrl) url = baseUrl + 'pages/page-1/' starter = indirectStarter(url, compile(tagre("a", "href", r'(%spages/[^"]+)' % rurl, after="nav-last"))) stripUrl = baseUrl + 'pages/page-%s' imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/sites/\d+/\d+/\d+/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%spages/[^"]+)' % rurl, after="prev")) help = 'Index format: n (unpadded)' class GastroPhobia(_BasicScraper): description = u'Regularly updated comic about a single mom barbarian in Ancient Greece.' url = 'http://www.gastrophobia.com/' stripUrl = url + 'index.php?date=%s' firstStripUrl = stripUrl % '2008-07-30' imageSearch = compile(r']*>(?!
)') prevSearch = compile(r'« Previous') help = 'Index format: nnn' class GeeksNextDoor(_BasicScraper): description = u'Geeks Next Door' url = 'http://www.geeksnextcomic.com/' stripUrl = url + '%s.html' firstStripUrl = stripUrl % '2010-10-04' imageSearch = compile(tagre("img", "src", r'(images/GND\d+[^"]+)')) prevSearch = compile(tagre("a", "href", r'(\d+-\d+-\d+\.html)') + tagre("img", "src", r'images/nav_prev\.png')) help = 'Index format: yyyy-mm-dd' # 403 error when getting image files, disable for now class _GeneralProtectionFault(_BasicScraper): description = u'General Protection Fault' url = 'http://www.gpf-comics.com/' rurl = escape(url) stripUrl = url + 'archive/%s' firstStripUrl = stripUrl % '1998/11/02' imageSearch = compile(tagre("img", "src", r'(/comics/[^"]*)')) prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl) + tagre("img", "alt", "Previous Comic")) help = 'Index format: yyyy/mm/dd' @classmethod def namer(cls, imageUrl, pageUrl): """Remove random stuff from filename.""" imageName = imageUrl.split('/')[-1] return imageName[:11] + imageName[-4:] class GirlGenius(_BasicScraper): description = u'Adventure, Romance, Mad Science!' baseUrl = 'http://www.girlgeniusonline.com/' rurl = escape(baseUrl) url = baseUrl + 'comic.php' stripUrl = url + '?date=%s' firstStripUrl = stripUrl % '20021104' imageSearch = compile(tagre("img", "src", r"(%sggmain/strips/[^']*)" % rurl, quote="'")) prevSearch = compile(tagre("a", "id", "topprev", quote="\"", before=r"(%s[^\"']+)" % rurl)) multipleImagesPerStrip = True help = 'Index format: yyyymmdd' class GirlsWithSlingshots(_BasicScraper): url = 'http://www.girlswithslingshots.com/' rurl = escape(url) stripUrl = url + 'comic/gws%s/' firstStripUrl = stripUrl % '1' imageSearch = ( compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)), compile(tagre("img", "src", r'(http://cdn\.girlswithslingshots\.com/comics/[^"]+)')), ) prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl, after="prev")) help = 'Index format: nnn' class GlassHalfEmpty(_BasicScraper): description = u'A Glass Half Empty cartoon by Dan Markowitz' url = 'http://www.defectivity.com/ghe/index.php' stripUrl = url + '?strip_id=%s' firstStripUrl = stripUrl % '0' imageSearch = compile(r'src="(comics/.+?)"') prevSearch = compile(tagre("a", "href", r'(\?strip_id=\d+)') + tagre("img", "src", r'\.\./images/arrowbuttons/onback\.jpg')) help = 'Index format: nnn' class GleefulNihilism(_BasicScraper): description = u'pointless comics with a sideways grin' url = 'http://gleefulnihilism.com/' rurl = escape(url) stripUrl = url + 'comic/%s/' firstStripUrl = stripUrl % 'amoeba' imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl) + '‹') help = 'Index format: stripname' class GoblinsComic(_BasicScraper): description = u'Goblins' url = 'http://www.goblinscomic.org/' rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '06252005' prevSearch = compile(tagre("a", "href", r'(%s[-\d]+/)' % rurl, after="prev")) imageSearch = compile(tagre("img", "src", r'(%scomics/\d+\.[^"]+)' % rurl)) help = 'Index format: ddmmyyyy' class GoGetARoomie(_BasicScraper): description = u"Go Get a Roomie!" url = 'http://www.gogetaroomie.com/index.php' stripUrl = url + '?id=%s' firstStripUrl = stripUrl % '1' imageSearch = compile(tagre('img', 'src', r'(comics/[^"]+)')) prevSearch = compile(tagre('a', 'href', r'([^"]+)', after='rel="prev"')) help = 'Index format: nnn' class GoneWithTheBlastwave(_BasicScraper): description = u'Gone with the Blastwave - Type E webcomic.' url = 'http://www.blastwave-comic.com/index.php?p=comic&nro=1' starter = indirectStarter(url, compile(r'href="(index.php\?p=comic&nro=\d+)">