diff --git a/dosagelib/plugins/a.py b/dosagelib/plugins/a.py index 703c40d1b..42733b20e 100644 --- a/dosagelib/plugins/a.py +++ b/dosagelib/plugins/a.py @@ -2,7 +2,7 @@ # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2013 Bastian Kleineidam -from re import compile, MULTILINE +from re import compile, escape, MULTILINE from ..util import tagre from ..scraper import _BasicScraper from ..helpers import regexNamer, bounceStarter, indirectStarter @@ -11,14 +11,17 @@ from ..helpers import regexNamer, bounceStarter, indirectStarter class AbleAndBaker(_BasicScraper): url = 'http://www.jimburgessdesign.com/comics/index.php' stripUrl = url + '?comic=%s' + firstStripUrl = stripUrl % '1' imageSearch = compile(tagre('img', 'src', r'(comics/.+)')) prevSearch = compile(tagre('a', 'href', r'(.+\d+)') + '.+?previous.gif') help = 'Index format: nnn' class AbsurdNotions(_BasicScraper): - url = 'http://www.absurdnotions.org/page129.html' - stripUrl = 'http://www.absurdnotions.org/page%s.html' + baseurl = 'http://www.absurdnotions.org/' + url = baseurl + 'page129.html' + stripUrl = baseurl + 'page%s.html' + firstStripUrl = stripUrl % '1' imageSearch = compile(tagre('img', 'src', r'(an[^"]+)')) multipleImagesPerStrip = True prevSearch = compile(tagre('a', 'href', r'([^"]+)') + tagre('img', 'src', 'nprev\.gif')) @@ -27,11 +30,12 @@ class AbsurdNotions(_BasicScraper): class AbstruseGoose(_BasicScraper): url = 'http://abstrusegoose.com/' - starter = bounceStarter(url, - compile(tagre('a', 'href', r'(http://abstrusegoose\.com/\d+)')+"Next »")) + rurl = escape(url) + starter = bounceStarter(url, compile(tagre('a', 'href', r'(%s\d+)' % rurl)+"Next »")) stripUrl = url + '%s' - imageSearch = compile(tagre('img', 'src', r'(http://abstrusegoose\.com/strips/[^<>"]+)')) - prevSearch = compile(tagre('a', 'href', r'(http://abstrusegoose\.com/\d+)') + r'« Previous') + firstStripUrl = stripUrl % '1' + imageSearch = compile(tagre('img', 'src', r'(%sstrips/[^<>"]+)' % rurl)) + prevSearch = compile(tagre('a', 'href', r'(%s\d+)' % rurl) + r'« Previous') help = 'Index format: n (unpadded)' @classmethod @@ -44,6 +48,7 @@ class AbstruseGoose(_BasicScraper): class AcademyVale(_BasicScraper): url = 'http://www.imagerie.com/vale/' stripUrl = url + 'avarch.cgi?%s' + firstStripUrl = stripUrl % '001' imageSearch = compile(tagre('img', 'src', r'(avale\d{4}-\d{2}\.gif)')) prevSearch = compile(tagre('a', 'href', r'(avarch[^">]+)', quote="") + tagre('img', 'src', 'AVNavBack\.gif')) help = 'Index format: nnn' @@ -52,7 +57,7 @@ class AcademyVale(_BasicScraper): class AhoiPolloi(_BasicScraper): url = 'http://ahoipolloi.blogger.de/' stripUrl = url + '?day=%s' - firstStripUrl = stripUrl % '20060305' + firstStripUrl = stripUrl % '20060306' multipleImagesPerStrip = True lang = 'de' imageSearch = compile(tagre('img', 'src', r'(/static/antville/ahoipolloi/images/[^"]+)')) @@ -69,29 +74,33 @@ class ALessonIsLearned(_BasicScraper): prevSearch = compile(tagre("a", "href", r"(index\.php\?comic=\d+)", quote="'")+r"[^>]+previous") starter = indirectStarter(url, prevSearch) stripUrl = url + 'index.php?comic=%s' + firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r"(cmx/lesson\d+\.[a-z]+)")) help = 'Index format: nnn' class Alice(_BasicScraper): url = 'http://alice.alicecomics.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://alice\.alicecomics\.com/wp-content/uploads/\d+/\d+/\d+-\d+-\d+[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://alice\.alicecomics\.com/alicecomics/[^"]+)', after="previous")) + imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/\d+-\d+-\d+[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%salicecomics/[^"]+)' % rurl, after="previous")) help = 'Index format: name' class AlienLovesPredator(_BasicScraper): url = 'http://alienlovespredator.com/' - stripUrl = url + '%s' + stripUrl = url + '%s/' + firstStripUrl = stripUrl % '2004/10/12/unavoidable-delay' imageSearch = compile(tagre("img", "src", r'([^"]+)', after='border="1" alt="" width="750"')) prevSearch = compile(tagre("a", "href", r'([^"]+)', after="prev")) - help = 'Index format: yyyy/mm/dd/name/' + help = 'Index format: yyyy/mm/dd/name' class AlphaLuna(_BasicScraper): url = 'http://www.alphaluna.net/' stripUrl = url + 'issue-%s/' + firstStripUrl = stripUrl % '1/cover' imageSearch = compile(tagre("a", "href", r'[^"]*/(?:issue-|support/upcoming)[^"]+') + tagre("img", "src", r'([^"]*/PAGINAS/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)') + tagre("img", "alt", "Prev")) help = 'Index format: issue/page (e.g. 4/05)' @@ -102,11 +111,13 @@ class AlphaLunaSpanish(AlphaLuna): lang = 'es' url = 'http://alphaluna.net/spanish/' stripUrl = url + 'issue-%s/' + firstStripUrl = stripUrl % '1/portada' class Altermeta(_BasicScraper): url = 'http://altermeta.net/' stripUrl = url + 'archive.php?comic=%s' + firstStripUrl = stripUrl % '0' imageSearch = compile(r'') prevSearch = compile(r'Back') class AmazingSuperPowers(_BasicScraper): url = 'http://www.amazingsuperpowers.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.amazingsuperpowers\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.amazingsuperpowers\.com/[^"]+)', after="prev")) + firstStripUrl = stripUrl % '2007/09/heredity' + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/mm/name' @@ -136,15 +150,18 @@ class Angels2200(_BasicScraper): class Antics(_BasicScraper): url = 'http://www.anticscomic.com/' + rurl = escape(url) stripUrl = url + '?p=%s' - imageSearch = compile(tagre("img", "src", r'(http://www\.anticscomic\.com/comics/\d+-\d+-\d+[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.anticscomic\.com/\?p=\d+)', after='prev')) + firstStripUrl = stripUrl % '3' + imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after='prev')) help = 'Index format: number' class AppleGeeks(_BasicScraper): url = 'http://www.applegeeks.com/' stripUrl = url + 'comics/viewcomic.php?issue=%s' + firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r'((?:/comics/)?issue\d+\.jpg)')) prevSearch = compile(r'
Previous Comic
\s*

', MULTILINE) help = 'Index format: n (unpadded)' @@ -153,6 +170,7 @@ class AppleGeeks(_BasicScraper): class Achewood(_BasicScraper): url = 'http://www.achewood.com/' stripUrl = url + 'index.php?date=%s' + firstStripUrl = stripUrl % '00000000' imageSearch = compile(tagre("img", "src", r'(/comic\.php\?date=\d+)')) prevSearch = compile(tagre("a", "href", r'(index\.php\?date=\d+)', after="Previous")) help = 'Index format: mmddyyyy' @@ -162,6 +180,7 @@ class Achewood(_BasicScraper): class ASofterWorld(_BasicScraper): url = 'http://www.asofterworld.com/' stripUrl = url + 'index.php?id=%s' + firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("p", "id", "thecomic") + r'\s*' + tagre("img", "src", r'(http://www\.asofterworld\.com/clean/[^"]+)')) prevSearch = compile(tagre("a", "href", "(index\.php\?id=\d+)")+'< back') @@ -169,10 +188,12 @@ class ASofterWorld(_BasicScraper): class AstronomyPOTD(_BasicScraper): - url = 'http://antwrp.gsfc.nasa.gov/apod/astropix.html' + baseurl = 'http://antwrp.gsfc.nasa.gov/apod/' + url = baseurl + 'astropix.html' starter = bounceStarter(url, compile(tagre("a", "href", r'(ap\d{6}\.html)') + ">")) - stripUrl = 'http://antwrp.gsfc.nasa.gov/apod/ap%s.html' + stripUrl = baseurl + 'ap%s.html' + firstStripUrl = stripUrl % '061012' imageSearch = compile(tagre("a", "href", r'(image/\d{4}/[^"]+)')) multipleImagesPerStrip = True prevSearch = compile(tagre("a", "href", r'(ap\d{6}\.html)') + "<") @@ -202,7 +223,8 @@ class AfterStrife(_BasicScraper): class ALLCAPS(_BasicScraper): url = 'http://www.allcapscomix.com/' - stripUrl = url + '%s' + stripUrl = url + '%s/' + firstStripUrl = stripUrl % '2008/08/welcome-to-all-caps' imageSearch = compile(tagre("img", "src", r'(http://www\.allcapscomix\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)')+r"[^<]+Previous") help = 'Index format: yyyy/mm/strip-name' @@ -211,6 +233,7 @@ class ALLCAPS(_BasicScraper): class ASkeweredParadise(_BasicScraper): url = 'http://aspcomics.net/' stripUrl = url + 'comic/%s' + firstStripUrl = stripUrl % '001' imageSearch = compile(tagre("img", "src", r'(http://aspcomics\.net/sites/default/files[^"]*/asp\d+\.jpg)[^"]+')) prevSearch = compile(tagre("a", "href", "(/comic/\d+)")+r"[^>]+Previous") help = 'Index format: nnn' @@ -221,6 +244,7 @@ class AGirlAndHerFed(_BasicScraper): starter = bounceStarter(url, compile(r'[^>]+Back')) stripUrl = url + '1.%s.html' + firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r'(img/strip/[^"]+\.jpg)')) prevSearch = compile(r'[^>]+Back') help = 'Index format: nnn' @@ -229,6 +253,7 @@ class AGirlAndHerFed(_BasicScraper): class AetheriaEpics(_BasicScraper): url = 'http://aetheria-epics.schala.net/' stripUrl = url + '%s.html' + firstStripUrl = stripUrl % '00001' imageSearch = compile(tagre("img", "src", r'(\d{5}\.jpg)')) prevSearch = compile(tagre("a", "href", r'(\d{5}\.html)') + "Previous") help = 'Index format: nnn' @@ -236,10 +261,11 @@ class AetheriaEpics(_BasicScraper): class AirForceBlues(_BasicScraper): url = 'http://www.afblues.com/' - stripUrl = url + 'wordpress/%s' + stripUrl = url + 'wordpress/%s/' + firstStripUrl = stripUrl % '1997/09/07/need-a-clue-do-ya' imageSearch = compile(tagre("img", "src", r'(http://www\.afblues\.com/wordpress/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)', after='Previous')) - help = 'Index format: yyyy/mm/dd/name/' + help = 'Index format: yyyy/mm/dd/stripname' class AlienShores(_BasicScraper): @@ -252,23 +278,27 @@ class AlienShores(_BasicScraper): class AllTheGrowingThings(_BasicScraper): url = 'http://growingthings.typodmary.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://growingthings\.typodmary\.com/files/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://growingthings\.typodmary\.com/[^"]+)', after="prev")) + firstStripUrl = stripUrl % '2009/04/21/all-the-growing-things' + imageSearch = compile(tagre("img", "src", r'(%sfiles/comics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/mm/dd/strip-name' class Amya(_BasicScraper): url = 'http://www.amyachronicles.com/' + rurl = escape(url) stripUrl = url + 'archives/%s' - imageSearch = compile(tagre("img", "src", r'(http://www\.amyachronicles\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.amyachronicles\.com/archives/\d+)', after="Previous")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%sarchives/\d+)' % rurl, after="Previous")) help = 'Index format: n' class Angband(_BasicScraper): url = 'http://angband.calamarain.net/' stripUrl = url + 'view.php?date=%s' + firstStripUrl = stripUrl % '2005-12-30' imageSearch = compile(tagre("img", "src", r'(comics/Scroll[^"]+)')) prevSearch = compile(tagre("a", "href", r'(view\.php\?date\=[^"]+)')+"Previous") help = 'Index format: yyyy-mm-dd' @@ -276,9 +306,10 @@ class Angband(_BasicScraper): class AlsoBagels(_BasicScraper): url = 'http://alsobagels.com/' + rurl = escape(url) stripUrl = url + 'index.php/comic/%s/' - imageSearch = compile(tagre("img", "src", r'(http://alsobagels\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://alsobagels\.com/index\.php/comic/[^"]+)', after="Previous")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%sindex\.php/comic/[^"]+)' % rurl, after="Previous")) help = 'Index format: strip-name' @@ -292,10 +323,12 @@ class Annyseed(_BasicScraper): class AxeCop(_BasicScraper): url = 'http://axecop.com/' - starter = indirectStarter(url, compile(tagre("a", "href", r'(http://axecop\.com/index\.php/acepisodes/read/episode_\d+/)'))) + rurl = escape(url) + starter = indirectStarter(url, + compile(tagre("a", "href", r'(%sindex\.php/acepisodes/read/episode_\d+/)' % rurl))) stripUrl = url + 'index.php/acepisodes/read/%s/' firstStripUrl = stripUrl % 'episode_0' - imageSearch = compile(tagre("img", "src", r'(http://axecop\.com/images/uploads/(?:axecop|AXE-COP|acmarried|nightmonster)[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://axecop\.com/index\.php/acepisodes/read/[^"]+)') + + imageSearch = compile(tagre("img", "src", r'(%simages/uploads/(?:axecop|AXE-COP|acmarried|nightmonster)[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%sindex\.php/acepisodes/read/[^"]+)' % rurl) + tagre("img", "src", r'http://axecop\.com/acimages/buttons/page_left\.png')) help = 'Index format: stripname' diff --git a/dosagelib/plugins/b.py b/dosagelib/plugins/b.py index dd75c4b55..6093e18de 100644 --- a/dosagelib/plugins/b.py +++ b/dosagelib/plugins/b.py @@ -2,7 +2,7 @@ # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2013 Bastian Kleineidam -from re import compile +from re import compile, escape from ..util import tagre from ..scraper import _BasicScraper @@ -20,6 +20,7 @@ class BackwaterPlanet(_BasicScraper): class BadassMuthas(_BasicScraper): url = 'http://badassmuthas.com/pages/comic.php' stripUrl = url + '?%s' + firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r'(/images/comicsissue[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)') + tagre("img", "src", r'/images/comicsbuttonBack\.gif')) help = 'Index format: nnn' @@ -28,6 +29,7 @@ class BadassMuthas(_BasicScraper): class BadMachinery(_BasicScraper): url = 'http://scarygoround.com/' stripUrl = url + '?date=%s' + firstStripUrl = stripUrl % '20090918' imageSearch = compile(tagre("img", "src", r'(strips/\d+[^"]+)')) prevSearch = compile(tagre("a", "href", r'(\?date=\d+)') + 'Previous') help = 'Index format: yyyymmdd' @@ -35,32 +37,38 @@ class BadMachinery(_BasicScraper): class Bardsworth(_BasicScraper): url = 'http://www.bardsworth.com/' + rurl = escape(url) stripUrl = url + '?p=%s' - imageSearch = compile(tagre("img", "src", r'(http://www\.bardsworth\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.bardsworth\.com/[^"]+)', after="prev")) + firstStripUrl = stripUrl % '750' + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: nnn' class Baroquen(_BasicScraper): url = 'http://www.baroquencomics.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.baroquencomics\.com/Comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.baroquencomics\.com/[^"]+)', after='prev')) + firstStripUrl = stripUrl % '2008/11/05/raise-the-curtains' + imageSearch = compile(tagre("img", "src", r'(%sComics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after='prev')) help = 'Index format: yyyy/mm/dd/strip-name' class Bearmageddon(_BasicScraper): url = 'http://bearmageddon.com/' + rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2011/08/01/page-1' - imageSearch = compile(tagre("img", "src", r'(http://bearmageddon\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://bearmageddon\.com/\d+/\d+/\d+/[^"]+)', after='navi-prev')) + 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 BetterDays(_BasicScraper): url = 'http://jaynaylor.com/betterdays/' stripUrl = url + 'archives/%s.html' + firstStripUrl = stripUrl % '2003/04/post-2' imageSearch = compile(tagre("img", "src", r'(/betterdays/comic/[^>]+)', quote="")) prevSearch = compile(tagre("a", "href", r'([^"]+)') + '« Previous') help = 'Index format: yyyy/mm/' @@ -68,9 +76,10 @@ class BetterDays(_BasicScraper): class BetweenFailures(_BasicScraper): url = 'http://betweenfailures.com/' + rurl = escape(url) stripUrl = url + 'archives/archive/%s' - imageSearch = compile(tagre("img", "src", r'(http://betweenfailures\.com/wp-content/webcomic/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://betweenfailures\.com/archives/archive/[^"]+)', after="previous")) + imageSearch = compile(tagre("img", "src", r'(%swp-content/webcomic/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%sarchives/archive/[^"]+)' % rurl, after="previous")) help = 'Index format: stripnum-strip-name' @@ -85,6 +94,7 @@ class BigFatWhale(_BasicScraper): class BiggerThanCheeses(_BasicScraper): url = 'http://www.biggercheese.com/' stripUrl = url + 'index.php?comic=%s' + firstStripUrl = stripUrl % '1' imageSearch = compile(r'src="(comics/.+?)" alt') prevSearch = compile(r'"(index.php\?comic=.+?)".+?_back') help = 'Index format: n (unpadded)' @@ -92,15 +102,18 @@ class BiggerThanCheeses(_BasicScraper): class BillyTheDunce(_BasicScraper): url = 'http://www.duncepress.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.duncepress\.com/comics/[^"]+)')) - prevSearch = compile(r'

]+Previous') @@ -255,6 +282,7 @@ class BoxerHockey(_BasicScraper): class BoyOnAStickAndSlither(_BasicScraper): url = 'http://www.boasas.com/' stripUrl = url + 'page/%s' + firstStripUrl = stripUrl % '2' imageSearch = compile(tagre("img", "src", r'(http://\d+\.media\.tumblr\.com/[^"]+_1280\.png)')) prevSearch = compile(tagre("a", "href", r'(/page/\d+)') + "Next page") help = 'Index format: n (unpadded)' @@ -268,6 +296,7 @@ class BrightlyWound(_BasicScraper): baseUrl = 'http://www.brightlywound.com/' url = baseUrl + '?comic=137' stripUrl = baseUrl + '?comic=%s' + fristStripUrl = stripUrl % '0' imageSearch = compile(tagre("img", "src", r"(comic/[^']+)", quote="'")) prevSearch = compile(r'
" + tagre("a", "href", r'(http://catalyst\.spiderforest\.com/comic\.php\?comic_id=\d+)')) + firstStripUrl = stripUrl % '1' + imageSearch = compile(tagre("img", "src", r'((?:%s)?comics/[^"]+)' % rurl)) + prevSearch = compile("
" + tagre("a", "href", r'(%scomic\.php\?comic_id=\d+)' % rurl)) help = 'Index format: number' @@ -54,17 +60,19 @@ class Catena(_BasicScraper): class ChainsawSuit(_BasicScraper): url = 'http://chainsawsuit.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://chainsawsuit\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://chainsawsuit\.com/\d+/\d+/\d+/[^"]+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/mm/dd/stripname' class ChannelAte(_BasicScraper): url = 'http://www.channelate.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.channelate\.com/comics/\d+-\d+-\d+[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.channelate\.com/\d+/\d+/\d+/[^"]+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)', after="prev")) help = 'Index format: yyyy/mm/dd/name' @@ -126,25 +134,28 @@ class Comedity(_BasicScraper): class Commissioned(_BasicScraper): url = 'http://www.commissionedcomic.com/' + rurl = escape(url) stripUrl = url + '?p=%s' - imageSearch = compile(tagre("img", "src", r'(http://www\.commissionedcomic\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.commissionedcomic\.com/\?p=\d+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev")) help = 'Index format: n' class Concession(_BasicScraper): url = 'http://concessioncomic.com/' + rurl = escape(url) stripUrl = url + 'index.php?pid=%s' - imageSearch = compile(tagre("img", "src", r'(http://concessioncomic\.com/comics/[^"]+)', after="Comic")) - prevSearch = compile(tagre("a", "href", r'(http://concessioncomic\.com/index\.php\?pid=\d+)', after="nav-prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl, after="Comic")) + prevSearch = compile(tagre("a", "href", r'(%sindex\.php\?pid=\d+)' % rurl, after="nav-prev")) help = 'Index format: number' class CoolCatStudio(_BasicScraper): url = 'http://www.coolcatstudio.com/' + rurl = escape(url) stripUrl = url + 'strips-cat/ccs%s' - imageSearch = compile(tagre("img", "src", r'(http://www\.coolcatstudio\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.coolcatstudio\.com/strips-cat/[^"]+)', before="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%sstrips-cat/[^"]+)' % rurl, before="prev")) help = 'Index format: yyyymmdd' @@ -233,23 +244,27 @@ class CrimsonDark(_BasicScraper): class CatsAndCameras(_BasicScraper): url = 'http://catsncameras.com/cnc/' + rurl = escape(url) stripUrl = url + '?p=%s' - imageSearch = compile(r'') + imageSearch = compile(tagre("img", "src", r'(%scnc/comics/[^"]+)' % rurl)) + prevSearch = compile(tagre("div", "class", r'nav-previous') + + tagre("a", "href", r'(%scnc/[^"]+)' % rurl)) help = 'Index format: nnn' class CowboyJedi(_BasicScraper): url = 'http://www.cowboyjedi.com/' + rurl = escape(url) stripUrl = url + '%s' - imageSearch = compile(tagre("img", "src", r'(http://www\.cowboyjedi.\com/comics/[^"]+)')) - prevSearch = compile(r'') multipleImagesPerStrip = True prevSearch = compile(r'Previous Week,') @@ -217,18 +223,21 @@ class DreamKeepersPrelude(_BasicScraper): class DresdenCodak(_BasicScraper): url = 'http://dresdencodak.com/' + rurl = escape(url) stripUrl = None - imageSearch = compile(r'') - starter = indirectStarter('http://dresdencodak.com/', compile(r'
')) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl) + tagre("img", "src", r"%sm_prev\.png" % rurl)) + starter = indirectStarter(url, compile(tagre("div", "id", "preview") + + tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl))) class DrMcNinja(_BasicScraper): url = 'http://drmcninja.com/' + rurl = escape(url) stripUrl = url + 'archives/comic/%s/' firstStripUrl = stripUrl % '0p1' - imageSearch = compile(tagre("img", "src", r'(http://drmcninja\.com/comics/\d+-\d+-\d+[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://drmcninja\.com/archives/comic/[^"]+)', after="prev")) + 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' @@ -243,7 +252,8 @@ class Drowtales(_BasicScraper): # 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'(http://www\.dumbingofage\.com/\d+/[^"]+)', after="prev")) - imageSearch = compile(tagre("img", "src", r'(http://www\.dumbingofage\.com/comics/\d+-\d+-\d+[^"]+)')) + 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' diff --git a/dosagelib/plugins/e.py b/dosagelib/plugins/e.py index 9093bf0b1..273a028ed 100644 --- a/dosagelib/plugins/e.py +++ b/dosagelib/plugins/e.py @@ -2,7 +2,7 @@ # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2013 Bastian Kleineidam -from re import compile, IGNORECASE +from re import compile, escape, IGNORECASE from ..helpers import indirectStarter from ..scraper import _BasicScraper @@ -76,9 +76,10 @@ class ElGoonishShiveNP(_BasicScraper): class Ellerbisms(_BasicScraper): url = 'http://www.ellerbisms.com/' + rurl = escape(url) stripUrl = url + '?p=%s' - imageSearch = compile(tagre("img", "src", r'(http://www\.ellerbisms\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.ellerbisms\.com/[^"]+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: nnn' @@ -132,17 +133,19 @@ class EvilInc(_BasicScraper): class Exiern(_BasicScraper): url = 'http://www.exiern.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.exiern\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.exiern\.com/[^"]+)', after="prev")) + 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(_BasicScraper): url = 'http://www.exploitationnow.com/' + rurl = escape(url) stripUrl = url + '%s' - imageSearch = compile(tagre("img", "src", r'(http://www\.exploitationnow\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.exploitationnow\.com/[^"]+)', after="navi-prev")) + 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/num' @@ -156,16 +159,18 @@ class ExtraLife(_BasicScraper): class ExtraOrdinary(_BasicScraper): url = 'http://exocomics.com/' + rurl = escape(url) stripUrl = url + '%s' firstStripUrl = stripUrl % '01' - prevSearch = compile(tagre("a", "href", r'(http://www\.exocomics\.com/\d+)', before="prev")) - imageSearch = compile(tagre("img", "src", r'(http://www\.exocomics\.com/comics/comics/\d+\.[^"]+)')) + 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'(http://theeye\.katbox\.net/wp-content/uploads/[^"]+)', after="data-webcomic-parent")) - prevSearch = compile(tagre("a", "href", r'(http://theeye\.katbox\.net/comic/[^"]+)', after="previous")) + 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' diff --git a/dosagelib/plugins/f.py b/dosagelib/plugins/f.py index d8840f492..f6a981e4b 100644 --- a/dosagelib/plugins/f.py +++ b/dosagelib/plugins/f.py @@ -2,7 +2,7 @@ # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2013 Bastian Kleineidam -from re import compile, IGNORECASE, MULTILINE +from re import compile, escape, IGNORECASE, MULTILINE from ..util import tagre from ..scraper import _BasicScraper @@ -18,13 +18,14 @@ class FalconTwin(_BasicScraper): class Fallen(_BasicScraper): - url = 'http://www.fallencomic.com/fal-page.htm' - stripUrl = 'http://www.fallencomic.com/pages/part%s/%s-p%s.htm' + baseurl = 'http://www.fallencomic.com/' + url = baseurl + 'fal-page.htm' + stripUrl = baseurl + 'pages/part%s/%s-p%s.htm' imageSearch = compile(r'Back', IGNORECASE) help = 'Index format: nn-m (comicNumber-partNumber)' starter = indirectStarter(url, - compile(r'\(NEW \d{2}/\d{2}/\d{2}\)\s*\n*\s*\d+', MULTILINE)) + compile(r'\(NEW \d{2}/\d{2}/\d{2}\)\s*\n*\s*\d+', MULTILINE)) @classmethod def namer(cls, imageUrl, pageUrl): @@ -44,7 +45,7 @@ class FantasyRealms(_BasicScraper): prevSearch = compile(r'') help = 'Index format: nnn' class NekoTheKitty(_BasicScraper): url = 'http://www.nekothekitty.net/' + rurl = escape(url) stripUrl = url + 'comics/%s' - starter = bounceStarter(url, compile(tagre("a", "href", r'(http://www\.nekothekitty\.net/comics/[^"]+)') + - tagre("img", "src", r'http://www\.nekothekitty\.net/files/smallnext.png'))) + starter = bounceStarter(url, compile(tagre("a", "href", r'(%scomics/[^"]+)' % rurl) + + tagre("img", "src", r'%sfiles/smallnext\.png' % rurl))) imageSearch = compile(tagre("img", "src", r'(http://(?:img\d+|www)\.smackjeeves\.com/images/uploaded/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.nekothekitty\.net/comics/[^"]+)') + - tagre("img", "src", r'http://www\.nekothekitty\.net/files/smallprev.png')) + prevSearch = compile(tagre("a", "href", r'(%scomics/[^"]+)' % rurl) + + tagre("img", "src", r'%sfiles/smallprev\.png' % rurl)) help = 'Index format: n/n-name' @@ -100,35 +104,40 @@ class NichtLustig(_BasicScraper): class Nnewts(_BasicScraper): url = 'http://nnewts.com/' + rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % 'nnewts-page-1' - imageSearch = compile(tagre("img", "src", r'(http://nnewts\.com/newty/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://nnewts\.com/(?:nnewts-)?page-\d+/)', after="navi-prev")) + imageSearch = compile(tagre("img", "src", r'(%snewty/comics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s(?:nnewts-)?page-\d+/)' % rurl, after="navi-prev")) help = 'Index format: page-number' class Nodwick(_BasicScraper): url = 'http://comic.nodwick.com/' + rurl = escape(url) stripUrl = url + "?p=%s" - imageSearch = compile(tagre("img", "src", r'(http://comic\.nodwick\.com/nodwickstrips/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://comic\.nodwick\.com/\?p=\d+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%snodwickstrips/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev")) help = 'Index format: stripnumber' class NobodyScores(_BasicScraper): url = 'http://nobodyscores.loosenutstudio.com/' + rurl = escape(url) stripUrl = url + 'index.php?id=%s' - imageSearch = compile(tagre("img", "src", r'(http://nobodyscores\.loosenutstudio\.com/comix/[^"]+)')) + imageSearch = compile(tagre("img", "src", r'(%scomix/[^"]+)' % rurl)) multipleImagesPerStrip = True - prevSearch = compile(r'the one before ') + prevSearch = compile(r'the one before ' % rurl) help = 'Index format: nnn' class NoNeedForBushido(_BasicScraper): - url = 'http://noneedforbushido.com/latest/' - stripUrl = 'http://noneedforbushido.com/%s/' - imageSearch = compile(tagre("img", "src", r'(http://noneedforbushido\.com/comics/comic/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://noneedforbushido\.com/[^"]+)', after="previous-comic-link")) + baseurl = 'http://noneedforbushido.com/' + rurl = escape(baseurl) + url = baseurl + 'latest/' + stripUrl = baseurl + '%s/' + imageSearch = compile(tagre("img", "src", r'(%scomics/comic/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="previous-comic-link")) help = 'Index format: yyyy/comic/nnn' diff --git a/dosagelib/plugins/num.py b/dosagelib/plugins/num.py index 0e6cb7880..97c3201c3 100644 --- a/dosagelib/plugins/num.py +++ b/dosagelib/plugins/num.py @@ -11,7 +11,8 @@ from ..scraper import _BasicScraper class NineteenNinetySeven(_BasicScraper): name = '1997' url = 'http://www.1977thecomic.com/' - stripUrl = url + '%s' + stripUrl = url + '%s/' + firstStripUrl = stripUrl % '1977-comics/from-the-beginning-part-1' imageSearch = compile(tagre("img", "src", r'(http://www\.1977thecomic\.com/comics-1977/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)')+"Previous") help = 'Index format: yyyy/mm/dd/strip-name' diff --git a/dosagelib/plugins/o.py b/dosagelib/plugins/o.py index 299f0b0da..1db13cc93 100644 --- a/dosagelib/plugins/o.py +++ b/dosagelib/plugins/o.py @@ -2,7 +2,7 @@ # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2013 Bastian Kleineidam -from re import compile +from re import compile, escape from ..scraper import _BasicScraper from ..helpers import indirectStarter from ..util import tagre, urlopen @@ -10,20 +10,22 @@ from ..util import tagre, urlopen class OctopusPie(_BasicScraper): url = 'http://www.octopuspie.com/' + rurl = escape(url) starter = indirectStarter(url, - compile(tagre("a", "href", r'(http://www\.octopuspie\.com/[^"]+)') + - tagre("img", "src", r'http://www\.octopuspie\.com/junk/latest\.png'))) + compile(tagre("a", "href", r'(%s[^"]+)' % rurl) + + tagre("img", "src", r'%sjunk/latest\.png' % rurl))) stripUrl = url + '%s' - imageSearch = compile(tagre("img", "src", r'(http://www\.octopuspie\.com/strippy/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.octopuspie\.com/[^"]+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%sstrippy/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy-mm-dd/nnn-strip-name' class OddFish(_BasicScraper): url = 'http://www.odd-fish.net/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.odd-fish\.net/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.odd-fish\.net/[^"]+)', after="navi-prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="navi-prev")) help = 'Index format: stripname' @@ -45,27 +47,30 @@ class Oglaf(_BasicScraper): class OkCancel(_BasicScraper): url = 'http://okcancel.com/' + rurl = escape(url) stripUrl = url + 'comic/%s.html' - imageSearch = compile(tagre("img", "src", r'(http://okcancel\.com/strips/okcancel\d{8}\.gif)')) - prevSearch = compile(tagre("div", "class", "previous") + tagre("a", "href", r'(http://okcancel\.com/comic/\d{1,4}\.html)')) + imageSearch = compile(tagre("img", "src", r'(%sstrips/okcancel\d{8}\.gif)' % rurl)) + prevSearch = compile(tagre("div", "class", "previous") + tagre("a", "href", r'(%scomic/\d{1,4}\.html)' % rurl)) starter = indirectStarter(url, prevSearch) help = 'Index format: yyyymmdd' class OmakeTheater(_BasicScraper): url = 'http://omaketheater.com/' + rurl = escape(url) stripUrl = url + 'comic/%s' imageSearch = compile(tagre("img", "src", r'(http://media\.omaketheater\.com/4koma/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://omaketheater\.com/comic/\d+/)', after="prev")) + prevSearch = compile(tagre("a", "href", r'(%scomic/\d+/)' % rurl, after="prev")) starter = indirectStarter(url, - compile(tagre("a", "href", r'(http://omaketheater\.com/comic/\d+/)'))) + compile(tagre("a", "href", r'(%scomic/\d+/)' % rurl))) help = 'Index format: number (unpadded)' class OnTheEdge(_BasicScraper): url = 'http://ontheedgecomics.com/' - stripUrl = 'http://ontheedgecomics.com/comic/%s' - imageSearch = compile(r'') help = 'Index format: nnn (unpadded)' @@ -80,10 +85,11 @@ class OneQuestion(_BasicScraper): class OrnerBoy(_BasicScraper): url = 'http://www.orneryboy.com/' + rurl = escape(url) stripUrl = url + 'index.php?comicID=%s' firstStripUrl = stripUrl % '1' imageSearch = compile(tagre("img", "src", r'(comics/\d+\.[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.orneryboy\.com/index\.php\?comicID=\d+)') + + prevSearch = compile(tagre("a", "href", r'(%sindex\.php\?comicID=\d+)' % rurl) + tagre("img", "src", r'images/prev_a\.gif')) help = 'Index format: number' diff --git a/dosagelib/plugins/p.py b/dosagelib/plugins/p.py index 37bdaa560..79688a101 100644 --- a/dosagelib/plugins/p.py +++ b/dosagelib/plugins/p.py @@ -2,7 +2,7 @@ # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2013 Bastian Kleineidam -from re import compile +from re import compile, escape from ..scraper import _BasicScraper from ..helpers import bounceStarter, queryNamer, indirectStarter from ..util import tagre @@ -10,9 +10,10 @@ from ..util import tagre class PandyLand(_BasicScraper): url = 'http://pandyland.net/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://pandyland\.net/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://pandyland\.net/\d+/)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s\d+/)' % rurl, after="prev")) help = 'Index format: number' @@ -27,10 +28,11 @@ class ParadigmShift(_BasicScraper): class ParallelUniversum(_BasicScraper): url = 'http://www.paralleluniversum.net/' + rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '001-der-comic-ist-tot' - imageSearch = compile(tagre("img", "src", r'(http://www\.paralleluniversum\.net/comics/\d+-\d+-\d+[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.paralleluniversum\.net/[^"]+/)') + + imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+/)' % rurl) + tagre("span", "class", "prev")) help = 'Index format: number-stripname' lang = 'de' @@ -38,15 +40,17 @@ class ParallelUniversum(_BasicScraper): class PartiallyClips(_BasicScraper): url = 'http://partiallyclips.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://partiallyclips\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://partiallyclips\.com/[^"]+)', after="prev")) + 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 PastelDefender(_BasicScraper): - url = 'http://www.pasteldefender.com/coverbackcover.html' - stripUrl = 'http://www.pasteldefender.com/%s.html' + baseurl = 'http://www.pasteldefender.com/' + url = baseurl + 'coverbackcover.html' + stripUrl = baseurl + '%s.html' imageSearch = compile(r'next')) - stripUrl = 'http://www.redmeat.com/redmeat/%s/index.html' + stripUrl = baseurl + '%s/index.html' imageSearch = compile(r']*>') prevSearch = compile(r'previous') help = 'Index format: yyyy-mm-dd' diff --git a/dosagelib/plugins/s.py b/dosagelib/plugins/s.py index c127a7f96..a767e6d3f 100644 --- a/dosagelib/plugins/s.py +++ b/dosagelib/plugins/s.py @@ -2,7 +2,7 @@ # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2013 Bastian Kleineidam -from re import compile, MULTILINE, IGNORECASE, sub +from re import compile, escape, MULTILINE, IGNORECASE, sub from os.path import splitext from ..scraper import _BasicScraper from ..helpers import indirectStarter, bounceStarter @@ -11,9 +11,11 @@ from ..util import tagre class SailorsunOrg(_BasicScraper): url = 'http://sailorsun.org/' + rurl = escape(url) stripUrl = url + '?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")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + rurl = escape(url) + prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev")) help = 'Index format: n (unpadded)' @@ -27,19 +29,21 @@ class SamAndFuzzy(_BasicScraper): class SandraAndWoo(_BasicScraper): url = 'http://www.sandraandwoo.com/' + rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2000/01/01/welcome-to-sandra-and-woo' - imageSearch = compile(tagre("img", "src", r'(http://www\.sandraandwoo\.com/comics/\d+-\d+-\d+-[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.sandraandwoo\.com/\d+/\d+/\d+/[^"]+/)', after="prev")) + 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 SandraAndWooGerman(_BasicScraper): url = 'http://www.sandraandwoo.com/woode/' + rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2008/10/19/ein-ausgefuchster-waschbar' - imageSearch = compile(tagre("img", "src", r'(http://www\.sandraandwoo\.com/woode/comics/\d+-\d+-\d+-[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.sandraandwoo\.com/woode/\d+/\d+/\d+/[^"]+/)', after="prev")) + 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' @@ -54,9 +58,10 @@ class ScaryGoRound(_BasicScraper): class ScenesFromAMultiverse(_BasicScraper): url = 'http://amultiverse.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://amultiverse\.com/files/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://amultiverse\.com/\d+\d+/\d+/\d+/[^"]+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%sfiles/comics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s\d+\d+/\d+/\d+/[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/mm/dd/stripname' @@ -79,9 +84,10 @@ class SchoolBites(_BasicScraper): class Schuelert(_BasicScraper): url = 'http://www.schuelert.de/' + rurl = escape(url) stripUrl = None - imageSearch = compile(tagre("img", "src", r"(http://www.schuelert.de/wp-content/[^']+)", quote="'")) - prevSearch = compile(tagre("a", "href", r'(http://www\.schuelert\.de/index\.php\?paged=\d+)') + "«") + imageSearch = compile(tagre("img", "src", r"(%swp-content/[^']+)" % rurl, quote="'")) + prevSearch = compile(tagre("a", "href", r'(%sindex\.php\?paged=\d+)' % rurl) + "«") multipleImagesPerStrip = True help = 'Index format: none' lang = 'de' @@ -89,10 +95,11 @@ class Schuelert(_BasicScraper): class Science(_BasicScraper): url = 'http://sci-ence.org/' + rurl = escape(url) stripUrl = url + '%s/' firstStripUrl = stripUrl % 'periodic-table-element-ass' - prevSearch = compile(tagre("a", "href", r'(http://sci-ence\.org/[^"]+/)', after="prev")) - imageSearch = compile(tagre("img", "src", r'(http://sci-ence\.org/comics/\d+-\d+-\d+[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+/)' % rurl, after="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl)) help = 'Index format: stripname' description = u'A comic about science, technology, skepticism, geekery, video games, atheism, and more.' @@ -142,18 +149,20 @@ class Sheldon(_BasicScraper): class Shivae(_BasicScraper): url = 'http://shivae.net/' + rurl = escape(url) stripUrl = url + 'blog/%s/' - imageSearch = compile(tagre("img", "src", r'(http://shivae\.net/files/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://shivae\.net/blog/[^"]+)', after="Previous")) + imageSearch = compile(tagre("img", "src", r'(%sfiles/comics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%sblog/[^"]+)' % rurl, after="Previous")) help = 'Index format: yyyy/mm/dd/stripname' # XXX disallowed by robots.txt class _Shortpacked(_BasicScraper): url = 'http://www.shortpacked.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.shortpacked\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.shortpacked\.com/\d+/comic/[^"]+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s\d+/comic/[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/comic/book-nn/mm-name1/name2' @@ -189,9 +198,10 @@ class SkinDeep(_BasicScraper): class SlightlyDamned(_BasicScraper): url = 'http://www.sdamned.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.sdamned\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.sdamned\.com/[^"]+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/mm/number' @@ -251,14 +261,15 @@ class SnowFlakes(_BasicScraper): 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'(http://www\.snowflamecomic\.com/wp-content/uploads/\d+/\d+/[^"]+)', after="Snow[Ff]lame the fan made")) + imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/[^"]+)' % rurl, after="Snow[Ff]lame the fan made")) prevSearch = compile(tagre("span", "class", "mininav-prev") + - tagre("a", "href", r'(http://www\.snowflamecomic\.com/\?comic=snowflame[^"]+)')) + tagre("a", "href", r'(%s\?comic=snowflame[^"]+)' % rurl)) starter = bounceStarter(url, compile(tagre("span", "class", "mininav-next") + - tagre("a", "href", r'(http://www\.snowflamecomic\.com/\?comic=snowflame[^"]+)'))) + tagre("a", "href", r'(%s\?comic=snowflame[^"]+)' % rurl))) help = 'Index format: chapter-page' def getStripIndexUrl(self, index): @@ -276,25 +287,29 @@ class SnowFlame(_BasicScraper): class SodiumEyes(_BasicScraper): url = 'http://sodiumeyes.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://sodiumeyes\.com/comic/[^ ]+)', quote="")) - prevSearch = compile(tagre("a", "href", r'(http://sodiumeyes\.com/[^"]+)', after="prev")) + 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): - url = 'http://www.sorcery101.net/sorcery-101/' + baseurl = 'http://www.sorcery101.net/' + url = baseurl + 'sorcery-101/' + rurl = escape(baseurl) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.sorcery101\.net/wp-content/uploads/\d+/\d+/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.sorcery101\.net/sorcery-101/[^"]+)', after="previous-")) + 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/' - imageSearch = compile(tagre("img", "src", r'(http://spacetrawler\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://spacetrawler\.com/\d+/\d+/\d+/[^"]+)', after="navi-prev")) + 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' @@ -309,26 +324,29 @@ class SpareParts(_BasicScraper): class Spinnerette(_BasicScraper): url = 'http://www.spinnyverse.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.spinnyverse\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.spinnyverse\.com/[^"]+)', before="Previous Comic")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, before="Previous Comic")) help = 'Index format: number' class SPQRBlues(_BasicScraper): url = 'http://spqrblues.com/IV/' + rurl = escape(url) stripUrl = url + '?p=%s' - imageSearch = compile(tagre("img", "src", r'(http://spqrblues\.com/IV/comics/\d+\.png)')) - prevSearch = compile(tagre("a", "href", r'(http://spqrblues\.com/IV/\?p=\d+)', after="prev")) + 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' # 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'(http://www\.stationv3\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.stationv3\.com/d/\d+\.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' @@ -343,9 +361,10 @@ class StickyDillyBuns(_BasicScraper): class Stubble(_BasicScraper): url = 'http://stubblecomics.com/' + rurl = escape(url) stripUrl = url + '?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")) + 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' @@ -386,17 +405,19 @@ class StuffNoOneToldMe(_BasicScraper): class StrawberryDeathCake(_BasicScraper): url = 'http://strawberrydeathcake.com/' + rurl = escape(url) stripUrl = url + '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")) + 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 SuburbanTribe(_BasicScraper): url = 'http://www.pixelwhip.com/' + rurl = escape(url) stripUrl = url + '?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")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev")) help = 'Index format: nnnn' @@ -430,9 +451,10 @@ class StarCrossdDestiny(_BasicScraper): class Spamusement(_BasicScraper): url = 'http://spamusement.com/' + rurl = escape(url) stripUrl = url + 'index.php/comics/view/%s' - imageSearch = compile(r'', IGNORECASE) + imageSearch = compile(r'' % rurl, IGNORECASE) help = 'Index format: n (unpadded)' starter = indirectStarter(url, prevSearch) @@ -448,7 +470,8 @@ class _StrangeCandy(_BasicScraper): class SupernormalStep(_BasicScraper): url = 'http://supernormalstep.com/' + rurl = escape(url) stripUrl = url + '?p=%s' - imageSearch = compile(tagre("img", "src", r'(http://supernormalstep\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://supernormalstep\.com/\?p=\d+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s\?p=\d+)' % rurl, after="prev")) help = 'Index format: number' diff --git a/dosagelib/plugins/t.py b/dosagelib/plugins/t.py index 1e7ca460f..977b3490a 100644 --- a/dosagelib/plugins/t.py +++ b/dosagelib/plugins/t.py @@ -2,7 +2,7 @@ # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2012-2013 Bastian Kleineidam -from re import compile, IGNORECASE +from re import compile, escape, IGNORECASE from ..scraper import _BasicScraper from ..helpers import indirectStarter from ..util import tagre @@ -34,12 +34,13 @@ class TheNoob(_BasicScraper): class TheOrderOfTheStick(_BasicScraper): - url = 'http://www.giantitp.com/comics/oots0863.html' - stripUrl = 'http://www.giantitp.com/comics/oots%s.html' + baseurl = 'http://www.giantitp.com/' + url = baseurl + 'comics/oots0863.html' + stripUrl = baseurl + 'comics/oots%s.html' imageSearch = compile(r'') prevSearch = compile(r'') multipleImagesPerStrip = True prevSearch = compile(r'\d{4} -\s+\d{4}') @@ -65,19 +67,21 @@ class TheWotch(_BasicScraper): class ThisIsIndexed(_BasicScraper): url = 'http://thisisindexed.com/' + rurl = escape(url) stripUrl = url + 'page/%s' - imageSearch = compile(tagre("img", "src", r'(http://thisisindexed\.com/wp-content/uploads/\d+/\d+/card[^"]+)')) + imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/card[^"]+)' % rurl)) multipleImagesPerStrip = True prevSearch = compile(tagre("div", "class", "nav-previous") + - tagre("a", "href", r'(http://thisisindexed\.com/page/\d+/)')) + tagre("a", "href", r'(%spage/\d+/)' % rurl)) help = 'Index format: number' class ThunderAndLightning(_BasicScraper): url = 'http://www.talcomic.com/wp/' + rurl = escape(url) stripUrl = url + '%s/' - prevSearch = compile(tagre("a", "href", r'(http://www\.talcomic\.com/wp/[^"]+)', after="prev")) - imageSearch = compile(tagre("img", "src", r'(http://www\.talcomic\.com/wp/comics/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(%swp/[^"]+)' % rurl, after="prev")) + imageSearch = compile(tagre("img", "src", r'(%swp/comics/[^"]+)' % rurl)) help = 'Index format: yyyy/mm/dd/page-nn' @classmethod @@ -87,17 +91,19 @@ class ThunderAndLightning(_BasicScraper): class TinyKittenTeeth(_BasicScraper): url = 'http://www.tinykittenteeth.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.tinykittenteeth\.com/comics/[^"]+)')) + imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl)) prevSearch = compile(tagre("a", "href", r'([^"]+)', after="Previous")) help = 'Index format: yyyy/mm/dd/stripname (unpadded)' class ToonHole(_BasicScraper): url = 'http://www.toonhole.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://www\.toonhole\.com/comics/\d+-\d+-\d+[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://www\.toonhole\.com/\d+/\d+/[^"]+)', after="prev")) + imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl)) + prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/[^"]+)' % rurl, after="prev")) help = 'Index format: yyyy/mm/stripname' def shouldSkipUrl(self, url): @@ -115,9 +121,10 @@ class _TwoLumps(_BasicScraper): class TwoTwoOneFour(_BasicScraper): url = 'http://www.nitrocosm.com/go/2214_classic/' + rurl = escape(url) stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://content\.nitrocosm\.com/[^"]+)', before="gallery_display")) - prevSearch = compile(tagre("a", "href", r'(http://www\.nitrocosm\.com/go/2214_classic/\d+/)', after="Previous")) + prevSearch = compile(tagre("a", "href", r'(%s\d+/)' % rurl, after="Previous")) help = 'Index format: n (unpadded)' @@ -131,32 +138,37 @@ class TheWhiteboard(_BasicScraper): class HMHigh(_BasicScraper): name = 'TheFallenAngel/HMHigh' - url = 'http://www.thefallenangel.co.uk/hmhigh/' + baseurl = 'http://www.thefallenagel.co.uk/' + url = baseurl + 'hmhigh/' + rurl = escape(baseurl) stripUrl = url + '?id=%s' - imageSearch = compile(r'Prev') + imageSearch = compile(r'Prev' % rurl) help = 'Index format: nnn' class TheOuterQuarter(_BasicScraper): url = 'http://theouterquarter.com/' + rurl = escape(url) stripUrl = url + 'comic/%s' - imageSearch = compile(r'') help = 'Index format: stripname' @@ -35,8 +36,8 @@ class WayfarersMoon(_BasicScraper): class WebDesignerCOTW(_BasicScraper): url = 'http://www.webdesignerdepot.com/' - starter = indirectStarter(url, - compile(tagre("a", "href", r'(http://www\.webdesignerdepot\.com/\d+/\d+/[^"]+/)'))) + rurl = escape(url) + starter = indirectStarter(url, compile(tagre("a", "href", r'(%s\d+/\d+/[^"]+/)' % rurl))) stripUrl = url + '%s/' firstStripUrl = stripUrl % '2009/11/comics-of-the-week-1' imageSearch = ( @@ -46,7 +47,7 @@ class WebDesignerCOTW(_BasicScraper): compile(tagre("img", "src", r'(http://netdna\.webdesignerdepot\.com/uploads/comics/\d+\.[^"]+)')), ) multipleImagesPerStrip = True - prevSearch = compile(tagre("link", "href", r"(http://www\.webdesignerdepot\.com/\d+/\d+/[^']+)", before='prev', quote="'")) + prevSearch = compile(tagre("link", "href", r"(%s\d+/\d+/[^']+)" % rurl, before='prev', quote="'")) help = 'Index format: yyyy/mm/stripname' description = "The content revolves around web design, blogging and funny situations that we encounter in our daily lives as designers and this week we focus on Christmas. These great cartoons are created by Jerry King, an award-winning cartoonist who’s one of the most published, prolific and versatile cartoonists in the world today." @@ -63,24 +64,28 @@ class WebDesignerCOTW(_BasicScraper): class WeCanSleepTomorrow(_BasicScraper): url = 'http://wecansleeptomorrow.com/' + rurl = escape(url) stripUrl = url + '%s/' - imageSearch = compile(tagre("img", "src", r'(http://wecansleeptomorrow\.com/comics/[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(http://wecansleeptomorrow\.com/[^"]+)', after="prev")) + 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 WhiteNinja(_BasicScraper): - url = 'http://www.whiteninjacomics.com/comics.shtml' - stripUrl = 'http://www.whiteninjacomics.com/comics/%s.shtml' + baseurl = 'http://www.whiteninjacomics.com/' + url = baseurl + 'comics.shtml' + stripUrl = baseurl + 'comics/%s.shtml' imageSearch = compile(r'