diff --git a/dosagelib/comic.py b/dosagelib/comic.py index 82e3666e2..70e12fec4 100644 --- a/dosagelib/comic.py +++ b/dosagelib/comic.py @@ -1,5 +1,7 @@ # -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs +# Copyright (C) 2012 Bastian Kleineidam + import urllib2 import os import locale diff --git a/dosagelib/configuration.py b/dosagelib/configuration.py index 06dd4a7c5..a1fd67a4f 100644 --- a/dosagelib/configuration.py +++ b/dosagelib/configuration.py @@ -1,3 +1,4 @@ +# Copyright (C) 2012 Bastian Kleineidam """ Define basic configuration data like version or application name. """ diff --git a/dosagelib/helpers.py b/dosagelib/helpers.py index 64f16d8c1..075fd2212 100644 --- a/dosagelib/helpers.py +++ b/dosagelib/helpers.py @@ -25,21 +25,16 @@ def regexNamer(regex): return _namer -def constStarter(latestUrl): - """Start from constant URL.""" - @staticmethod - def _starter(): - return latestUrl - return _starter - - def bounceStarter(latestUrl, nextSearch): """Get start URL by "bouncing" back and forth one time.""" @classmethod def _starter(cls): url = fetchUrl(latestUrl, cls.prevSearch) - if url: - url = fetchUrl(url, nextSearch) + if not url: + raise ValueError("could not find prevSearch pattern %r in %s" % (cls.prevSearch.pattern, latestUrl)) + url = fetchUrl(url, nextSearch) + if not url: + raise ValueError("could not find nextSearch pattern %r in %s" % (nextSearch.pattern, latestUrl)) return url return _starter @@ -48,7 +43,10 @@ def indirectStarter(baseUrl, latestSearch): """Get start URL by indirection.""" @staticmethod def _starter(): - return fetchUrl(baseUrl, latestSearch) + url = fetchUrl(baseUrl, latestSearch) + if not url: + raise ValueError("could not find latestSearch pattern %r in %s" % (latestSearch.pattern, baseUrl)) + return url return _starter diff --git a/dosagelib/plugins/a.py b/dosagelib/plugins/a.py index ba5358474..7ea4e6040 100644 --- a/dosagelib/plugins/a.py +++ b/dosagelib/plugins/a.py @@ -1,5 +1,7 @@ # -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs +# Copyright (C) 2012 Bastian Kleineidam + from re import compile, MULTILINE from ..util import tagre from ..scraper import _BasicScraper diff --git a/dosagelib/plugins/b.py b/dosagelib/plugins/b.py index 2e778f38e..5b523d27c 100644 --- a/dosagelib/plugins/b.py +++ b/dosagelib/plugins/b.py @@ -1,5 +1,7 @@ # -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs +# Copyright (C) 2012 Bastian Kleineidam + from re import compile from ..util import tagre diff --git a/dosagelib/plugins/c.py b/dosagelib/plugins/c.py index 58e218cee..8ea739223 100644 --- a/dosagelib/plugins/c.py +++ b/dosagelib/plugins/c.py @@ -1,51 +1,28 @@ # -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs +# Copyright (C) 2012 Bastian Kleineidam + from re import compile from ..scraper import _BasicScraper -from ..helpers import constStarter, bounceStarter +from ..helpers import bounceStarter, indirectStarter from ..util import tagre, getQueryParams -class CalvinAndHobbes(_BasicScraper): - starter = bounceStarter('http://www.gocomics.com/calvinandhobbes/', - compile(tagre("a", "href", "(/calvinandhobbes/\d+/\d+/\d+)")+"Next feature")) - stripUrl = 'http://www.gocomics.com/calvinandhobbes/%s' - imageSearch = compile(tagre("img", "src", "(http://assets\.amuniversal\.com/[a-f0-9]+)")) - prevSearch = compile(tagre("a", "href", "(/calvinandhobbes/\d+/\d+/\d+)")+"Previous feature") - help = 'Index format: yyyy/mm/dd' - - @classmethod - def namer(cls, imageUrl, pageUrl): - prefix, year, month, day = pageUrl.rsplit('/', 3) - return "%s%s%s.gif" % (year, month, day) - - -class CandyCartoon(_BasicScraper): - latestUrl = 'http://www.candycartoon.com/' - stripUrl = latestUrl + 'archives/%s.html' - imageSearch = compile(r'[^prev') - help = 'Index format: nnnnnn' - - - class CaptainSNES(_BasicScraper): - latestUrl = 'http://captainsnes.com/' - stripUrl = latestUrl + '?date=%s' - imageSearch = compile(r'') - help = 'Index format: yyyymmdd' - + latestUrl = 'http://www.captainsnes.com/' + stripUrl = latestUrl + '%s/' + imageSearch = compile(r"') + help = 'Index format: yyyy/mm/dd/nnn-stripname' class CaribbeanBlue(_BasicScraper): latestUrl = 'http://cblue.katbox.net/' - stripUrl = latestUrl + 'index.php?strip_id=%s' - imageSearch = compile(r'="(.+?strips/.+?)"') - prevSearch = compile(r'‹') + stripUrl = latestUrl + '?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")) help = 'Index format: n' - class CoolCatStudio(_BasicScraper): latestUrl = 'http://www.coolcatstudio.com/' stripUrl = latestUrl + '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="cniprevt")) + 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")) help = 'Index format: yyyymmdd' - class CourtingDisaster(_BasicScraper): latestUrl = 'http://www.courting-disaster.com/' stripUrl = latestUrl + 'archive/%s.html' - imageSearch = compile(r'(/comics/.+?)"') - prevSearch = compile(r']+?>') + imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(/archive/\d+\.html)') + tagre("img", "src", r'/images/previous\.gif')) help = 'Index format: yyyymmdd' - class CrapIDrewOnMyLunchBreak(_BasicScraper): latestUrl = 'http://crap.jinwicked.com/' stripUrl = latestUrl + '%s' @@ -168,7 +121,6 @@ class CrapIDrewOnMyLunchBreak(_BasicScraper): help = 'Index format: yyyy/mm/dd/name' - class CtrlAltDel(_BasicScraper): latestUrl = 'http://www.cad-comic.com/cad/' stripUrl = latestUrl + '%s' @@ -186,34 +138,31 @@ class CtrlAltDelSillies(CtrlAltDel): class Curvy(_BasicScraper): latestUrl = 'http://www.c.urvy.org/' stripUrl = latestUrl + '?date=%s' - imageSearch = compile(r'(/c/.+?)"') - prevSearch = compile(r'(/\?date=.+?)"><< Previous page') + imageSearch = compile(tagre("img", "src", r'(/c/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(/\?date=\d+)') + tagre("img", "src", "/nav/prev\.png")) help = 'Index format: yyyymmdd' def cloneManga(name, shortName, lastStrip=None): url = 'http://manga.clone-army.org' baseUrl = '%s/%s.php' % (url, shortName) - stripUrl = baseUrl + '?page=%s' - if lastStrip is None: - starter = bounceStarter(baseUrl, compile(tagre("a", "href", r'([^"]+)')+tagre("img", "src", r"next\.gif"))) - else: - starter = constStarter(stripUrl % lastStrip) def namer(self, imageUrl, pageUrl): return '%03d' % int(getQueryParams(pageUrl)['page'][0]) - return type('CloneManga_%s' % name, - (_BasicScraper,), - dict( - name='CloneManga/' + name, - starter=starter, - stripUrl=stripUrl, - imageSearch=compile(tagre("img", "src", r'((?:%s/)?%s/[^"]+)' % (url, shortName), after="center")), - prevSearch=compile(tagre("a", "href", r'([^"]+)')+tagre("img", "src", r"previous\.gif")), - help='Index format: n', - namer=namer) + attrs = dict( + name='CloneManga/' + name, + stripUrl = baseUrl + '?page=%s', + imageSearch=compile(tagre("img", "src", r'((?:%s/)?%s/[^"]+)' % (url, shortName), after="center")), + prevSearch=compile(tagre("a", "href", r'([^"]+)')+tagre("img", "src", r"previous\.gif")), + help='Index format: n', + namer=namer, ) + if lastStrip is None: + attrs['starter'] = indirectStarter(baseUrl, compile(tagre("a", "href", r'([^"]+)')+tagre("img", "src", r"last\.gif"))) + else: + attrs['latestUrl'] = attrs['stripUrl'] % lastStrip + return type('CloneManga_%s' % name, (_BasicScraper,), attrs) anm = cloneManga('AprilAndMay', 'anm') @@ -233,148 +182,14 @@ class CatAndGirl(_BasicScraper): help = 'Index format: n (unpadded)' -def comicsDotCom(name, section): - latestUrl = 'http://www.gocomics.com/%s' % name - - @classmethod - def namer(cls, imageUrl, pageUrl): - prefix, year, month, day = pageUrl.split('/', 3) - return "%s_%s%s%s.gif" % (name, year, month, day) - - return type('GoComicsDotCom_%s' % name, - (_BasicScraper,), - dict( - name='GoComicsDotCom/' + name, - stripUrl=latestUrl + '/%s', - imageSearch=compile(tagre("img", "src", r'(http://assets\.amuniversal\.com/[0-9a-f]+)')), - prevSearch=compile(tagre("a", "href", "(/%s/\d+/\d+/\d+)")+"Previous"), - help='Index format: yyyy/mm/dd', - namer=namer) - ) - -# http://www.gocomics.com/features -# XXX - -# http://www.gocomics.com/explore/editorial_list -# XXX - -# http://www.gocomics.com/explore/sherpa_list -# XXX - -acaseinpoint = comicsDotCom('acaseinpoint', 'comics') -agnes = comicsDotCom('agnes', 'creators') -alleyoop = comicsDotCom('alleyoop', 'comics') -andycapp = comicsDotCom('andycapp', 'creators') -arlonjanis = comicsDotCom('arlonjanis', 'comics') -ballardst = comicsDotCom('ballardst', 'creators') -barkeaterlake = comicsDotCom('barkeaterlake', 'comics') -bc = comicsDotCom('bc', 'creators') -ben = comicsDotCom('ben', 'comics') -betty = comicsDotCom('betty', 'comics') -bignate = comicsDotCom('bignate', 'comics') -bonanas = comicsDotCom('bonanas', 'wash') -bornloser = comicsDotCom('bornloser', 'comics') -buckets = comicsDotCom('buckets', 'comics') -candorville = comicsDotCom('candorville', 'wash') -cheapthrills = comicsDotCom('cheapthrills', 'wash') -chickweed = comicsDotCom('chickweed', 'comics') -committed = comicsDotCom('committed', 'comics') -dilbert = comicsDotCom('dilbert', 'comics') -drabble = comicsDotCom('drabble', 'comics') -fatcats = comicsDotCom('fatcats', 'comics') -ferdnand = comicsDotCom('ferdnand', 'comics') -flightdeck = comicsDotCom('flightdeck', 'creators') -floandfriends = comicsDotCom('floandfriends', 'creators') -franknernest = comicsDotCom('franknernest', 'comics') -frazz = comicsDotCom('frazz', 'comics') -geech = comicsDotCom('geech', 'comics') -genepool = comicsDotCom('genepool', 'wash') -getfuzzy = comicsDotCom('getfuzzy', 'comics') -gofish = comicsDotCom('gofish', 'comics') -graffiti = comicsDotCom('graffiti', 'comics') -grandave = comicsDotCom('grandave', 'comics') -grizzwells = comicsDotCom('grizzwells', 'comics') -heathcliff = comicsDotCom('heathcliff', 'creators') -hedge = comicsDotCom('hedge', 'comics') -herbnjamaal = comicsDotCom('herbnjamaal', 'creators') -herman = comicsDotCom('herman', 'comics') -humblestumble = comicsDotCom('humblestumble', 'comics') -janesworld = comicsDotCom('janesworld', 'comics') -jumpstart = comicsDotCom('jumpstart', 'comics') -kitncarlyle = comicsDotCom('kitncarlyle', 'comics') -liberty = comicsDotCom('liberty', 'creators') -lilabner = comicsDotCom('lilabner', 'comics') -luann = comicsDotCom('luann', 'comics') -marmaduke = comicsDotCom('marmaduke', 'comics') -meg = comicsDotCom('meg', 'comics') -moderatelyconfused = comicsDotCom('moderatelyconfused', 'comics') -momma = comicsDotCom('momma', 'creators') -monty = comicsDotCom('monty', 'comics') -motley = comicsDotCom('motley', 'comics') -nancy = comicsDotCom('nancy', 'comics') -naturalselection = comicsDotCom('naturalselection', 'creators') -offthemark = comicsDotCom('offthemark', 'comics') -onebighappy = comicsDotCom('onebighappy', 'creators') -othercoast = comicsDotCom('othercoast', 'creators') -pcnpixel = comicsDotCom('pcnpixel', 'wash') -peanuts = comicsDotCom('peanuts', 'comics') -pearls = comicsDotCom('pearls', 'comics') -pibgorn = comicsDotCom('pibgorn', 'comics') -pickles = comicsDotCom('pickles', 'wash') -raisingduncan = comicsDotCom('raisingduncan', 'comics') -reality = comicsDotCom('reality', 'comics') -redandrover = comicsDotCom('redandrover', 'wash') -ripleys = comicsDotCom('ripleys', 'comics') -roseisrose = comicsDotCom('roseisrose', 'comics') -rubes = comicsDotCom('rubes', 'creators') -rudypark = comicsDotCom('rudypark', 'comics') -shirleynson = comicsDotCom('shirleynson', 'comics') -soup2nutz = comicsDotCom('soup2nutz', 'comics') -speedbump = comicsDotCom('speedbump', 'creators') -spotthefrog = comicsDotCom('spotthefrog', 'comics') -strangebrew = comicsDotCom('strangebrew', 'creators') -sunshineclub = comicsDotCom('sunshineclub', 'comics') -tarzan = comicsDotCom('tarzan', 'comics') -thatslife = comicsDotCom('thatslife', 'wash') -wizardofid = comicsDotCom('wizardofid', 'creators') -workingdaze = comicsDotCom('workingdaze', 'comics') -workingitout = comicsDotCom('workingitout', 'creators') - - -def creators(name, shortname): - return type('Creators_%s' % name, - (_BasicScraper,), - dict( - name='Creators/' + name, - latestUrl='http://www.creators.com/comics_show.cfm?ComicName=%s' % (shortname,), - stripUrl=None, - imageSearch=compile(tagre("img", "src", r'(\d{4}/[^"]+/[^"]+\.[^"]+)')), - prevSearch=compile(tagre("a", "href", r'(comics_show\.cfm\?next=\d+&ComicName=[^"]+)', after='Previous Comic')), - help='Indexing unsupported') - ) - - -arc = creators('Archie', 'arc') -shg = creators('AskShagg', 'shg') -hev = creators('ForHeavensSake', 'hev') -rug = creators('Rugrats', 'rug') -sou = creators('StateOfTheUnion', 'sou') -din = creators('TheDinetteSet', 'din') -lil = creators('TheMeaningOfLila', 'lil') -wee = creators('WeePals', 'wee') -zhi = creators('ZackHill', 'zhi') - - - class CyanideAndHappiness(_BasicScraper): - latestUrl = 'http://www.explosm.net/comics' - stripUrl = latestUrl + '/%s' - imageSearch = compile(r'Cyanide and Happiness, a daily webcomic< Previous') + latestUrl = 'http://www.explosm.net/comics/' + stripUrl = latestUrl + '%s/' + imageSearch = compile(tagre("img", "src", r'(http:\/\/www\.explosm\.net/db/files/Comics/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(/comics/\d+/)', before="prev")) help = 'Index format: n (unpadded)' - class CrimsonDark(_BasicScraper): latestUrl = 'http://www.davidcsimon.com/crimsondark/' stripUrl = latestUrl + 'index.php?view=comic&strip_id=%s' @@ -383,16 +198,6 @@ class CrimsonDark(_BasicScraper): help = 'Index format: n (unpadded)' - -class CrimesOfCybeleCity(_BasicScraper): - latestUrl = 'http://www.pulledpunches.com/crimes/' - stripUrl = 'http://www.beaglespace.com/pulledpunches/crimes/?p=%s' - imageSearch = compile(r'Next>')) - stripUrl = 'http://corydoncafe.com/comic-%s.html' - imageSearch = compile(r'<Previous') - help = 'Index format: nnn' + starter = bounceStarter('http://corydoncafe.com/', compile(tagre("a", "href", r"(http://corydoncafe\.com/\d+/[^']+)", after="next", quote="'"))) + stripUrl = 'http://corydoncafe.com/%s.php' + imageSearch = compile(tagre("img", "src", r"(\./[^']+)", quote="'")) + prevSearch = compile(tagre("a", "href", r"(http://corydoncafe\.com/\d+/[^']+)", after="prev", quote="'")) + help = 'Index format: yyyy/stripname' @classmethod def namer(cls, imageUrl, pageUrl): return pageUrl.split('/')[-1].split('.')[0] - class CraftedFables(_BasicScraper): latestUrl = 'http://www.craftedfables.com/' stripUrl = 'http://www.caf-fiends.net/craftedfables/?p=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.caf-fiends\.net/craftedfables/comics/[^"]+)')) prevSearch = compile(r'') help = 'Index format: nnn' - - - -class Currhue(_BasicScraper): - latestUrl = 'http://www.currhue.com/' - stripUrl = latestUrl + '?p=%s' - imageSearch = compile(tagre("img", "src", r'(http://www\.currhue\.com/comics/[^"]+)')) - prevSearch = compile(r'
') + imageSearch = compile(tagre("img", "src", r'(http://www\.whatisdeepfried\.com/comics/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(http://www\.whatisdeepfried\.com/[^"]+)', after="prev")) help = 'Index format: non' - class DoemainOfOurOwn(_BasicScraper): latestUrl = 'http://www.doemain.com/' stripUrl = latestUrl + 'index.cgi/%s' @@ -58,7 +59,6 @@ class DoemainOfOurOwn(_BasicScraper): help = 'Index format: yyyy-mm-dd' - class DrFun(_BasicScraper): latestUrl = 'http://www.ibiblio.org/Dave/ar00502.htm' stripUrl = 'http://www.ibiblio.org/Dave/ar%s.htm' @@ -95,26 +95,17 @@ class DreamKeepersPrelude(_BasicScraper): class Drowtales(_BasicScraper): latestUrl = 'http://www.drowtales.com/mainarchive.php' - stripUrl = latestUrl + '?location=%s' - imageSearch = compile(r'src=".(/tmpmanga/.+?)"') - prevSearch = compile(r'.+?back') - help = 'Index format: nnn.html' - + stripUrl = latestUrl + '?sid=%s' + imageSearch = compile(tagre("img", "src", r'("http://www.drowtales.com/mainarchive/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(\?sid=\d+)', before="link_prev_top")) + help = 'Index format: number' class DieselSweeties(_BasicScraper): latestUrl = 'http://www.dieselsweeties.com/' stripUrl = latestUrl + 'archive/%s' - imageSearch = compile(r'src="(/hstrips/.+?)"') - prevSearch = compile(r'href="(/archive/.+?)">(') starter = indirectStarter('http://dresdencodak.com/', compile(r'
')) - - -class DonkBirds(_BasicScraper): - latestUrl = 'http://www.donkbirds.com/' - stripUrl = latestUrl + 'index.php?date=%s' - imageSearch = compile(r'Previous') - help = 'Index format: yyyy-mm-dd' - - - -class DrawnByDrunks(_BasicScraper): - starter = bounceStarter('http://www.drawnbydrunks.co.uk/', compile(r'
')) - stripUrl = 'http://www.drawnbydrunks.co.uk/?p=%s' - imageSearch = compile(r'') - help = 'Index format: nnn' - - @classmethod - def namer(cls, imageUrl, pageUrl): - return pageUrl.split('=')[-1] - - - -class DeathCord(_BasicScraper): - latestUrl = 'http://deathchord.com/index.php' - stripUrl = 'http://deathchord.com/__.php?comicID=%s' - imageSearch = compile(r'?.+?]+?alt="Previous" />') - help = 'Index format: nnn' diff --git a/dosagelib/plugins/drunkduck.py b/dosagelib/plugins/drunkduck.py index d56c8ba95..2a4a5852e 100644 --- a/dosagelib/plugins/drunkduck.py +++ b/dosagelib/plugins/drunkduck.py @@ -1,5 +1,7 @@ # -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs +# Copyright (C) 2012 Bastian Kleineidam + from re import compile, IGNORECASE from ..scraper import _BasicScraper diff --git a/dosagelib/plugins/e.py b/dosagelib/plugins/e.py index 9967bbb94..a07f7d946 100644 --- a/dosagelib/plugins/e.py +++ b/dosagelib/plugins/e.py @@ -1,5 +1,7 @@ # -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs +# Copyright (C) 2012 Bastian Kleineidam + from re import compile, IGNORECASE from ..helpers import indirectStarter @@ -9,28 +11,19 @@ from ..util import tagre class EerieCuties(_BasicScraper): latestUrl = 'http://www.eeriecuties.com/' - stripUrl = latestUrl + 'd/%s.html' - imageSearch = compile(r'(/comics/.+?)"') - prevSearch = compile(r'(/d/.+?.html).+?/previous_day.gif') - help = 'Index format: yyyymmdd' - - -class EdgeTheDevilhunter(_BasicScraper): - name = 'KeenSpot/EdgeTheDevilhunter' - latestUrl = 'http://www.edgethedevilhunter.com/' - stripUrl = latestUrl + 'comics/%s' - imageSearch = compile(r'(http://www.edgethedevilhunter.com/comics/.+?)" alt') - prevSearch = compile(r'(http://www.edgethedevilhunter.com/comics/.+?)">
  • ') - prevSearch = compile(r']+?src="([^"]*?comics/.+?)"') prevSearch = compile(r'><Previous') - help = 'Index format: yyyy-mm-dd' - - - -class EternalVenture(_BasicScraper): - latestUrl = 'http://www.pulledpunches.com/venture/' - stripUrl = 'http://www.beaglespace.com/pulledpunches/venture/?p=%s' - imageSearch = compile(r'< Previous') + prevSearch = compile(r'< Previous') help = 'Index format: yyyymmdd' @@ -113,26 +86,25 @@ class EverybodyLovesEricRaymond(_BasicScraper): class EvilDiva(_BasicScraper): latestUrl = 'http://www.evildivacomics.com/' - stripUrl = latestUrl + '%s.html' + stripUrl = latestUrl + '?p=%s' imageSearch = compile(r'(/comics/.+?)"') prevSearch = compile(r'http.+?com/(.+?)".+?"prev') - help = 'Index format: cpn (unpadded)' + help = 'Index format: n (unpadded)' class EvilInc(_BasicScraper): latestUrl = 'http://www.evil-comic.com/' - stripUrl = latestUrl + 'd/%s.html' - imageSearch=compile(tagre("img", "src", r'(/comic[s|/][^"]+)')) - prevSearch=compile(tagre("a", "href", r'[^"]*(/d/\d+\.s?html)')+r"[^>]+/images/(?:nav_02|previous_day)\.gif") - help='Index format: yyyymmdd' + stripUrl = latestUrl + 'archive/%s.html' + imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'([^"]+)') + tagre("img", "src", r'/images/previous\.gif')) + help = 'Index format: yyyymmdd' class Exiern(_BasicScraper): latestUrl = 'http://www.exiern.com/' - stripUrl = latestUrl + 'comic/%s' - imageSearch = compile(r']*>') - help = 'Index format: yyyy-mm-dd' - + latestUrl = 'http://www.exploitationnow.com/' + stripUrl = latestUrl + '%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")) + help = 'Index format: yyyy-mm-dd/num' class Ellerbisms(_BasicScraper): latestUrl = 'http://www.ellerbisms.com/' stripUrl = latestUrl + '?p=%s' - imageSearch = compile(r'') + imageSearch = compile(tagre("img", "src", r'(http://www\.ellerbisms\.com/wp-content/uploads/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(http://www\.ellerbisms\.com/[^"]+)', after="prev")) help = 'Index format: nnn' + diff --git a/dosagelib/plugins/f.py b/dosagelib/plugins/f.py index 0ad30cb93..c12b392c6 100644 --- a/dosagelib/plugins/f.py +++ b/dosagelib/plugins/f.py @@ -1,5 +1,7 @@ # -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs +# Copyright (C) 2012 Bastian Kleineidam + from re import compile, IGNORECASE, MULTILINE from ..util import tagre @@ -32,35 +34,24 @@ class FeyWinds(_BasicScraper): compile(r'(comic/page.php\?id.+?)"')) - -class FightCastOrEvade(_BasicScraper): - latestUrl = 'http://www.fightcastorevade.net/' - stripUrl = latestUrl + 'd/%s' - imageSearch = compile(tagre("img", "src", r'"(http://www\.fightcastorevade\.net/comics/[^"]+)')) - prevSearch = compile(r'"(.+?/d/.+?)".+?previous') - help = 'Index format: yyyymmdd.html' - - - class FilibusterCartoons(_BasicScraper): latestUrl = 'http://www.filibustercartoons.com/' stripUrl = latestUrl + 'index.php/%s' imageSearch = compile(tagre("img", "src", r'(http://www\.filibustercartoons\.com/comics/[^"]+)')) - prevSearch = compile(r'<') @@ -72,20 +63,9 @@ class Footloose(_BasicScraper): stripUrl = 'http://footloosecomic.com/footloose/pages.php?page=%s' imageSearch = compile(r']).+?(/footloose/.+?)".+?(?:prev)') -# prevSearch = compile(r'(?:first.+?[^>]).+?(/footloose/.+?html).+?(?:prev|Prev)') help = 'Index format: n (unpadded)' - -class FragileGravity(_BasicScraper): - latestUrl = 'http://www.fragilegravity.com/' - stripUrl = latestUrl + 'core.php?archive=%s' - imageSearch = compile(r']', IGNORECASE) - prevSearch = compile(r'(?<=first.gif)*(?<=)*', IGNORECASE) - help = 'Index format: yyyymmdd' - - class FredoAndPidjin(_BasicScraper): homepage = 'http://www.pidjin.net/' + stripUrl = None help = 'Index format: yyyy/mm/dd/name' imageSearch = compile(tagre('img', 'src', '(http://cdn\.pidjin\.net/wp-content/uploads/\d\d\d\d/\d\d/\d+[^"]+\.png)')) prevSearch = compile(tagre('a', 'href', '([^"]+)')+"Prev") starter = indirectStarter(homepage, compile(tagre('a', 'href', "("+homepage+r'\d\d\d\d/\d\d/\d\d/[^"]+/)'))) + diff --git a/dosagelib/plugins/fallenangel.py b/dosagelib/plugins/fallenangel.py new file mode 100644 index 000000000..43c6e8082 --- /dev/null +++ b/dosagelib/plugins/fallenangel.py @@ -0,0 +1,45 @@ +# -*- coding: iso-8859-1 -*- +# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs +# Copyright (C) 2012 Bastian Kleineidam + +def fallenangel(name, shortname): + pass # XXX + +class _TheFallenAngel(_BasicScraper): + imageSearch = compile(r'SRC="(http://www.thefallenangel.co.uk/\w+comics/.+?)"') + prevSearch = compile(r' ]+?src="http://www.thefallenangel.co.uk/images/previousday.jpg"') + help = 'Index format: yyyymmdd' + + @property + def baseUrl(self): + return 'http://www.thefallenangel.co.uk/cgi-bin/%sautokeen/autokeenlite.cgi' % (self.shortName,) + + + @property + def stripUrl(self): + return self.baseUrl + '?date=%s' + + + def starter(self): + return self.baseUrl + + + +class HighMaintenance(_TheFallenAngel): + name = 'TheFallenAngel/HighMaintenance' + shortName = 'hm' + + + +class FAWK(_TheFallenAngel): + name = 'TheFallenAngel/FAWK' + shortName = 'fawk' + + + +class MalloryChan(_TheFallenAngel): + name = 'TheFallenAngel/MalloryChan' + shortName = 'mallorychan' + + + diff --git a/dosagelib/plugins/g.py b/dosagelib/plugins/g.py index 4dd87fc52..ec8162708 100644 --- a/dosagelib/plugins/g.py +++ b/dosagelib/plugins/g.py @@ -1,5 +1,7 @@ # -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs +# Copyright (C) 2012 Bastian Kleineidam + from re import compile from ..scraper import _BasicScraper @@ -9,17 +11,18 @@ from ..util import tagre class Galaxion(_BasicScraper): latestUrl = 'http://galaxioncomics.com/' - stripUrl = latestUrl + '?p=%s' - imageSearch = compile(r'(wordpress/comics/.+?)"') - prevSearch = compile(r'\| ◄ Previous<') + starter = indirectStarter('http://garanos.alexheberling.com/pages/page-1/', + compile(tagre("a", "href", r'(http://garanos\.alexheberling\.com/pages/[^"]+)', after="navi-last"))) + stripUrl = 'http://garanos.alexheberling.com/pages/page-%s' + imageSearch = compile(tagre("img", "src", r'(http://garanos\.alexheberling\.com/comics/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(http://garanos\.alexheberling\.com/pages/[^"]+)', after="prev")) help = 'Index format: n (unpadded)' @@ -31,41 +34,30 @@ class GUComics(_BasicScraper): help = 'Index format: yyyymmdd' - class GenrezvousPoint(_BasicScraper): - latestUrl = 'http://genrezvouspoint.com/' + latestUrl = 'http://www.genrezvouspoint.com/' stripUrl = latestUrl + 'index.php?comicID=%s' imageSearch = compile(r']+?href="(.+?)">PREVIOUS') help = 'Index format: nnn' - class GirlGenius(_BasicScraper): latestUrl = 'http://girlgeniusonline.com/comic.php' - stripUrl = 'http://www.girlgeniusonline.com/comic.php\?date=%s' + stripUrl = 'http://www.girlgeniusonline.com/comic.php?date=%s' imageSearch = compile(r"(/ggmain/strips/.+?)'") prevSearch = compile(r" ]*>]+src="images/gwsmenu/back_off.jpg"') + latestUrl = 'http://www.girlswithslingshots.com/' + stripUrl = latestUrl + 'comic/gws-%s/' + imageSearch = compile(tagre("img", "src", r'(http://cdn\.girlswithslingshots\.com/comics/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(http://www\.girlswithslingshots\.com/comic/[^"]+)', after="prev")) help = 'Index format: nnn' -class Girly(_BasicScraper): - latestUrl = 'http://girlyyy.com/' - stripUrl = latestUrl + 'go/%s' - imageSearch = compile(r'  < prev') - - help = 'Index format: nnn' - class GleefulNihilism(_BasicScraper): latestUrl = 'http://gleefulnihilism.com/' stripUrl = latestUrl + 'comics/%s/' @@ -82,7 +74,6 @@ class Goats(_BasicScraper): help = 'Index format: yymmdd' - class GoneWithTheBlastwave(_BasicScraper): starter = indirectStarter('http://www.blastwave-comic.com/index.php?p=comic&nro=1', compile(r'href="(index.php\?p=comic&nro=\d+)">]+?src="/images/previous_day') - help = 'Index format: yyyy/mm/dd' - + stripUrl = latestUrl + '%s' + imageSearch = compile(tagre("img", "src", r'(http://gunshowcomic\.com/comics/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'([^"]+)') + tagre("img", "src", r'[^"]+menu/small/previous\.gif')) + help = 'Index format: n' class GleefulNihilism(_BasicScraper): latestUrl = 'http://gleefulnihilism.com/' - stripUrl = latestUrl + 'comics/2009/12/01/just-one-of-the-perks/%s' - imageSearch = compile(r']+?>Previous') + stripUrl = latestUrl + 'comics/%s/' + imageSearch = compile(tagre("img", "src", r'(http://gleefulnihilism\.com/comics/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(http://gleefulnihilism\.com/comics/[^"]+)', after="Previous")) help = 'Index format: yyyy/mm/dd/strip-name' - class GastroPhobia(_BasicScraper): latestUrl = 'http://www.gastrophobia.com/' stripUrl = latestUrl + 'index.php?date=%s' @@ -132,7 +119,6 @@ class GastroPhobia(_BasicScraper): help = 'Index format: yyyy-mm-dd' - class Geeks(_BasicScraper): latestUrl = 'http://sevenfloorsdown.com/geeks/' stripUrl = latestUrl + 'archives/%s' @@ -141,7 +127,6 @@ class Geeks(_BasicScraper): help = 'Index format: nnn' - class GlassHalfEmpty(_BasicScraper): latestUrl = 'http://www.defectivity.com/ghe/index.php' stripUrl = latestUrl + '?strip_id=%s' diff --git a/dosagelib/plugins/h.py b/dosagelib/plugins/h.py index 35c2179c2..9c151d93e 100644 --- a/dosagelib/plugins/h.py +++ b/dosagelib/plugins/h.py @@ -1,67 +1,22 @@ -# -*- coding: iso-8859-1 -*- -# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs +# Copyright (C) 2012 Bastian Kleineidam + from re import compile - from ..scraper import _BasicScraper - - -class HappyMedium(_BasicScraper): - latestUrl = 'http://happymedium.fast-bee.com/' - stripUrl = latestUrl + '%s' - imageSearch = compile(r'(/comics/.+?)"') - prevSearch = compile(r'com(/.+?)".+?"prev">◄') - help = 'Index format: yyyy/mm/chapter-n-page-n' - - - -class Heliothaumic(_BasicScraper): - latestUrl = 'http://thaumic.net/' - stripUrl = latestUrl + '%s' - imageSearch = compile(r'') - help = 'Index format: yyyy/mm/dd/n(unpadded)-comicname' - - - -class Housd(_BasicScraper): - latestUrl = 'http://housd.net/archive_page.php?comicID=1284' - stripUrl = 'http://housd.net/archive_page.php?comicID=%s' - imageSearch = compile(r'"(.+?/comics/.+?)"') - prevSearch = compile(r'"(h.+?comicID=.+?)".+?prev') - help = 'Index format: nnnn' - - - -class HateSong(_BasicScraper): - latestUrl = 'http://hatesong.com/' - stripUrl = latestUrl + '%s/' - imageSearch = compile(r'src="(http://www.hatesong.com/strips/.+?)"') - prevSearch = compile(r'
    ]+?src="/images/previous_day.png"') - help = 'Index format: yyyy/mm/dd' - + latestUrl = 'http://horribleville.com/' + stripUrl = latestUrl + 'd/%s.html' + imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(/d/[^"]+)') + tagre("img", "src", r'/images/previous\.png')) + help = 'Index format: yyyymmdd' class HelpDesk(_BasicScraper): - latestUrl = 'http://www.ubersoft.net/' - stripUrl = latestUrl + 'comic/hd/%s/%s/%s' - imageSearch = compile(r'src="(http://www.ubersoft.net/files/comics/hd/hd\d{8}.png)') - prevSearch = compile(r'(.+?)previous') - help = 'Index format: yyyy/mm/name' + latestUrl = 'https://www.eviscerati.org/comics?page=78' + stripUrl = 'https://www.eviscerati.org/comics?page=%s' + imageSearch = compile(tagre("img", "src", r'(https://www\.eviscerati\.org/files/comics/[^"]+)')) + prevSearch = compile(tagre("li", "class", r'pager-previous[^"]+') + tagre("a", "href", r'(/comics\?page=%d+)')) + help = 'Index format: n' - - -class HardGraft(_BasicScraper): - latestUrl = 'http://hard-graft.net/' - stripUrl = latestUrl + '?p=%s' - imageSearch = compile(r'') prevSearch = compile(r'Previous ') help = 'Index format: nnn' @@ -30,54 +31,6 @@ class InsideOut(_BasicScraper): help = 'Index format: n_comic_name' - -class InkTank(_BasicScraper): - shortName = 'inktank' - - def starter(self): - return self.baseUrl + self.shortName + '/' - - -def inkTank(name, shortName): - @classmethod - def _namer(cls, imageUrl, pageUrl): - return '20%s-%s' % (imageUrl[-6:-4], imageUrl[-12:-7]) - - baseUrl = 'http://www.inktank.com/%s/' % (shortName,) - return type('InkTank_%s' % name, - (_BasicScraper,), - dict( - name='InkTank/' + name, - latestUrl=baseUrl, - stripUrl=baseUrl + 'd/%s.html', - imageSearch=compile(r'Edellinen') - - - -class ICantDrawFeet(_BasicScraper): - latestUrl = 'http://icantdrawfeet.com/' - stripUrl = 'http://icantdrawfeet.com/%s' - imageSearch = compile(r'src="(http://icantdrawfeet.com/comics/.+?)"') - prevSearch = compile(r'Previous Strip') - help = 'Index format: n (unpadded)' - +from ..util import tagre class JerkCity(_BasicScraper): latestUrl = 'http://www.jerkcity.com/' - stripUrl = latestUrl + 'jerkcity%s' - imageSearch = compile(r'"jerkcity.+?">.+?"(/jerkcity.+?)"') - prevSearch = compile(r'"(jerkcity.+?)">.+?"/jerkcity.+?"') - help = 'Index format: unknown' - + stripUrl = latestUrl + '_jerkcity%s.html' + imageSearch = compile(tagre("img", "src", r'(/jerkcity[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(/_jerkcity[^"]+)') + r'<<Previous') + help = 'Index format: n' class JoeAndMonkey(_BasicScraper): @@ -31,10 +23,10 @@ class JoeAndMonkey(_BasicScraper): help = 'Index format: nnn' - class JoyOfTech(_BasicScraper): - latestUrl = 'http://www.geekculture.com/joyoftech/index.html' - stripUrl = 'http://www.geekculture.com/joyoftech/joyarchives/%s.html' - imageSearch = compile(r'The Joy') - prevSearch = compile(r'<a href=(?:]*>)?]*>
    [\s\n]*Previous Joy', MULTILINE) + latestUrl = 'http://www.geekculture.com/joyoftech/' + stripUrl = latestUrl + 'joyarchives/%s.html' + imageSearch = compile(tagre("img", "src", r'(joyimages/[^"]+)')) + prevSearch = compile(tagre("a", "href", r'(joyarchives/[^"]+)') + r'.+?Previous', MULTILINE) help = 'Index format: nnn' + diff --git a/dosagelib/plugins/k.py b/dosagelib/plugins/k.py index 6cf1fc6bf..0bdff3ed7 100644 --- a/dosagelib/plugins/k.py +++ b/dosagelib/plugins/k.py @@ -1,24 +1,12 @@ # -*- coding: iso-8859-1 -*- # Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs -from re import compile, IGNORECASE +# Copyright (C) 2012 Bastian Kleineidam +from re import compile, IGNORECASE from ..scraper import _BasicScraper from ..util import tagre -class KernelPanic(_BasicScraper): - latestUrl = 'http://www.ubersoft.net/kpanic/' - stripUrl = latestUrl + 'd/%s' - imageSearch = compile(r'src="(.+?/kp/kp.+?)" ') - prevSearch = compile(r'