From 7f78bea1af6a5a80f7c21f9dd6edc692509b0947 Mon Sep 17 00:00:00 2001 From: Bastian Kleineidam Date: Mon, 4 Feb 2013 21:00:26 +0100 Subject: [PATCH] Always have an url attribute in comic scrapers. --- dosagelib/plugins/a.py | 109 ++++++++++++------------ dosagelib/plugins/arcamax.py | 6 +- dosagelib/plugins/b.py | 94 ++++++++++---------- dosagelib/plugins/c.py | 127 ++++++++++++++-------------- dosagelib/plugins/clonemanga.py | 2 +- dosagelib/plugins/creators.py | 2 +- dosagelib/plugins/d.py | 68 +++++++-------- dosagelib/plugins/drunkduck.py | 1 + dosagelib/plugins/e.py | 73 ++++++++-------- dosagelib/plugins/f.py | 39 ++++----- dosagelib/plugins/g.py | 59 ++++++------- dosagelib/plugins/gocomics.py | 4 +- dosagelib/plugins/h.py | 4 +- dosagelib/plugins/i.py | 20 ++--- dosagelib/plugins/j.py | 20 ++--- dosagelib/plugins/k.py | 26 +++--- dosagelib/plugins/keenspot.py | 2 +- dosagelib/plugins/l.py | 18 ++-- dosagelib/plugins/m.py | 38 ++++----- dosagelib/plugins/n.py | 45 +++++----- dosagelib/plugins/nuklearpower.py | 4 +- dosagelib/plugins/num.py | 4 +- dosagelib/plugins/o.py | 32 +++---- dosagelib/plugins/p.py | 73 ++++++++-------- dosagelib/plugins/pensandtales.py | 2 +- dosagelib/plugins/petitesymphony.py | 6 +- dosagelib/plugins/q.py | 8 +- dosagelib/plugins/r.py | 19 +++-- dosagelib/plugins/s.py | 107 +++++++++++------------ dosagelib/plugins/smackjeeves.py | 1 + dosagelib/plugins/snafu.py | 2 +- dosagelib/plugins/t.py | 46 +++++----- dosagelib/plugins/u.py | 12 +-- dosagelib/plugins/universal.py | 6 +- dosagelib/plugins/v.py | 26 +++--- dosagelib/plugins/w.py | 38 ++++----- dosagelib/plugins/webcomiceu.py | 6 +- dosagelib/plugins/webcomicnation.py | 2 +- dosagelib/plugins/wlpcomics.py | 1 + dosagelib/plugins/x.py | 6 +- dosagelib/plugins/y.py | 8 +- dosagelib/plugins/z.py | 16 ++-- dosagelib/scraper.py | 2 +- scripts/mktestpage.py | 6 +- 44 files changed, 602 insertions(+), 588 deletions(-) diff --git a/dosagelib/plugins/a.py b/dosagelib/plugins/a.py index f793eabf3..ef40da93a 100644 --- a/dosagelib/plugins/a.py +++ b/dosagelib/plugins/a.py @@ -9,40 +9,40 @@ from ..helpers import regexNamer, bounceStarter, indirectStarter class ALessonIsLearned(_BasicScraper): - baseUrl = 'http://www.alessonislearned.com/' + url = 'http://www.alessonislearned.com/' prevSearch = compile(tagre("a", "href", r"(index\.php\?comic=\d+)", quote="'")+r"[^>]+previous") - starter = indirectStarter(baseUrl, prevSearch) - stripUrl = baseUrl + 'index.php?comic=%s' + starter = indirectStarter(url, prevSearch) + stripUrl = url + 'index.php?comic=%s' imageSearch = compile(tagre("img", "src", r"(cmx/lesson\d+\.[a-z]+)")) help = 'Index format: nnn' class ASofterWorld(_BasicScraper): - latestUrl = 'http://www.asofterworld.com/' - stripUrl = latestUrl + 'index.php?id=%s' + url = 'http://www.asofterworld.com/' + stripUrl = url + 'index.php?id=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.asofterworld\.com/clean/[^"]+)')) prevSearch = compile(tagre("a", "href", "(index\.php\?id=\d+)")+'< back') help = 'Index format: n (unpadded)' class AbleAndBaker(_BasicScraper): - latestUrl = 'http://www.jimburgessdesign.com/comics/index.php' - stripUrl = latestUrl + '?comic=%s' + url = 'http://www.jimburgessdesign.com/comics/index.php' + stripUrl = url + '?comic=%s' imageSearch = compile(tagre('img', 'src', r'(comics/.+)')) prevSearch = compile(tagre('a', 'href', r'(.+\d+)') + '.+?previous.gif') help = 'Index format: nnn' class AbominableCharlesChristopher(_BasicScraper): - latestUrl = 'http://www.abominable.cc/' - stripUrl = latestUrl + '%s' + url = 'http://www.abominable.cc/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://www\.abominable\.cc/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)')+"[^<]+Previous") help = 'Index format: yyyy/mm/dd/comicname' class AbsurdNotions(_BasicScraper): - latestUrl = 'http://www.absurdnotions.org/page129.html' + url = 'http://www.absurdnotions.org/page129.html' stripUrl = 'http://www.absurdnotions.org/page%s.html' imageSearch = compile(tagre('img', 'src', r'(an[^"]+)')) multipleImagesPerStrip = True @@ -51,9 +51,10 @@ class AbsurdNotions(_BasicScraper): class AbstruseGoose(_BasicScraper): - starter = bounceStarter('http://abstrusegoose.com/', + url = 'http://abstrusegoose.com/' + starter = bounceStarter(url, compile(tagre('a', 'href', r'(http://abstrusegoose\.com/\d+)')+"Next »")) - stripUrl = 'http://abstrusegoose.com/%s' + 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') help = 'Index format: n (unpadded)' @@ -66,71 +67,70 @@ class AbstruseGoose(_BasicScraper): class AcademyVale(_BasicScraper): - latestUrl = 'http://www.imagerie.com/vale/' - stripUrl = latestUrl + 'avarch.cgi?%s' + url = 'http://www.imagerie.com/vale/' + stripUrl = url + 'avarch.cgi?%s' 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' class Alice(_BasicScraper): - latestUrl = 'http://alice.alicecomics.com/' - stripUrl = latestUrl + '%s/' + url = 'http://alice.alicecomics.com/' + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://alice\.alicecomics\.com/wp-content/webcomic/alicecomics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://alice\.alicecomics\.com/archive/[^"]+)', after="previous")) help = 'Index format: name' class AlienLovesPredator(_BasicScraper): - latestUrl = 'http://alienlovespredator.com/' - stripUrl = latestUrl + '%s' + url = 'http://alienlovespredator.com/' + stripUrl = url + '%s' 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/' class Altermeta(_BasicScraper): - latestUrl = 'http://altermeta.net/' - stripUrl = latestUrl + 'archive.php?comic=%s' + url = 'http://altermeta.net/' + stripUrl = url + 'archive.php?comic=%s' imageSearch = compile(r'') prevSearch = compile(r'Back') class AmazingSuperPowers(_BasicScraper): - latestUrl = 'http://www.amazingsuperpowers.com/' - stripUrl = latestUrl + '%s/' + url = 'http://www.amazingsuperpowers.com/' + 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")) help = 'Index format: yyyy/mm/name' class Angels2200(_BasicScraper): - latestUrl = 'http://www.janahoffmann.com/angels/' - stripUrl = latestUrl + '%s' + url = 'http://www.janahoffmann.com/angels/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r"(http://www\.janahoffmann\.com/angels/comics/[^']+)", quote="'")) prevSearch = compile(tagre("a", "href", r'([^"]+)')+"« Previous") help = 'Index format: yyyy/mm/dd/part--comic-' class AppleGeeks(_BasicScraper): - latestUrl = 'http://www.applegeeks.com/' - stripUrl = latestUrl + 'comics/viewcomic.php?issue=%s' + url = 'http://www.applegeeks.com/' + stripUrl = url + 'comics/viewcomic.php?issue=%s' imageSearch = compile(tagre("img", "src", r'((?:/comics/)?issue\d+\.jpg)')) prevSearch = compile(r'
Previous Comic
\s*

', MULTILINE) help = 'Index format: n (unpadded)' class Achewood(_BasicScraper): - latestUrl = 'http://www.achewood.com/' - stripUrl = latestUrl + 'index.php?date=%s' + url = 'http://www.achewood.com/' + stripUrl = url + 'index.php?date=%s' 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' @@ -138,8 +138,8 @@ class Achewood(_BasicScraper): class AstronomyPOTD(_BasicScraper): - starter = bounceStarter( - 'http://antwrp.gsfc.nasa.gov/apod/astropix.html', + url = 'http://antwrp.gsfc.nasa.gov/apod/astropix.html' + starter = bounceStarter(url, compile(r'>')) stripUrl = 'http://antwrp.gsfc.nasa.gov/apod/ap%s.html' imageSearch = compile(r'") help = 'Index format: yyyy/mm/strip-name' class ASkeweredParadise(_BasicScraper): - latestUrl = 'http://aspcomics.net/' - stripUrl = latestUrl + 'comic/%s' + url = 'http://aspcomics.net/' + stripUrl = url + 'comic/%s' 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' class AGirlAndHerFed(_BasicScraper): - starter = bounceStarter('http://www.agirlandherfed.com/', + url = 'http://www.agirlandherfed.com/' + starter = bounceStarter(url, compile(r'[^>]+Back')) - stripUrl = 'http://www.agirlandherfed.com/1.%s.html' + stripUrl = url + '1.%s.html' imageSearch = compile(tagre("img", "src", r'(img/strip/[^"]+\.jpg)')) prevSearch = compile(r'[^>]+Back') help = 'Index format: nnn' class AetheriaEpics(_BasicScraper): - latestUrl = 'http://aetheria-epics.schala.net/' - stripUrl = latestUrl + '%s.html' + url = 'http://aetheria-epics.schala.net/' + stripUrl = url + '%s.html' imageSearch = compile(tagre("img", "src", r'(\d{5}\.jpg)')) prevSearch = compile(tagre("a", "href", r'(\d{5}\.html)') + "Previous") help = 'Index format: nnn' class AirForceBlues(_BasicScraper): - latestUrl = 'http://www.afblues.com/' - stripUrl = latestUrl + 'wordpress/%s' + url = 'http://www.afblues.com/' + stripUrl = url + 'wordpress/%s' 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/' class AlienShores(_BasicScraper): - latestUrl = 'http://alienshores.com/alienshores_band/' - stripUrl = latestUrl + '%s' + url = 'http://alienshores.com/alienshores_band/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://alienshores\.com/alienshores_band/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://alienshores\.com/[^"]+)', after="prev")) help = 'Index format: yyyy/mm/dd/p/' class AllTheGrowingThings(_BasicScraper): - latestUrl = 'http://growingthings.typodmary.com/' - stripUrl = latestUrl + '%s/' + url = 'http://growingthings.typodmary.com/' + 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")) help = 'Index format: yyyy/mm/dd/strip-name' class Amya(_BasicScraper): - latestUrl = 'http://www.amyachronicles.com/' - stripUrl = latestUrl + 'archives/%s' + url = 'http://www.amyachronicles.com/' + 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")) help = 'Index format: n' class Angband(_BasicScraper): - latestUrl = 'http://angband.calamarain.net/' - stripUrl = latestUrl + 'view.php?date=%s' + url = 'http://angband.calamarain.net/' + stripUrl = url + 'view.php?date=%s' imageSearch = compile(tagre("img", "src", r'(comics/Scroll[^"]+)')) prevSearch = compile(tagre("a", "href", r'(view\.php\?date\=[^"]+)')+"Previous") help = 'Index format: yyyy-mm-dd' class AlsoBagels(_BasicScraper): - latestUrl = 'http://alsobagels.com/' - stripUrl = latestUrl + 'index.php/comic/%s/' + url = 'http://alsobagels.com/' + 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")) help = 'Index format: strip-name' class Annyseed(_BasicScraper): - latestUrl = 'http://www.colourofivy.com/annyseed_webcomic_latest.htm' + url = 'http://www.colourofivy.com/annyseed_webcomic_latest.htm' stripUrl = 'http://www.colourofivy.com/annyseed_webcomic%s.htm' imageSearch = compile(tagre("img", "src", r'(Annyseed[^"]+)')) prevSearch = compile(r']+)', quote="")) prevSearch = compile(tagre("a", "href", r'([^"]+)') + '« Previous') help = 'Index format: yyyy/mm/' class BiggerThanCheeses(_BasicScraper): - latestUrl = 'http://www.biggercheese.com/' - stripUrl = latestUrl + 'index.php?comic=%s' + url = 'http://www.biggercheese.com/' + stripUrl = url + 'index.php?comic=%s' imageSearch = compile(r'src="(comics/.+?)" alt') prevSearch = compile(r'"(index.php\?comic=.+?)".+?_back') help = 'Index format: n (unpadded)' class BizarreUprising(_BasicScraper): - latestUrl = 'http://www.bizarreuprising.com/' - stripUrl = latestUrl + 'view/%s' + url = 'http://www.bizarreuprising.com/' + stripUrl = url + 'view/%s' imageSearch = compile(tagre("img", "src", r'(comic/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(view/\d+/[^"]+)') + tagre("img", "src", r'images/b_prev\.gif')) help = 'Index format: n/name' class Blip(_BasicScraper): - latestUrl = 'http://blipcomic.com/' - stripUrl = latestUrl + 'index.php?strip_id=%s' + url = 'http://blipcomic.com/' + stripUrl = url + 'index.php?strip_id=%s' imageSearch = compile(r'(istrip_files/strips/.+?)"') prevSearch = compile(r'First.+?"(index.php\?strip_id=.+?)".+?prev') help = 'Index format: n' class BlueCrashKit(_BasicScraper): - latestUrl = 'http://www.bluecrashkit.com/cheese/' - stripUrl = latestUrl + 'node/%s' + url = 'http://www.bluecrashkit.com/cheese/' + stripUrl = url + 'node/%s' imageSearch = compile(r'(/cheese/files/comics/.+?)"') prevSearch = compile(r'(/cheese/node/.+?)".+?previous') help = 'Index format: non' class BMovieComic(_BasicScraper): - latestUrl = 'http://www.bmoviecomic.com/' - stripUrl = latestUrl + '?cid=%s' + url = 'http://www.bmoviecomic.com/' + stripUrl = url + '?cid=%s' imageSearch = compile(r'"(comics/.+?)"') prevSearch = compile(r'(\?cid=.+?)".+?Prev') help = 'Index format: n' @@ -70,33 +70,33 @@ class BMovieComic(_BasicScraper): ### mainline -c BratHalla:360-backup-dad-unstable-plans/ ### to get earlier comics class BratHalla(_BasicScraper): - latestUrl = 'http://brat-halla.com/' - stripUrl = latestUrl + 'comic/%s' + url = 'http://brat-halla.com/' + stripUrl = url + 'comic/%s' imageSearch = compile(r"(/comics/.+?)' target='_blank") prevSearch = compile(r'headernav2".+?"(http.+?)"') help = 'Index format: non' class Brink(_BasicScraper): - latestUrl = 'http://paperfangs.com/brink/' - stripUrl = latestUrl + '?p=%s' + url = 'http://paperfangs.com/brink/' + stripUrl = url + '?p=%s' imageSearch = compile(tagre("img", "src", r'(http://paperfangs\.com/brink/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://paperfangs\.com/brink/[^"]+)', after="prev")) help = 'Index format: n' class BoredAndEvil(_BasicScraper): - baseUrl = 'http://www.boredandevil.com/' - stripUrl = baseUrl + '?date=%s' + url = 'http://www.boredandevil.com/' + stripUrl = url + '?date=%s' imageSearch = compile(tagre("img", "src", r'(strips/[^"]+)')) prevSearch = compile(r'First Comic.+Next page") help = 'Index format: n (unpadded)' @@ -107,40 +107,40 @@ class BoyOnAStickAndSlither(_BasicScraper): class ButternutSquash(_BasicScraper): - latestUrl = 'http://www.butternutsquash.net/' - stripUrl = latestUrl + '%s' + url = 'http://www.butternutsquash.net/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://www\.butternutsquash\.net/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.butternutsquash\.net/[^"]+)', after="prev")) help = 'Index format: yyyy/mm/dd/strip-name-author-name' class BlankIt(_BasicScraper): - latestUrl = 'http://blankitcomics.com/' - stripUrl = latestUrl + '%s' + url = 'http://blankitcomics.com/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://blankitcomics\.com/bicomics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)', after='rel="prev"')) help = 'Index format: yyyy/mm/dd/name' class BobWhite(_BasicScraper): - latestUrl = 'http://www.bobwhitecomics.com/' - stripUrl = latestUrl + '?webcomic_post=%s' + url = 'http://www.bobwhitecomics.com/' + stripUrl = url + '?webcomic_post=%s' imageSearch = compile(tagre("img", "src", r"(http://www\.bobwhitecomics\.com/wp/wp-content/webcomic/untitled/\d+.jpg)")) prevSearch = compile(tagre("a", "href", "(http://www\.bobwhitecomics\.com/\?webcomic_post=\d+)")+r'[^"]+Previous') help = 'Index format: yyyymmdd' class BigFatWhale(_BasicScraper): - latestUrl = 'http://www.bigfatwhale.com/' - stripUrl = latestUrl + 'archives/bfw_%s.htm' + url = 'http://www.bigfatwhale.com/' + stripUrl = url + 'archives/bfw_%s.htm' imageSearch = compile(tagre("img", "src", r'(archives/bfw_[^"]+|bfw_[^"]+)')) prevSearch = compile(r' HREF="(.+?)" TARGET="_top" TITLE="Previous Cartoon"') help = 'Index format: nnn' class BadassMuthas(_BasicScraper): - latestUrl = 'http://badassmuthas.com/pages/comic.php' - stripUrl = latestUrl + '?%s' + url = 'http://badassmuthas.com/pages/comic.php' + stripUrl = url + '?%s' 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' @@ -148,7 +148,7 @@ class BadassMuthas(_BasicScraper): class BrightlyWound(_BasicScraper): baseUrl = 'http://www.brightlywound.com/' - latestUrl = baseUrl + '?comic=137' + url = baseUrl + '?comic=137' stripUrl = baseUrl + '?comic=%s' imageSearch = compile(tagre("img", "src", r"(comic/[^']+)", quote="'")) prevSearch = compile(r'

') help = 'Index format: yyyy-mm-dd' class BloodBound(_BasicScraper): - latestUrl = 'http://bloodboundcomic.com/' - stripUrl = latestUrl + '%s' + url = 'http://bloodboundcomic.com/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://bloodboundcomic\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://bloodboundcomic\.com/[^"]+)', after="prev")) help = 'Index format: yyyy/mm/name' class BookOfBiff(_BasicScraper): - latestUrl = 'http://www.thebookofbiff.com/' - stripUrl = latestUrl + '%s' + url = 'http://www.thebookofbiff.com/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'([^"]+/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)', after="Previous")) help = 'Index format: yyyy/mm/dd/stripnum-strip-name' class BillyTheDunce(_BasicScraper): - latestUrl = 'http://www.duncepress.com/' - stripUrl = latestUrl + '%s/' + url = 'http://www.duncepress.com/' + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://www\.duncepress\.com/comics/[^"]+)')) prevSearch = compile(r'
') multipleImagesPerStrip = True @@ -19,8 +19,8 @@ class CaptainSNES(_BasicScraper): class CaseyAndAndy(_BasicScraper): - latestUrl = 'http://www.galactanet.com/comic/' - stripUrl = latestUrl + 'view.php?strip=%s' + url = 'http://www.galactanet.com/comic/' + stripUrl = url + 'view.php?strip=%s' imageSearch = compile(tagre("img", "src", r'(Strip\d+\.gif)')) prevSearch = compile(tagre("a", "href", r'(view\.php\?strip=\d+)') + tagre("img", "src", r'previous\.gif')) @@ -28,8 +28,8 @@ class CaseyAndAndy(_BasicScraper): class CaribbeanBlue(_BasicScraper): - latestUrl = 'http://cblue.katbox.net/' - stripUrl = latestUrl + 'archive/%s' + url = 'http://cblue.katbox.net/' + stripUrl = url + 'archive/%s' imageSearch = compile(tagre("img", "src", r'(http://cblue\.katbox\.net/wp-content/webcomic/cblue/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://cblue\.katbox\.net/archive/[^"]+)', after="previous")) help = 'Index format: nnn-stripname' @@ -37,7 +37,7 @@ class CaribbeanBlue(_BasicScraper): class Catalyst(_BasicScraper): baseUrl = "http://catalyst.spiderforest.com/" - latestUrl = baseUrl + "comic.php?comic_id=415" + url = baseUrl + "comic.php?comic_id=415" stripUrl = baseUrl + "comic.php?comic_id=%s" imageSearch = compile(tagre("img", "src", r'(http://catalyst\.spiderforest\.com/comics/[^"]+)')) prevSearch = compile("
" + tagre("a", "href", r'(http://catalyst\.spiderforest\.com/comic\.php\?comic_id=\d+)')) @@ -45,47 +45,47 @@ class Catalyst(_BasicScraper): class Catena(_BasicScraper): - latestUrl = 'http://catenamanor.com/' - stripUrl = latestUrl + '%s' + url = 'http://catenamanor.com/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://catenamanor\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)', after='rel="prev"')) help = 'Index format: yyyy/mm/dd/' class ChasingTheSunset(_BasicScraper): - latestUrl = 'http://www.fantasycomic.com/' - stripUrl = latestUrl + 'index.php?p=c%s' + url = 'http://www.fantasycomic.com/' + stripUrl = url + 'index.php?p=c%s' imageSearch = compile(r'(/cmsimg/.+?)".+?comic-img') prevSearch = compile(r']+/images/(?:nav_02|previous_day)\.gif") help='Index format: yyyymmdd' class Chisuji(_BasicScraper): - latestUrl = 'http://www.chisuji.com/' - stripUrl = latestUrl + '%s' + url = 'http://www.chisuji.com/' + stripUrl = url + '%s' imageSearch = compile(r'') help = 'Index format: yyyy/mm/dd/strip-name' class ChugworthAcademy(_BasicScraper): - latestUrl = 'http://chugworth.com/' - stripUrl = latestUrl + '?p=%s' + url = 'http://chugworth.com/' + stripUrl = url + '?p=%s' imageSearch = compile(r'Comic') prevSearch = compile(r'<a href=]+?title="Previous">') help = 'Index format: n (unpadded)' class ChugworthAcademyArchive(_BasicScraper): - latestUrl = 'http://chugworth.com/archive/?strip_id=422' + url = 'http://chugworth.com/archive/?strip_id=422' stripUrl = 'http://chugworth.com/archive/?strip_id=%s' imageSearch = compile(r'&laq') help = 'Index format: non' class Comedity(_BasicScraper): - latestUrl = 'http://www.comedity.com/' - stripUrl = latestUrl + 'index.php?strip_id=%s' + url = 'http://www.comedity.com/' + stripUrl = url + 'index.php?strip_id=%s' imageSearch = compile(r' *\"Prior") help = 'Index format: n (unpadded)' class CyanideAndHappiness(_BasicScraper): - _latestUrl = 'http://www.explosm.net/comics/' - starter = bounceStarter(_latestUrl, compile(tagre("a", "href", r"(/comics/\d+/)", before="next"))) - stripUrl = _latestUrl + '%s/' + url = 'http://www.explosm.net/comics/' + starter = bounceStarter(url, compile(tagre("a", "href", r"(/comics/\d+/)", before="next"))) + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://(?:www\.)?explosm\.net/db/files/[^"]+)', before="a daily webcomic")) prevSearch = compile(tagre("a", "href", r'(/comics/\d+/)', before="prev")) help = 'Index format: n (unpadded)' @@ -194,48 +194,48 @@ class CyanideAndHappiness(_BasicScraper): class CrimsonDark(_BasicScraper): - latestUrl = 'http://www.davidcsimon.com/crimsondark/' - stripUrl = latestUrl + 'index.php?view=comic&strip_id=%s' + url = 'http://www.davidcsimon.com/crimsondark/' + stripUrl = url + 'index.php?view=comic&strip_id=%s' imageSearch = compile(r'src="(.+?strips/.+?)"') prevSearch = compile(r'') help = 'Index format: nnn' class CowboyJedi(_BasicScraper): - latestUrl = 'http://www.cowboyjedi.com/' - stripUrl = latestUrl + '%s' + url = 'http://www.cowboyjedi.com/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://www\.cowboyjedi.\com/comics/[^"]+)')) prevSearch = compile(r'') help = 'Index format: nnn' @@ -243,7 +243,7 @@ class Chester5000XYV(_BasicScraper): class Champ2010(_BasicScraper): # the latest URL is hard coded since the comic is discontinued - latestUrl = 'http://jedcollins.com/champ2010/champ-12-30-10.html' + url = 'http://jedcollins.com/champ2010/champ-12-30-10.html' stripUrl = 'http://jedcollins.com/champ2010/%s.html' imageSearch = compile(tagre("img", "src", r'(http://jedcollins\.com/champ2010/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://jedcollins\.com/champ2010/[^"]+)', after="Previous")) @@ -251,24 +251,25 @@ class Champ2010(_BasicScraper): class Chucklebrain(_BasicScraper): - latestUrl = 'http://www.chucklebrain.com/main.php' - stripUrl = latestUrl + '?img=%s' + url = 'http://www.chucklebrain.com/main.php' + stripUrl = url + '?img=%s' imageSearch = compile(tagre("img", "src", r'(/images/strip[^"]+)')) prevSearch = compile(r'') diff --git a/dosagelib/plugins/clonemanga.py b/dosagelib/plugins/clonemanga.py index 708fc6d0f..8a50f27eb 100644 --- a/dosagelib/plugins/clonemanga.py +++ b/dosagelib/plugins/clonemanga.py @@ -48,7 +48,7 @@ def add(name, shortName, imageFolder=None, lastStrip=None): if lastStrip is None: attrs['starter'] = _starter else: - attrs['latestUrl'] = attrs['stripUrl'] % lastStrip + attrs['url'] = attrs['stripUrl'] % lastStrip globals()[classname] = make_scraper(classname, **attrs) diff --git a/dosagelib/plugins/creators.py b/dosagelib/plugins/creators.py index 4840f9bcb..a081f943a 100644 --- a/dosagelib/plugins/creators.py +++ b/dosagelib/plugins/creators.py @@ -13,7 +13,7 @@ def add(name, path): classname = 'Creators_%s' % name globals()[classname] = make_scraper(classname, name = 'Creators/' + name, - latestUrl = baseurl + path + '.html', + url = baseurl + path + '.html', stripUrl = baseurl + path + '/%s.html', imageSearch = _imageSearch, prevSearch = compile(tagre("a", "href", r'(%s/\d+\.html)' % path) + diff --git a/dosagelib/plugins/d.py b/dosagelib/plugins/d.py index f9d821c9c..d4818a38b 100644 --- a/dosagelib/plugins/d.py +++ b/dosagelib/plugins/d.py @@ -10,18 +10,18 @@ from ..util import tagre class DailyDose(_BasicScraper): - baseUrl = 'http://dailydoseofcomics.com/' - starter = indirectStarter(baseUrl, + url = 'http://dailydoseofcomics.com/' + starter = indirectStarter(url, compile(tagre("a", "href", r'(http://dailydoseofcomics\.com/[^"]+)', after="preview"))) - stripUrl = baseUrl + '%s/' + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'([^"]+)', before="align(?:none|center)")) prevSearch = compile(tagre("a", "href", r'(http://dailydoseofcomics\.com/[^"]+)', after="prev")) help = 'Index format: stripname' class Damonk(_BasicScraper): - latestUrl = 'http://www.damonk.com/' - stripUrl = latestUrl + 'd/%s.html' + url = 'http://www.damonk.com/' + stripUrl = url + 'd/%s.html' imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)') + tagre("img", "src", r'/images/previous_day\.gif')) @@ -30,7 +30,7 @@ class Damonk(_BasicScraper): # XXX disallowed /search by robots.txt class _DandyAndCompany(_BasicScraper): - latestUrl = 'http://www.dandyandcompany.com/' + url = 'http://www.dandyandcompany.com/' stripUrl = None multipleImagesPerStrip = True imageSearch = compile(tagre("a", "href", r'(http://\d+\.bp\.blogspot\.com/[^"]+)', after="imageanchor")) @@ -39,32 +39,32 @@ class _DandyAndCompany(_BasicScraper): class DarkWings(_BasicScraper): - latestUrl = 'http://www.flowerlarkstudios.com/dark-wings/' - stripUrl = latestUrl + '%s' + url = 'http://www.flowerlarkstudios.com/dark-wings/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://www\.flowerlarkstudios\.com/dark-wings/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.flowerlarkstudios\.com/dark-wings/[^"]+)', after="navi-prev")) help = 'Index format: yyyy/mm/dd/page-nn-mm' class DeathToTheExtremist(_BasicScraper): - latestUrl = 'http://www.dtecomic.com/' - stripUrl = latestUrl + '?n=%s' + url = 'http://www.dtecomic.com/' + stripUrl = url + '?n=%s' imageSearch = compile(r'"(comics/.*?)"') prevSearch = compile(r' <.+?/aprev.gif"') help = 'Index format: nnn' class DeepFried(_BasicScraper): - latestUrl = 'http://www.whatisdeepfried.com/' - stripUrl = latestUrl + '%s' + url = 'http://www.whatisdeepfried.com/' + stripUrl = url + '%s' 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 DMFA(_BasicScraper): - latestUrl = 'http://www.missmab.com/' - stripUrl = latestUrl + 'Comics/Vol_%s.php' + url = 'http://www.missmab.com/' + stripUrl = url + 'Comics/Vol_%s.php' imageSearch = compile(tagre("img", "src", r'((?:Comics/|Vol)[^"]+)')) multipleImagesPerStrip = True prevSearch = compile(tagre("a", "href", r'((?:Comics/)?Vol[^"]+)')+ @@ -73,15 +73,15 @@ class DMFA(_BasicScraper): class DoemainOfOurOwn(_BasicScraper): - latestUrl = 'http://www.doemain.com/' - stripUrl = latestUrl + 'index.cgi/%s' + url = 'http://www.doemain.com/' + stripUrl = url + 'index.cgi/%s' imageSearch = compile(r"Previous Strip') multipleImagesPerStrip = True @@ -90,40 +90,40 @@ class DrFun(_BasicScraper): class Dracula(_BasicScraper): - latestUrl = 'http://draculacomic.net/' - stripUrl = latestUrl + 'comic.php?comicID=%s' + url = 'http://draculacomic.net/' + stripUrl = url + 'comic.php?comicID=%s' imageSearch = compile(tagre("img", "src", r'(comics/[^"]+)')) prevSearch = compile(r' « Prev') help = 'Index format: nnn' class DragonTails(_BasicScraper): - latestUrl = 'http://www.dragon-tails.com/' - stripUrl = latestUrl + 'archive.php?date=%s' + url = 'http://www.dragon-tails.com/' + stripUrl = url + 'archive.php?date=%s' imageSearch = compile(r'"(newcomic/.+?)"') prevSearch = compile(r'"(archive.+?)">.+n_2') help = 'Index format: yyyy-mm-dd' class DreamKeepersPrelude(_BasicScraper): - latestUrl = 'http://www.dreamkeeperscomic.com/Prelude.php' - stripUrl = latestUrl + '?pg=%s' + url = 'http://www.dreamkeeperscomic.com/Prelude.php' + stripUrl = url + '?pg=%s' imageSearch = compile(r'(images/PreludeNew/.+?)"') prevSearch = compile(r'(Prelude.php\?pg=.+?)"') help = 'Index format: n' class Drowtales(_BasicScraper): - latestUrl = 'http://www.drowtales.com/mainarchive.php' - stripUrl = latestUrl + '?sid=%s' + url = 'http://www.drowtales.com/mainarchive.php' + stripUrl = url + '?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' + url = 'http://www.dieselsweeties.com/' + stripUrl = url + 'archive/%s' imageSearch = compile(tagre("img", "src", r'(/hstrips/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/archive/\d+)') + tagre("img", "src", r'(?:http://www\.dieselsweeties\.com/ximages/blackbackarrow160.png|/ximages/prev\.gif)')) @@ -136,23 +136,23 @@ class DieselSweeties(_BasicScraper): class DominicDeegan(_BasicScraper): - latestUrl = 'http://www.dominic-deegan.com/' - stripUrl = latestUrl + 'view.php?date=%s' + url = 'http://www.dominic-deegan.com/' + stripUrl = url + 'view.php?date=%s' imageSearch = compile(tagre("img", "src", r'(comics/\d+\.gif)')) prevSearch = compile(r'"(view.php\?date=[^"]+)".+?prev21') help = 'Index format: yyyy-mm-dd' class DorkTower(_BasicScraper): - latestUrl = 'http://www.dorktower.com/' - stripUrl = latestUrl + '%s/' + url = 'http://www.dorktower.com/' + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://www\.dorktower\.com/files/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.dorktower\.com/[^"]+)')+"Previous") help = 'Index format: yyyy/mm/dd/stripname-dd-mm-yy' class DresdenCodak(_BasicScraper): - latestUrl = 'http://dresdencodak.com/' + url = 'http://dresdencodak.com/' stripUrl = None imageSearch = compile(r'') @@ -160,8 +160,8 @@ class DresdenCodak(_BasicScraper): class Dilbert(_BasicScraper): - latestUrl = 'http://dilbert.com/' - stripUrl = latestUrl + '%s/' + url = 'http://dilbert.com/' + stripUrl = url + '%s/' prevSearch = compile(tagre("a", "href", r'(/\d+-\d+-\d+/)', after="STR_Prev")) imageSearch = compile(tagre("img", "src", r'(/dyn/str_strip/[^"]+\.strip\.zoom\.gif)')) help = 'Index format: yyyy-mm-dd' diff --git a/dosagelib/plugins/drunkduck.py b/dosagelib/plugins/drunkduck.py index 649d26143..8fba609a8 100644 --- a/dosagelib/plugins/drunkduck.py +++ b/dosagelib/plugins/drunkduck.py @@ -40,6 +40,7 @@ def add(name, path): globals()[classname] = make_scraper(classname, name = 'DrunkDuck/' + name, + url = _url, starter = _starter, stripUrl = _url + '%s/', imageSearch = _imageSearch, diff --git a/dosagelib/plugins/e.py b/dosagelib/plugins/e.py index ce0b9f804..1442db73e 100644 --- a/dosagelib/plugins/e.py +++ b/dosagelib/plugins/e.py @@ -10,32 +10,32 @@ from ..util import tagre class EdibleDirt(_BasicScraper): - latestUrl = 'http://eddirt.frozenreality.co.uk/' - stripUrl = latestUrl + 'index.php?id=%s' + url = 'http://eddirt.frozenreality.co.uk/' + stripUrl = url + 'index.php?id=%s' imageSearch = compile(tagre("img", "src", r'(strips/[^"]+)')) prevSearch = compile(tagre("a", "href", r"(index\.php\?id=\d+)")+"Previous") help = 'Index format: number' class EerieCuties(_BasicScraper): - latestUrl = 'http://www.eeriecuties.com/' - stripUrl = latestUrl + 'strips-ec/%s' + url = 'http://www.eeriecuties.com/' + stripUrl = url + 'strips-ec/%s' imageSearch = compile(tagre("img", "src", r'(http://ace\.eeriecuties\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)', before="prev")) help = 'Index format: stripname' class Eriadan(_BasicScraper): - latestUrl = 'http://www.shockdom.com/webcomics/eriadan/' - stripUrl = latestUrl + '%s' + url = 'http://www.shockdom.com/webcomics/eriadan/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://www\.shockdom\.com/webcomics/eriadan/files/[^"]+)', after='width="800"')) prevSearch = compile(tagre("a", "href", r'([^"]+)', after="prev")) help = 'Index format: yyyy/mm/dd/nnn (unpadded)' class ElfOnlyInn(_BasicScraper): - latestUrl = 'http://www.elfonlyinn.net/' - stripUrl = latestUrl + 'd/%s.html' + url = 'http://www.elfonlyinn.net/' + stripUrl = url + 'd/%s.html' imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)') + tagre("img", "src", r'/images/previous_day\.gif')) @@ -44,8 +44,8 @@ class ElfOnlyInn(_BasicScraper): class ElGoonishShive(_BasicScraper): name = 'KeenSpot/ElGoonishShive' - latestUrl = 'http://www.egscomics.com/' - stripUrl = latestUrl + '?date=%s' + url = 'http://www.egscomics.com/' + stripUrl = url + '?date=%s' imageSearch = compile(r"'(comics/.+?)'") prevSearch = compile(r"]+?onmouseover=\'\$\("navimg(6|2)"\)') help = 'Index format: yyyy-mm-dd' class EmergencyExit(_BasicScraper): - latestUrl = 'http://www.eecomics.net/' - stripUrl = latestUrl + "?strip_id=%s" + url = 'http://www.eecomics.net/' + stripUrl = url + "?strip_id=%s" imageSearch = compile(r'"(comics/.+?)"') prevSearch = compile(tagre("a", "href", r'(\?strip_id=\d+)') + tagre("img", "alt", r"Prior")) help = 'Index format: n' @@ -70,15 +70,15 @@ class EmergencyExit(_BasicScraper): # XXX disallowed by robots.txt class _ErrantStory(_BasicScraper): - latestUrl = 'http://www.errantstory.com/' - stripUrl = latestUrl + '%s' + url = 'http://www.errantstory.com/' + stripUrl = url + '%s' imageSearch = compile(r']+?src="([^"]*?comics/.+?)"') prevSearch = compile(r'><Previous') help = 'Index format: yyyy-mm-dd/num' class Evercrest(_BasicScraper): - latestUrl = 'http://www.evercrest.com/archives/20030308' + url = 'http://www.evercrest.com/archives/20030308' stripUrl = 'http://www.evercrest.com/archives/%s' imageSearch = compile(r'< Previous') @@ -86,62 +86,63 @@ class Evercrest(_BasicScraper): class EverybodyLovesEricRaymond(_BasicScraper): - latestUrl = 'http://geekz.co.uk/lovesraymond/' - stripUrl = latestUrl + 'archive/%s' + url = 'http://geekz.co.uk/lovesraymond/' + stripUrl = url + 'archive/%s' imageSearch = compile(r'') help = 'Index format: name-of-old-comic' class EvilDiva(_BasicScraper): - latestUrl = 'http://www.evildivacomics.com/' - stripUrl = latestUrl + '?p=%s' + url = 'http://www.evildivacomics.com/' + stripUrl = url + '?p=%s' imageSearch = compile(r'(/comics/.+?)"') prevSearch = compile(r'http.+?com/(.+?)".+?"prev') help = 'Index format: n (unpadded)' class EvilInc(_BasicScraper): - latestUrl = 'http://www.evil-comic.com/' - stripUrl = latestUrl + 'archive/%s.html' + url = 'http://www.evil-comic.com/' + stripUrl = url + '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 + '?p=%s' + url = 'http://www.exiern.com/' + stripUrl = url + '?p=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.exiern\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.exiern\.com/[^"]+)', after="prev")) help = 'Index format: n' class ExiernDarkReflections(_BasicScraper): - latestUrl = 'http://darkreflections.exiern.com/' - stripUrl = latestUrl + 'index.php?strip_id=%s' + url = 'http://darkreflections.exiern.com/' + stripUrl = url + 'index.php?strip_id=%s' imageSearch = compile(r'"(istrip.+?)"') prevSearch = compile(r'First.+?(/index.+?)".+?prev') help = 'Index format: n' class ExtraLife(_BasicScraper): - latestUrl = 'http://www.myextralife.com/' - stripUrl = latestUrl + 'comic/%s/' + url = 'http://www.myextralife.com/' + stripUrl = url + 'comic/%s/' imageSearch = compile(tagre("img", "src", r'(http://www\.myextralife\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)', after="prev")) help = 'Index format: stripname' class EyeOfRamalach(_BasicScraper): - latestUrl = 'http://theeye.katbox.net/' - stripUrl = latestUrl + 'archive/%s/' + url = 'http://theeye.katbox.net/' + stripUrl = url + 'archive/%s/' imageSearch = compile(tagre("img", "src", r'(http://theeye\.katbox\.net/wp-content/webcomic/theeye/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://theeye\.katbox\.net/archive/[^"]+)', after="previous")) help = 'Index format: n (unpadded)' class EarthsongSaga(_BasicScraper): - starter = indirectStarter('http://www.earthsongsaga.com/', compile(tagre("a", "href", r'([^"]+)') + tagre("img", "src", r'[^"]+current\.jpg'))) + url = 'http://www.earthsongsaga.com/' + starter = indirectStarter(url, compile(tagre("a", "href", r'([^"]+)') + tagre("img", "src", r'[^"]+current\.jpg'))) stripUrl = None imageSearch = compile(tagre("img", "src", r'((?:\.\./)?images/vol\d+/ch\d+/\d+\.\w+)')) prevSearch = compile(tagre("a", "href", r'([^"]+)', after="Previous")) @@ -153,16 +154,16 @@ class EarthsongSaga(_BasicScraper): class ExploitationNow(_BasicScraper): - latestUrl = 'http://www.exploitationnow.com/' - stripUrl = latestUrl + '%s' + url = 'http://www.exploitationnow.com/' + 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")) help = 'Index format: yyyy-mm-dd/num' class Ellerbisms(_BasicScraper): - latestUrl = 'http://www.ellerbisms.com/' - stripUrl = latestUrl + '?p=%s' + url = 'http://www.ellerbisms.com/' + 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")) help = 'Index format: nnn' diff --git a/dosagelib/plugins/f.py b/dosagelib/plugins/f.py index 2dec7679d..59deb08ed 100644 --- a/dosagelib/plugins/f.py +++ b/dosagelib/plugins/f.py @@ -10,40 +10,40 @@ from ..helpers import indirectStarter class FalconTwin(_BasicScraper): - latestUrl = 'http://www.falcontwin.com/' - stripUrl = latestUrl + 'index.html?strip=%s' + url = 'http://www.falcontwin.com/' + stripUrl = url + 'index.html?strip=%s' imageSearch = compile(r'"(strips/.+?)"') prevSearch = compile(r'"prev">Previous Strip') help = 'Index format: nnn' class FeyWinds(_BasicScraper): + url = 'http://kitsune.rydia.net/index.html' stripUrl = 'http://kitsune.rydia.net/comic/page.php?id=%s' imageSearch = compile(r"(../comic/pages//.+?)'") prevSearch = compile(r"(page.php\?id=.+?)'.+?navprevious.png") help = 'Index format: n (unpadded)' - starter = indirectStarter('http://kitsune.rydia.net/index.html', - compile(r'(comic/page.php\?id.+?)"')) + starter = indirectStarter(url, compile(r'(comic/page.php\?id.+?)"')) class FilibusterCartoons(_BasicScraper): - latestUrl = 'http://www.filibustercartoons.com/' - stripUrl = latestUrl + 'index.php/%s' + url = 'http://www.filibustercartoons.com/' + stripUrl = url + 'index.php/%s' imageSearch = compile(tagre("img", "src", r'(http://www\.filibustercartoons\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.filibustercartoons\.com/[^"]+)', after="prev")) help = 'Index format: yyyy/mm/dd/name' class FlakyPastry(_BasicScraper): - latestUrl = 'http://flakypastry.runningwithpencils.com/index.php' + url = 'http://flakypastry.runningwithpencils.com/index.php' stripUrl = 'http://flakypastry.runningwithpencils.com/comic.php?strip_id=%s' imageSearch = compile(r']).+?(/footloose/.+?)".+?(?:prev)') @@ -76,7 +76,7 @@ class Footloose(_BasicScraper): class Freefall(_BasicScraper): - latestUrl = 'http://freefall.purrsia.com/default.htm' + url = 'http://freefall.purrsia.com/default.htm' stripUrl = 'http://freefall.purrsia.com/ff%s/fc%s.htm' imageSearch = compile(r'Previous') @@ -84,17 +84,18 @@ class Freefall(_BasicScraper): class FantasyRealms(_BasicScraper): - stripUrl = 'http://www.fantasyrealmsonline.com/manga/%s.php' + url = 'http://www.fantasyrealmsonline.com/' + stripUrl = url + 'manga/%s.php' imageSearch = compile(r' ') help = 'Index format: yymmdd' @@ -80,24 +81,24 @@ class GoneWithTheBlastwave(_BasicScraper): class GrrlPower(_BasicScraper): - latestUrl = 'http://www.grrlpowercomic.com/' - stripUrl = latestUrl + 'archives/%s' + url = 'http://www.grrlpowercomic.com/' + stripUrl = url + 'archives/%s' imageSearch = compile(tagre("img", "src", r'(http://www\.grrlpowercomic\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.grrlpowercomic\.com/archives/\d+)', after="navi-prev")) help = 'Index format: number' class GunnerkrigCourt(_BasicScraper): - latestUrl = 'http://www.gunnerkrigg.com/' - stripUrl = latestUrl + '?p=%s' + url = 'http://www.gunnerkrigg.com/' + stripUrl = url + '?p=%s' imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(\?p=\d+)') + tagre("img", "src", "http://www\.gunnerkrigg\.com/images/prev_a\.jpg")) help = 'Index format: number' class Gunshow(_BasicScraper): - latestUrl = 'http://gunshowcomic.com/' - stripUrl = latestUrl + '%s' + url = 'http://gunshowcomic.com/' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://gunshowcomic\.com/comics/[^"]+)')) multipleImagesPerStrip = True prevSearch = compile(tagre("a", "href", r'([^"]+)') + tagre("img", "src", r'[^"]*menu/small/previous\.gif')) @@ -105,40 +106,40 @@ class Gunshow(_BasicScraper): class GleefulNihilism(_BasicScraper): - latestUrl = 'http://gleefulnihilism.com/' - stripUrl = latestUrl + 'comics/%s/' + url = 'http://gleefulnihilism.com/' + stripUrl = url + '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' + url = 'http://www.gastrophobia.com/' + stripUrl = url + 'index.php?date=%s' imageSearch = compile(r']*>(?!
)') prevSearch = compile(r'« Previous') help = 'Index format: nnn' class GlassHalfEmpty(_BasicScraper): - latestUrl = 'http://www.defectivity.com/ghe/index.php' - stripUrl = latestUrl + '?strip_id=%s' + url = 'http://www.defectivity.com/ghe/index.php' + stripUrl = url + '?strip_id=%s' 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 GreystoneInn(_BasicScraper): - latestUrl = 'http://www.greystoneinn.net/' - stripUrl = latestUrl + 'd/%s.html' + url = 'http://www.greystoneinn.net/' + stripUrl = url + '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' diff --git a/dosagelib/plugins/gocomics.py b/dosagelib/plugins/gocomics.py index ab6434bce..cd5959e1d 100644 --- a/dosagelib/plugins/gocomics.py +++ b/dosagelib/plugins/gocomics.py @@ -13,6 +13,7 @@ _nextSearch = compile(tagre("a", "href", r'(/[^"]+/\d+/\d+/\d+)', after="next")) def add(name, shortname): baseUrl = 'http://www.gocomics.com' + url = baseUrl + shortname classname = 'GoComics_%s' % name @classmethod @@ -21,7 +22,8 @@ def add(name, shortname): return "%s_%s%s%s.gif" % (name, year, month, day) globals()[classname] = make_scraper(classname, - starter = bounceStarter(baseUrl + shortname, _nextSearch), + url = url, + starter = bounceStarter(url, _nextSearch), name='GoComics/' + name, stripUrl=baseUrl + quote(shortname) + '/%s', imageSearch = _imageSearch, diff --git a/dosagelib/plugins/h.py b/dosagelib/plugins/h.py index 371e0cf26..918b11f56 100644 --- a/dosagelib/plugins/h.py +++ b/dosagelib/plugins/h.py @@ -6,8 +6,8 @@ from ..util import tagre class HorribleVille(_BasicScraper): - latestUrl = 'http://horribleville.com/' - stripUrl = latestUrl + 'd/%s.html' + url = 'http://horribleville.com/' + stripUrl = url + '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' diff --git a/dosagelib/plugins/i.py b/dosagelib/plugins/i.py index bad5380f5..d860eb874 100644 --- a/dosagelib/plugins/i.py +++ b/dosagelib/plugins/i.py @@ -8,40 +8,40 @@ from ..util import tagre class IanJay(_BasicScraper): - latestUrl = 'http://ianjay.net/' - stripUrl = latestUrl + '?p=%s' + url = 'http://ianjay.net/' + stripUrl = url + '?p=%s' imageSearch = compile(tagre("img", "src", r'(http://ianjay\.net/comics/\d+[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://ianjay\.net/\?p=\d+)', after="Previous")) help = 'Index foramt: nnn' class IDreamOfAJeanieBottle(_BasicScraper): - latestUrl = 'http://jeaniebottle.com/' - stripUrl = latestUrl + '?p=%s' + url = 'http://jeaniebottle.com/' + stripUrl = url + '?p=%s' imageSearch = compile(r'(/comics/.+?)"') prevSearch = compile(tagre("a", "href", r'(http://jeaniebottle\.com/\?p=\d+)', after="prev")) help = 'Index format: n (unpadded)' class IrregularWebcomic(_BasicScraper): - latestUrl = 'http://www.irregularwebcomic.net/' - stripUrl = latestUrl + '%s.html' + url = 'http://www.irregularwebcomic.net/' + stripUrl = url + '%s.html' imageSearch = compile(r'') prevSearch = compile(r'Previous ') help = 'Index format: nnn' class InsideOut(_BasicScraper): - latestUrl = 'http://www.insideoutcomic.com/' - stripUrl = latestUrl + 'html/%s.html' + url = 'http://www.insideoutcomic.com/' + stripUrl = url + 'html/%s.html' imageSearch = compile(r'Picture12LYR.+?C="(.+?/assets/images/.+?)"') prevSearch = compile(r'Picture7LYR.+?F="(.+?/html/.+?)"') help = 'Index format: n_comic_name' class ItsWalky(_BasicScraper): - latestUrl = 'http://www.itswalky.com/' - stripUrl = latestUrl + 'd/%s.html' + url = 'http://www.itswalky.com/' + stripUrl = url + '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' diff --git a/dosagelib/plugins/j.py b/dosagelib/plugins/j.py index 5b0e23a1b..6ea5dd018 100644 --- a/dosagelib/plugins/j.py +++ b/dosagelib/plugins/j.py @@ -8,40 +8,40 @@ from ..util import tagre class JackCannon(_BasicScraper): - latestUrl = 'http://fancyadventures.com/' - stripUrl = latestUrl + '%s/' + url = 'http://fancyadventures.com/' + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://fancyadventures\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://fancyadventures\.com/[^"]+)', after="prev")) help = 'Index format: yyyy/mm/dd/page-nnn' class JerkCity(_BasicScraper): - latestUrl = 'http://www.jerkcity.com/' - stripUrl = latestUrl + '_jerkcity%s.html' + url = 'http://www.jerkcity.com/' + stripUrl = url + '_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): - latestUrl = 'http://www.joeandmonkey.com/' - stripUrl = latestUrl + '%s' + url = 'http://www.joeandmonkey.com/' + stripUrl = url + '%s' imageSearch = compile(r'"(/comic/[^"]+)"') prevSearch = compile(r"Previous") help = 'Index format: nnn' class JohnnyWander(_BasicScraper): - latestUrl = 'http://www.johnnywander.com/' - stripUrl = latestUrl + 'comics/%s' + url = 'http://www.johnnywander.com/' + stripUrl = url + 'comics/%s' imageSearch = compile(tagre("img", "src", r'(http://www\.johnnywander\.com/files/comics/\d+\.jpg)')) prevSearch = compile(tagre("a", "href", r'(/comics/\d+)') + r'prev') help = 'Index format: nnn' class JustAnotherEscape(_BasicScraper): - latestUrl = 'http://www.justanotherescape.com/' - stripUrl = latestUrl + 'index.cgi?date=%s' + url = 'http://www.justanotherescape.com/' + stripUrl = url + 'index.cgi?date=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.justanotherescape\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.justanotherescape\.com//index\.cgi\?date=\d+)') + tagre("img", "alt", "Previous Comic")) diff --git a/dosagelib/plugins/k.py b/dosagelib/plugins/k.py index 27a06a5d6..56914b330 100644 --- a/dosagelib/plugins/k.py +++ b/dosagelib/plugins/k.py @@ -7,7 +7,7 @@ from ..scraper import _BasicScraper from ..util import tagre class Key(_BasicScraper): - latestUrl = 'http://key.shadilyn.com/latestpage.html' + url = 'http://key.shadilyn.com/latestpage.html' stripUrl = 'http://key.shadilyn.com/pages/%s.html' imageSearch = compile(r'"((?:images/.+?)|(?:pages/images/.+?))"') prevSearch = compile(r']*>Previous Strip', IGNORECASE) help = 'Index format: yyyy-mm-dd' @@ -43,15 +43,15 @@ class KevinAndKell(_BasicScraper): class KhaosKomix(_BasicScraper): adult = True - latestUrl = 'http://www.khaoskomix.com/' - stripUrl = latestUrl + 'komix/%s' + url = 'http://www.khaoskomix.com/' + stripUrl = url + 'komix/%s' imageSearch = compile(tagre("img", "src", r'(http://www\.khaoskomix\.com/komiximg/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.khaoskomix\.com/komix/[^"]+)', after="Prev")) help = 'Index format: stripname' class KillerKomics(_BasicScraper): - latestUrl = 'http://www.killerkomics.com/web-comics/index_ang.cfm' + url = 'http://www.killerkomics.com/web-comics/index_ang.cfm' stripUrl = 'http://www.killerkomics.com/web-comics/%s.cfm' imageSearch = compile(r'') help = 'Index format: yyyymmdd' diff --git a/dosagelib/plugins/m.py b/dosagelib/plugins/m.py index dd56361f4..c85590ee8 100644 --- a/dosagelib/plugins/m.py +++ b/dosagelib/plugins/m.py @@ -10,79 +10,79 @@ from ..util import tagre # broken links - disable for now class _MadamAndEve(_BasicScraper): - latestUrl = 'http://www.madamandeve.co.za/week_of_cartns.php' + url = 'http://www.madamandeve.co.za/week_of_cartns.php' stripUrl = None imageSearch = compile(r'') prevSearch = compile(r'Prev') help = 'Index format: nnnn' class Meiosis(_BasicScraper): - latestUrl = 'http://meiosiswebcomic.com/' - stripUrl = latestUrl + '%s/' + url = 'http://meiosiswebcomic.com/' + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://meiosiswebcomic\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://meiosiswebcomic\.com/[^"]+)', after="navi-prev")) help = 'Index format: yyyy/mm/ddmmyyyy' class MacHall(_BasicScraper): - latestUrl = 'http://www.machall.com/' - stripUrl = latestUrl + 'view.php?date=%s' + url = 'http://www.machall.com/' + stripUrl = url + 'view.php?date=%s' imageSearch = compile(r']+?src=\'drop_shadow/previous.gif\'>') help = 'Index format: yyyy-mm-dd' class Melonpool(_BasicScraper): - latestUrl = 'http://www.melonpool.com/' - stripUrl = latestUrl + '?p=%s' + url = 'http://www.melonpool.com/' + stripUrl = url + '?p=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.melonpool\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.melonpool\.com/\?p=\d+)', after="prev")) help = 'Index format: n' class Misfile(_BasicScraper): - latestUrl = 'http://www.misfile.com/' - stripUrl = latestUrl + '?date=%s' + url = 'http://www.misfile.com/' + stripUrl = url + '?date=%s' imageSearch = compile(tagre("img", "src", r"(comics/[^']+)", quote="'")) prevSearch = compile(tagre("link", "href", r"([^']+)", quote="'", before="Previous")) help = 'Index format: yyyy-mm-dd' class MysteriesOfTheArcana(_BasicScraper): - latestUrl = 'http://mysteriesofthearcana.com/' - stripUrl = latestUrl + 'index.php?action=comics&cid=%s' + url = 'http://mysteriesofthearcana.com/' + stripUrl = url + 'index.php?action=comics&cid=%s' imageSearch = compile(tagre("img", "src", r'(image\.php\?type=com&i=[^"]+)')) prevSearch = compile(tagre("a", "href", r'(index\.php[^"]+)', after="navprevious")) help = 'Index format: n (unpadded)' diff --git a/dosagelib/plugins/n.py b/dosagelib/plugins/n.py index 6e8d061fd..7301f9d0c 100644 --- a/dosagelib/plugins/n.py +++ b/dosagelib/plugins/n.py @@ -9,23 +9,23 @@ from ..util import tagre class NamirDeiter(_BasicScraper): - latestUrl = 'http://www.namirdeiter.com/' - stripUrl = latestUrl + 'comics/index.php?date=%s' + url = 'http://www.namirdeiter.com/' + stripUrl = url + 'comics/index.php?date=%s' imageSearch = compile(tagre("img", "src", r"'?(http://www\.namirdeiter\.com/comics/\d+\.jpg)'?", quote="")) prevSearch = compile(tagre("a", "href", r'(http://www\.namirdeiter\.com/comics/index\.php\?date=\d+)', quote="'")+"Previous") help = 'Index format: yyyymmdd' class NeoEarth(_BasicScraper): - latestUrl = 'http://www.neo-earth.com/NE/' - stripUrl = latestUrl + 'index.php?date=%s' + url = 'http://www.neo-earth.com/NE/' + stripUrl = url + 'index.php?date=%s' imageSearch = compile(r'Previous') help = 'Index format: yyyy-mm-dd' class NewAdventuresOfBobbin(_BasicScraper): - latestUrl = 'http://www.bobbin-comic.com/bobbin_strips/' + url = 'http://www.bobbin-comic.com/bobbin_strips/' imageSearch = compile(tagre("a", "href", r'(\d+\.gif)')) multipleImagesPerStrip = True prevSearch = None @@ -33,23 +33,23 @@ class NewAdventuresOfBobbin(_BasicScraper): class NewWorld(_BasicScraper): - latestUrl = 'http://www.tfsnewworld.com/' - stripUrl = latestUrl + '%s' + url = 'http://www.tfsnewworld.com/' + stripUrl = url + '%s' imageSearch = compile(r'') help = 'Index format: nnn' class NobodyScores(_BasicScraper): - latestUrl = 'http://nobodyscores.loosenutstudio.com/' - stripUrl = latestUrl + 'index.php?id=%s' + url = 'http://nobodyscores.loosenutstudio.com/' + stripUrl = url + 'index.php?id=%s' imageSearch = compile(tagre("img", "src", r'(http://nobodyscores\.loosenutstudio\.com/comix/[^"]+)')) multipleImagesPerStrip = True prevSearch = compile(r'the one before ') diff --git a/dosagelib/plugins/nuklearpower.py b/dosagelib/plugins/nuklearpower.py index 7c26c7517..4a7d84df5 100644 --- a/dosagelib/plugins/nuklearpower.py +++ b/dosagelib/plugins/nuklearpower.py @@ -11,12 +11,12 @@ _prevSearch = compile(tagre("a", "href", r'([^"]+)') + "Previous") def add(name, shortname): baseUrl = 'http://www.nuklearpower.com/' - latestUrl = baseUrl + shortname + '/' + url = baseUrl + shortname + '/' classname = 'NuklearPower_%s' % name globals()[classname] = make_scraper(classname, name='NuklearPower/' + name, - latestUrl = latestUrl, + url = url, stripUrl = baseUrl + '%s', imageSearch = _imageSearch, prevSearch = _prevSearch, diff --git a/dosagelib/plugins/num.py b/dosagelib/plugins/num.py index 7504bad25..df6cd164b 100644 --- a/dosagelib/plugins/num.py +++ b/dosagelib/plugins/num.py @@ -10,8 +10,8 @@ from ..scraper import _BasicScraper class NineteenNinetySeven(_BasicScraper): name = '1997' - latestUrl = 'http://www.1977thecomic.com/' - stripUrl = latestUrl + '%s' + url = 'http://www.1977thecomic.com/' + stripUrl = url + '%s' 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 7852c1584..649366bd0 100644 --- a/dosagelib/plugins/o.py +++ b/dosagelib/plugins/o.py @@ -9,25 +9,26 @@ from ..util import tagre class OctopusPie(_BasicScraper): - starter = indirectStarter('http://www.octopuspie.com/', + url = 'http://www.octopuspie.com/' + starter = indirectStarter(url, compile(tagre("a", "href", r'(http://www\.octopuspie\.com/[^"]+)') + tagre("img", "src", r'http://www\.octopuspie\.com/junk/latest\.png'))) - stripUrl = 'http://www.octopuspie.com/%s' + 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")) help = 'Index format: yyyy-mm-dd/nnn-strip-name' class OddFish(_BasicScraper): - latestUrl = 'http://www.odd-fish.net/' - stripUrl = latestUrl + '%s/' + url = 'http://www.odd-fish.net/' + 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")) help = 'Index format: stripname' class OnTheEdge(_BasicScraper): - latestUrl = 'http://ontheedgecomics.com/' + url = 'http://ontheedgecomics.com/' stripUrl = 'http://ontheedgecomics.com/comic/%s' imageSearch = compile(r'') @@ -35,40 +36,41 @@ class OnTheEdge(_BasicScraper): class OneQuestion(_BasicScraper): - latestUrl = 'http://onequestioncomic.com/' - stripUrl = latestUrl + 'comic.php?strip_id=%s' + url = 'http://onequestioncomic.com/' + stripUrl = url + 'comic.php?strip_id=%s' imageSearch = compile(tagre("img", "src", r'(istrip_files/strips/\d+\.jpg)')) prevSearch = compile(tagre("a", "href", r'(comic\.php\?strip_id=\d+)') + tagre("img", "src", r'img/arrow_prev\.jpg')) help = 'Index format: n (unpadded)' class OurHomePlanet(_BasicScraper): - latestUrl = 'http://gdk.gd-kun.net/' - stripUrl = latestUrl + '%s.html' + url = 'http://gdk.gd-kun.net/' + stripUrl = url + '%s.html' imageSearch = compile(r']+?> \<\-  ') help = 'Index format: yyyymmdd' diff --git a/dosagelib/plugins/p.py b/dosagelib/plugins/p.py index d266bcde9..f2064475c 100644 --- a/dosagelib/plugins/p.py +++ b/dosagelib/plugins/p.py @@ -9,23 +9,23 @@ from ..util import tagre class PandyLand(_BasicScraper): - latestUrl = 'http://pandyland.net/' - stripUrl = latestUrl + '%s/' + url = 'http://pandyland.net/' + 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")) help = 'Index format: number' class PartiallyClips(_BasicScraper): - latestUrl = 'http://partiallyclips.com/' - stripUrl = latestUrl + '%s/' + url = 'http://partiallyclips.com/' + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://partiallyclips\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://partiallyclips\.com/[^"]+)', after="prev")) help = 'Index format: yyyy/mm/dd/stripname' class PastelDefender(_BasicScraper): - latestUrl = 'http://www.pasteldefender.com/coverbackcover.html' + url = 'http://www.pasteldefender.com/coverbackcover.html' stripUrl = 'http://www.pasteldefender.com/%s.html' imageSearch = compile(r'First Comic)Archives/Strip.+?|(?=.+?">Previous Comic)(?!.+?">First Comic)Strip.+?)"') help = 'Index format: n (unpadded)' class PennyAndAggie(_BasicScraper): - baseUrl = 'http://www.pennyandaggie.com/' - stripUrl = baseUrl + 'index.php?p=%s' + url = 'http://www.pennyandaggie.com/' + stripUrl = url + 'index.php?p=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.pennyandaggie\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r"(index\.php\?p=\d+)", quote="'") + tagre("img", "src", r'http://pennyandaggie\.com/images/previous_day\.gif', quote="")) - starter = indirectStarter(baseUrl, prevSearch) + starter = indirectStarter(url, prevSearch) help = 'Index format: n (unpadded)' class PennyArcade(_BasicScraper): - baseUrl = 'http://penny-arcade.com/comic/' - starter = bounceStarter(baseUrl, + url = 'http://penny-arcade.com/comic/' + starter = bounceStarter(url, compile(tagre("a", "href", r'(http://penny-arcade\.com/comic/[^"]+)', before="btnNext")) ) - stripUrl = baseUrl + '%s' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://art\.penny-arcade\.com/photos/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://penny-arcade\.com/comic/[^"]+)', before="btnPrev")) help = 'Index format: yyyy/mm/dd' @@ -67,32 +67,33 @@ class PennyArcade(_BasicScraper): class PeppermintSaga(_BasicScraper): - latestUrl = 'http://www.pepsaga.com/' - stripUrl = latestUrl + '?p=%s' + url = 'http://www.pepsaga.com/' + stripUrl = url + '?p=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.pepsaga\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.pepsaga\.com/\?p=\d+)', after="prev")) help = 'Index format: number' class PicPakDog(_BasicScraper): - latestUrl = 'http://www.picpak.net/' - stripUrl = latestUrl + 'comics/%s/' + url = 'http://www.picpak.net/' + stripUrl = url + 'comics/%s/' imageSearch = compile(tagre("img", "src", r'(http://www\.picpak\.net/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.picpak\.net/comics/[^"]+)', after="navi-prev")) help = 'Index format: yyyy/mm/dd/stripname' class Pixel(_BasicScraper): - latestUrl = 'http://pixelcomic.net/' - stripUrl = latestUrl + '%s.php' + url = 'http://pixelcomic.net/' + stripUrl = url + '%s.php' imageSearch = compile(tagre("img", "src", r'(\d+\.png)')) prevSearch = compile(tagre("a", "href", r'(http://pixelcomic\.net/\d+\.php)', before="prev")) help = 'Index format: nnn' class PiledHigherAndDeeper(_BasicScraper): - starter = bounceStarter('http://www.phdcomics.com/comics/archive.php', compile(r'')) - stripUrl = 'http://www.phdcomics.com/comics/archive.php?comicid=%s' + url = 'http://www.phdcomics.com/comics/archive.php' + starter = bounceStarter(url, compile(r'')) + stripUrl = url + '?comicid=%s' imageSearch = compile(r'') help = 'Index format: n (unpadded)' @@ -100,59 +101,59 @@ class PiledHigherAndDeeper(_BasicScraper): class Pimpette(_BasicScraper): - latestUrl = 'http://pimpette.ca/' - stripUrl = latestUrl + 'index.php?date=%s' + url = 'http://pimpette.ca/' + stripUrl = url + 'index.php?date=%s' imageSearch = compile(tagre("img", "src", r'(strips/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(index\.php\?date=\d+)') + "Previous") help = 'Index format: yyyymmdd' class Precocious(_BasicScraper): - baseUrl = 'http://www.precociouscomic.com/' - starter = indirectStarter(baseUrl, + url = 'http://www.precociouscomic.com/' + starter = indirectStarter(url, compile(tagre("a", "href", r'(/archive/comic/[^"]+)') + tagre("img", "src", r"/templates/precocious_main/images/next_arrow\.png")) ) - stripUrl = baseUrl + 'archive/comic/%s' + stripUrl = url + 'archive/comic/%s' imageSearch = compile(tagre("img", "src", r'(/comics/\d+\.jpg)')) prevSearch = compile(tagre("a", "href", r'(/archive/comic/[^"]+)') + tagre("img", "src", r"/templates/precocious_main/images/back_arrow\.png")) help = 'Index format: yyyy/mm/dd' class PvPonline(_BasicScraper): - latestUrl = 'http://pvponline.com/comic' - stripUrl = latestUrl + '%s' + url = 'http://pvponline.com/comic' + stripUrl = url + '%s' imageSearch = compile(tagre("img", "src", r'(http://newcdn\.pvponline\.com/img/comic/pvp[^"]+\.jpg)')) prevSearch = compile(tagre("a", "href", r'(http://pvponline\.com/comic/[^"]+)', after="Previous")) help = 'Index format: yyyy/mm/dd/stripname' class ProperBarn(_BasicScraper): - latestUrl = 'http://www.nitrocosm.com/go/gag/' - stripUrl = latestUrl + '%s/' + url = 'http://www.nitrocosm.com/go/gag/' + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://content\.nitrocosm\.com/gag/\d+\.[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.nitrocosm\.com/go/gag/\d+/)', after="nav_btn_previous")) help = 'Index format: nnn' class PunksAndNerds(_BasicScraper): - latestUrl = 'http://www.punksandnerds.com/' - stripUrl = latestUrl + '?p=%s' + url = 'http://www.punksandnerds.com/' + stripUrl = url + '?p=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.punksandnerds\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.punksandnerds\.com/\?p=\d+)', after="navi-prev")) help = 'Index format: nnn' class PunksAndNerdsOld(_BasicScraper): - latestUrl = 'http://original.punksandnerds.com/' - stripUrl = latestUrl + 'd/%s.html' + url = 'http://original.punksandnerds.com/' + stripUrl = url + 'd/%s.html' imageSearch = compile(r' src="(/comics/.+?)"') prevSearch = compile(r'>]+?>]+?src="/previouscomic.gif">') help = 'Index format: yyyymmdd' class PlanescapeSurvival(_BasicScraper): - latestUrl = 'http://planescapecomic.com/' - stripUrl = latestUrl + '%s.html' + url = 'http://planescapecomic.com/' + stripUrl = url + '%s.html' imageSearch = compile(r'src="(comics/.+?)"') prevSearch = compile(r'Previous[^>].+?navtable_01.gif') help = 'Index format: yyyy-mm-dd' class RedMeat(_BasicScraper): - starter = bounceStarter('http://www.redmeat.com/redmeat/current/index.html', compile(r'next')) + url = 'http://www.redmeat.com/redmeat/current/index.html' + starter = bounceStarter(url, compile(r'next')) stripUrl = 'http://www.redmeat.com/redmeat/%s/index.html' imageSearch = compile(r']*>') prevSearch = compile(r'previous') diff --git a/dosagelib/plugins/s.py b/dosagelib/plugins/s.py index 377bb1908..29e30d1f0 100644 --- a/dosagelib/plugins/s.py +++ b/dosagelib/plugins/s.py @@ -10,15 +10,15 @@ from ..util import tagre class SailorsunOrg(_BasicScraper): - latestUrl = 'http://sailorsun.org/' - stripUrl = latestUrl + '?p=%s' + url = 'http://sailorsun.org/' + 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")) help = 'Index format: n (unpadded)' class SamAndFuzzy(_BasicScraper): - latestUrl = 'http://www.samandfuzzy.com/' + url = 'http://www.samandfuzzy.com/' stripUrl = 'http://samandfuzzy.com/%s' imageSearch = compile(r'(/comics/.+?)" alt') prevSearch = compile(r'">]+?>') help = 'Index format: yymmdd' class SodiumEyes(_BasicScraper): - latestUrl = 'http://sodiumeyes.com/' - stripUrl = latestUrl + '%s/' + url = 'http://sodiumeyes.com/' + 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")) help = 'Index format: yyyy/mm/dd/stripname' @@ -127,7 +127,7 @@ class SodiumEyes(_BasicScraper): class Sorcery101(_BasicScraper): baseUrl = 'http://www.sorcery101.net/' - latestUrl = baseUrl + 'sorcery-101/' + url = baseUrl + 'sorcery-101/' stripUrl = baseUrl + 'sorcery101/%s/' imageSearch = compile(tagre("img", "src", r'(http://www\.sorcery101\.net/comics/sorcery101/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.sorcery101\.net/sorcery101/[^"]+)', after="previous-comic-link")) @@ -136,7 +136,7 @@ class Sorcery101(_BasicScraper): class SpareParts(_BasicScraper): baseUrl = 'http://www.sparepartscomics.com/' - latestUrl = baseUrl + 'comics/?date=20080328' + url = baseUrl + 'comics/?date=20080328' stripUrl = baseUrl + 'comics/index.php?date=%s' imageSearch = compile(tagre("img", "src", r'(http://www\.sparepartscomics\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(index\.php\?date=\d+)', quote="'") + "Previous Comic") @@ -144,16 +144,16 @@ class SpareParts(_BasicScraper): class Spinnerette(_BasicScraper): - latestUrl = 'http://www.spinnyverse.com/' - stripUrl = latestUrl + '%s/' + url = 'http://www.spinnyverse.com/' + 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")) help = 'Index format: number' class SPQRBlues(_BasicScraper): - latestUrl = 'http://spqrblues.com/IV/' - stripUrl = latestUrl + '?p=%s' + url = 'http://spqrblues.com/IV/' + 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")) help = 'Index format: number' @@ -161,8 +161,8 @@ class SPQRBlues(_BasicScraper): # XXX disallowed by robots.txt class _StationV3(_BasicScraper): - latestUrl = 'http://www.stationv3.com/' - stripUrl = latestUrl + 'd/%s.html' + url = 'http://www.stationv3.com/' + 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)') + tagre("img", "src", r'http://www\.stationv3\.com/images/previous\.gif')) @@ -170,32 +170,32 @@ class _StationV3(_BasicScraper): class Stubble(_BasicScraper): - latestUrl = 'http://stubblecomics.com/' - stripUrl = latestUrl + '?p=%s' + url = 'http://stubblecomics.com/' + 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")) help = 'Index format: number' class StrawberryDeathCake(_BasicScraper): - latestUrl = 'http://strawberrydeathcake.com/' - stripUrl = latestUrl + 'archive/%s/' + url = 'http://strawberrydeathcake.com/' + 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")) help = 'Index format: stripname' class SuburbanTribe(_BasicScraper): - latestUrl = 'http://www.pixelwhip.com/' - stripUrl = latestUrl + '?p=%s' + url = 'http://www.pixelwhip.com/' + 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")) help = 'Index format: nnnn' class SomethingPositive(_BasicScraper): - latestUrl = 'http://www.somethingpositive.net/' - stripUrl = latestUrl + 'sp%s.shtml' + url = 'http://www.somethingpositive.net/' + stripUrl = url + 'sp%s.shtml' imageSearch = compile(tagre("img", "src", r'(sp\d+\.png)')) prevSearch = compile(tagre("a", "href", r'(sp\d+\.shtml)') + "(?:" + tagre("img", "src", r'images/previous\.gif') + "|Previous)") @@ -204,11 +204,12 @@ class SomethingPositive(_BasicScraper): class SexyLosers(_BasicScraper): adult = True - stripUrl = 'http://www.sexylosers.com/%s.html' + url = 'http://www.sexylosers.com/' + stripUrl = url + '%s.html' imageSearch = compile(r'<<', IGNORECASE) help = 'Index format: nnn' - starter = indirectStarter('http://www.sexylosers.com/', + starter = indirectStarter(url, compile(r'SEXY LOSERS Latest SL Comic \(#\d+\)', IGNORECASE)) @classmethod @@ -219,7 +220,7 @@ class SexyLosers(_BasicScraper): class StarCrossdDestiny(_BasicScraper): - latestUrl = 'http://www.starcrossd.net/comic.html' + url = 'http://www.starcrossd.net/comic.html' stripUrl = 'http://www.starcrossd.net/archives/%s.html' imageSearch = compile(tagre("img", "src", r'(http://www\.starcrossd\.net/(?:ch1|strips|book2)/[^"]+)')) prevSearch = compile(r']*"[^"]*"[^>]*>prev', IGNORECASE) @@ -238,26 +239,26 @@ class StarCrossdDestiny(_BasicScraper): class Spamusement(_BasicScraper): - stripUrl = 'http://spamusement.com/index.php/comics/view/%s' + url = 'http://spamusement.com/' + stripUrl = url + 'index.php/comics/view/%s' imageSearch = compile(r'', IGNORECASE) help = 'Index format: n (unpadded)' - - starter = indirectStarter('http://spamusement.com/', prevSearch) + starter = indirectStarter(url, prevSearch) # XXX disallowed by robots.txt class _StrangeCandy(_BasicScraper): - latestUrl = 'http://www.strangecandy.net/' - stripUrl = latestUrl + 'd/%s.html' + url = 'http://www.strangecandy.net/' + stripUrl = url + 'd/%s.html' imageSearch = compile(tagre("img", "src", r'(/comics/\d+\.jpg)')) prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)') + tagre("img", "alt", "Previous comic")) help = 'Index format: yyyyddmm' class SMBC(_BasicScraper): - latestUrl = 'http://www.smbc-comics.com/' - stripUrl = latestUrl + 'index.php?db=comics&id=%s' + url = 'http://www.smbc-comics.com/' + stripUrl = url + 'index.php?db=comics&id=%s' imageSearch = compile(r'') prevSearch = compile(r'131,13,216,84"\n\s+href="(.+?)#comic"\n>', MULTILINE) help = 'Index format: nnnn' diff --git a/dosagelib/plugins/smackjeeves.py b/dosagelib/plugins/smackjeeves.py index 9d774a8e8..5f5dbd413 100644 --- a/dosagelib/plugins/smackjeeves.py +++ b/dosagelib/plugins/smackjeeves.py @@ -50,6 +50,7 @@ def add(name, url, description, adult, bounce): globals()[classname] = make_scraper(classname, name = 'SmackJeeves/' + name, adult = adult, + url = url, starter = _starter, prevUrlModifier = lambda cls, url: modifier(url), stripUrl = url + '%s/', diff --git a/dosagelib/plugins/snafu.py b/dosagelib/plugins/snafu.py index 2c72c9998..d8ca2c31f 100644 --- a/dosagelib/plugins/snafu.py +++ b/dosagelib/plugins/snafu.py @@ -15,7 +15,7 @@ def add(name, host): globals()[classname] = make_scraper(classname, name='SnafuComics/%s' % name, - latestUrl = baseUrl, + url = baseUrl, stripUrl = baseUrl + '?comic_id=%s', imageSearch = _imageSearch, prevSearch = _prevSearch, diff --git a/dosagelib/plugins/t.py b/dosagelib/plugins/t.py index 1f7f98356..e9cc800ad 100644 --- a/dosagelib/plugins/t.py +++ b/dosagelib/plugins/t.py @@ -9,23 +9,23 @@ from ..util import tagre class TheDevilsPanties(_BasicScraper): - latestUrl = 'http://thedevilspanties.com/' - stripUrl = latestUrl + 'archives/%s' + url = 'http://thedevilspanties.com/' + stripUrl = url + 'archives/%s' imageSearch = compile(tagre("img", "src", r'(http://cdn\.thedevilspanties\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/archives/\d+)', after="Previous")) help = 'Index format: number' class TheNoob(_BasicScraper): - latestUrl = 'http://www.thenoobcomic.com/index.php' - stripUrl = latestUrl + '?pos=%s' + url = 'http://www.thenoobcomic.com/index.php' + stripUrl = url + '?pos=%s' imageSearch = compile(tagre("img", "src", r'(/headquarters/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(\?pos=\d+)', before="comic_nav_previous_button")) help = 'Index format: nnnn' class TheOrderOfTheStick(_BasicScraper): - latestUrl = 'http://www.giantitp.com/comics/oots0863.html' + url = 'http://www.giantitp.com/comics/oots0863.html' stripUrl = 'http://www.giantitp.com/comics/oots%s.html' imageSearch = compile(r'') prevSearch = compile(r'') multipleImagesPerStrip = True @@ -47,8 +47,8 @@ class TheParkingLotIsFull(_BasicScraper): class TheWotch(_BasicScraper): - latestUrl = 'http://www.thewotch.com/' - stripUrl = latestUrl + '?date=%s' + url = 'http://www.thewotch.com/' + stripUrl = url + '?date=%s' imageSearch = compile(r"', IGNORECASE) prevSearch = compile(r' previous', IGNORECASE) help = 'Index format: twb or wb + n wg. twb1000' @@ -98,24 +98,24 @@ class TheWhiteboard(_BasicScraper): class HMHigh(_BasicScraper): name = 'TheFallenAngel/HMHigh' - latestUrl = 'http://www.thefallenangel.co.uk/hmhigh/' - stripUrl = latestUrl + '?id=%s' + url = 'http://www.thefallenangel.co.uk/hmhigh/' + stripUrl = url + '?id=%s' imageSearch = compile(r'Prev') help = 'Index format: nnn' class TheOuterQuarter(_BasicScraper): - latestUrl = 'http://theouterquarter.com/' - stripUrl = latestUrl + 'comic/%s' + url = 'http://theouterquarter.com/' + stripUrl = url + 'comic/%s' imageSearch = compile(r'

]+?>Previous') help = 'Index format: strip-name' class WeCanSleepTomorrow(_BasicScraper): - latestUrl = 'http://wecansleeptomorrow.com/' - stripUrl = latestUrl + '%s/' + url = 'http://wecansleeptomorrow.com/' + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://wecansleeptomorrow\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(http://wecansleeptomorrow\.com/[^"]+)', after="prev")) help = 'Index format: yyyy/mm/dd/stripname' class Wondermark(_BasicScraper): - latestUrl = 'http://wondermark.com/' - stripUrl = latestUrl + '%s/' + url = 'http://wondermark.com/' + stripUrl = url + '%s/' imageSearch = compile(r'') help = 'Index format: nnn' diff --git a/dosagelib/plugins/webcomiceu.py b/dosagelib/plugins/webcomiceu.py index 5bf177a03..caeaaefe1 100644 --- a/dosagelib/plugins/webcomiceu.py +++ b/dosagelib/plugins/webcomiceu.py @@ -9,12 +9,12 @@ _prevSearch = compile(tagre("a", "href", r'(\?id=\d+)') + tagre("img", "src", r' _imageSearch = compile(tagre("img", "src", r'([^"]+/img/comic/[^"]+)', after="comicimg")) def add(name, shortname): - latestUrl = 'http://%s.webcomic.eu/' % shortname + url = 'http://%s.webcomic.eu/' % shortname classname = 'WebcomicEu_%s' % name globals()[classname] = make_scraper(classname, name = 'WebcomicEu/' + name, - latestUrl = latestUrl, - stripUrl = latestUrl + '?id=%s', + url = url, + stripUrl = url + '?id=%s', imageSearch = _imageSearch, prevSearch = _prevSearch, help = 'Index format: number', diff --git a/dosagelib/plugins/webcomicnation.py b/dosagelib/plugins/webcomicnation.py index 4046ebec5..7f2270eb8 100644 --- a/dosagelib/plugins/webcomicnation.py +++ b/dosagelib/plugins/webcomicnation.py @@ -14,7 +14,7 @@ def add(name, subpath): classname = 'WebcomicsNation_%s' % name globals()[classname] = make_scraper(classname, name = 'WebcomicsNation/' + name, - latestUrl = baseUrl + subpath, + url = baseUrl + subpath, stripUrl = baseUrl + '?view=archive&chapter=%s', imageSearch = _imageSearch, multipleImagesPerStrip = True, diff --git a/dosagelib/plugins/wlpcomics.py b/dosagelib/plugins/wlpcomics.py index 889967111..2436f96bc 100644 --- a/dosagelib/plugins/wlpcomics.py +++ b/dosagelib/plugins/wlpcomics.py @@ -23,6 +23,7 @@ def add(name, path): globals()[classname] = make_scraper(classname, name = 'WLP/' + name, + url = baseUrl, starter = bounceStarter(baseUrl, _nextSearch), stripUrl = baseUrl + '%s.html', imageSearch = _imageSearch, diff --git a/dosagelib/plugins/x.py b/dosagelib/plugins/x.py index 09100a5a3..1311314dd 100644 --- a/dosagelib/plugins/x.py +++ b/dosagelib/plugins/x.py @@ -10,9 +10,9 @@ from ..util import tagre class xkcd(_BasicScraper): - baseUrl = 'http://xkcd.com/' - starter = bounceStarter(baseUrl, compile(tagre("a", "href", r'(/\d+/)', before="next"))) - stripUrl = baseUrl + '%s/' + url = 'http://xkcd.com/' + starter = bounceStarter(url, compile(tagre("a", "href", r'(/\d+/)', before="next"))) + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://imgs\.xkcd\.com/comics/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(/\d+/)', before="prev")) help = 'Index format: n (unpadded)' diff --git a/dosagelib/plugins/y.py b/dosagelib/plugins/y.py index 71193b371..baf92e279 100644 --- a/dosagelib/plugins/y.py +++ b/dosagelib/plugins/y.py @@ -8,8 +8,8 @@ from ..util import tagre class YAFGC(_BasicScraper): - latestUrl = 'http://yafgc.net/' - stripUrl = latestUrl + '?id=%s' + url = 'http://yafgc.net/' + stripUrl = url + '?id=%s' imageSearch = compile(tagre("img", "src", r'(http://yafgc\.net/img/comic/\d+\.jpg)')) prevSearch = compile(tagre("a", "href", r'(http://yafgc\.net/\?id=\d+)') + tagre("img", "src", r'/img/navbar/go_to_previous\.gif')) @@ -17,8 +17,8 @@ class YAFGC(_BasicScraper): class YouSayItFirst(_BasicScraper): - latestUrl = 'http://www.yousayitfirst.com/' - stripUrl = latestUrl + 'comics/index.php?date=%s' + url = 'http://www.yousayitfirst.com/' + stripUrl = url + 'comics/index.php?date=%s' imageSearch = compile(tagre("img", "src", r"(http://www\.yousayitfirst\.com/comics/[^>']+)", quote="'?")) prevSearch = compile(tagre("a", "href", r'(http://www\.yousayitfirst\.com/comics/index\.php\?date=\d+)', quote="'") + "Previous") help = 'Index format: yyyymmdd' diff --git a/dosagelib/plugins/z.py b/dosagelib/plugins/z.py index bb16bc59a..5dba51e80 100644 --- a/dosagelib/plugins/z.py +++ b/dosagelib/plugins/z.py @@ -9,16 +9,16 @@ from ..helpers import bounceStarter class ZapComic(_BasicScraper): - latestUrl = 'http://www.zapcomic.com/' - stripUrl = latestUrl + '%s/' + url = 'http://www.zapcomic.com/' + stripUrl = url + '%s/' imageSearch = compile(tagre("img", "src", r'(http://www\.zapcomic\.com\?comic_object=\d+)')) prevSearch = compile(tagre("a", "href", r'(http://www\.zapcomic\.com/[^"]+)', after="previous-comic-link")) help = 'Index format: yyyy/mm/nnn-stripname' class Zapiro(_BasicScraper): - baseUrl = 'http://www.mg.co.za/zapiro/' - starter = bounceStarter(baseUrl, + url = 'http://www.mg.co.za/zapiro/' + starter = bounceStarter(url, compile(tagre("a", "href", r'(http://mg\.co\.za/cartoon/[^"]+)')+"Newer")) stripUrl = 'http://mg.co.za/cartoon/%s' imageSearch = compile(tagre("img", "src", r'(http://cdn\.mg\.co\.za/crop/content/cartoons/[^"]+)')) @@ -32,16 +32,16 @@ class Zapiro(_BasicScraper): class ZebraGirl(_BasicScraper): - latestUrl = 'http://www.zebragirl.net/' - stripUrl = latestUrl + '?date=%s' + url = 'http://www.zebragirl.net/' + stripUrl = url + '?date=%s' imageSearch = compile(tagre("img", "src", r"(comics/[^']+)", quote="'")) prevSearch = compile(tagre("link", "href", r"(/\?date=[^']+)", quote="'", before='Previous')) help = 'Index format: yyyy-mm-dd' class ZombieHunters(_BasicScraper): - latestUrl = 'http://www.thezombiehunters.com/' - stripUrl = latestUrl + '?strip_id=%s' + url = 'http://www.thezombiehunters.com/' + stripUrl = url + '?strip_id=%s' imageSearch = compile(tagre("img", "src", r'(/istrip_files/strips/[^"]+)')) prevSearch = compile(tagre("a", "href", r'(\?strip_id=\d+)') + tagre("img", "id", "prevcomic")) help = 'Index format: n(unpadded)' diff --git a/dosagelib/scraper.py b/dosagelib/scraper.py index 3c94a814f..09a31ecd2 100644 --- a/dosagelib/scraper.py +++ b/dosagelib/scraper.py @@ -127,7 +127,7 @@ class _BasicScraper(object): @classmethod def starter(cls): """Get starter URL from where to scrape comic strips.""" - return cls.latestUrl + return cls.url @classmethod def namer(cls, imageUrl, pageUrl): diff --git a/scripts/mktestpage.py b/scripts/mktestpage.py index 3a7f2e7d1..1550e08e4 100755 --- a/scripts/mktestpage.py +++ b/scripts/mktestpage.py @@ -172,15 +172,11 @@ def get_testentry(line): entry = { "status": Status.ok if line.startswith(". ") else Status.error, "name": name, - "url": "", + "url": scraper.url, "description": scraper.description, "error": None, "adult": scraper.adult, } - try: - entry["url"] = scraper.starter() - except Exception as msg: - print("WARNING:", msg, file=sys.stderr) return key, entry