From 13a34098547b028093ad3a997ec8729521c3a524 Mon Sep 17 00:00:00 2001 From: Tobias Gruetzmacher Date: Sun, 17 Apr 2016 19:42:43 +0200 Subject: [PATCH] Remove some comics that are gone or block us. --- dosagelib/plugins/b.py | 108 ---------------------------------- dosagelib/plugins/c.py | 42 ------------- dosagelib/plugins/creators.py | 8 --- dosagelib/plugins/d.py | 9 --- dosagelib/plugins/e.py | 16 ----- dosagelib/plugins/f.py | 23 -------- dosagelib/plugins/l.py | 19 ------ dosagelib/plugins/n.py | 26 +------- dosagelib/plugins/o.py | 22 ------- dosagelib/plugins/t.py | 30 ---------- 10 files changed, 1 insertion(+), 302 deletions(-) diff --git a/dosagelib/plugins/b.py b/dosagelib/plugins/b.py index 6f6eb331d..2927cf03b 100644 --- a/dosagelib/plugins/b.py +++ b/dosagelib/plugins/b.py @@ -14,14 +14,6 @@ from .common import (_ComicControlScraper, _WordPressScraper, WP_PREV_SEARCH, xpath_class) -class BackwaterPlanet(_BasicScraper): - url = 'http://www.backwaterplanet.com/current.htm' - stripUrl = 'http://www.backwaterplanet.com/archive/bwp%s.htm' - imageSearch = compile(r'') - prevSearch = compile(r']+Previous') - help = 'Index format: n (unpadded)' - - @classmethod - def prevUrlModifier(cls, prevUrl): - if prevUrl: - return prevUrl.replace("www.boxerhockey.com", "boxerhockey.fireball20xl.com") - - class BoyOnAStickAndSlither(_BasicScraper): url = 'http://www.boasas.com/' stripUrl = url + 'page/%s' @@ -266,54 +206,6 @@ class BratHalla(_WordPressScraper): url = 'http://brat-halla.com/' -class BrentalFloss(_BasicScraper): - url = 'http://brentalflossthecomic.com/' - stripUrl = url + '?id=%s' - firstStripUrl = stripUrl % '1' - imageSearch = compile(tagre("img", "src", r'([^"]*/img/comic/[^"]*)')) - prevSearch = compile(tagre("a", "href", r'([^"]*)') + "Prev") - help = 'Index format: n' - - @classmethod - def prevUrlModifier(cls, prevUrl): - if prevUrl: - return prevUrl.replace("www.", "") - - -class BrentalFlossFit(BrentalFloss): - name = 'BrentalFloss/FlossedInTime' - url = 'http://brentalflossthecomic.com/fit/' - stripUrl = url + '?id=%s' - firstStripUrl = stripUrl % '1' - - @classmethod - def prevUrlModifier(cls, prevUrl): - if prevUrl: - return prevUrl.replace("\n", "") - - @classmethod - def imageUrlModifier(cls, url, data): - if url: - return url.replace("\n", "") - - -class BrentalFlossGuest(BrentalFloss): - name = 'BrentalFloss/GuestComics' - url = 'http://brentalflossthecomic.com/guestcomics/' - stripUrl = url + '?id=%s' - firstStripUrl = stripUrl % '1' - - -class BrightlyWound(_BasicScraper): - baseUrl = 'http://www.brightlywound.com/' - url = baseUrl + '?comic=137' - stripUrl = baseUrl + '?comic=%s' - firstStripUrl = stripUrl % '0' - imageSearch = compile(tagre("img", "src", r"(comic/[^']+)", quote="'")) - prevSearch = compile(r'
<.+?/aprev.gif"') - help = 'Index format: nnn' - - class DeepFried(_BasicScraper): url = 'http://www.whatisdeepfried.com/' rurl = escape(url) diff --git a/dosagelib/plugins/e.py b/dosagelib/plugins/e.py index fb58dc10a..993f8495b 100644 --- a/dosagelib/plugins/e.py +++ b/dosagelib/plugins/e.py @@ -151,22 +151,6 @@ class EmergencyExit(_BasicScraper): help = 'Index format: n' -class Eriadan(_BasicScraper): - url = 'http://www.shockdom.com/webcomics/eriadan/' - rurl = escape(url) - stripUrl = url + '%s/' - multipleImagesPerStrip = True - imageSearch = compile(tagre("img", "src", r'(%sfiles/[^"]+)' % rurl, - after='width="[68]00"')) - prevSearch = compile(tagre("a", "href", r'([^"]+)', after="prev")) - help = 'Index format: yyyy/mm/dd/nnn (unpadded)' - - def shouldSkipUrl(self, url, data): - return url in ( - self.stripUrl % "2013/04/02/istruzioni-per-il-non-uso", # video - ) - - class ErrantStory(_BasicScraper): url = 'http://www.errantstory.com/' stripUrl = url + '%s' diff --git a/dosagelib/plugins/f.py b/dosagelib/plugins/f.py index 8ab4306b3..b39677d4d 100644 --- a/dosagelib/plugins/f.py +++ b/dosagelib/plugins/f.py @@ -9,7 +9,6 @@ from re import compile, escape, IGNORECASE from ..util import tagre from ..scraper import _BasicScraper, _ParserScraper from ..helpers import indirectStarter -from .common import _WordPressScraper class FalconTwin(_BasicScraper): @@ -40,17 +39,6 @@ class FauxPas(_BasicScraper): help = 'Index format: nnn' -class FeyWinds(_BasicScraper): - baseUrl = 'http://kitsune.rydia.net/' - url = baseUrl + 'index.html' - stripUrl = baseUrl + 'comic/page.php?id=%s' - imageSearch = compile(r"(../comic/pages//.+?)'") - prevSearch = compile(r"(page.php\?id=.+?)'.+?navprevious.png") - latestSearch = compile(r'(comic/page.php\?id.+?)"') - help = 'Index format: n (unpadded)' - starter = indirectStarter - - class FilibusterCartoons(_BasicScraper): url = 'http://www.filibustercartoons.com/' rurl = escape(url) @@ -130,10 +118,6 @@ class ForLackOfABetterComic(_BasicScraper): help = 'Index format: number' -class FowlLanguage(_WordPressScraper): - url = 'http://www.fowllanguagecomics.com/' - - class Fragile(_ParserScraper): url = 'http://www.fragilestory.com/' imageSearch = '//div[@id="comic_strip"]/a[@class="nobg"]/img' @@ -141,13 +125,6 @@ class Fragile(_ParserScraper): firstStripUrl = url + 'strips/chapter_01' -class FragileSpanish(_ParserScraper): - url = 'http://es.fragilestory.com/' - imageSearch = '//div[@id="content_comics"]/a[@class="nobg"]/img' - prevSearch = '//a[@class="comicnav" and contains(text(),"Anterior")]' - lang = 'es' - - class FredoAndPidjin(_BasicScraper): url = 'http://www.pidjin.net/' stripUrl = url + '%s/' diff --git a/dosagelib/plugins/l.py b/dosagelib/plugins/l.py index 71ce04a05..fd5f6f6e2 100644 --- a/dosagelib/plugins/l.py +++ b/dosagelib/plugins/l.py @@ -75,25 +75,6 @@ class LetsSpeakEnglish(_ComicControlScraper): url = 'http://www.marycagle.com' -class Lint(_BasicScraper): - url = 'http://www.purnicellin.com/lint/' - rurl = escape(url) - stripUrl = url + '%s/' - firstStripUrl = stripUrl % '2004/01/10/01102004' - imageSearch = compile(r'') - help = 'Index format: yyyy/mm/dd/num-name' - - -class LinuxComFridayFunnies(_BasicScraper): - url = 'https://www.linux.com/news/friday-funnies/' - stripUrl = url + '%s' - firstStripUrl = stripUrl % 'the-road-to-japan' - imageSearch = compile(tagre("img", "src", r'(/news/friday-funnies/episode/[^"]+\?format=image[^"]+)')) - prevSearch = compile(tagre("a", "href", r'(/news/friday-funnies/[^"]+)') + "Previous") - help = 'Index format: stripname' - - class LittleGamers(_BasicScraper): url = 'http://www.little-gamers.com/' stripUrl = url + '%s/' diff --git a/dosagelib/plugins/n.py b/dosagelib/plugins/n.py index 91a5715ed..64bedbbda 100644 --- a/dosagelib/plugins/n.py +++ b/dosagelib/plugins/n.py @@ -7,7 +7,7 @@ from __future__ import absolute_import, division, print_function from re import compile, escape -from ..scraper import _BasicScraper, _ParserScraper +from ..scraper import _BasicScraper from ..helpers import indirectStarter from ..util import tagre from .common import (_ComicControlScraper, _WordPressScraper, WP_LATEST_SEARCH, @@ -49,23 +49,6 @@ class Nedroid(_WordPressScraper): prevSearch = '//a[@rel="prev"]' -class NekkoAndJoruba(_BasicScraper): - url = 'http://www.nekkoandjoruba.com/' - stripUrl = url + '?p=%s' - firstStripUrl = stripUrl % '7' - imageSearch = compile(r'') - help = 'Index format: nnn' - - -class NekoTheKitty(_ParserScraper): - url = 'http://www.nekothekitty.net/' - stripUrl = url + 'comics/%s' - firstStripUrl = stripUrl % '936393/001-video-games' - imageSearch = '//a[@id="comic_image"]/img' - prevSearch = '//a[text()="<-"]' - - class NeoEarth(_BasicScraper): url = 'http://www.neo-earth.com/NE/' stripUrl = url + 'index.php?date=%s' @@ -80,13 +63,6 @@ class NerfNow(_WordPressScraper): prevSearch = '//li[@id="nav_previous"]/a' -class NewAdventuresOfBobbin(_BasicScraper): - url = 'http://www.bobbin-comic.com/bobbin_strips/' - imageSearch = compile(tagre("a", "href", r'(\d+\.gif)')) - multipleImagesPerStrip = True - help = 'Index format: none' - - class NewWorld(_BasicScraper): url = 'http://www.tfsnewworld.com/' stripUrl = url + '%s/' diff --git a/dosagelib/plugins/o.py b/dosagelib/plugins/o.py index c81fbe563..8723e97d4 100644 --- a/dosagelib/plugins/o.py +++ b/dosagelib/plugins/o.py @@ -65,16 +65,6 @@ class OmakeTheater(_ParserScraper): help = 'Index format: number (unpadded)' -class OneQuestion(_BasicScraper): - url = 'http://onequestioncomic.com/' - stripUrl = url + 'comic.php?strip_id=%s' - firstStripUrl = stripUrl % '1' - imageSearch = compile(tagre("img", "src", r'((?:\.\./)?istrip_files/strips/\d+\.\w{3,4})')) - 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 OnTheEdge(_WordPressScraper): url = 'http://ontheedgecomics.com/' firstStripUrl = 'http://ontheedgecomics.com/comic/ote0001/' @@ -106,18 +96,6 @@ class Optipess(_WordPressScraper): textSearch = '//div[@id="comic"]//img/@alt' -class OrnerBoy(_BasicScraper): - url = 'http://www.orneryboy.com/' - rurl = escape(url) - stripUrl = url + 'index.php?comicID=%s' - firstStripUrl = stripUrl % '1' - imageSearch = compile(tagre("img", "src", r'(comics/\d+\.[^"]+)')) - prevSearch = compile(tagre("a", "href", - r'(%sindex\.php\?comicID=\d+)' % rurl) + - tagre("img", "src", r'images/prev_a\.gif')) - help = 'Index format: number' - - class OurHomePlanet(_BasicScraper): url = 'http://gdk.gd-kun.net/' stripUrl = url + '%s.html' diff --git a/dosagelib/plugins/t.py b/dosagelib/plugins/t.py index 90f39c1ee..848a6c50c 100644 --- a/dosagelib/plugins/t.py +++ b/dosagelib/plugins/t.py @@ -90,16 +90,6 @@ class TheOrderOfTheStick(_BasicScraper): return pageUrl.rsplit('/', 1)[-1][:-5] -class TheOuterQuarter(_BasicScraper): - url = 'http://theouterquarter.com/' - rurl = escape(url) - stripUrl = url + 'comic/%s' - firstStripUrl = stripUrl % 'oq-the-first-take/4' - imageSearch = compile(r'