Fix a bunch of modules.

This commit is contained in:
Tobias Gruetzmacher 2017-04-16 01:06:41 +02:00
parent 2d9b9e36c8
commit 0973570295
10 changed files with 21 additions and 37 deletions

View file

@ -102,12 +102,10 @@ class CatVersusHuman(_ParserScraper):
starter = indirectStarter starter = indirectStarter
class ChainsawSuit(_ParserScraper): class ChainsawSuit(_WordPressScraper):
url = 'http://chainsawsuit.com/' url = 'http://chainsawsuit.com/comic/'
rurl = escape(url) stripUrl = url + 'archive/%s/'
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2008/03/12/strip-338' firstStripUrl = stripUrl % '2008/03/12/strip-338'
imageSearch = '//div[@id="comic"]//img'
prevSearch = '//img[@alt="previous"]/..' prevSearch = '//img[@alt="previous"]/..'
help = 'Index format: yyyy/mm/dd/stripname' help = 'Index format: yyyy/mm/dd/stripname'

View file

@ -36,7 +36,6 @@ class ComicSherpa(_ParserScraper):
cls('AcornPark', 'csdfe'), cls('AcornPark', 'csdfe'),
cls('Adulting', 'cskky'), cls('Adulting', 'cskky'),
cls('AJAndMagnus', 'csrxy'), cls('AJAndMagnus', 'csrxy'),
cls('AlisonWard', 'cspgh'),
cls('AllInGoodTime', 'csjhr'), cls('AllInGoodTime', 'csjhr'),
cls('AmandaTheGreat', 'cssyr'), cls('AmandaTheGreat', 'cssyr'),
cls('AndNow', 'csnxr'), cls('AndNow', 'csnxr'),
@ -48,7 +47,6 @@ class ComicSherpa(_ParserScraper):
cls('BatchRejection', 'csgny'), cls('BatchRejection', 'csgny'),
cls('Bazoobee', 'csfos'), cls('Bazoobee', 'csfos'),
cls('BeMisery', 'csiiq'), cls('BeMisery', 'csiiq'),
cls('BeneathTheFerns', 'csgzn'),
cls('BigJim', 'csiao'), cls('BigJim', 'csiao'),
cls('Bluebonnets', 'cston'), cls('Bluebonnets', 'cston'),
cls('BlueSkiesToons', 'csfoy'), cls('BlueSkiesToons', 'csfoy'),
@ -93,7 +91,6 @@ class ComicSherpa(_ParserScraper):
cls('GIRTH', 'csbjw'), cls('GIRTH', 'csbjw'),
cls('GrandmaSnoops', 'csscq'), cls('GrandmaSnoops', 'csscq'),
cls('GrannyAnny', 'cskpg'), cls('GrannyAnny', 'cskpg'),
cls('Gravy', 'csgvd'),
cls('GreenPieces', 'csnwy'), cls('GreenPieces', 'csnwy'),
cls('GunstonStreet', 'csgru'), cls('GunstonStreet', 'csgru'),
cls('HallEditorialCartoons', 'csgzx'), cls('HallEditorialCartoons', 'csgzx'),
@ -116,7 +113,6 @@ class ComicSherpa(_ParserScraper):
cls('LiliAndDerek', 'csvsy'), cls('LiliAndDerek', 'csvsy'),
cls('LilleysSillies', 'cstka'), cls('LilleysSillies', 'cstka'),
cls('LimboRoad', 'csfpp'), cls('LimboRoad', 'csfpp'),
cls('Loose', 'csmyn'),
cls('LumAndAbner', 'cscji'), cls('LumAndAbner', 'cscji'),
cls('MadDogGhettoCop', 'cskwp'), cls('MadDogGhettoCop', 'cskwp'),
cls('MarysNature', 'csogt'), cls('MarysNature', 'csogt'),

View file

@ -10,7 +10,7 @@ from re import compile, escape
from ..scraper import _BasicScraper, _ParserScraper from ..scraper import _BasicScraper, _ParserScraper
from ..helpers import indirectStarter, bounceStarter, xpath_class from ..helpers import indirectStarter, bounceStarter, xpath_class
from ..util import tagre from ..util import tagre
from .common import _WordPressScraper from .common import _WPNaviIn
class DamnLol(_ParserScraper): class DamnLol(_ParserScraper):
@ -56,10 +56,9 @@ class DarthsAndDroids(_BasicScraper):
imageSearch = compile(tagre("img", "src", r'(/comics/darths\d\d\d\d\.jpg)')) imageSearch = compile(tagre("img", "src", r'(/comics/darths\d\d\d\d\.jpg)'))
class DasLebenIstKeinPonyhof(_WordPressScraper): class DasLebenIstKeinPonyhof(_WPNaviIn):
url = 'http://sarahburrini.com/wordpress/' url = 'http://sarahburrini.com/wordpress/'
firstStripUrl = url + 'comic/mein-erster-webcomic/' firstStripUrl = url + 'comic/mein-erster-webcomic/'
multipleImagesPerStrip = True
lang = 'de' lang = 'de'

View file

@ -1,7 +1,7 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs
# Copyright (C) 2012-2014 Bastian Kleineidam # Copyright (C) 2012-2014 Bastian Kleineidam
# Copyright (C) 2015-2016 Tobias Gruetzmacher # Copyright (C) 2015-2017 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function from __future__ import absolute_import, division, print_function
@ -111,7 +111,6 @@ class KeenSpot(_ParserScraper):
cls('WeirdingWillows', 'weirdingwillows'), cls('WeirdingWillows', 'weirdingwillows'),
cls('WICKEDPOWERED', 'wickedpowered'), cls('WICKEDPOWERED', 'wickedpowered'),
cls('WisdomOfMoo', 'wisdomofmoo'), cls('WisdomOfMoo', 'wisdomofmoo'),
cls('Yirmumah', 'yirmumah', path="%s/"),
# END AUTOUPDATE # END AUTOUPDATE
) )

View file

@ -1,7 +1,7 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs
# Copyright (C) 2012-2014 Bastian Kleineidam # Copyright (C) 2012-2014 Bastian Kleineidam
# Copyright (C) 2015-2016 Tobias Gruetzmacher # Copyright (C) 2015-2017 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function from __future__ import absolute_import, division, print_function
@ -51,14 +51,6 @@ class LasLindas(_BasicScraper):
help = 'Index format: stripname' help = 'Index format: stripname'
class LastNerdsOnEarth(_ParserScraper):
baseUrl = 'http://www.lastnerdsonearth.com/'
url = baseUrl + 'latest/'
firstStripUrl = baseUrl + 'ch1p1'
imageSearch = '//div[@id="content"]/a/img'
prevSearch = '//div[@id="comicnav"]/a[img[contains(@src, "nav-prev")]]'
class LeastICouldDo(_BasicScraper): class LeastICouldDo(_BasicScraper):
url = 'http://www.leasticoulddo.com/' url = 'http://www.leasticoulddo.com/'
rurl = escape(url) rurl = escape(url)

View file

@ -113,6 +113,7 @@ class Meiosis(_WordPressScraper):
class Melonpool(_WordPressScraper): class Melonpool(_WordPressScraper):
url = 'http://www.melonpool.com/' url = 'http://www.melonpool.com/'
allow_errors = (500,)
class MenageA3(_BasicScraper): class MenageA3(_BasicScraper):

View file

@ -182,15 +182,11 @@ class PokeyThePenguin(_ParserScraper):
return "%s/index%d.html" % (prefix, num) return "%s/index%d.html" % (prefix, num)
class PoorlyDrawnLines(_BasicScraper): class PoorlyDrawnLines(_ParserScraper):
url = 'http://poorlydrawnlines.com/comic/' url = 'http://poorlydrawnlines.com/comic/'
rurl = escape(url) firstStripUrl = url + 'campus-characters/'
stripUrl = url + '%s' imageSearch = '//div[%s]//img' % xpath_class('comic')
firstStripUrl = stripUrl % 'campus-characters/' prevSearch = '//a[@rel="prev"]'
imageSearch = compile(tagre("img", "src", r'(http://poorlydrawnlines\.com/wp-content/uploads/\d+/\d+/[^"]+)'))
prevSearch = compile(tagre("li", "class", r'previous') +
tagre("a", "href", r'(%s[^"]+)' % rurl))
help = 'Index Format: name'
class Precocious(_ParserScraper): class Precocious(_ParserScraper):

View file

@ -161,10 +161,11 @@ class TwoGuysAndGuy(_BasicScraper):
class Twokinds(_ParserScraper): class Twokinds(_ParserScraper):
url = 'http://twokinds.keenspot.com/' url = 'http://twokinds.keenspot.com/'
imageSearch = ('//p[@id="cg_img"]//img', stripUrl = url + 'comic/%s/'
'//article/p//img') firstStripUrl = stripUrl % '1'
prevSearch = ('//a[@id="cg_back"]', imageSearch = '//article[%s]//img' % xpath_class('comic')
'//a[%s]' % xpath_class('navprev')) prevSearch = '//a[%s]' % xpath_class('navprev')
help = 'Index format: n (unpadded)'
class TwoLumps(_BasicScraper): class TwoLumps(_BasicScraper):

View file

@ -20,9 +20,11 @@ class ComicSherpaUpdater(ComicListUpdater):
'Rufus', 'Rufus',
# too short # too short
'BeneathTheFerns',
'BillyAndCo', 'BillyAndCo',
'BuffaloChips', 'BuffaloChips',
'Crawdiddy', 'Crawdiddy',
'Gravy',
'NewFeature', 'NewFeature',
) )

View file

@ -2,7 +2,7 @@
# -*- coding: utf-8 -*- # -*- coding: utf-8 -*-
# Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs # Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs
# Copyright (C) 2012-2014 Bastian Kleineidam # Copyright (C) 2012-2014 Bastian Kleineidam
# Copyright (C) 2015-2016 Tobias Gruetzmacher # Copyright (C) 2015-2017 Tobias Gruetzmacher
""" """
Script to get a list of KeenSpot comics and save the info in a Script to get a list of KeenSpot comics and save the info in a
JSON file for further processing. JSON file for further processing.
@ -26,6 +26,7 @@ class KeenSpotUpdater(ComicListUpdater):
"LastBlood", "LastBlood",
"TheGodChild", "TheGodChild",
"Twokinds", "Twokinds",
"Yirmumah",
) )
extra = { extra = {
@ -34,7 +35,6 @@ class KeenSpotUpdater(ComicListUpdater):
'MysticRevolution': 'path="?cid=%s"', 'MysticRevolution': 'path="?cid=%s"',
'PunchAnPie': 'path="daily/%s.html"', 'PunchAnPie': 'path="daily/%s.html"',
'ShockwaveDarkside': 'path="2d/%s.html"', 'ShockwaveDarkside': 'path="2d/%s.html"',
'Yirmumah': 'path="%s/"',
} }
def collect_results(self): def collect_results(self):