Minor URL fixes, switched some modules to https

This commit is contained in:
Tobias Gruetzmacher 2019-12-31 01:44:19 +01:00
parent be41a692ba
commit e5cb27ffa4
16 changed files with 31 additions and 32 deletions

View file

@ -348,8 +348,8 @@ class Annyseed(_ParserScraper):
class ApartmentForTwo(_ParserScraper): class ApartmentForTwo(_ParserScraper):
url = 'http://www.apartmentfor2.com/' url = 'https://apartmentfor2.com/'
stripUrl = url + 'index.php?date=%s' stripUrl = url + 'comics/index.php?date=%s'
firstStripUrl = url + 'comics/' firstStripUrl = url + 'comics/'
imageSearch = '//a/img[contains(@src, "comics/")]' imageSearch = '//a/img[contains(@src, "comics/")]'
prevSearch = '//a[./img[contains(@src, "previous")]]' prevSearch = '//a[./img[contains(@src, "previous")]]'

View file

@ -283,8 +283,8 @@ class BusinessCat(_WPNaviIn):
class ButImACatPerson(_WordPressScraper): class ButImACatPerson(_WordPressScraper):
url = 'http://www.bicatperson.com/' url = 'https://www.bicatperson.com/'
stripUrl = 'comic/%s/' stripUrl = url + 'comic/%s/'
firstStripUrl = 'sketches-1' firstStripUrl = 'sketches-1'

View file

@ -181,7 +181,7 @@ class CatVersusHuman(_ParserScraper):
class CavesAndCritters(_ParserScraper): class CavesAndCritters(_ParserScraper):
url = 'https://cavesandcritters.com/?ao_confirm' url = 'https://cavesandcritters.com/?ao_confirm'
stripUrl = url + 'https://cavesandcritters.com/cnc_webcomic/%s/' stripUrl = 'https://cavesandcritters.com/cnc_webcomic/%s/'
firstStripUrl = stripUrl % '01_000' firstStripUrl = stripUrl % '01_000'
imageSearch = '//div[@class="webcomic-image"]//img' imageSearch = '//div[@class="webcomic-image"]//img'
prevSearch = '//a[contains(@class, "previous-webcomic-link")]' prevSearch = '//a[contains(@class, "previous-webcomic-link")]'
@ -204,7 +204,7 @@ class Centralia2050(_WordPressScraper):
class ChainsawSuit(_WordPressScraper): class ChainsawSuit(_WordPressScraper):
url = 'http://chainsawsuit.com/comic/' url = 'http://chainsawsuit.com/comic/'
stripUrl = url + 'archive/%s/' stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2008/03/12/strip-338' firstStripUrl = stripUrl % '2008/03/12/strip-338'
prevSearch = '//img[@alt="previous"]/..' prevSearch = '//img[@alt="previous"]/..'
help = 'Index format: yyyy/mm/dd/stripname' help = 'Index format: yyyy/mm/dd/stripname'
@ -229,8 +229,8 @@ class ChannelAte(_WPNavi):
class ChasingTheSunset(_BasicScraper): class ChasingTheSunset(_BasicScraper):
url = 'http://www.fantasycomic.com/' url = 'http://www.fantasycomic.com/'
stripUrl = url + 'index.php?p=c%s' stripUrl = url + 'index.php?p=%s'
firstStripUrl = stripUrl % '1' firstStripUrl = stripUrl % 'c1'
imageSearch = compile(r'(/cmsimg/.+?)".+?comic-img') imageSearch = compile(r'(/cmsimg/.+?)".+?comic-img')
prevSearch = compile(r'<a href="(.+?)" title="" ><img src="(images/eye-prev.png|images/cn-prev.png)"') prevSearch = compile(r'<a href="(.+?)" title="" ><img src="(images/eye-prev.png|images/cn-prev.png)"')
help = 'Index format: n' help = 'Index format: n'

View file

@ -109,7 +109,7 @@ class DeerMe(_ParserScraper):
class Delve(_WordPressScraper): class Delve(_WordPressScraper):
url = 'http://thisis.delvecomic.com/NewWP/' url = 'https://thisis.delvecomic.com/NewWP/'
stripUrl = url + 'comic/%s/' stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'in-too-deep' firstStripUrl = stripUrl % 'in-too-deep'
adult = True adult = True
@ -203,7 +203,7 @@ class Dilbert(_ParserScraper):
class DocRat(_ParserScraper): class DocRat(_ParserScraper):
url = 'http://www.docrat.com.au/' url = 'https://www.docrat.com.au/'
stripUrl = url + 'comic/%s/' stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'begin-with-eye-contact' firstStripUrl = stripUrl % 'begin-with-eye-contact'
imageSearch = '//div[@class="webcomic-image"]//img' imageSearch = '//div[@class="webcomic-image"]//img'
@ -242,7 +242,7 @@ class DoghouseDiaries(_ParserScraper):
class DominicDeegan(_ParserScraper): class DominicDeegan(_ParserScraper):
url = 'http://www.dominic-deegan.com/' url = 'https://www.dominic-deegan.com/'
stripUrl = url + 'comic/%s/' stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % '0001-20020521' firstStripUrl = stripUrl % '0001-20020521'
imageSearch = '//img[contains(@class, "wp-post-image")]' imageSearch = '//img[contains(@class, "wp-post-image")]'

View file

@ -246,7 +246,7 @@ class ExtraLife(_BasicScraper):
class ExtraOrdinary(_ParserScraper): class ExtraOrdinary(_ParserScraper):
url = 'http://www.exocomics.com/' url = 'https://www.exocomics.com/'
stripUrl = url + '%s' stripUrl = url + '%s'
firstStripUrl = stripUrl % '01' firstStripUrl = stripUrl % '01'
prevSearch = '//a[%s]' % xpath_class('prev') prevSearch = '//a[%s]' % xpath_class('prev')

View file

@ -152,7 +152,7 @@ class Fragile(_ParserScraper):
class FredoAndPidjin(_ParserScraper): class FredoAndPidjin(_ParserScraper):
url = 'http://www.pidjin.net/' url = 'https://www.pidjin.net/'
stripUrl = url + '%s/' stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2006/02/19/goofy-monday' firstStripUrl = stripUrl % '2006/02/19/goofy-monday'
imageSearch = '//div[%s]//img' % xpath_class("episode") imageSearch = '//div[%s]//img' % xpath_class("episode")

View file

@ -67,7 +67,7 @@ class GeeksNextDoor(_BasicScraper):
class Ginpu(_WPNavi): class Ginpu(_WPNavi):
url = 'http://www.ginpu.us/' url = 'https://www.ginpu.us/'
stripUrl = url + 'comic/%s/' stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'filler-2' firstStripUrl = stripUrl % 'filler-2'
@ -163,7 +163,7 @@ class GoneWithTheBlastwave(_BasicScraper):
class GrrlPower(_WordPressScraper): class GrrlPower(_WordPressScraper):
url = 'http://grrlpowercomic.com/' url = 'https://grrlpowercomic.com/'
stripUrl = url + 'archives/comic/%s/' stripUrl = url + 'archives/comic/%s/'
firstStripUrl = stripUrl % 'gp0001' firstStripUrl = stripUrl % 'gp0001'

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) 2015-2017 Tobias Gruetzmacher # Copyright (C) 2015-2019 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function from __future__ import absolute_import, division, print_function
@ -53,7 +53,7 @@ class LastResort(_WordPressScraper):
class LeastICouldDo(_ParserScraper): class LeastICouldDo(_ParserScraper):
url = 'http://www.leasticoulddo.com/' url = 'https://leasticoulddo.com/'
stripUrl = url + 'comic/%s' stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % '20030210' firstStripUrl = stripUrl % '20030210'
imageSearch = '//div[@id="content-comic"]//img' imageSearch = '//div[@id="content-comic"]//img'

View file

@ -98,7 +98,7 @@ class Meek(_WordPressScraper):
class MegaTokyo(_BasicScraper): class MegaTokyo(_BasicScraper):
url = 'http://megatokyo.com/' url = 'https://megatokyo.com/'
stripUrl = url + 'strip/%s' stripUrl = url + 'strip/%s'
firstStripUrl = stripUrl % '1' firstStripUrl = stripUrl % '1'
imageSearch = compile(r'"(strips/.+?)"', IGNORECASE) imageSearch = compile(r'"(strips/.+?)"', IGNORECASE)

View file

@ -20,7 +20,7 @@ class Namesake(_ComicControlScraper):
class NamirDeiter(_ParserScraper): class NamirDeiter(_ParserScraper):
baseUrl = 'http://www.namirdeiter.com/comics/' baseUrl = 'https://www.namirdeiter.com/comics/'
stripUrl = baseUrl + 'index.php?date=%s' stripUrl = baseUrl + 'index.php?date=%s'
url = stripUrl % '20150410' url = stripUrl % '20150410'
firstStripUrl = baseUrl firstStripUrl = baseUrl
@ -98,7 +98,7 @@ class Nicky510(_WPNavi):
class NicoleAndDerek(_ParserScraper): class NicoleAndDerek(_ParserScraper):
url = 'https://www.nicoleandderek.com/' url = 'https://nicoleandderek.com/'
stripUrl = url + 'comics/index.php?date=%s' stripUrl = url + 'comics/index.php?date=%s'
firstStripUrl = url + 'comics/' firstStripUrl = url + 'comics/'
imageSearch = '//a/img[contains(@src, "comics/")]' imageSearch = '//a/img[contains(@src, "comics/")]'

View file

@ -166,7 +166,7 @@ class OurHomePlanet(_ParserScraper):
class OutOfPlacers(_WordPressScraper): class OutOfPlacers(_WordPressScraper):
url = 'http://www.valsalia.com/' url = 'http://www.valsalia.com/'
stripUrl = 'comic/%s/' stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'prologue/01' firstStripUrl = stripUrl % 'prologue/01'

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) 2015-2017 Tobias Gruetzmacher # Copyright (C) 2015-2019 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function from __future__ import absolute_import, division, print_function
@ -94,8 +94,7 @@ class PennyAndAggie(_BasicScraper):
class PennyArcade(_ParserScraper): class PennyArcade(_ParserScraper):
url = 'http://www.penny-arcade.com/comic/' url = 'https://www.penny-arcade.com/comic/'
rurl = escape(url)
stripUrl = url + '%s' stripUrl = url + '%s'
firstStripUrl = stripUrl % '1998/11/18' firstStripUrl = stripUrl % '1998/11/18'
imageSearch = '//div[@id="comicFrame"]//img' imageSearch = '//div[@id="comicFrame"]//img'

View file

@ -32,7 +32,7 @@ class RaynaOnTheRiver(_WordPressScraper):
class RealLife(_WordPressScraper): class RealLife(_WordPressScraper):
url = 'http://reallifecomics.com/' url = 'https://reallifecomics.com/'
stripUrl = url + 'comic.php?comic=%s' stripUrl = url + 'comic.php?comic=%s'
firstStripUrl = stripUrl % 'title-1' firstStripUrl = stripUrl % 'title-1'
help = 'Index format: monthname-dd-yyyy' help = 'Index format: monthname-dd-yyyy'

View file

@ -619,13 +619,13 @@ class SuburbanJungle(_ParserScraper):
class SuburbanJungleRoughHousing(_WordPressScraper): class SuburbanJungleRoughHousing(_WordPressScraper):
url = 'http://roughhouse.suburbanjungle.com/' url = 'http://roughhouse.suburbanjungle.com/'
stripUrl = url + '/comic/%s/' stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'rough-housing-issue-1-cover' firstStripUrl = stripUrl % 'rough-housing-issue-1-cover'
class Supercell(_ParserScraper): class Supercell(_ParserScraper):
url = 'https://www.supercellcomic.com/' url = 'https://www.supercellcomic.com/'
stripUrl = url + '/pages/%s.html' stripUrl = url + 'pages/%s.html'
firstStripUrl = stripUrl % '0001' firstStripUrl = stripUrl % '0001'
imageSearch = '//div[@class="comicpage"]//img' imageSearch = '//div[@class="comicpage"]//img'
prevSearch = '//div[@class="comicnav"]/a[./img[contains(@src, "comnav_02")]]' prevSearch = '//div[@class="comicnav"]/a[./img[contains(@src, "comnav_02")]]'

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) 2015-2017 Tobias Gruetzmacher # Copyright (C) 2015-2019 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function from __future__ import absolute_import, division, print_function
@ -172,7 +172,7 @@ class TheProbabilityBomb(_ParserScraper):
class TheRockCocks(_BasicScraper): class TheRockCocks(_BasicScraper):
url = 'http://rockcocks.slipshine.net/' url = 'http://rockcocks.slipshine.net/'
rurl = escape(url) rurl = escape(url)
stripUrl = url + 'comics/%s' stripUrl = url + 'comic/%s'
firstStripUrl = stripUrl % "page-1-nsfw-track-1-start" firstStripUrl = stripUrl % "page-1-nsfw-track-1-start"
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl, after='id="cc-comic"')) imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl, after='id="cc-comic"'))
prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl, after='rel="prev"')) prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl, after='rel="prev"'))
@ -284,7 +284,7 @@ class TrippingOverYou(_BasicScraper):
class TumbleDryComics(_WordPressScraper): class TumbleDryComics(_WordPressScraper):
url = 'http://tumbledrycomics.com/' url = 'https://www.tumbledrycomics.com/'
stripUrl = url + 'comic/%s/' stripUrl = url + 'comic/%s/'
firstStripUrl = stripUrl % 'we-need-to-get-high-jpg' firstStripUrl = stripUrl % 'we-need-to-get-high-jpg'
textSearch = '//div[@id="comic"]//img/@alt' textSearch = '//div[@id="comic"]//img/@alt'

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) 2015-2017 Tobias Gruetzmacher # Copyright (C) 2015-2019 Tobias Gruetzmacher
from __future__ import absolute_import, division, print_function from __future__ import absolute_import, division, print_function
@ -37,7 +37,7 @@ class UnicornJelly(_BasicScraper):
class UnlikeMinerva(_ParserScraper): class UnlikeMinerva(_ParserScraper):
baseUrl = 'https://www.unlikeminerva.com/archive/index.php' baseUrl = 'https://unlikeminerva.com/archive/index.php'
stripUrl = baseUrl + '?week=%s' stripUrl = baseUrl + '?week=%s'
url = stripUrl % '127' url = stripUrl % '127'
firstStripUrl = stripUrl % '26' firstStripUrl = stripUrl % '26'