2016-04-03 20:58:01 +00:00
|
|
|
# -*- coding: utf-8 -*-
|
2016-10-28 22:21:41 +00:00
|
|
|
# Copyright (C) 2004-2008 Tristan Seligmann and Jonathan Jacobs
|
2014-01-05 15:50:57 +00:00
|
|
|
# Copyright (C) 2012-2014 Bastian Kleineidam
|
2017-04-15 23:06:41 +00:00
|
|
|
# Copyright (C) 2015-2017 Tobias Gruetzmacher
|
2016-04-03 20:58:01 +00:00
|
|
|
|
|
|
|
from __future__ import absolute_import, division, print_function
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2013-04-10 16:19:11 +00:00
|
|
|
from re import compile, escape
|
2016-04-03 20:58:01 +00:00
|
|
|
|
2015-05-07 11:57:10 +00:00
|
|
|
from ..scraper import _BasicScraper, _ParserScraper
|
2019-07-14 09:09:20 +00:00
|
|
|
from ..helpers import bounceStarter, indirectStarter
|
2012-11-21 20:57:26 +00:00
|
|
|
from ..util import tagre
|
2019-07-18 08:30:21 +00:00
|
|
|
from .common import _ComicControlScraper, _WordPressScraper, _WPNaviIn
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2019-06-28 04:48:07 +00:00
|
|
|
class Lackadaisy(_ParserScraper):
|
|
|
|
url = 'https://www.lackadaisy.com/comic.php'
|
|
|
|
stripUrl = url + '?comicid=%s'
|
2013-04-25 19:06:12 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2019-06-28 04:48:07 +00:00
|
|
|
imageSearch = '//div[@id="content"]/img'
|
|
|
|
prevSearch = '//div[@class="prev"]/a'
|
|
|
|
nextSearch = '//div[@class="next"]/a'
|
2013-04-25 19:06:12 +00:00
|
|
|
help = 'Index format: n'
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = bounceStarter
|
2013-04-25 19:06:12 +00:00
|
|
|
|
2019-06-28 04:48:07 +00:00
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
# Use comic id for filename
|
|
|
|
num = pageUrl.rsplit('=', 1)[-1]
|
|
|
|
ext = imageUrl.rsplit('.', 1)[-1]
|
2013-04-25 19:06:12 +00:00
|
|
|
return 'lackadaisy_%s.%s' % (num, ext)
|
|
|
|
|
|
|
|
|
2016-04-03 20:58:01 +00:00
|
|
|
class Laiyu(_WordPressScraper):
|
2017-11-27 00:04:35 +00:00
|
|
|
url = 'http://www.flowerlarkstudios.com/comicpage/preliminary-concepts/welcome/'
|
2016-04-03 20:58:01 +00:00
|
|
|
firstStripUrl = url
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2016-04-03 20:58:01 +00:00
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class LasLindas(_BasicScraper):
|
2013-02-04 20:00:26 +00:00
|
|
|
url = 'http://laslindas.katbox.net/'
|
2013-04-10 16:19:11 +00:00
|
|
|
rurl = escape(url)
|
2013-02-19 19:58:04 +00:00
|
|
|
stripUrl = url + 'comic/%s/'
|
2013-04-10 16:19:11 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/[^"]+)' % rurl, after="attachment-full"))
|
2013-04-04 16:30:02 +00:00
|
|
|
multipleImagesPerStrip = True
|
2013-04-10 16:19:11 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'(%scomic/[^"]+)' % rurl, after="previous"))
|
2012-11-21 20:57:26 +00:00
|
|
|
help = 'Index format: stripname'
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2019-06-23 09:10:24 +00:00
|
|
|
class LastResort(_WordPressScraper):
|
|
|
|
url = 'http://www.lastres0rt.com/'
|
|
|
|
stripUrl = url + 'comic/%s/'
|
|
|
|
firstStripUrl = stripUrl % 'that-sound-you-hear-is-a-shattered-stereotype'
|
|
|
|
|
|
|
|
|
2017-12-14 23:00:25 +00:00
|
|
|
class LeastICouldDo(_ParserScraper):
|
2013-03-06 19:21:10 +00:00
|
|
|
url = 'http://www.leasticoulddo.com/'
|
|
|
|
stripUrl = url + 'comic/%s'
|
2017-12-14 23:00:25 +00:00
|
|
|
firstStripUrl = stripUrl % '20030210'
|
|
|
|
imageSearch = '//div[@id="content-comic"]//img'
|
|
|
|
prevSearch = '//a[@rel="prev"]'
|
|
|
|
latestSearch = '//a[@id="latest-comic"]'
|
2016-04-13 18:01:51 +00:00
|
|
|
starter = indirectStarter
|
2013-03-06 19:21:10 +00:00
|
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
|
|
|
2016-04-03 22:12:53 +00:00
|
|
|
class LetsSpeakEnglish(_ComicControlScraper):
|
|
|
|
url = 'http://www.marycagle.com'
|
|
|
|
|
|
|
|
|
2018-04-21 00:25:11 +00:00
|
|
|
class LifeAintNoPonyFarm(_WordPressScraper):
|
|
|
|
url = 'http://sarahburrini.com/en/'
|
|
|
|
firstStripUrl = url + 'comic/my-first-webcomic/'
|
|
|
|
multipleImagesPerStrip = True
|
|
|
|
|
|
|
|
|
2019-10-26 09:02:52 +00:00
|
|
|
class LilithsWord(_ComicControlScraper):
|
|
|
|
url = 'http://www.lilithword.com/'
|
|
|
|
stripUrl = url + 'comic/%s'
|
|
|
|
firstStripUrl = stripUrl % 'prologue-page-00'
|
|
|
|
|
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
return imageUrl.rsplit('/', 1)[-1].split('-', 1)[1]
|
|
|
|
|
|
|
|
|
2013-03-06 19:21:10 +00:00
|
|
|
class LittleGamers(_BasicScraper):
|
|
|
|
url = 'http://www.little-gamers.com/'
|
|
|
|
stripUrl = url + '%s/'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '2000/12/01/99'
|
2013-03-06 19:21:10 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://little-gamers\.com/comics/[^"]+)'))
|
2013-03-26 16:36:06 +00:00
|
|
|
prevSearch = compile(tagre("a", "href", r'(http://www\.little-gamers\.com/[^"]+)', before="comic-nav-prev-link"))
|
2013-03-06 19:21:10 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/name'
|
|
|
|
|
|
|
|
|
2019-07-06 18:23:09 +00:00
|
|
|
class LittleTales(_ParserScraper):
|
|
|
|
url = 'http://www.little-tales.com/'
|
|
|
|
stripUrl = url + 'index.php?Strip=%s'
|
|
|
|
firstStripUrl = stripUrl % '1'
|
|
|
|
url = stripUrl % '450'
|
|
|
|
imageSearch = '//img[contains(@src, "strips/")]'
|
|
|
|
prevSearch = '//a[./img[@alt="BACK"]]'
|
|
|
|
nextSearch = '//a[./img[@alt="FORWARD"]]'
|
|
|
|
starter = bounceStarter
|
|
|
|
nav = {
|
|
|
|
'517': '515',
|
|
|
|
'449': '447'
|
|
|
|
}
|
|
|
|
|
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
page = pageUrl.rsplit('=', 1)[-1]
|
|
|
|
ext = imageUrl.rsplit('.', 1)[-1]
|
|
|
|
return page + '.' + ext
|
|
|
|
|
|
|
|
def getPrevUrl(self, url, data):
|
|
|
|
# Skip missing pages with broken navigation links
|
|
|
|
page = url.rsplit('=', 1)[1]
|
|
|
|
if page in self.nav:
|
|
|
|
return self.stripUrl % self.nav[page]
|
|
|
|
return super(LittleTales, self).getPrevUrl(url, data)
|
|
|
|
|
|
|
|
|
2015-05-31 23:33:50 +00:00
|
|
|
class LoadingArtist(_ParserScraper):
|
2016-08-16 09:20:35 +00:00
|
|
|
url = 'http://www.loadingartist.com/latest'
|
2015-05-31 23:33:50 +00:00
|
|
|
imageSearch = '//div[@class="comic"]//img'
|
|
|
|
prevSearch = "//a[contains(concat(' ', @class, ' '), ' prev ')]"
|
2013-03-06 19:00:30 +00:00
|
|
|
|
2016-04-03 20:58:01 +00:00
|
|
|
|
2016-05-01 23:25:34 +00:00
|
|
|
class LoFiJinks(_WPNaviIn):
|
|
|
|
url = 'http://hijinksensue.com/comic/learning-to-love-again/'
|
|
|
|
firstStripUrl = 'http://hijinksensue.com/comic/lo-fijinks-everything-i-know-anout-james-camerons-avatar-movie/'
|
|
|
|
endOfLife = True
|
|
|
|
|
|
|
|
|
2015-05-07 11:57:10 +00:00
|
|
|
class LookingForGroup(_ParserScraper):
|
2019-07-14 09:09:20 +00:00
|
|
|
url = 'https://www.lfg.co/'
|
|
|
|
stripUrl = url + 'page/%s/'
|
2013-04-10 21:57:09 +00:00
|
|
|
firstStripUrl = stripUrl % '1'
|
2018-08-12 21:39:51 +00:00
|
|
|
imageSearch = '//div[@id="comic-img"]//img'
|
2019-07-14 09:09:20 +00:00
|
|
|
prevSearch = '//a[@class="comic-nav-prev"]'
|
|
|
|
latestSearch = '//div[@id="feature-lfg-footer"]/a[contains(@href, "page/")]'
|
|
|
|
starter = indirectStarter
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: nnn'
|
2019-07-14 09:09:20 +00:00
|
|
|
|
|
|
|
def namer(self, imageUrl, pageUrl):
|
|
|
|
page = pageUrl.rstrip('/').rsplit('/', 1)[-1]
|
|
|
|
return page.replace('2967', '647')
|