2012-06-20 20:41:04 +00:00
|
|
|
# -*- coding: iso-8859-1 -*-
|
|
|
|
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
|
2012-11-21 20:57:26 +00:00
|
|
|
# Copyright (C) 2012 Bastian Kleineidam
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2012-11-21 20:57:26 +00:00
|
|
|
from re import compile, IGNORECASE
|
2012-10-11 10:03:12 +00:00
|
|
|
from ..scraper import _BasicScraper
|
|
|
|
from ..helpers import indirectStarter
|
2012-11-21 20:57:26 +00:00
|
|
|
from ..util import tagre
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
2012-12-08 20:30:51 +00:00
|
|
|
class TheDevilsPanties(_BasicScraper):
|
|
|
|
latestUrl = 'http://thedevilspanties.com/'
|
|
|
|
stripUrl = latestUrl + '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'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class TheNoob(_BasicScraper):
|
|
|
|
latestUrl = 'http://www.thenoobcomic.com/index.php'
|
2012-12-04 06:02:40 +00:00
|
|
|
stripUrl = latestUrl + '?pos=%s'
|
2012-11-25 06:56:46 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(/headquarters/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(\?pos=\d+)', before="comic_nav_previous_button"))
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: nnnn'
|
|
|
|
|
|
|
|
|
|
|
|
class TheOrderOfTheStick(_BasicScraper):
|
2012-11-25 06:56:46 +00:00
|
|
|
latestUrl = 'http://www.giantitp.com/comics/oots0863.html'
|
2012-12-04 06:02:40 +00:00
|
|
|
stripUrl = 'http://www.giantitp.com/comics/oots%s.html'
|
2012-12-07 23:45:18 +00:00
|
|
|
imageSearch = compile(r'<IMG src="(/comics/images/[^"]+)">')
|
2012-06-20 19:58:13 +00:00
|
|
|
prevSearch = compile(r'<A href="(/comics/oots\d{4}\.html)"><IMG src="/Images/redesign/ComicNav_Back.gif"')
|
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
starter = indirectStarter('http://www.giantitp.com/', compile(r'<A href="(/comics/oots\d{4}\.html)"'))
|
|
|
|
|
2012-12-07 23:45:18 +00:00
|
|
|
@classmethod
|
|
|
|
def namer(cls, imageUrl, pageUrl):
|
|
|
|
return pageUrl.rsplit('/', 1)[-1][:-5]
|
2012-06-20 19:58:13 +00:00
|
|
|
|
|
|
|
|
|
|
|
class TheParkingLotIsFull(_BasicScraper):
|
|
|
|
latestUrl = 'http://plif.courageunfettered.com/archive/arch2002.htm'
|
2012-11-25 06:56:46 +00:00
|
|
|
stripUrl = 'http://plif.courageunfettered.com/archive/arch%s.htm'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<td align="center"><A TARGET=_parent HREF="(wc\d+\..+?)">')
|
2012-12-04 06:02:40 +00:00
|
|
|
multipleImagesPerStrip = True
|
|
|
|
prevSearch = compile(r'\d{4} -\s+<A HREF="(arch\d{4}\.htm)">\d{4}')
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: nnn'
|
|
|
|
|
|
|
|
|
|
|
|
class TheWotch(_BasicScraper):
|
|
|
|
latestUrl = 'http://www.thewotch.com/'
|
2012-11-25 06:56:46 +00:00
|
|
|
stripUrl = latestUrl + '?date=%s'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r"<img.+?src='(comics/.+?)'")
|
2012-12-04 06:02:40 +00:00
|
|
|
prevSearch = compile(r"<link rel='Previous' href='(/\?date=\d+-\d+-\d+)'")
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: yyyy-mm-dd'
|
|
|
|
|
|
|
|
|
2012-12-08 20:30:51 +00:00
|
|
|
class ThunderAndLightning(_BasicScraper):
|
|
|
|
baseUrl = 'http://www.talcomic.com/wp/'
|
|
|
|
latestUrl = baseUrl + '?latestcomic'
|
|
|
|
stripUrl = baseUrl + '%s/'
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(http://www\.talcomic\.com/wp/[^"]+)', after="prev"))
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://www\.talcomic\.com/wp/comics/[^"]+)'))
|
|
|
|
help = 'Index format: yyyy/mm/dd/page-nn'
|
|
|
|
|
|
|
|
|
2012-11-21 20:57:26 +00:00
|
|
|
class TinyKittenTeeth(_BasicScraper):
|
|
|
|
latestUrl = 'http://www.tinykittenteeth.com/'
|
2012-11-25 06:56:46 +00:00
|
|
|
stripUrl = latestUrl + '%s/'
|
2012-11-21 20:57:26 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://www\.tinykittenteeth\.com/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'([^"]+)', after="Previous"))
|
2012-11-25 06:56:46 +00:00
|
|
|
help = 'Index format: yyyy/mm/dd/stripname (unpadded)'
|
2012-11-21 20:57:26 +00:00
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
|
2012-12-13 20:05:27 +00:00
|
|
|
# XXX disallowed by robots.txt
|
|
|
|
class _TwoLumps(_BasicScraper):
|
2012-12-08 20:30:51 +00:00
|
|
|
latestUrl = 'http://www.twolumps.net/'
|
|
|
|
stripUrl = latestUrl + 'd/%s.html'
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(/d/\d+\.html)', after="prev"))
|
|
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
|
|
|
2012-06-20 19:58:13 +00:00
|
|
|
class TwoTwoOneFour(_BasicScraper):
|
|
|
|
latestUrl = 'http://www.nitrocosm.com/go/2214_classic/'
|
2012-11-20 17:53:53 +00:00
|
|
|
stripUrl = latestUrl + '%s/'
|
2012-11-25 06:56:46 +00:00
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://content\.nitrocosm\.com/[^"]+)', before="gallery_display"))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(http://www\.nitrocosm\.com/go/2214_classic/\d+/)', after="Previous"))
|
2012-06-20 19:58:13 +00:00
|
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
|
|
|
|
|
|
class TheWhiteboard(_BasicScraper):
|
|
|
|
latestUrl = 'http://www.the-whiteboard.com/'
|
2012-11-20 17:53:53 +00:00
|
|
|
stripUrl = latestUrl + 'auto%s.html'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img SRC="(autotwb\d{1,4}.+?|autowb\d{1,4}.+?)">', IGNORECASE)
|
|
|
|
prevSearch = compile(r' <a href="(.+?)">previous</a>', IGNORECASE)
|
|
|
|
help = 'Index format: twb or wb + n wg. twb1000'
|
|
|
|
|
|
|
|
|
|
|
|
class HMHigh(_BasicScraper):
|
|
|
|
name = 'TheFallenAngel/HMHigh'
|
|
|
|
latestUrl = 'http://www.thefallenangel.co.uk/hmhigh/'
|
2012-11-20 17:53:53 +00:00
|
|
|
stripUrl = latestUrl + '?id=%s'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img src="(http://www.thefallenangel.co.uk/hmhigh/img/comic/.+?)"')
|
|
|
|
prevSearch = compile(r' <a href="(http://www.thefallenangel.co.uk/.+?)" title=".+?">Prev</a>')
|
|
|
|
help = 'Index format: nnn'
|
|
|
|
|
|
|
|
|
|
|
|
class TheOuterQuarter(_BasicScraper):
|
|
|
|
latestUrl = 'http://theouterquarter.com/'
|
2012-11-20 17:53:53 +00:00
|
|
|
stripUrl = latestUrl + 'comic/%s'
|
2012-06-20 19:58:13 +00:00
|
|
|
imageSearch = compile(r'<img src="(http://theouterquarter.com/comics/.+?)"')
|
|
|
|
prevSearch = compile(r'<div class="nav-previous"><a href="([^"]+)" rel="prev">')
|
|
|
|
help = 'Index format: nnn'
|
2012-12-08 20:30:51 +00:00
|
|
|
|
|
|
|
|
|
|
|
class TracyAndTristan(_BasicScraper):
|
|
|
|
latestUrl = 'http://tandt.thecomicseries.com/'
|
|
|
|
stripUrl = latestUrl + 'comics/%s'
|
|
|
|
imageSearch = compile(tagre("img", "src", r'(http://tandt\.thecomicseries\.com/images/comics/[^"]+)'))
|
|
|
|
prevSearch = compile(tagre("a", "href", r'(/comics/\d+)', after="prev"))
|
|
|
|
help = 'Index format: number'
|