dosage/dosagelib/plugins/t.py

194 lines
6.8 KiB
Python
Raw Normal View History

# -*- coding: utf-8 -*-
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
2014-01-05 15:50:57 +00:00
# Copyright (C) 2012-2014 Bastian Kleineidam
# Copyright (C) 2015-2016 Tobias Gruetzmacher
2012-06-20 19:58:13 +00:00
from __future__ import absolute_import, division, print_function
2016-05-06 23:50:10 +00:00
from re import compile, escape, IGNORECASE
2016-05-06 23:50:10 +00:00
2015-04-26 09:52:31 +00:00
from ..scraper import _BasicScraper, _ParserScraper
2012-10-11 10:03:12 +00:00
from ..helpers import indirectStarter
from ..util import tagre
2016-10-13 22:14:53 +00:00
from .common import (_ComicControlScraper, _TumblrScraper, _WordPressScraper,
xpath_class)
2012-06-20 19:58:13 +00:00
2013-02-06 21:27:40 +00:00
class TheBrads(_BasicScraper):
url = 'http://bradcolbow.com/archive/C4/'
2013-04-10 21:57:09 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % 'P125'
2013-03-07 18:54:18 +00:00
imageSearch = compile(tagre("img", "src", r'(http://s3\.amazonaws\.com/the_brads/the-?brads[-_][^"]+)'))
2013-02-06 21:27:40 +00:00
prevSearch = compile(tagre("a", "href", r'(http://bradcolbow\.com/archive/C4/[^"]+)', before="prev"))
multipleImagesPerStrip = True
help = 'Index format: a letter and a number'
2012-12-08 20:30:51 +00:00
class TheDevilsPanties(_BasicScraper):
url = 'http://thedevilspanties.com/'
stripUrl = url + 'archives/%s'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '300'
2012-12-08 20:30:51 +00:00
imageSearch = compile(tagre("img", "src", r'(http://cdn\.thedevilspanties\.com/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/archives/\d+)',
after="Previous"))
2012-12-08 20:30:51 +00:00
help = 'Index format: number'
class TheDreamlandChronicles(_WordPressScraper):
url = 'http://www.thedreamlandchronicles.com/'
2015-04-26 09:52:31 +00:00
class TheGamerCat(_ParserScraper):
url = "http://www.thegamercat.com/"
stripUrl = url + "comic/%s/"
firstStripUrl = stripUrl % "06102011"
css = True
imageSearch = '#comic img'
prevSearch = '.comic-nav-previous'
help = 'Index format: stripname'
2013-04-25 19:20:48 +00:00
2014-01-31 03:32:07 +00:00
class TheGentlemansArmchair(_WordPressScraper):
url = 'http://thegentlemansarmchair.com/'
2014-02-18 20:00:43 +00:00
class TheLandscaper(_BasicScraper):
2016-05-06 23:50:10 +00:00
stripUrl = 'http://landscaper.visual-assault.net/comic/%s'
url = stripUrl % 'latest'
2014-02-18 20:00:43 +00:00
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src",
r'(/comics/comic/comic_page/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/comic/[^"]+)') +
'‹ Previous')
2014-02-18 20:00:43 +00:00
help = 'Index format: name'
class TheMelvinChronicles(_WordPressScraper):
url = 'http://melvin.jeaniebottle.com/'
2016-05-06 23:50:10 +00:00
class TheNoob(_WordPressScraper):
url = 'http://thenoobcomic.com/'
stripUrl = url + 'comic/%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1'
2016-05-06 23:50:10 +00:00
help = 'Index format: n (unpadded)'
2012-06-20 19:58:13 +00:00
class TheOrderOfTheStick(_BasicScraper):
url = 'http://www.giantitp.com/'
stripUrl = url + 'comics/oots%s.html'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '0001'
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"')
latestSearch = compile(r'<A href="(/comics/oots\d{4}\.html)"')
2012-06-20 19:58:13 +00:00
help = 'Index format: n (unpadded)'
starter = indirectStarter
2012-06-20 19:58:13 +00:00
def namer(self, image_url, page_url):
return page_url.rsplit('/', 1)[-1][:-5]
2012-06-20 19:58:13 +00:00
class TheParkingLotIsFull(_BasicScraper):
2013-04-13 18:58:00 +00:00
baseUrl = 'http://plif.courageunfettered.com/'
url = baseUrl + 'archive/arch2002.htm'
stripUrl = baseUrl + 'archive/arch%s.htm'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '1998'
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'
2016-05-06 23:50:10 +00:00
class TheThinHLine(_TumblrScraper):
url = 'http://thinhline.tumblr.com/'
2016-05-06 23:50:10 +00:00
firstStripUrl = url + 'post/4177372348/thl-1-a-cats-got-his-tongue-click-on-the'
imageSearch = '//img[@id="content-image"]/@data-src'
prevSearch = '//div[@id="pagination"]/a[text()=">"]'
latestSearch = '//a[@class="timestamp"]'
adult = True
2016-05-06 23:50:10 +00:00
indirectImageSearch = '//div[@id="post"]//a[not(@rel) and img]'
def getComicStrip(self, url, data):
"""The comic strip image is in a separate page."""
2016-05-06 23:50:10 +00:00
subPage = self.fetchUrl(url, data, self.indirectImageSearch)
pageData = self.getPage(subPage)
return super(TheThinHLine, self).getComicStrip(subPage, pageData)
class TheWhiteboard(_BasicScraper):
url = 'http://www.the-whiteboard.com/'
stripUrl = url + 'auto%s.html'
imageSearch = compile(r'<img SRC="(autotwb\d{1,4}.+?|autowb\d{1,4}.+?)">', IGNORECASE)
prevSearch = compile(r'&nbsp<a href="(.+?)">previous</a>', IGNORECASE)
help = 'Index format: twb or wb + n wg. twb1000'
2016-05-06 23:50:10 +00:00
class TheWotch(_WordPressScraper):
url = 'http://www.thewotch.com/'
2016-05-06 23:50:10 +00:00
firstStripUrl = url + '?comic=enter-the-wotch'
2012-06-20 19:58:13 +00:00
2013-02-06 21:08:36 +00:00
class ThisIsIndexed(_BasicScraper):
url = 'http://thisisindexed.com/'
rurl = escape(url)
2013-02-06 21:08:36 +00:00
stripUrl = url + 'page/%s'
imageSearch = compile(tagre("img", "src", r'(%swp-content/uploads/\d+/\d+/card[^"]+)' % rurl))
2013-02-06 21:08:36 +00:00
multipleImagesPerStrip = True
prevSearch = compile(tagre("div", "class", "nav-previous") +
2013-04-11 16:27:43 +00:00
tagre("a", "href", r'(%spage/\d+/)[^"]*' % rurl))
2013-02-06 21:08:36 +00:00
help = 'Index format: number'
2016-05-06 23:50:10 +00:00
class ThreePanelSoul(_ComicControlScraper):
url = 'http://threepanelsoul.com/'
2016-05-06 23:50:10 +00:00
firstStripUrl = url + 'comic/a-test-comic'
2016-05-06 23:50:10 +00:00
class ToonHole(_WordPressScraper):
2016-05-16 21:16:29 +00:00
url = 'http://toonhole.com/'
2013-02-06 21:08:36 +00:00
stripUrl = url + '%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2009/12/toon-hole-coming-soon-2010'
2016-05-06 23:50:10 +00:00
prevSearch = '//a[@rel="prev"]'
2013-02-06 21:08:36 +00:00
help = 'Index format: yyyy/mm/stripname'
def shouldSkipUrl(self, url, data):
2013-03-08 05:47:00 +00:00
return url in (self.stripUrl % "2013/03/if-game-of-thrones-was-animated",)
2013-03-07 17:22:24 +00:00
2013-02-06 21:08:36 +00:00
2012-12-08 20:30:51 +00:00
class TracyAndTristan(_BasicScraper):
url = 'http://tandt.thecomicseries.com/'
rurl = escape(url)
stripUrl = url + 'comics/%s'
imageSearch = compile(tagre("img", "src", r'(%simages/comics/[^"]+)' % rurl))
2012-12-08 20:30:51 +00:00
prevSearch = compile(tagre("a", "href", r'(/comics/\d+)', after="prev"))
help = 'Index format: number'
2013-04-25 19:23:31 +00:00
class TwoGuysAndGuy(_BasicScraper):
url = 'http://www.twogag.com/'
rurl = escape(url)
stripUrl = url + 'archives/%s'
firstStripUrl = stripUrl % '4'
imageSearch = compile(tagre('img', 'src', r'(%scomics/\d{4}-\d{2}-\d{2}[^"]*)' % rurl))
prevSearch = compile(tagre('a', 'href', r'(%sarchives/\d+)' % rurl,
after='title="Previous"'))
2013-04-25 19:23:31 +00:00
help = 'Index format: number'
adult = True
2016-10-13 22:14:53 +00:00
class Twokinds(_ParserScraper):
url = 'http://twokinds.keenspot.com/'
imageSearch = ('//p[@id="cg_img"]//img',
'//article/p//img')
prevSearch = ('//a[@id="cg_back"]',
'//a[%s]' % xpath_class('navprev'))
class TwoLumps(_BasicScraper):
url = 'http://www.twolumps.net/'
stripUrl = url + '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'