110 lines
4.1 KiB
Python
110 lines
4.1 KiB
Python
# -*- coding: iso-8859-1 -*-
|
|
# Copyright (C) 2004-2005 Tristan Seligmann and Jonathan Jacobs
|
|
# Copyright (C) 2012-2013 Bastian Kleineidam
|
|
|
|
from re import compile, escape
|
|
from ..scraper import _BasicScraper
|
|
from ..helpers import indirectStarter
|
|
from ..util import tagre, urlopen
|
|
|
|
|
|
class OctopusPie(_BasicScraper):
|
|
url = 'http://www.octopuspie.com/'
|
|
rurl = escape(url)
|
|
starter = indirectStarter(url,
|
|
compile(tagre("a", "href", r'(%s[^"]+)' % rurl) +
|
|
tagre("img", "src", r'%sjunk/latest\.png' % rurl)))
|
|
stripUrl = url + '%s'
|
|
imageSearch = compile(tagre("img", "src", r'(%sstrippy/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="prev"))
|
|
help = 'Index format: yyyy-mm-dd/nnn-strip-name'
|
|
|
|
|
|
class OddFish(_BasicScraper):
|
|
url = 'http://www.odd-fish.net/'
|
|
rurl = escape(url)
|
|
stripUrl = url + '%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(%scomics/[^"]+)' % rurl))
|
|
prevSearch = compile(tagre("a", "href", r'(%s[^"]+)' % rurl, after="navi-prev"))
|
|
help = 'Index format: stripname'
|
|
|
|
|
|
class Oglaf(_BasicScraper):
|
|
url = 'http://oglaf.com/'
|
|
stripUrl = url + '%s/'
|
|
imageSearch = compile(tagre("img", "src", r'(http://media\.oglaf\.com/comic/[^"]+)', before="strip"))
|
|
prevSearch = compile(tagre("a", "href", r'(/[^"]+)') + tagre("div", "id", "pvs?"))
|
|
help = 'Index format: stripname/nn'
|
|
adult = True
|
|
|
|
@classmethod
|
|
def starter(cls):
|
|
# click the "I am 18" button
|
|
data = {"over18": " "}
|
|
urlopen(cls.url, cls.session, data=data, stream=False, referrer=cls.url)
|
|
return cls.url
|
|
|
|
|
|
class OkCancel(_BasicScraper):
|
|
url = 'http://okcancel.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + 'comic/%s.html'
|
|
imageSearch = compile(tagre("img", "src", r'(%sstrips/okcancel\d{8}\.gif)' % rurl))
|
|
prevSearch = compile(tagre("div", "class", "previous") + tagre("a", "href", r'(%scomic/\d{1,4}\.html)' % rurl))
|
|
starter = indirectStarter(url, prevSearch)
|
|
help = 'Index format: yyyymmdd'
|
|
|
|
|
|
class OmakeTheater(_BasicScraper):
|
|
url = 'http://omaketheater.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + 'comic/%s'
|
|
imageSearch = compile(tagre("img", "src", r'(http://media\.omaketheater\.com/4koma/[^"]+)'))
|
|
prevSearch = compile(tagre("a", "href", r'(%scomic/\d+/)' % rurl, after="prev"))
|
|
starter = indirectStarter(url,
|
|
compile(tagre("a", "href", r'(%scomic/\d+/)' % rurl)))
|
|
help = 'Index format: number (unpadded)'
|
|
|
|
|
|
class OnTheEdge(_BasicScraper):
|
|
url = 'http://ontheedgecomics.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + 'comic/%s'
|
|
imageSearch = compile(r'<img src="(%scomics/.+?)"' % rurl)
|
|
prevSearch = compile(r'<a href="([^"]+)" rel="prev">')
|
|
help = 'Index format: nnn (unpadded)'
|
|
|
|
|
|
class OneQuestion(_BasicScraper):
|
|
url = 'http://onequestioncomic.com/'
|
|
stripUrl = url + 'comic.php?strip_id=%s'
|
|
imageSearch = compile(tagre("img", "src", r'((?:\.\./)?istrip_files/strips/\d+\.jpg)'))
|
|
prevSearch = compile(tagre("a", "href", r'(comic\.php\?strip_id=\d+)') + tagre("img", "src", r'img/arrow_prev\.jpg'))
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
class OrnerBoy(_BasicScraper):
|
|
url = 'http://www.orneryboy.com/'
|
|
rurl = escape(url)
|
|
stripUrl = url + 'index.php?comicID=%s'
|
|
firstStripUrl = stripUrl % '1'
|
|
imageSearch = compile(tagre("img", "src", r'(comics/\d+\.[^"]+)'))
|
|
prevSearch = compile(tagre("a", "href", r'(%sindex\.php\?comicID=\d+)' % rurl) +
|
|
tagre("img", "src", r'images/prev_a\.gif'))
|
|
help = 'Index format: number'
|
|
|
|
|
|
class OurHomePlanet(_BasicScraper):
|
|
url = 'http://gdk.gd-kun.net/'
|
|
stripUrl = url + '%s.html'
|
|
imageSearch = compile(r'<img src="(pages/comic.+?)"')
|
|
prevSearch = compile(r'coords="50,18,95,65".+?href="(.+?\.html)".+?alt=')
|
|
help = 'Index format: n (unpadded)'
|
|
|
|
|
|
class OverCompensating(_BasicScraper):
|
|
url = 'http://www.overcompensating.com/'
|
|
stripUrl = url + 'posts/%s.html'
|
|
imageSearch = compile(r'<img src="(/comics/.+?)"')
|
|
prevSearch = compile(r'"><a href="(.+?)"[^>]+?> \<\- </a>')
|
|
help = 'Index format: yyyymmdd'
|