dosage/dosagelib/plugins/h.py

80 lines
3.3 KiB
Python
Raw Normal View History

2013-04-14 07:02:14 +00:00
# -*- coding: iso-8859-1 -*-
2014-01-05 15:50:57 +00:00
# Copyright (C) 2012-2014 Bastian Kleineidam
2012-06-20 19:58:13 +00:00
from re import compile, escape
2012-10-11 10:03:12 +00:00
from ..scraper import _BasicScraper
2013-03-26 16:35:10 +00:00
from ..util import tagre, getPageContent, fetchUrls
from ..helpers import bounceStarter
2013-03-26 16:35:10 +00:00
class HagarTheHorrible(_BasicScraper):
url = 'http://www.hagarthehorrible.net/'
stripUrl = 'http://www.hagardunor.net/comicstrips_us.php?serietype=9&colortype=1&serieno=%s'
firstStripUrl = stripUrl % '1'
multipleImagesPerStrip = True
2013-03-26 19:12:26 +00:00
imageSearch = compile(tagre("img", "src", r'(stripus\d+/(?:Hagar_The_Horrible_?|h)\d+[^ >]+)', quote=""))
2013-03-26 16:35:10 +00:00
prevUrl = r'(comicstrips_us\.php\?serietype\=9\&colortype\=1\&serieno\=\d+)'
prevSearch = compile(tagre("a", "href", prevUrl, after="Previous"))
help = 'Index format: number'
@classmethod
def starter(cls):
"""Return last gallery link."""
url = 'http://www.hagardunor.net/comics.php'
content = getPageContent(url, cls.session)[0]
pattern = compile(tagre("a", "href", cls.prevUrl))
for starturl in fetchUrls(url, content, url, pattern):
pass
return starturl
class HarkAVagrant(_BasicScraper):
url = 'http://www.harkavagrant.com/'
rurl = escape(url)
starter = bounceStarter(url,
compile(tagre("a", "href", r'(%sindex\.php\?id=\d+)' % rurl) +
tagre("img", "src", "buttonnext.png")))
stripUrl = url + 'index.php?id=%s'
firstStripUrl = stripUrl % '1'
imageSearch = compile(tagre("img", "src", r'(%s[^"]+)' % rurl, after='BORDER'))
prevSearch = compile(tagre("a", "href", r'(%sindex\.php\?id=\d+)' % rurl) +
tagre("img", "src", "buttonprevious.png"))
help = 'Index format: number'
@classmethod
def namer(cls, imageUrl, pageUrl):
filename = imageUrl.rsplit('/', 1)[1]
num = pageUrl.rsplit('=', 1)[1]
return '%s-%s' % (num, filename)
2012-06-20 19:58:13 +00:00
2013-02-06 05:58:06 +00:00
class HijinksEnsue(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'HijiNKS ENSUE is a geek pop culture webcomic that makes fun of the latest news in tv, movies, Sci-Fi, technology and the Internet'
2013-02-06 05:58:06 +00:00
url = 'http://hijinksensue.com/'
rurl = escape(url)
2013-02-06 05:58:06 +00:00
stripUrl = url + '%s/'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '2007/05/11/a-soul-as-black-as-eyeliner'
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/\d+/[^"]+)' % rurl, after="navi-prev"))
2013-04-10 21:57:09 +00:00
help = 'Index format: yyyy/mm/dd/stripname'
2013-02-06 05:58:06 +00:00
2013-03-21 17:33:16 +00:00
class Hipsters(_BasicScraper):
2013-04-14 07:02:14 +00:00
description = u'a weekly webcomic series by Adrian vom Baur - Hipsters vs. Vampires - Hipsters vs. Dinosaurs - Hipsters vs. Robots'
2013-03-21 17:33:16 +00:00
url = 'http://www.hipsters-comic.com/'
rurl = escape(url)
2013-03-21 17:33:16 +00:00
stripUrl = url + '%s/'
firstStripUrl = stripUrl % '2010/08/hip01'
imageSearch = compile(tagre("img", "src", r'(%scomics/\d+-\d+-\d+[^"]+)' % rurl))
prevSearch = compile(tagre("a", "href", r'(%s\d+/\d+/[^"]+)' % rurl, after="prev"))
2013-03-21 17:33:16 +00:00
help = 'Index format: yyyy/dd/stripname'
2012-06-20 19:58:13 +00:00
class HorribleVille(_BasicScraper):
url = 'http://horribleville.com/'
stripUrl = url + 'd/%s.html'
2013-04-10 21:57:09 +00:00
firstStripUrl = stripUrl % '20051220'
2012-11-21 20:57:26 +00:00
imageSearch = compile(tagre("img", "src", r'(/comics/[^"]+)'))
prevSearch = compile(tagre("a", "href", r'(/d/[^"]+)') + tagre("img", "src", r'/images/previous\.png'))
help = 'Index format: yyyymmdd'