dosage/dosagelib/plugins/h.py

74 lines
2.7 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
from __future__ import absolute_import, division, print_function
2012-06-20 19:58:13 +00:00
from re import compile, escape
from ..scraper import _BasicScraper
from ..util import tagre
from ..helpers import bounceStarter
from .common import _WordPressScraper
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'
data = cls.getPage(url)
2013-03-26 16:35:10 +00:00
pattern = compile(tagre("a", "href", cls.prevUrl))
for starturl in cls.fetchUrls(url, data, pattern):
2013-03-26 16:35:10 +00:00
pass
return starturl
class HappyJar(_WordPressScraper):
url = 'http://www.happyjar.com/'
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
class Hipsters(_WordPressScraper):
url = 'http://www.hipsters-comic.com/'
firstStripUrl = 'http://www.hipsters-comic.com/comic/hip01/'
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'))
2012-11-21 20:57:26 +00:00
help = 'Index format: yyyymmdd'