calibre/recipes/fudzilla.recipe

42 lines
1.3 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2010 Starson17'
'''
fudzilla.com
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class Fudzilla(BasicNewsRecipe):
title = u'Fudzilla'
__author__ = 'Starson17'
language = 'en'
description = 'Tech news'
oldest_article = 7
remove_javascript = True
max_articles_per_feed = 100
no_stylesheets = True
use_embedded_content = False
remove_tags_before = dict(name='div', attrs={'class':['padding']})
remove_tags = [dict(name='td', attrs={'class':['left','right']}),
dict(name='div', attrs={'id':['toolbar','buttons']}),
dict(name='div', attrs={'class':['artbannersxtd','back_button']}),
dict(name='span', attrs={'class':['pathway']}),
dict(name='th', attrs={'class':['pagenav_next','pagenav_prev']}),
dict(name='table', attrs={'class':['headlines']}),
]
feeds = [
(u'Posts', u'http://www.fudzilla.com/?format=feed')
]
preprocess_regexps = [
(re.compile(r'<p class="MsoNormal"> Welcome.*</p> ', re.DOTALL|re.IGNORECASE), lambda match: '')
]