calibre/resources/recipes/evz.ro.recipe
2010-07-08 09:43:04 -06:00

53 lines
1.9 KiB
Plaintext

__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
evz.ro
'''
import re
from calibre.web.feeds.news import BasicNewsRecipe
class EVZ_Ro(BasicNewsRecipe):
title = 'evz.ro'
__author__ = 'Darko Miletic'
description = 'News from Romania'
publisher = 'evz.ro'
category = 'news, politics, Romania'
oldest_article = 2
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'utf8'
use_embedded_content = False
language = 'ro'
masthead_url = 'http://www.evz.ro/fileadmin/images/logo.gif'
extra_css = ' body{font-family: Georgia,Arial,Helvetica,sans-serif } .firstP{font-size: 1.125em} .author,.articleInfo{font-size: small} '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
preprocess_regexps = [
(re.compile(r'<head>.*?<title>', re.DOTALL|re.IGNORECASE),lambda match: '<head><title>')
,(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')
]
remove_tags = [
dict(name=['form','embed','iframe','object','base','link','script','noscript'])
,dict(attrs={'class':['section','statsInfo','email il']})
,dict(attrs={'id' :'gallery'})
]
remove_tags_after = dict(attrs={'class':'section'})
keep_only_tags = [dict(attrs={'class':'single'})]
remove_attributes = ['height','width']
feeds = [(u'Articles', u'http://www.evz.ro/rss.xml')]
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup