home
***
CD-ROM
|
disk
|
FTP
|
other
***
search
/
Chip 2011 November
/
CHIP_2011_11.iso
/
Programy
/
Narzedzia
/
Calibre
/
calibre-0.8.18.msi
/
file_280
/
fe_india.recipe
< prev
next >
Wrap
Text File
|
2011-09-09
|
2KB
|
47 lines
__license__ = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
financialexpress.com
'''
from calibre.web.feeds.news import BasicNewsRecipe
class FE_India(BasicNewsRecipe):
title = 'The Financial Express'
__author__ = 'Darko Miletic'
description = 'Financial news from India'
publisher = 'The Indian Express Limited'
category = 'news, politics, finances, India'
oldest_article = 30
max_articles_per_feed = 200
no_stylesheets = True
encoding = 'cp1252'
use_embedded_content = False
language = 'en_IN'
remove_empty_feeds = True
masthead_url = 'http://static.expressindia.com/frontend/fe/images/fe_logo.jpg'
publication_type = 'magazine'
extra_css = ' body{font-family: Arial,Helvetica,sans-serif } '
conversion_options = {
'comment' : description
, 'tags' : category
, 'publisher' : publisher
, 'language' : language
}
keep_only_tags = [dict(attrs={'class':'txt'})]
remove_attributes = ['width','height']
feeds = [(u'Articles', u'http://www.expressindia.com/syndications/fe.xml')]
def print_version(self, url):
article_raw = url.rpartition('/')[0]
article_id = article_raw.rpartition('/')[2]
return 'http://www.financialexpress.com/printer/news/' + article_id + '/'
def preprocess_html(self, soup):
for item in soup.findAll(style=True):
del item['style']
return soup