mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
79 lines
3.0 KiB
Plaintext
79 lines
3.0 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
foxnews.com
|
|
'''
|
|
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
class FoxNews(BasicNewsRecipe):
|
|
title = 'FOX News'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Breaking News from FOX'
|
|
publisher = 'FOXNews.com'
|
|
category = 'news, breaking news, latest news, current news, world news, national news, USA'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 200
|
|
no_stylesheets = True
|
|
encoding = 'utf8'
|
|
use_embedded_content = False
|
|
language = 'en'
|
|
publication_type = 'newsportal'
|
|
remove_empty_feeds = True
|
|
extra_css = """
|
|
body{font-family: Arial,sans-serif }
|
|
.caption{font-size: x-small}
|
|
.author,.dateline{font-size: small}
|
|
"""
|
|
|
|
conversion_options = {
|
|
'comment' : description
|
|
, 'tags' : category
|
|
, 'publisher' : publisher
|
|
, 'language' : language
|
|
}
|
|
|
|
remove_attributes = ['xmlns','lang']
|
|
|
|
remove_tags=[
|
|
dict(attrs={'class':['user-control','logo','ad-300x250','url-description']})
|
|
,dict(name=['meta','base','link','iframe','object','embed'])
|
|
]
|
|
|
|
keep_only_tags=[dict(attrs={'id':'article-print'})]
|
|
remove_tags_after =dict(attrs={'class':'url-description'})
|
|
|
|
feeds = [
|
|
(u'Latest Headlines', u'http://feeds.foxnews.com/foxnews/latest' )
|
|
,(u'National' , u'http://feeds.foxnews.com/foxnews/national' )
|
|
,(u'World' , u'http://feeds.foxnews.com/foxnews/world' )
|
|
,(u'Politics' , u'http://feeds.foxnews.com/foxnews/politics' )
|
|
,(u'Business' , u'http://feeds.foxnews.com/foxnews/business' )
|
|
,(u'SciTech' , u'http://feeds.foxnews.com/foxnews/scitech' )
|
|
,(u'Health' , u'http://feeds.foxnews.com/foxnews/health' )
|
|
,(u'Entertainment' , u'http://feeds.foxnews.com/foxnews/entertainment' )
|
|
]
|
|
|
|
def print_version(self, url):
|
|
return url + 'print'
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
for item in soup.findAll('a'):
|
|
limg = item.find('img')
|
|
if item.string is not None:
|
|
str = item.string
|
|
item.replaceWith(str)
|
|
else:
|
|
if limg:
|
|
item.name = 'div'
|
|
item.attrs = []
|
|
else:
|
|
str = self.tag_to_string(item)
|
|
item.replaceWith(str)
|
|
for item in soup.findAll('img'):
|
|
if not item.has_key('alt'):
|
|
item['alt'] = 'image'
|
|
return soup
|
|
|