mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-11-24 15:25:01 -05:00
75 lines
3.4 KiB
Plaintext
75 lines
3.4 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
foxnews.com
|
|
'''
|
|
|
|
import re
|
|
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 } img{margin-bottom: 0.4em} .caption{font-size: x-small} '
|
|
|
|
preprocess_regexps = [
|
|
(re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')
|
|
]
|
|
|
|
conversion_options = {
|
|
'comment' : description
|
|
, 'tags' : category
|
|
, 'publisher' : publisher
|
|
, 'language' : language
|
|
}
|
|
|
|
remove_attributes = ['xmlns']
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'id' :['story','browse-story-content']})
|
|
,dict(name='div', attrs={'class':['posts articles','slideshow']})
|
|
,dict(name='h4' , attrs={'class':'storyDate'})
|
|
,dict(name='h1' , attrs={'xmlns:functx':'http://www.functx.com'})
|
|
,dict(name='div', attrs={'class':'authInfo'})
|
|
,dict(name='div', attrs={'id':'articleCont'})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name='div', attrs={'class':['share-links','quigo quigo2','share-text','storyControls','socShare','btm-links']})
|
|
,dict(name='div', attrs={'id' :['otherMedia','loomia_display','img-all-path','story-vcmId','story-url','pane-browse-story-comments','story_related']})
|
|
,dict(name='ul' , attrs={'class':['tools','tools alt','tools alt2','tabs']})
|
|
,dict(name='a' , attrs={'class':'join-discussion'})
|
|
,dict(name='ul' , attrs={'class':['tools','tools alt','tools alt2']})
|
|
,dict(name='p' , attrs={'class':'see_fullarchive'})
|
|
,dict(name=['object','embed','link','script'])
|
|
]
|
|
|
|
|
|
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 preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
return self.adeify_images(soup)
|
|
|