calibre/recipes/the_oz.recipe
2020-12-23 10:39:43 +05:30

69 lines
2.4 KiB
Python

#!/usr/bin/env python
__license__ = 'GPL v3'
__copyright__ = '2009, Matthew Briggs'
__docformat__ = 'restructuredtext en'
'''
http://www.theaustralian.news.com.au/
'''
from calibre.web.feeds.news import BasicNewsRecipe
def classes(classes):
q = frozenset(classes.split(' '))
return dict(attrs={
'class': lambda x: x and frozenset(x.split()).intersection(q)})
class DailyTelegraph(BasicNewsRecipe):
title = u'The Australian'
__author__ = u'Kovid Goyal'
description = (u'National broadsheet newspaper from down under - colloquially known as The Oz'
'. You will need to have a subscription to '
'http://www.theaustralian.com.au to get full articles.')
language = 'en_AU'
oldest_article = 2
needs_subscription = 'optional'
max_articles_per_feed = 30
remove_javascript = True
no_stylesheets = True
encoding = 'utf8'
remove_empty_feeds = True
ignore_duplicate_articles = {'url'}
keep_only_tags = [
classes('story-headline'),
dict(id='story'),
]
remove_tags = [
dict(id='comments'),
classes('story-info story-header-tools module-controls story-sidebar'
' story-footer story-footer-tools story-extras story-related vms-nav'
' vms-endcard vms-discover share-tools story-comments-link'
' vms-controls ooyala-player vms-countdown vms-header comments')
]
feeds = [
(u'National News', u'https://www.news.com.au/content-feeds/latest-news-national/'),
(u'World News', u'https://www.news.com.au/content-feeds/latest-news-world/'),
(u'Entertainment', u'https://www.news.com.au/content-feeds/latest-news-entertainment/'),
(u'Technology', u'https://www.news.com.au/content-feeds/latest-news-technology/'),
(u'Lifestyle', u'https://www.news.com.au/content-feeds/latest-news-lifestyle/'),
(u'Sport', u'https://www.news.com.au/content-feeds/latest-news-sport/'),
(u'Finance', u'https://www.news.com.au/content-feeds/latest-news-finance/'),
(u'Travel', u'https://www.news.com.au/content-feeds/latest-news-travel/'),
]
def get_article_url(self, article):
ans = article.link
if '/video/' in ans:
return
return ans
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
img['src'] = img['data-src']
return soup