mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-06-23 15:30:45 -04:00
67 lines
2.8 KiB
Plaintext
67 lines
2.8 KiB
Plaintext
__license__ = 'GPL v3'
|
|
__copyright__ = '2010-2011, Darko Miletic <darko.miletic at gmail.com>'
|
|
'''
|
|
smh.com.au
|
|
'''
|
|
from calibre.web.feeds.news import BasicNewsRecipe
|
|
|
|
|
|
class Smh_au(BasicNewsRecipe):
|
|
title = 'The Sydney Morning Herald'
|
|
__author__ = 'Darko Miletic'
|
|
description = 'Breaking news from Sydney, Australia and the world. Features the latest business, sport, entertainment, travel, lifestyle, and technology news.' # noqa
|
|
publisher = 'Fairfax Digital'
|
|
category = 'news, politics, Australia, Sydney'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 200
|
|
no_stylesheets = True
|
|
ignore_duplicate_articles = {'title', 'url'}
|
|
use_embedded_content = False
|
|
encoding = 'utf-8'
|
|
use_embedded_content = False
|
|
language = 'en_AU'
|
|
remove_empty_feeds = True
|
|
masthead_url = 'http://images.smh.com.au/2010/02/02/1087188/smh-620.jpg'
|
|
publication_type = 'newspaper'
|
|
extra_css = """
|
|
h1{font-family: Georgia,"Times New Roman",Times,serif }
|
|
body{font-family: Arial,Helvetica,sans-serif}
|
|
.cT-imageLandscape,.cT-imagePortrait{font-size: x-small}
|
|
"""
|
|
|
|
feeds = [
|
|
('Politics', 'http://www.smh.com.au/rssheadlines/political-news/article/rss.xml'),
|
|
('NSW News', 'http://www.smh.com.au/rssheadlines/nsw/article/rss.xml'),
|
|
('World', 'http://www.smh.com.au/rssheadlines/world/article/rss.xml'),
|
|
('National', 'http://www.smh.com.au/rssheadlines/national/article/rss.xml'),
|
|
('Business', 'http://www.smh.com.au/rssheadlines/business/article/rss.xml'),
|
|
('Entertainment', 'http://feeds.smh.com.au/rssheadlines/entertainment.xml'),
|
|
('Technology', 'http://www.smh.com.au/rssheadlines/technology-news/article/rss.xml'),
|
|
('Health', 'http://www.smh.com.au/rssheadlines/health/article/rss.xml'),
|
|
('Sport', 'http://feeds.smh.com.au/rssheadlines/sport.xml'),
|
|
('Cricket', 'http://www.smh.com.au/rssheadlines/cricket/article/rss.xml'),
|
|
]
|
|
|
|
remove_tags_after = [
|
|
dict(name='div', attrs={'class': 'articleBody'})
|
|
]
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'id': 'content'})
|
|
]
|
|
remove_tags = [
|
|
dict(name='div', attrs={
|
|
'id': ['googleAds', 'moreGoogleAds', 'comments', 'video-player-content']}),
|
|
dict(name='div', attrs={'class': 'cT-imageMultimedia'}),
|
|
dict(name=['object', 'embed', 'iframe']),
|
|
dict(attrs={'class': 'hidden'}),
|
|
dict(name=['link', 'meta', 'base', 'embed', 'object', 'iframe'])
|
|
]
|
|
remove_attributes = ['width', 'height', 'lang']
|
|
|
|
def preprocess_html(self, soup):
|
|
for item in soup.findAll(style=True):
|
|
del item['style']
|
|
for item in soup.findAll('bod'):
|
|
item.name = 'div'
|
|
return soup
|