calibre/recipes/abc_au.recipe
2020-05-16 15:05:19 +05:30

96 lines
4.6 KiB
Python

#!/usr/bin/env python
# vim:fileencoding=utf-8
from __future__ import unicode_literals, division, absolute_import, print_function
__license__ = 'GPL v3'
__copyright__ = '2020, Pat Stapleton <pat.stapleton at gmail.com>'
'''
Recipe for ABC News Australia (online)
'''
from calibre.web.feeds.news import BasicNewsRecipe
class ABCNews(BasicNewsRecipe):
title = 'ABC News'
language = 'en_AU'
__author__ = 'Pat Stapleton'
description = 'From the Australian Broadcasting Corporation. The ABC is owned and funded by the Australian Government, but is editorially independent.'
masthead_url = 'https://www.abc.net.au/cm/lb/8212706/data/news-logo-2017---desktop-print-data.png'
cover_url = 'https://www.abc.net.au/news/linkableblob/8413676/data/abc-news-og-data.jpg'
cover_margins = (0,20,'#000000')
scale_news_images_to_device = True
oldest_article = 2 # days
simultaneous_downloads = 10
max_articles_per_feed = 100
publication_type = 'newspaper'
# auto_cleanup = True # enable this as a backup option if recipe stops working
# use_embedded_content = False # if set to true will assume that all the article content is within the feed (i.e. won't try to fetch more data)
no_stylesheets = True
remove_javascript = True
keep_only_tags = [dict(id='content')] # the article content is contained in <main id="content" /> tag
# ************************************
# Regular expressions for remove_tags:
# ************************************
# remove aside tag - used for overlapping boxes within article
# aside_reg_exp = '^.*aside.*$'
# ************************************
# Clear out all the unwanted html tags:
# ************************************
remove_tags = [
# dict(name='aside', attrs={'name': re.compile(aside_reg_exp, re.IGNORECASE)})
{
'name': ['meta', 'link', 'noscript', 'aside']
},
{
'attrs': {
'data-component': ['Ticker', 'PublishedDate', 'Timestamp', 'Link', 'ShareLink', 'ShareUtility',
'RelatedStories', 'ArticleTopStories', 'ArticleTopStoriesCard', 'ArticleJustInStories',
'RelatedTopics', 'Player', 'ArticleSidebar', 'TopStoriesSidebar', 'UtilityBar']
}
}
]
# ************************************
# Tidy up the output to look neat for reading
# ************************************
remove_attributes = ['width', 'height', 'style']
extra_css = '.byline{font-size:smaller;margin-bottom:10px;}.inline-caption{display:block;font-size:smaller;text-decoration: none;}'
# ************************************
# Fix images (dynamically generated by ABC news)
# ************************************
def preprocess_html(self, soup):
for img in soup.findAll('img', attrs={'data-src': True}):
for x in img['data-src'].split():
if '/' in x:
img['src'] = x
return soup
compress_news_images = True
feeds = [
('Top Stories', 'https://www.abc.net.au/news/feed/45910/rss.xml'),
('Politics', 'https://www.abc.net.au/news/feed/1534/rss.xml'),
('World', 'https://www.abc.net.au/news/feed/4405318/rss.xml'),
('Business', 'https://www.abc.net.au/news/feed/51892/rss.xml'),
('Analysis', 'https://www.abc.net.au/news/feed/7571268/rss.xml'),
('Sport', 'https://www.abc.net.au/news/feed/2942460/rss.xml'),
('Science', 'https://www.abc.net.au/news/feed/8132426/rss.xml'),
('Health', 'https://www.abc.net.au/news/feed/9167762/rss.xml'),
('Arts and Entertainment', 'https://www.abc.net.au/news/feed/472/rss.xml'),
('Fact Check', 'https://www.abc.net.au/news/feed/5306468/rss.xml'),
# ('Adelaide', 'https://www.abc.net.au/news/feed/8057540/rss.xml'), #enable by removing # at start of line
# ('Brisbane', 'https://www.abc.net.au/news/feed/8053540/rss.xml'), #enable by removing # at start of line
# ('Canberra', 'https://www.abc.net.au/news/feed/8057234/rss.xml'), #enable by removing # at start of line
# ('Darwin', 'https://www.abc.net.au/news/feed/8057648/rss.xml'), #enable by removing # at start of line
# ('Hobart', 'https://www.abc.net.au/news/feed/8054562/rss.xml'), #enable by removing # at start of line
# ('Melbourne', 'https://www.abc.net.au/news/feed/8057136/rss.xml'), #enable by removing # at start of line
# ('Perth', 'https://www.abc.net.au/news/feed/8057096/rss.xml'), #enable by removing # at start of line
# ('Sydney', 'https://www.abc.net.au/news/feed/8055316/rss.xml'), #enable by removing # at start of line
]