mirror of
https://github.com/kovidgoyal/calibre.git
synced 2025-07-09 03:04:10 -04:00
65 lines
3.5 KiB
Python
65 lines
3.5 KiB
Python
__license__ = 'GPL v3'
|
|
__copyright__ = '2010, limawhiskey <limawhiskey at gmail.com>'
|
|
'''
|
|
news.bbc.co.uk/sport/
|
|
'''
|
|
import re
|
|
|
|
from calibre.web.feeds.recipes import BasicNewsRecipe
|
|
|
|
|
|
class BBC(BasicNewsRecipe):
|
|
title = 'BBC Sport'
|
|
__author__ = 'limawhiskey, Darko Miletic, Starson17'
|
|
description = 'Sports news from UK. A fast version that does not download pictures'
|
|
oldest_article = 2
|
|
max_articles_per_feed = 100
|
|
no_stylesheets = True
|
|
use_embedded_content = False
|
|
encoding = 'utf8'
|
|
publisher = 'BBC'
|
|
category = 'sport, news, UK, world'
|
|
language = 'en_GB'
|
|
publication_type = 'newsportal'
|
|
extra_css = ' body{ font-family: Verdana,Helvetica,Arial,sans-serif } .introduction{font-weight: bold} .story-feature{display: block; padding: 0; border: 1px solid; width: 40%; font-size: small} .story-feature h2{text-align: center; text-transform: uppercase} ' # noqa: E501
|
|
preprocess_regexps = [(re.compile(r'<!--.*?-->', re.DOTALL), lambda m: '')]
|
|
conversion_options = {
|
|
'comments': description, 'tags': category, 'language': language, 'publisher': publisher, 'linearize_tables': True
|
|
}
|
|
|
|
keep_only_tags = [
|
|
dict(name='div', attrs={'class': ['ds', 'mxb']}),
|
|
dict(attrs={'class': ['story-body', 'storybody']})
|
|
]
|
|
|
|
remove_tags = [
|
|
dict(name='div', attrs={'class': ['storyextra', 'share-help', 'embedded-hyper',
|
|
'story-feature wide ', 'story-feature narrow', 'cap', 'caption', 'q1', 'sihf',
|
|
'mva', 'videoInStoryC', 'sharesb', 'mvtb']}),
|
|
dict(name=['img']), dict(name=['br'])
|
|
]
|
|
|
|
remove_attributes = ['width', 'height']
|
|
|
|
feeds = [
|
|
('Sport Front Page',
|
|
'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/front_page/rss.xml'),
|
|
('Football', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/football/rss.xml'),
|
|
('Cricket', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/cricket/rss.xml'),
|
|
('Formula 1', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/motorsport/formula_one/rss.xml'),
|
|
('Commonwealth Games', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/commonwealth_games/delhi_2010/rss.xml'),
|
|
('Golf', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/golf/rss.xml'),
|
|
('Rugby Union', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/rugby_union/rss.xml'),
|
|
('Rugby League', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/rugby_league/rss.xml'),
|
|
('Tennis', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/tennis/rss.xml'),
|
|
('Motorsport', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/motorsport/rss.xml'),
|
|
('Boxing', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/boxing/rss.xml'),
|
|
('Athletics', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/athletics/rss.xml'),
|
|
('Snooker', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/other_sports/snooker/rss.xml'),
|
|
('Horse Racing', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/other_sports/horse_racing/rss.xml'),
|
|
('Cycling', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/other_sports/cycling/rss.xml'),
|
|
('Disability Sport', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/other_sports/disability_sport/rss.xml'),
|
|
('Other Sport', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/other_sports/rss.xml'),
|
|
('Olympics 2012', 'http://newsrss.bbc.co.uk/rss/sportonline_uk_edition/olympics/london_2012/rss.xml'),
|
|
]
|