Bit of extra code added - removes the word "Tweet" that appeared occasionally at the end of articles.
Spoiler:
Code:
import time, re
from calibre.web.feeds.news import BasicNewsRecipe
class AdvancedUserRecipe1306097511(BasicNewsRecipe):
title = u'Metro UK'
description = 'News as provide by The Metro -UK'
__author__ = 'Dave Asbury'
no_stylesheets = True
oldest_article = 1
max_articles_per_feed = 25
remove_empty_feeds = True
remove_javascript = True
preprocess_regexps = [(re.compile(r'Tweet'), lambda a : '')]
language = 'en_GB'
masthead_url = 'http://e-edition.metro.co.uk/images/metro_logo.gif'
extra_css = 'h2 {font: sans-serif medium;}'
keep_only_tags = [
dict(name='h1'),dict(name='h2', attrs={'class':'h2'}),
dict(attrs={'class':['img-cnt figure']}),
dict(attrs={'class':['art-img']}),
dict(name='div', attrs={'class':'art-lft'})
]
remove_tags = [dict(name='div', attrs={'class':[ 'news m12 clrd clr-b p5t shareBtm', 'commentForm', 'metroCommentInnerWrap',
'art-rgt','pluck-app pluck-comm','news m12 clrd clr-l p5t', 'flt-r' ]}),
dict(attrs={'class':[ 'metroCommentFormWrap','commentText','commentsNav','avatar','submDateAndTime']})
]
feeds = [
(u'News', u'http://www.metro.co.uk/rss/news/'), (u'Money', u'http://www.metro.co.uk/rss/money/'), (u'Sport', u'http://www.metro.co.uk/rss/sport/'), (u'Film', u'http://www.metro.co.uk/rss/metrolife/film/'), (u'Music', u'http://www.metro.co.uk/rss/metrolife/music/'), (u'TV', u'http://www.metro.co.uk/rss/tv/'), (u'Showbiz', u'http://www.metro.co.uk/rss/showbiz/'), (u'Weird News', u'http://www.metro.co.uk/rss/weird/'), (u'Travel', u'http://www.metro.co.uk/rss/travel/'), (u'Lifestyle', u'http://www.metro.co.uk/rss/lifestyle/'), (u'Books', u'http://www.metro.co.uk/rss/lifestyle/books/'), (u'Food', u'http://www.metro.co.uk/rss/lifestyle/restaurants/')]