import re from calibre.web.feeds.news import BasicNewsRecipe class Reuters(BasicNewsRecipe): title = 'Reuters' description = 'Global news' __author__ = 'Kovid Goyal and Sujata Raman' use_embedded_content = False language = 'en' max_articles_per_feed = 10 no_stylesheets = True remove_javascript = True extra_css = ''' body{font-family:arial,helvetica,sans;} h1{ font-size:larger ; font-weight:bold; } .byline{color:#006E97;font-size:x-small; font-weight:bold;} .location{font-size:x-small; font-weight:bold;} .timestamp{font-size:x-small; } ''' keep_only_tags = [dict(name='div', attrs={'class':'column2 gridPanel grid8'})] remove_tags = [dict(name='div', attrs={'id':['recommendedArticles','relatedNews','relatedVideo','relatedFactboxes']}), dict(name='p', attrs={'class':['relatedTopics']}), dict(name='a', attrs={'id':['fullSizeLink']}), dict(name='div', attrs={'class':['photoNav','relatedTopicButtons','articleComments','gridPanel grid8','footerHalf gridPanel grid1','gridPanel grid2','gridPanel grid3']}),] preprocess_regexps = [ (re.compile(i[0], re.IGNORECASE | re.DOTALL), i[1]) for i in [ ##(r'.*?' , lambda match : ''), (r'

.*?', lambda match : ''), (r'.*?', lambda match : ''), (r'.*?', lambda match : ''), (r'.*?

', lambda match : ''), (r'

Share:

.*?', lambda match : ''), (r'

.*?

', lambda match : '

'), ] ] feeds = [ ('Top Stories', 'http://feeds.reuters.com/reuters/topNews?format=xml'), ('US News', 'http://feeds.reuters.com/reuters/domesticNews?format=xml'), ('World News', 'http://feeds.reuters.com/reuters/worldNews?format=xml'), ('Politics News', 'http://feeds.reuters.com/reuters/politicsNews?format=xml'), ('Science News', 'http://feeds.reuters.com/reuters/scienceNews?format=xml'), ('Environment News', 'http://feeds.reuters.com/reuters/Environment?format=xml'), ('Technology News', 'http://feeds.reuters.com/reuters/technologyNews?format=xml'), ('Oddly Enough News', 'http://feeds.reuters.com/reuters/oddlyEnoughNews?format=xml') ]