Read The Straits Times on your iPad or Kindle in no time. Click download to load the free ebook on your reader.

Check out all the available public recipes or write your own with these quick start guides. ReadBeam is built on calibre, so everything in the docs and the fora applies here as well.

Download for free »

Singapore newspaper

Language: en

Requires Subscription: No, it's available as free ebook

Schedule Every morning

			  
__license__   = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
www.straitstimes.com
'''

import re
from calibre.web.feeds.recipes import BasicNewsRecipe

class StraitsTimes(BasicNewsRecipe):
    title                  = 'The Straits Times'
    __author__             = 'Darko Miletic'
    description            = 'Singapore newspaper'
    oldest_article         = 2
    max_articles_per_feed  = 100
    no_stylesheets         = True
    use_embedded_content   = False
    encoding               = 'cp1252'
    publisher              = 'Singapore Press Holdings Ltd.'
    category               = 'news, politics, singapore, asia'
    language               = 'en_SG'
    extra_css              = ' .top_headline{font-size: x-large; font-weight: bold} '

    conversion_options = {
                             'comments'  : description
                            ,'tags'      : category
                            ,'language'  : language
                            ,'publisher' : publisher
                         }

    preprocess_regexps = [
                           (re.compile(
                            r'<meta name="description" content="[^"]+"\s*/?>',
                            re.IGNORECASE|re.DOTALL),
                            lambda m:''),
                           (re.compile(r'<!--.+?-->', re.IGNORECASE|re.DOTALL),
                               lambda m: ''),
                         ]
    remove_tags = [
                     dict(name=['object','link','map'])
                    ,dict(name='div',attrs={'align':'left'})
                  ]

    keep_only_tags = [dict(name='div', attrs={'class':'stleft'})]
    remove_tags_after=dict(name='div',attrs={'class':'hr_thin'})

    feeds = [
               (u'Singapore'       , u'http://www.straitstimes.com/STI/STIFILES/rss/break_singapore.xml' )
              ,(u'SE Asia'         , u'http://www.straitstimes.com/STI/STIFILES/rss/break_sea.xml'       )
              ,(u'Money'           , u'http://www.straitstimes.com/STI/STIFILES/rss/break_money.xml'     )
              ,(u'Sport'           , u'http://www.straitstimes.com/STI/STIFILES/rss/break_sport.xml'     )
              ,(u'World'           , u'http://www.straitstimes.com/STI/STIFILES/rss/break_world.xml'     )
              ,(u'Tech & Science'  , u'http://www.straitstimes.com/STI/STIFILES/rss/break_tech.xml'      )
              ,(u'Lifestyle'       , u'http://www.straitstimes.com/STI/STIFILES/rss/break_lifestyle.xml' )
            ]

    def preprocess_html(self, soup):
        for item in soup.findAll(style=True):
            del item['style']
        return soup