Read The West Australian 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 »

News from Australia

Language: en

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

Schedule Every morning

			  __license__   = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
thewest.com.au
'''

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

class TheWest(BasicNewsRecipe):
    title                 = 'The West Australian'
    __author__            = 'Darko Miletic'
    description           = 'News from Australia'
    publisher             = 'thewest.com.au'
    category              = 'news, politics, Australia'
    oldest_article        = 2
    max_articles_per_feed = 200
    no_stylesheets        = True
    encoding              = 'utf8'
    use_embedded_content  = False
    language              = 'en_AU'
    remove_empty_feeds    = True
    publication_type      = 'newspaper'
    masthead_url          = 'http://l.yimg.com/ao/i/mp/properties/news/02/wan/img/wan-logo-h49.png'
    extra_css             = ' .article{font-family: Arial,Helvetica,sans-serif } .image{font-size: x-small} '

    preprocess_regexps = [
       (re.compile(r'</title>.*?</head>', re.DOTALL|re.IGNORECASE),lambda match: '</title></head>')
    ]

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

    remove_tags       = [
                          dict(attrs={'class':['tools','lhs']})
                         ,dict(attrs={'id'   :'tools-bottom'})
                         ,dict(attrs={'href' :'http://twitter.com/thewest_com_au'})
                        ]
    keep_only_tags    = [dict(attrs={'class':'mod article'})]
    remove_attributes = ['width','height']


    feeds = [
               (u'WA News'       , u'http://d.yimg.com/au.rss.news.yahoo.com/thewest/wa.xml'            )
              ,(u'National'      , u'http://d.yimg.com/au.rss.news.yahoo.com/thewest/national.xml'      )
              ,(u'World'         , u'http://d.yimg.com/au.rss.news.yahoo.com/thewest/world.xml'         )
              ,(u'Offbeat'       , u'http://d.yimg.com/au.rss.news.yahoo.com/thewest/offbeat.xml'       )
              ,(u'Business'      , u'http://d.yimg.com/au.rss.news.yahoo.com/thewest/business.xml'      )
              ,(u'Sport'         , u'http://d.yimg.com/au.rss.news.yahoo.com/thewest/sport.xml'         )
              ,(u'Entertainment' , u'http://d.yimg.com/au.rss.news.yahoo.com/thewest/entertainment.xml' )
              ,(u'Travel'        , u'http://d.yimg.com/au.rss.news.yahoo.com/thewest/travel.xml'        )
              ,(u'Life+Style'    , u'http://d.yimg.com/au.rss.news.yahoo.com/thewest/lifestyle.xml'     )
            ]

    def get_article_url(self, article):
        return article.get('guid',  None)

    def preprocess_html(self, soup):
        return self.adeify_images(soup)