__license__   = 'GPL v3'
__copyright__ = '2010, Darko Miletic <darko.miletic at gmail.com>'
'''
news.bbc.co.uk
'''

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

class BBC(BasicNewsRecipe):
    title                  = 'The BBC'
    __author__             = 'Darko Miletic'
    description            = 'Global news and current affairs from the British Broadcasting Corporation'
    oldest_article         = 2
    max_articles_per_feed  = 100
    no_stylesheets         = True
    #delay                  = 1
    use_embedded_content   = False
    encoding               = 'utf8'
    publisher              = 'BBC'
    category               = '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} '
    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(attrs={'id'   :['meta-information','story-body']})
                          ,dict(attrs={'class':['mxb'             ,'storybody' ]})
                        ]
    remove_tags       = [
                           dict(name=['object','link','table'])
                          ,dict(attrs={'class':['caption','caption full-width','story-actions','hidden','sharesb','audioInStoryC']})
                        ]
    remove_tags_after = dict(attrs={'class':'sharesb'})
    remove_attributes = ['width','height']

    feeds          = [
                      ('News Front Page', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/front_page/rss.xml'),
                      ('Science/Nature', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/science/nature/rss.xml'),
                      ('Technology', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/technology/rss.xml'),
                      ('Entertainment', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/entertainment/rss.xml'),
                      ('Magazine', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/uk_news/magazine/rss.xml'),
                      ('Business', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/business/rss.xml'),
                      ('Health', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/health/rss.xml'),
                      ('Americas', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/americas/rss.xml'),
                      ('Europe', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/europe/rss.xml'),
                      ('South Asia', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/south_asia/rss.xml'),
                      ('UK', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/uk_news/rss.xml'),
                      ('Asia-Pacific', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/asia-pacific/rss.xml'),
                      ('Africa', 'http://newsrss.bbc.co.uk/rss/newsonline_world_edition/africa/rss.xml'),
                    ]