__license__   = 'GPL v3'
__copyright__ = '2009-2010, Darko Miletic <darko.miletic at gmail.com>'
'''
www.boston.com
'''

from calibre.web.feeds.recipes import BasicNewsRecipe

class BusinessStandard(BasicNewsRecipe):
    title                  = 'The Boston Globe'
    __author__             = 'Darko Miletic'
    description            = 'News from Boston'
    oldest_article         = 2
    max_articles_per_feed  = 100
    no_stylesheets         = True
    delay                  = 1
    use_embedded_content   = False
    encoding               = 'cp1252'
    publisher              = 'Boston'
    category               = 'news, boston, usa, world'
    language               = 'en'
    publication_type       = 'newspaper'
    masthead_url           = 'http://cache.boston.com/images/globe/grslider/the_boston_globe.gif'
    extra_css              = ' body{font-family: Georgia, serif} div#articleBodyTop{display:block} '

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

    keep_only_tags   = [dict(attrs={'id':['INDblogEntry','blogEntry','articleHeader','articleGraphs','galleryShell']})]
    remove_tags      = [
                          dict(name=['object','link','script','iframe'])
                         ,dict(attrs={'id':['blogheadTools','bdc_emailWidget','tools','relatedContent']})
                       ]

    feeds = [
               (u'Top Stories'  , u'http://feeds.boston.com/boston/topstories'              )
              ,(u'Patriots news', u'http://feeds.boston.com/boston/sports/football/patriots')
              ,(u'National news', u'http://feeds.boston.com/boston/news/nation'             )
              ,(u'World news'   , u'http://feeds.boston.com/boston/news/world'              )
            ]

    def print_version(self, url):
        return url + '?page=full'

    def get_article_url(self, article):
        rawarticle = article.get('guid', None)
        return rawarticle.rpartition('?')[0]