from calibre.web.feeds.news import BasicNewsRecipe
## History:
## 1: Base Version
## 2: Added rules for wdr.de, ndr.de, br-online.de
## 3: Added rules for rbb-online.de, boerse.ard.de, sportschau.de

class Tagesschau(BasicNewsRecipe):
     title          = 'Tagesschau'
     description    = 'Nachrichten der ARD'
     publisher      = 'ARD'
     language       = 'de'
     version        = 3

     __author__            = 'Florian Andreas Pfaff, a.peter'
     oldest_article        = 7
     max_articles_per_feed = 100
     no_stylesheets        = True
     remove_javascript     = True

     feeds          = [('Tagesschau', 'http://www.tagesschau.de/xml/rss2')]

     remove_tags    = [
                       dict(name='div', attrs={'class':['linksZumThema schmal','teaserBox','boxMoreLinks','directLinks','teaserBox boxtext','fPlayer','zitatBox breit flashaudio','infobox ','footer clearfix','inner recommendations','teaser teaser-08 nachrichten smallstandard','infobox-rechts','infobox-links','csl2','teaserBox metaBlock','articleA archiveDisclaimer']}),
                       dict(name='div', attrs={'id':['pageFunctions']}), ## wdr.de
                       dict(name='div', attrs={'class':['chart','footerService','toplink','assetsLeft','assetsFullsize']}), ## boerse.ard.de
                       dict(name='div', attrs={'class':['ardMehrZumThemaLinks','socialBookmarks','ardContentEnd','ardDisclaimer']}), ## sportschau.de
                       dict(name='div', attrs={'id':['socialBookmarks','seitenanfang','comment']}),
                       dict(name='ul',  attrs={'class':['directLinks','directLinks weltatlas','iconList','right']}),
                       dict(name='strong', attrs={'class':['boxTitle inv','inv']}),
                       dict(name='div', attrs={'class':['moreInfo right','moreInfo']}),
                       dict(name='span', attrs={'class':['videoLink']}),
                       dict(name='img', attrs={'class':['zoom float_right']}),
                       dict(name='a', attrs={'id':['zoom']})
                      ]
     keep_only_tags = [dict(name='div', attrs={'id':'centerCol'}),
                       dict(name='div', attrs={'id':['mainColumn','ardContent']}),
                       dict(name='div', attrs={'class':['narrow clearfix','beitrag','detail_inlay','containerArticle noBorder','span-8']})]

     def get_masthead_url(self):
          return 'http://intern.tagesschau.de/html/img/image.jpg'