__license__   = 'GPL v3'
__copyright__ = '2010-2012, Darko Miletic <darko.miletic at gmail.com>'
'''
www.haaretz.com
'''

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

class Haaretz_en(BasicNewsRecipe):
    title                 = 'Haaretz'
    __author__            = 'Darko Miletic'
    description           = "Haaretz.com is the world's leading English-language Website for real-time news and analysis of Israel and the Middle East."
    publisher             = 'Haaretz'
    category              = "news, Haaretz, Israel news, Israel newspapers, Israel business news, Israel financial news, Israeli news,Israeli newspaper, Israeli newspapers, news from Israel, news in Israel, news Israel, news on Israel, newspaper Israel, Israel sports news, Israel diplomacy news"
    oldest_article        = 2
    max_articles_per_feed = 200
    no_stylesheets        = True
    encoding              = 'utf8'
    use_embedded_content  = False
    language              = 'en_IL'
    needs_subscription    = True
    remove_empty_feeds    = True
    publication_type      = 'newspaper'
    PREFIX                = 'http://www.haaretz.com'
    masthead_url          = PREFIX + '/images/logos/HaaretzLogo.gif'
    extra_css             = """
                                body{font-family: Verdana,Arial,Helvetica,sans-serif }
                                h1, .articleBody {font-family: Georgia, serif}
                                .authorBar {font-size: small}
                            """

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

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

    keep_only_tags    = [dict(attrs={'id':'threecolumns'})]
    remove_attributes = ['width','height']
    remove_tags       = [
                           dict(name=['iframe','link','object','embed'])
                          ,dict(name='div',attrs={'class':'rightcol'})
                        ]


    feeds = [
              (u'Headlines'             , 'http://feeds.feedburner.com/haaretz/LBao'        )
             ,(u'Opinion'               , 'http://feeds.feedburner.com/haaretz/opinions'    )
             ,(u'Defence and diplomacy' , 'http://feeds.feedburner.com/DefenseAndDiplomacy' )
             ,(u'National'              , 'http://feeds.feedburner.com/haaretz/National'    )
             ,(u'International'         , 'http://feeds.feedburner.com/InternationalRss'    )
             ,(u'Jewish World'          , 'http://feeds.feedburner.com/JewishWorldRss'      )
             ,(u'Business'              , 'http://feeds.feedburner.com/BusinessPrintRss'    )
             ,(u'Real Estate'           , 'http://feeds.feedburner.com/RealEstatePrintRss'  )
             ,(u'Features'              , 'http://feeds.feedburner.com/FeaturesPrintRss'    )
             ,(u'Arts & Leisure'        , 'http://feeds.feedburner.com/ArtsAndLeisureRss'   )
             ,(u'Books'                 , 'http://www.haaretz.com/cmlink/books-rss-1.264947?localLinksEnabled=false')
             ,(u'Food & Wine'           , 'http://feeds.feedburner.com/FoodAndWinePrintRss' )
             ,(u'Sports'                , 'http://feeds.feedburner.com/haaretz/Sport'       )
            ]

    def get_browser(self):
        br = BasicNewsRecipe.get_browser(self)
        br.open(self.PREFIX)
        if self.username is not None and self.password is not None:
            data = urllib.urlencode({ 'cb':'parseEngReply'
                                     ,'newsso':'true'
                                     ,'fromlogin':'true'
                                     ,'layer':'eng_login'
                                     ,'userName':self.username
                                     ,'password':self.password
                                   })
            br.open('https://sso.haaretz.com/sso/sso/signIn',data)
        return br

    def get_article_url(self, article):
        url = BasicNewsRecipe.get_article_url(self, article)
        return self.browser.open_novisit(url).geturl()

    def print_version(self, url):
        article = url.rpartition('/')[2]
        return 'http://www.haaretz.com/misc/article-print-page/' + article

    def preprocess_raw_html(self, raw, url):
       return '<html><head>'+raw[raw.find('</head>'):]