#!/usr/bin/env  python

__license__   = 'GPL v3'
__copyright__ = '2009, Darko Miletic <darko.miletic at gmail.com>'
'''
seattletimes.nwsource.com
'''

from calibre.web.feeds.news import BasicNewsRecipe

class SeattleTimes(BasicNewsRecipe):
    title                 = 'The Seattle Times'
    __author__            = 'Darko Miletic'
    description           = 'News from Seattle and USA'
    publisher             = 'The Seattle Times'
    category              = 'news, politics, USA'
    oldest_article        = 2
    max_articles_per_feed = 100
    no_stylesheets        = True
    use_embedded_content  = False
    encoding              = 'cp1252'
    language = 'en'

    feeds              = [
                          (u'Top Stories',
                              u'http://seattletimes.nwsource.com/rss/home.xml'),
                          #(u'Articles', u'http://seattletimes.nwsource.com/rss/seattletimes.xml')
                          (u'Business & Technology',
                              u'http://seattletimes.nwsource.com/rss/businesstechnology.xml'),
                          (u'Personal Technology',
                              u'http://seattletimes.nwsource.com/rss/personaltechnology.xml'),
                          (u'Entertainment & the Arts',
                              u'http://seattletimes.nwsource.com/rss/artsentertainment.xml'),
                          (u'Health',
                              u'http://seattletimes.nwsource.com/rss/health.xml'),
                          (u'Living',
                              u'http://seattletimes.nwsource.com/rss/living.xml'),
                          (u'Local News',
                              u'http://seattletimes.nwsource.com/rss/localnews.xml'),
                          (u'Nation & World',
                              u'http://seattletimes.nwsource.com/rss/nationworld.xml'),
                          (u'Opinion',
                              u'http://seattletimes.nwsource.com/rss/opinion.xml'),
                          (u'Politics',
                              u'http://seattletimes.nwsource.com/rss/politics.xml'),
                          (u'Sports',
                              u'http://seattletimes.nwsource.com/rss/sports.xml'),
                          (u'Nicole Brodeur',
                              u'http://seattletimes.nwsource.com/rss/nicolebrodeur.xml'),
                          (u'Danny Westneat',
                              u'http://seattletimes.nwsource.com/rss/dannywestneat.xml'),
                          (u'Jerry Large',
                              u'http://seattletimes.nwsource.com/rss/jerrylarge.xml'),
                          (u'Ron Judd',
                              u'http://seattletimes.nwsource.com/rss/ronjudd.xml'),
                          (u'Education',
                              u'http://seattletimes.nwsource.com/rss/education.xml'),
                          (u'Letters to the Editor',
                              u'http://seattletimes.nwsource.com/rss/northwestvoices.xml'),
                          (u'Travel',
                              u'http://seattletimes.nwsource.com/rss/travel.xml'),
                          (u'Outdoors',
                              u'http://seattletimes.nwsource.com/rss/outdoors.xml'),
                          (u'Steve Kelley',
                              u'http://seattletimes.nwsource.com/rss/stevekelley.xml'),
                          (u'Jerry Brewer',
                              u'http://seattletimes.nwsource.com/rss/jerrybrewer.xml'),
                          (u'Most Read Articles',
                              u'http://seattletimes.nwsource.com/rss/mostreadarticles.xml'),
                         ]

    keep_only_tags = [dict(id='content')]
    remove_tags        = [
                             dict(name=['object','link','script']),
                            {'class':['permission', 'note', 'bottomtools',
                                'homedelivery']},
                            dict(id=["rightcolumn", 'footer', 'adbottom']),
                         ]

    def print_version(self, url):
        return url
        start_url, sep, rest_url = url.rpartition('_')
        rurl, rsep, article_id = start_url.rpartition('/')
        return u'http://seattletimes.nwsource.com/cgi-bin/PrintStory.pl?document_id=' + article_id

    def preprocess_html(self, soup):
        mtag = '<meta http-equiv="Content-Language" content="en-US"/>'
        soup.head.insert(0,mtag)
        for item in soup.findAll(style=True):
            del item['style']
        return soup