ekathemerini.recipe

from calibre.web.feeds.recipes import BasicNewsRecipe
from calibre.ebooks.BeautifulSoup import BeautifulSoup, BeautifulStoneSoup

class Ekathimerini(BasicNewsRecipe):
    title                  = 'ekathimerini'
    __author__ = 'Thomas Scholl'
    description            = 'News from Greece, English edition'
    masthead_url           = 'http://wwk.kathimerini.gr/webadmin/EnglishNew/gifs/logo.gif'
    max_articles_per_feed  = 100
    oldest_article         = 100
    publisher              = 'Kathimerini'
    category               = 'news, GR'
    language               = 'en_GR'
    encoding               = 'windows-1253'
    conversion_options     = { 'linearize_tables': True}
    no_stylesheets         = True
    delay                  = 1
    keep_only_tags         = [dict(name='td', attrs={'class':'news'})]

    rss_url = 'http://ws.kathimerini.gr/xml_files/latestnews.xml'

    def find_articles(self, idx, category):
        for article in idx.findAll('item'):
            cat = u''
            cat_elem = article.find('subcat')
            if cat_elem:
                cat = self.tag_to_string(cat_elem)

            if cat == category:
                desc_html = self.tag_to_string(article.find('description'))
                description = self.tag_to_string(BeautifulSoup(desc_html))

                a = {
                        'title':  self.tag_to_string(article.find('title')),
                        'url': self.tag_to_string(article.find('link')),
                        'description': description,
                        'date' : self.tag_to_string(article.find('pubdate')),
                        }
                yield a


    def parse_index(self):
        idx_contents = self.browser.open(self.rss_url).read()
        idx = BeautifulStoneSoup(idx_contents, convertEntities=BeautifulStoneSoup.XML_ENTITIES)

        cats = list(set([self.tag_to_string(subcat) for subcat in idx.findAll('subcat')]))
        cats.sort()

        feeds = [(u'News',list(self.find_articles(idx, u'')))]

        for cat in cats:
            feeds.append((cat.capitalize(), list(self.find_articles(idx, cat))))

        return feeds

    def print_version(self, url):
       return url.replace('http://www.ekathimerini.com/4dcgi/', 'http://www.ekathimerini.com/4Dcgi/4dcgi/')