calibre/recipes/national_post.recipe

from calibre.web.feeds.recipes import BasicNewsRecipe


class NYTimes(BasicNewsRecipe):

    title = 'National Post'
    __author__ = 'Krittika Goyal'
    description = 'Canadian national newspaper'
    timefmt = ' [%d %b, %Y]'
    language = 'en_CA'
    needs_subscription = False

    no_stylesheets = True
    auto_cleanup = True
    auto_cleanup_keep = '//*[@class="npStoryPhoto npTxtPlain"]'

    # TO GET ARTICLE TOC
    def nejm_get_index(self):
        return self.index_to_soup('http://www.nationalpost.com/todays-paper/index.html')

    # To parse artice toc
    def parse_index(self):
        soup = self.nejm_get_index()

        div = soup.find(id='npContentMain')

        current_section = None
        current_articles = []
        feeds = []
        for x in div.findAll(True):
            if x.name == 'h4':
                # Section found
                if current_articles and current_section:
                    feeds.append((current_section, current_articles))
                current_section = self.tag_to_string(x)
                current_articles = []
                self.log('\tFound section:', current_section)
            if current_section is not None and x.name == 'h5':
                # Article found
                title = self.tag_to_string(x)
                a = x.find('a', href=True)
                if a is None:
                    continue
                url = a.get('href', False)
                if not url or not title:
                    continue
                # if url.startswith('story'):
                # url = 'http://www.nationalpost.com/todays-paper/'+url
                self.log('\t\tFound article:', title)
                self.log('\t\t\t', url)
                current_articles.append({'title': title, 'url': url,
                                         'description': '', 'date': ''})

        if current_articles and current_section:
            feeds.append((current_section, current_articles))

        return feeds