from calibre.web.feeds.news import BasicNewsRecipe, classes

class SwarajyaMag(BasicNewsRecipe):
    title = u'Swarajya Magazine'
    __author__ = 'unkn0wn'
    description = 'Swarajya - a big tent for liberal right of centre discourse that reaches out, engages and caters to the new India.'
    language = 'en_GB'
    no_stylesheets = True
    remove_javascript = True
    use_embedded_content = False
    remove_attributes = ['style', 'height', 'width']
    encoding = 'utf-8'
    
    keep_only_tags = [
        classes('_2PqtR _1sMRD ntw8h author-bio'),
    ]

    remove_tags = [
        classes('_JscD _2r17a'),
    ]
    
    def preprocess_html(self, soup):
        for img in soup.findAll('img', attrs={'data-src': True}):
            img['src'] = img['data-src'].split('?')[0] 
        return soup
    
    def parse_index(self):
        soup = self.index_to_soup('https://swarajyamag.com/issue/a-catalyst-for-growth')
        ans = []
        
        for a in soup.findAll(**classes('_2eOQr')):
            url = a['href']
            if url.startswith('/'):
                url = 'https://swarajyamag.com' + url
            title = self.tag_to_string(a)
            self.log(title, ' at ', url)
            ans.append({'title': title, 'url': url})
        return [('Articles', ans)]