calibre/recipes/el_correo.recipe

#!/usr/bin/env python
# vim:fileencoding=utf-8
'''
http://www.elcorreo.com/
'''

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


class elcorreo(BasicNewsRecipe):
    title = 'El Correo'
    __author__ = 'unkn0wn'
    description = 'Daily newspaper in Bilbao and the Basque Country of northern Spain'
    oldest_article = 1  # days
    language = 'es'
    no_stylesheets = True
    remove_attributes = ['height', 'width', 'style']
    ignore_duplicate_articles = {'url'}
    encoding = 'utf-8'
    masthead_url = 'https://s1.ppllstatics.com/starfish/1.3.76/assets/images/logos/logo-elcorreo.svg'
    remove_empty_feeds = True
    resolve_internal_links = True
    max_articles_per_feed = 25  # articles
    compress_news_images = True

    recipe_specific_options = {
        'days': {
            'short': 'Oldest article to download from this news source. In days ',
            'long': 'For example, 0.5, gives you articles from the past 12 hours',
            'default': str(oldest_article)
        }
    }

    def __init__(self, *args, **kwargs):
        BasicNewsRecipe.__init__(self, *args, **kwargs)
        d = self.recipe_specific_options.get('days')
        if d and isinstance(d, str):
            self.oldest_article = float(d)

    extra_css = '''
        .v-mdl-ath__inf, .v-mdl-ath__p--2, .v-mdl-ath__p {font-size:small; color:#404040;}
        .v-fc, .v-a-fig {  text-align:center; font-size:small; }
        #sub { font-style:italic; color:#202020; }
        blockquote, em { color:#202020; }
        img { display:block; margin:0 auto; }
    '''

    def get_cover_url(self):
        from datetime import date
        return 'https://portada.iperiodico.es/' + date.today().strftime('%Y/%m/%d') + '_elcorreo.750.jpg'

    keep_only_tags = [
        dict(name='article', attrs={'class': lambda x: x and set(x.split()).intersection(
            {'v-a--d-bs', 'v-a--d-opn', 'v-a--d-rpg'})}),
        classes(
            'v-d--ab-c v-d--rpg'
        )
    ]

    remove_tags = [
        dict(name=['svg', 'section', 'nav']),
        dict(attrs={'data-voc-component':['dropdown', 'modal', 'slider-grab']}),
        classes(
            'v-mdl-ath__img-c v-adv v-i-b v-mdl-ath__c--2 v-d-cmp-adv v-d-cmp-nws '
            'v-pill-m--zoom v-stk-adv slider-grab g-artboard v-d-cmp-rld v-pill-m--glly'
        )
    ]

    def preprocess_html(self, soup):
        art = soup.find('article')
        h1 = soup.find('h1')
        h2 = soup.find('h2')
        if h1 and art:
            art.insert_before(h1)
        if h2 and h1:
            h1.insert_after(h2)
            h2.name = 'p'
            h2['id'] = 'sub'
        for but in soup.findAll('button'):
            if but.find('img'):
                but.name = 'div'
            else:
                but.extract()
        x = soup.find(**classes('v-mdl-ath__c'))
        if x:
            for p in x.findAll('p'):
                p.name = 'div'
        return soup

    def get_browser(self, *args, **kwargs):
        kwargs['user_agent'] = 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)'
        br = BasicNewsRecipe.get_browser(self, *args, **kwargs)
        br.addheaders += [
            ('Referer', 'https://www.google.com/'),
            ('X-Forwarded-For', '66.249.66.1')
        ]
        return br

    # https://www.elcorreo.com/rss/
    feeds = [
        ('Portada', 'http://www.elcorreo.com/rss/atom/portada'),
        ('Mundo', 'http://www.elcorreo.com/rss/atom/?section=internacional'),
        ('Bizkaia', 'http://www.elcorreo.com/rss/atom/?section=bizkaia'),
        ('Opinión', 'https://www.elcorreo.com/rss/atom/?section=opinion'),
        ('Internacional', 'https://www.elcorreo.com/rss/atom/?section=internacional'),
        ('Ciencia', 'https://www.elcorreo.com/rss/atom/?section=ciencia'),
        # ('Guipuzkoa', 'http://www.elcorreo.com/rss/atom/?section=gipuzkoa'),
        # ('Araba', 'http://www.elcorreo.com/rss/atom/?section=araba'),
        # ('La Rioja', 'http://www.elcorreo.com/rss/atom/?section=larioja'),
        # ('Miranda', 'http://www.elcorreo.com/rss/atom/?section=miranda'),
        ('Economía', 'http://www.elcorreo.com/rss/atom/?section=economia'),
        # ('Culturas', 'http://www.elcorreo.com/rss/atom/?section=culturas'),
        ('Politica', 'http://www.elcorreo.com/rss/atom/?section=politica'),
        # ('De tiendas', 'https://www.elcorreo.com/rss/atom/?section=de-tiendas'),
        # ('Elecciones', 'https://www.elcorreo.com/rss/atom/?section=elecciones'),
        # ('Sociedad', 'https://www.elcorreo.com/rss/atom/?section=sociedad'),
        # ('Vivir', 'https://www.elcorreo.com/rss/atom/?section=vivir'),
        ('Tecnología', 'http://www.elcorreo.com/rss/atom/?section=tecnologia'),
        # ('Gente - Estilo', 'http://www.elcorreo.com/rss/atom/?section=gente-estilo'),
        # ('Planes', 'http://www.elcorreo.com/rss/atom/?section=planes'),
        # ('Athletic', 'http://www.elcorreo.com/rss/atom/?section=athletic'),
        # ('Alavés', 'http://www.elcorreo.com/rss/atom/?section=alaves'),
        # ('Bilbao Basket', 'http://www.elcorreo.com/rss/atom/?section=bilbaobasket'),
        # ('Baskonia', 'http://www.elcorreo.com/rss/atom/?section=baskonia'),
        ('Deportes', 'http://www.elcorreo.com/rss/atom/?section=deportes'),
        # ('Jaiak', 'http://www.elcorreo.com/rss/atom/?section=jaiak'),
        # ('La Blanca', 'http://www.elcorreo.com/rss/atom/?section=la-blanca-vitoria'),
        # ('Aste Nagusia', 'http://www.elcorreo.com/rss/atom/?section=aste-nagusia-bilbao'),
        # ('Semana Santa', 'http://www.elcorreo.com/rss/atom/?section=semana-santa'),
        # ('Festivales', 'http://www.elcorreo.com/rss/atom/?section=festivales')
    ]