Zérodeux (revue d'art contemporain) (French) -recipe

[alphonk]

Zérodeux (revue d'art contemporain) (French) -recipe

#!/usr/bin/env python

'''
zerodeux.fr
'''

from calibre.web.feeds.news import BasicNewsRecipe

class ZeroDeuxRecipe(BasicNewsRecipe):
    title = 'Zérodeux'
    __author__ = 'Kabonix'
    description = 'Revue d\'art contemporain trimestrielle'
    publisher = 'Zérodeux'
    category = 'art, contemporary art, criticism'
    language = 'fr'
    encoding = 'utf-8'
    oldest_article = 60
    max_articles_per_feed = 25
    
    no_stylesheets = True
    remove_javascript = True
    auto_cleanup = False
    
    feeds = [
        ('Essais', 'https://www.zerodeux.fr/category/essais/feed/'),
        ('Guests', 'https://www.zerodeux.fr/category/guests/feed/'),
        ('Interviews', 'https://www.zerodeux.fr/category/interviews/feed/'),
        ('Reviews', 'https://www.zerodeux.fr/category/reviews/feed/'),
        ('News', 'https://www.zerodeux.fr/category/news/feed/'),
        ('Special Web', 'https://www.zerodeux.fr/category/specialweb/feed/')
    ]
    
    def get_cover_url(self):
        soup = self.index_to_soup('https://www.zerodeux.fr')
        cover_div = soup.find('div', {'id': 'responsive_lightbox_image_widget-2'})
        if cover_div:
            cover_img = cover_div.find('img', {'class': 'rl-image-widget-image'})
            if cover_img and 'src' in cover_img.attrs:
                return cover_img['src']
        return None

    keep_only_tags = [
        dict(name='article', attrs={'id': 'single-post'})
    ]
    
    remove_tags = [
        dict(name='div', attrs={'class': ['single-associate', 'single-info', 'transition']}),
        dict(name='div', attrs={'id': ['sidebar', 'menu_footer']}),
        dict(name='ul', attrs={'class': ['single-info']}),  # Supprime le bloc "Partage"
        dict(name='li', text='Du même auteur :'),  # Supprime le titre "Du même auteur"
        dict(name='p', attrs={'class': ['recomand']})  # Supprime "articles liés"
    ]

    def preprocess_html(self, soup):
        # Nettoyage des styles
        for tag in soup.findAll(True):
            if 'style' in tag.attrs:
                del tag['style']
        
        # Nettoyage des images
        for img in soup.findAll('img'):
            for attr in ['srcset', 'sizes', 'loading', 'class', 'width', 'height', 'decoding', 'fetchpriority']:
                if attr in img.attrs:
                    del img[attr]
            
            if img.get('src', '').startswith('/'):
                img['src'] = 'https://www.zerodeux.fr' + img['src']
        
        # Suppression du texte "Partage :" et "Du même auteur :"
        for text in soup.findAll(text=True):
            if text.strip() in ['Partage :', 'Du même auteur :']:
                text.extract()
        
        return soup

    extra_css = '''
        h1 { font-size: 1.8em; font-weight: bold; margin: 0 0 1em 0; }
        h2 { font-size: 1.4em; font-weight: bold; margin: 1em 0; }
        .single-author { font-style: italic; margin-bottom: 1.5em; color: #666; }
        img { max-width: 100%; height: auto; margin: 1em auto; }
        figcaption { font-size: 0.9em; font-style: italic; color: #666; margin: 0.5em 0 1.5em 0; }
        p { margin-bottom: 1em; line-height: 1.5; }
        ol { margin: 1em 0 1em 2em; }
        blockquote { margin: 1em 0; padding: 0 1em; border-left: 3px solid #ccc; }
        .wp-block-image { margin: 1.5em 0; }
        .has-small-font-size { font-size: 0.9em; }
    '''
    
    def populate_article_metadata(self, article, soup, first):
        author_div = soup.find('div', {'class': 'single-author'})
        if author_div:
            author = author_div.get_text().strip()
            if author.startswith('par '):
                author = author[4:]
            article.author = author
        return