Alternatives Economiques (French) - recipe

[alphonk]

Alternatives Economiques (French)

#!/usr/bin/env python
from calibre.web.feeds.news import BasicNewsRecipe
import re
from bs4 import BeautifulSoup

class AlternativesEconomiques(BasicNewsRecipe):
    title = 'Alternatives Économiques'
    __author__ = 'Kabonix'
    description = 'Articles de toutes les rubriques (10 articles max par rubrique)'
    publisher = 'Alternatives Économiques'
    language = 'fr'
    
    oldest_article = 90
    max_articles_per_feed = 10
    no_stylesheets = True
    remove_javascript = True
    encoding = 'utf-8'
    auto_cleanup = False
    remove_empty_feeds = True
    remove_images = False
    
    def get_cover_url(self):
        """Récupère dynamiquement l'URL de la dernière une depuis MLP"""
        br = self.get_browser()
        try:
            # Accéder à la page du magazine sur MLP
            soup = self.index_to_soup(br.open('https://catalogueproduits.mlp.fr/produit.aspx?tit_code=1BMwusijpg0%3D').read())
            
            # Chercher la div qui contient les images
            gallery = soup.find('div', id='gallery')
            if gallery:
                img = gallery.find('img', id='couverture_1')
                if img and img.get('src'):
                    cover_url = img['src']
                    if not cover_url.startswith('http'):
                        cover_url = 'https://catalogueproduits.mlp.fr/' + cover_url
                    self.log('Cover URL found:', cover_url)
                    return cover_url
            
            self.log('Aucune couverture trouvée, utilisation de l\'image par défaut')
            return 'https://www.alternatives-economiques.fr/sites/all/themes/alternatives-economiques-main/assets/logo-alternatives-economiques.svg'
            
        except Exception as e:
            self.log.error('Erreur lors de la récupération de la couverture:', str(e))
            return 'https://www.alternatives-economiques.fr/sites/all/themes/alternatives-economiques-main/assets/logo-alternatives-economiques.svg'
    
    def is_article_url(self, url):
        article_pattern = re.compile(r'/[^/]+/00\d{6}$')
        return bool(article_pattern.search(url))

    def parse_index(self):
        articles = []
        base_url = 'https://www.alternatives-economiques.fr'
        
        thematiques = [
            'biodiversite', 'ideesdebats', 'entreprise', 'europe', 'direct-de-recherche',
            'asie', 'a-la-carte', 'chine', 'culture', 'des-idees-pour-sortir-de-la-crise',
            'amerique-du-sud', 'idees-0', 'transport', 'services-publics', 'allemagne',
            'face-a-face', 'politique-monetaire', 'logement', 'climat', 'innovation',
            'agir', 'economie-sociale-et-solidaire', 'societe', 'theorie', 'revenus',
            'tribune', 'conditions-de-travail', 'familles', 'politique', 'numerique',
            'histoire', 'sociorama', 'mondialisation', 'opinions', 'consommation',
            'dette', 'assurance-chomage', 'finance', 'temps-de-travail', 'emploi',
            'protection-sociale', 'refugies', 'royaume-uni', 'conjoncture', 'population',
            'libertes', 'jeunes', 'droit-du-travail', 'responsabilite-sociale', 'industrie',
            'economie', 'ukraine', 'immigration', 'travail', 'etats-unis',
            'inflation', 'relations-sociales', 'inegalites', 'management', 'energie',
            'environnement', 'fiscalite', 'social', 'elections-europeennes', 'retraites',
            'international', 'commerce-exterieur', 'sante', 'gestion', 'salaires',
            'education', 'lanceurs-dalerte', 'japon', 'geopolitique', 'afrique',
            'commerce', 'politiques-publiques', 'budget', 'grece', 'genre',
            'services', 'pollution', 'agriculture', 'legislatives', 'chomage',
            'graphorama', 'formation', 'budget-2025', 'territoires', 'espagne'
        ]
        
        special_sections = {
            'grands-formats': '/grands-formats',
            'dessin': '/dessin'
        }
        
        sections = {t: f'/thematiques/{t}' for t in thematiques}
        sections.update(special_sections)
        
        for section_name, section_path in sections.items():
            url = f'{base_url}{section_path}'
            self.log('Analyzing section:', url)
            try:
                soup = self.index_to_soup(url)
                feed_articles = self.extract_articles(soup, base_url)
                if feed_articles:
                    display_name = section_name.replace('-', ' ').title()
                    articles.append((display_name, feed_articles[:self.max_articles_per_feed]))
            except Exception as e:
                self.log.error(f'Error processing {section_name}: {str(e)}')
                continue
        
        return articles

    def extract_articles(self, soup, base_url):
        feed_articles = []
        processed_urls = set()
        
        for link in soup.find_all('a', href=True):
            article_url = link['href']
            if self.is_article_url(article_url):
                if not article_url.startswith('http'):
                    article_url = base_url + article_url
                
                if article_url in processed_urls:
                    continue
                processed_urls.add(article_url)
                
                try:
                    article_soup = self.index_to_soup(article_url)
                    h1_title = article_soup.find('h1', class_='o-head__title')
                    
                    if h1_title:
                        title = h1_title.get_text().strip()
                    else:
                        title_elem = link.find('h2')
                        if title_elem:
                            title = title_elem.get_text().strip()
                        else:
                            title = link.get_text().strip()
                            if not title:
                                title = article_url.split('/')[-2].replace('-', ' ').title()
                    
                    if title:
                        feed_articles.append({
                            'title': title,
                            'url': article_url,
                            'description': ''
                        })
                except Exception as e:
                    self.log.error(f'Error getting H1 title for {article_url}: {str(e)}')
                    continue
        
        return feed_articles

    keep_only_tags = [
        dict(name='h1', class_='o-head__title'),
        dict(name='div', class_='chapo'),
        dict(name='time', class_='o-infos__date-full'),
        dict(name='div', class_='o-page__content__who'),
        dict(name='div', class_='field-item even'),
        dict(name='div', attrs={'property': 'content:encoded'})
    ]

    remove_tags = [
        dict(name=['script', 'style', 'iframe', 'svg', 'audio', 'video', 'button', 'form', 'input']),
        dict(name='div', class_=[
            'c-article__social', 'social-buttons', 'social-sharing', 'social-media',
            'share-buttons', 'share-links', 'social-links', 'social-icons', 
            'embedded-content', 'embed-container', 'embed-wrapper', 'media-embed',
            'twitter-embed', 'facebook-embed', 'social-embed',
            'c-kiosk--single', 'c-comments', 'c-article__toolbar',
            'c-article__related', 'c-epigraph', 'newsletter-signup', 
            'twitter-tweet', 'twitter-timeline', 'twitter-follow-button',
            'c-footer__promo', 'o-page__block--offset--invert', 
            'newsletter-form', 'newsletter-block', 'newsletter',
            'c-kiosk--single__content', 'c-kiosk--single__figure',
            'c-kiosk--single__body', 'c-kiosk--single__cta',
            'field-name-field-issue-cover'
        ])
    ]

    extra_css = '''
        body { line-height: 1.6; margin: 1em; }
        h1 { font-size: 1.8em; margin-bottom: 0.5em; font-weight: bold; }
        .chapo { font-style: italic; margin: 1em 0; font-size: 1.2em; }
        .o-infos__date-full { color: #666; margin: 0.5em 0; font-size: 0.9em; }
        .o-page__content__who { color: #333; margin: 0.5em 0; font-weight: bold; }
        p { margin: 0.8em 0; }
        
        a { 
            text-decoration: none !important;
            color: inherit !important;
        }
        
        .o-page__figure-full {
            break-inside: avoid;
            margin: 1em 0;
            page-break-inside: avoid;
        }
        .o-page__figure-full figcaption {
            font-style: italic;
            text-align: center;
            margin-top: 0.5em;
            font-size: 0.9em;
            color: #666;
        }
    '''

    def preprocess_html(self, soup):
        # Remove unwanted tags
        for tag in soup.find_all(['script', 'style', 'iframe', 'svg', 'audio', 'video']):
            tag.decompose()
        
        # Clean attributes
        for tag in soup.find_all(True):
            if tag.name not in ['a', 'img']:
                allowed_attrs = {'src', 'href', 'alt', 'title'}
                tag.attrs = {k: v for k, v in tag.attrs.items() if k in allowed_attrs}
        
        return soup