From ebcfa3dd178e4aab8fb467760bc44541ac805afa Mon Sep 17 00:00:00 2001 From: Kovid Goyal Date: Sun, 19 Jan 2025 09:03:58 +0530 Subject: [PATCH] Update Arret sur images --- recipes/arret_sur_images.recipe | 217 ++++++++++++++++++++++++++------ 1 file changed, 179 insertions(+), 38 deletions(-) diff --git a/recipes/arret_sur_images.recipe b/recipes/arret_sur_images.recipe index 797d52127d..276c903d3a 100644 --- a/recipes/arret_sur_images.recipe +++ b/recipes/arret_sur_images.recipe @@ -1,55 +1,196 @@ -from __future__ import unicode_literals +#!/usr/bin/env python +# vim:fileencoding=utf-8 -__license__ = 'WTFPL' -__author__ = '2013, François D. ' -__description__ = 'Get some fresh news from Arrêt sur images' +import json +from datetime import datetime + +import mechanize +from zoneinfo import ZoneInfo + +from calibre import browser +from calibre.web.feeds.news import BasicNewsRecipe -from calibre.web.feeds.recipes import BasicNewsRecipe - - -class Asi(BasicNewsRecipe): - - title = 'Arrêt sur images' - __author__ = 'François D. (aka franek)' - description = 'Global news in french from news site "Arrêt sur images"' - - oldest_article = 7.0 +class ArretSurImages(BasicNewsRecipe): + title = 'Arrêt sur Images' + description = 'Site français d\'analyse des médias' language = 'fr' + encoding = 'utf-8' needs_subscription = True + oldest_article = 7 max_articles_per_feed = 100 - - simultaneous_downloads = 1 - timefmt = '[%a, %d %b %Y %I:%M +0200]' - cover_url = 'http://www.arretsurimages.net/images/header/menu/menu_1.png' - - use_embedded_content = False no_stylesheets = True remove_javascript = True feeds = [ - ('vite dit et gratuit', 'http://www.arretsurimages.net/vite-dit.rss'), - ('Toutes les chroniques', 'http://www.arretsurimages.net/chroniques.rss'), - ('Contenus et dossiers', 'http://www.arretsurimages.net/dossiers.rss'), + ('Arrêt sur images', 'https://api.arretsurimages.net/api/public/rss/all-content') ] - conversion_options = {'smarten_punctuation': True} + def default_cover(self, cover_file): + """ + Crée une couverture personnalisée avec le logo ASI + """ + from qt.core import QColor, QFont, QImage, QPainter, QPen, QRect, Qt - remove_tags = [dict(id='vite-titre'), dict(id='header'), dict(id='wrap-connexion'), dict(id='col_right'), - dict(name='div', attrs={'class': 'bloc-chroniqueur-2'}), dict(id='footercontainer')] + from calibre.gui2 import ensure_app, load_builtin_fonts, pixmap_to_data + try: + ensure_app() + load_builtin_fonts() - def print_version(self, url): - return url.replace('contenu.php', 'contenu-imprimable.php') + today = datetime.now(ZoneInfo('Europe/Paris')) + wkd = today.weekday() + french_weekday = {0:'Lundi',1:'Mardi',2:'Mercredi',3:'Jeudi',4:'Vendredi',5:'Samedi',6:'Dimanche'} + french_month = {1:'janvier', 2:'février', 3:'mars', 4:'avril', 5:'mai', 6:'juin', + 7:'juillet', 8:'août', 9:'septembre', 10:'octobre', 11:'novembre', 12:'décembre'} + + weekday = french_weekday[wkd] + month = french_month[today.month] + date_str = f"{weekday} {today.day} {month} {today.year}" + edition = today.strftime('Édition de %Hh') + + img = QImage(1400, 1920, QImage.Format_RGB888) + img.fill(QColor('white')) + + # Dessiner la bordure rouge + border_painter = QPainter(img) + border_pen = QPen(QColor('red')) + border_pen.setWidth(120) # Épaisseur de la bordure + border_painter.setPen(border_pen) + border_painter.drawRect(10, 10, img.width()-20, img.height()-20) # Marge de 10 pixels + border_painter.end() + + logo_url = 'https://www.arretsurimages.net/assets/img/front/logo-asi-grand.png' + logo_data = browser().open(logo_url).read() + logo = QImage() + logo.loadFromData(logo_data) + + logo_width = 800 + scaled_logo = logo.scaledToWidth(logo_width, Qt.SmoothTransformation) + + x = (img.width() - scaled_logo.width()) // 2 + y = (img.height() - scaled_logo.height()) // 2 - 100 + + p = QPainter(img) + p.drawImage(x, y, scaled_logo) + p.end() + + p = QPainter(img) + p.setPen(QPen(QColor('black'))) + + font = QFont('Liberation Sans', 36) + p.setFont(font) + + r = QRect(0, y + scaled_logo.height() + 50, img.width(), 100) + p.drawText(r, Qt.AlignmentFlag.AlignHCenter | Qt.AlignmentFlag.AlignVCenter, date_str) + + font.setItalic(True) + font.setPointSize(32) + p.setFont(font) + + r = QRect(0, y + scaled_logo.height() + 150, img.width(), 100) + p.drawText(r, Qt.AlignmentFlag.AlignHCenter | Qt.AlignmentFlag.AlignVCenter, edition) + + p.end() + + img_data = pixmap_to_data(img) + cover_file.write(img_data) + cover_file.flush() + return True + + except Exception as e: + print(f'Erreur lors de la création de la couverture: {e}') + return False def get_browser(self): - # Need to use robust HTML parser - br = BasicNewsRecipe.get_browser(self, use_robust_parser=True) - if self.username is not None and self.password is not None: - br.open('http://www.arretsurimages.net/index.php') - br.select_form(nr=0) - br.form.set_all_readonly(False) - br['redir'] = 'forum/login.php' - br['username'] = self.username - br['password'] = self.password - br.submit() + br = BasicNewsRecipe.get_browser(self) + if self.username and self.password: + auth_data = { + 'client_id': '1_1e3dazertyukilygfos7ldzertyuof7pfd', + 'client_secret': '2r8yd4a8un0fn45d93acfr3efrgthzdheifhrehihidg4dk5kds7ds23', + 'username': self.username, + 'password': self.password, + 'grant_type': 'password' + } + request = mechanize.Request( + 'https://api.arretsurimages.net/oauth/v2/token', + data=json.dumps(auth_data).encode('utf-8'), + headers={'Content-Type': 'application/json', 'Accept': 'application/json'} + ) + try: + response = br.open(request) + auth_response = json.loads(response.read().decode('utf-8')) + if 'access_token' in auth_response: + br.addheaders += [('Authorization', f'Bearer {auth_response["access_token"]}')] + print('Authentification réussie') + else: + print('Échec de l\'authentification - Vérifiez vos identifiants') + except Exception as e: + print(f'Erreur lors de l\'authentification: {str(e)}') return br + + def get_article_url(self, article): + url = article.get('link', article.get('guid')) + if url: + return url.replace('www.arretsurimages.net/', 'api.arretsurimages.net/api/public/contents/') + return None + + def preprocess_raw_html(self, raw_html, url): + try: + article_data = json.loads(raw_html) + authors = ', '.join([a.get('name', '') for a in article_data.get('authors', [])]) + cover_html = '' + if article_data.get('cover') and article_data['cover'].get('formats', {}).get('article_header'): + cover_slug = article_data['cover']['slug'] + cover_url = f'https://api.arretsurimages.net/api/public/media/{cover_slug}/action/show?format=article_header' + cover_html = f'{article_data.get(' + return f''' + + {article_data.get('title', 'Article sans titre')} + +
+

{article_data.get('title', 'Article sans titre')}

+
+

Par {authors or "Auteur inconnu"}

+
+ {cover_html} +
+

{article_data.get('lead', '')}

+ {article_data.get('content', '')} +
+
+ + + ''' + except Exception as e: + print(f'Erreur preprocessing HTML: {str(e)}') + return raw_html + + def preprocess_html(self, soup): + try: + for tag in soup.find_all(['asi-html', 'asi-image', 'asi-video']): + if tag.name == 'asi-html' and tag.get('data-html'): + tag.replace_with(soup.new_tag('div', attrs={'class': 'asi-content'}).append(tag['data-html'])) + elif tag.name == 'asi-image': + img_data = tag.get('data-image', {}) + if img_data: + try: + img_data = json.loads(img_data) + if img_data.get('slug'): + img_url = f'https://api.arretsurimages.net/api/public/media/{img_data["slug"]}/action/show?format=article_body' + img_tag = soup.new_tag('img', src=img_url) + if img_data.get('caption'): + caption_div = soup.new_tag('div', attrs={'class': 'image-caption'}) + caption_div.string = img_data['caption'] + tag.replace_with(img_tag) + img_tag.insert_after(caption_div) + else: + tag.replace_with(img_tag) + except Exception as e: + print(f'Erreur processing image: {str(e)}') + tag.decompose() + else: + tag.decompose() + return soup + except Exception as e: + print(f'Erreur preprocessing HTML: {str(e)}') + return soup