orgmode-to-gemini-blog/atom_generate.py

import os
import json
from datetime import datetime
import argparse
from utils import get_blog_template_conf
from website_config import configs_sites

# Configuration des arguments de la ligne de commande
parser = argparse.ArgumentParser(description="Générer un flux Atom des articles.")
parser.add_argument("blog", help="Le nom du dossier de blog.")
args = parser.parse_args()

template_content = get_blog_template_conf(args.blog)
website_ndd = template_content['NDD']

# Charger les données du fichier articles_info.json
json_file = f'sources/{args.blog}/build/articles_info.json'
with open(json_file, 'r', encoding='utf-8') as f:
    articles_info = json.load(f)

# Trier les articles par date décroissante
sorted_articles = sorted(articles_info.values(), key=lambda x: x['date'], reverse=True)

# Convert the date string to a valid ISO format
def convert_to_iso(date_str):
    # Check if the string contains 'T' and replace it with a single 'T'
    if 'T' in date_str:
        date_str = date_str.replace('T', '', 1)  # Replace only the first occurrence
    return f"{date_str[:4]}-{date_str[4:6]}-{date_str[6:8]}T{date_str[8:10]}:{date_str[10:12]}:{date_str[12:14]}"

# Génération du flux Atom
with open(f"html-websites/{args.blog}/feed/index.xml", "w", encoding="utf-8") as f:
    f.write('<?xml version="1.0" encoding="UTF-8"?>\n')
    f.write('<feed xmlns="http://www.w3.org/2005/Atom">\n')
    f.write(f'  <title>Flux Atom des articles de {args.blog}</title>\n')
    f.write(f'  <link href="{website_ndd}/feed"/>\n')
    f.write(f'  <updated>{datetime.fromisoformat(convert_to_iso(sorted_articles[0]["date"])).strftime("%Y-%m-%dT%H:%M:%S+00:00")}</updated>\n')
    f.write('  <id>tag:' + website_ndd + ',2023:/feed</id>\n')
    f.write('  <author>\n')
    f.write(f'    <name>{configs_sites[args.blog]["AUTHOR"]}</name>\n')
    f.write(f'    <email>{configs_sites[args.blog]["EMAIL"]}</email>\n')
    f.write('  </author>\n')
    f.write(f'  <link rel="self" href="{website_ndd}/feed"/>\n')
    
    print(f"Génération du flux Atom pour {len(sorted_articles)} articles")
    # Boucle des articles
    for article in sorted_articles:
        f.write('  <entry>\n')
        f.write(f'    <id>tag:{website_ndd},2023:{article["slug"]}</id>\n')
        f.write(f'    <title>{article["title"]}</title>\n')
        f.write(f'    <link href="{website_ndd}/{article["slug"]}"/>\n')
        f.write('    <content type="html"><![CDATA[\n')
        f.write(f'      {article["html_content"]}\n')
        f.write('    ]]></content>\n')
        f.write(f'    <summary>{article.get("extract", "")}</summary>\n')
        f.write(f'    <published>{datetime.fromisoformat(convert_to_iso(article["date"])).strftime("%Y-%m-%dT%H:%M:%S+00:00")}</published>\n')
        f.write(f'    <updated>{datetime.fromisoformat(convert_to_iso(article["date"])).strftime("%Y-%m-%dT%H:%M:%S+00:00")}</updated>\n')
        f.write('    <author>\n')
        f.write(f'      <name>{configs_sites[args.blog]["AUTHOR"]}</name>\n')
        f.write(f'      <email>{configs_sites[args.blog]["EMAIL"]}</email>\n')
        f.write('    </author>\n')
        f.write('  </entry>\n')
    
    f.write('</feed>')