Primer prototipo completado

email-processor.py

@@ -0,0 +1,123 @@
+import imaplib
+import email
+import os
+import requests
+import re
+from email.header import decode_header
+from dotenv import load_dotenv
+from bs4 import BeautifulSoup
+import xml.etree.ElementTree as ET
+from datetime import datetime
+
+load_dotenv()
+
+def clean_html(raw_html):
+    # Permite solo etiquetas básicas
+    allowed_tags = ['b', 'i', 'u', 'em', 'strong', 'blockquote', 'p', 'br']
+    soup = BeautifulSoup(raw_html, "html.parser")
+    
+    for tag in soup.find_all(True):
+        if tag.name not in allowed_tags:
+            tag.unwrap() # Elimina la etiqueta pero mantiene el texto interno
+        else:
+            tag.attrs = {} # Elimina atributos como class, style, id
+            
+    return str(soup)
+
+def get_sender_name(from_header):
+    # Extrae "Nombre" de "Nombre <correo@dominio.com>" o la parte antes del @
+    name, encoding = decode_header(from_header)[0]
+    if isinstance(name, bytes):
+        name = name.decode(encoding or "utf-8")
+    
+    if "<" in name:
+        name = name.split("<")[0].strip()
+    elif "@" in name:
+        name = name.split("@")[0]
+    return name.strip()
+
+def process_emails():
+    mail = imaplib.IMAP4_SSL(os.getenv("IMAP_SERVER"))
+    mail.login(os.getenv("IMAP_USER"), os.getenv("IMAP_PASS"))
+    mail.select(os.getenv("IMAP_FOLDER"))
+
+    status, messages = mail.search(None, 'ALL')
+    domain = os.getenv("DOMAIN_TO_SEARCH")
+    ignore_list = [w.strip().lower() for w in os.getenv("IGNORE_KEYWORDS").split(',')]
+
+    print(messages)
+
+    for m_id in messages[0].split():
+        res, msg_data = mail.fetch(m_id, '(RFC822)')
+        for response_part in msg_data:
+            if isinstance(response_part, tuple):
+                msg = email.message_from_bytes(response_part[1])
+                # 1. Obtener Asunto (Título de la página)
+                subject, encoding = decode_header(msg["Subject"])[0]
+                if isinstance(subject, bytes): 
+                    subject = subject.decode(encoding or "utf-8")
+                
+                # 2. Filtrar por dominio en el asunto (URL)
+                if domain not in subject.lower():
+                    continue
+
+                # 3. Obtener Remitente (Nombre sin dominio)
+                sender_raw = msg.get("From")
+                sender_name = get_sender_name(sender_raw)
+
+                # 4. Obtener Cuerpo y Limpiar HTML
+                body = ""
+                if msg.is_multipart():
+                    for part in msg.walk():
+                        if part.get_content_type() == "text/html":
+                            body = part.get_payload(decode=True).decode()
+                            break
+                else:
+                    body = msg.get_payload(decode=True).decode()
+                
+                # Validar ignore_list en el contenido
+                if any(word in body.lower() for word in ignore_list):
+                    continue
+
+                clean_body = clean_html(body)
+                rss_title = f"Comentario de {sender_name} sobre {subject}"
+
+                # --- ACCIONES ---
+
+                # HTML: Negritas, cursivas, etc.
+                if os.getenv("SAVE_HTML") == "True":
+                    with open(f"msg_{m_id.decode()}.html", "w", encoding="utf-8") as f:
+                        f.write(f"<h3>Remitente: {sender_name}</h3><div>{clean_body}</div>")
+
+                # XML: Formato RSS
+                if os.getenv("SAVE_XML") == "True":
+                    rss = ET.Element("rss", version="2.0")
+                    channel = ET.SubElement(rss, "channel")
+                    item = ET.SubElement(channel, "item")
+                    ET.SubElement(item, "title").text = rss_title
+                    ET.SubElement(item, "description").text = clean_body
+                    ET.SubElement(item, "author").text = sender_name
+                    ET.SubElement(item, "pubDate").text = datetime.now().strftime("%a, %d %b %Y %H:%M:%S GMT")
+                    ET.ElementTree(rss).write(f"msg_{m_id.decode()}.xml", encoding="utf-8", xml_declaration=True)
+
+                # Webhook: Enviar a la URL citada en el asunto
+                if os.getenv("SEND_WEBHOOK") == "True":
+                    # El asunto es la URL de la página citada
+                    target_url = subject if "http" in subject else f"http://{subject}"
+                    try:
+                        requests.post(os.getenv("WP_WEBHOOK_URL"), json={
+                            "auth_token": os.getenv("WEBHOOK_SECRET_TOKEN"),
+                            "target_page": target_url,
+                            "author_name": sender_name,
+                            "comment_content": clean_body
+                        })
+                    except: pass
+
+                # Borrar
+                mail.store(m_id, '+FLAGS', '\\Deleted')
+
+    mail.expunge()
+    mail.logout()
+
+if __name__ == "__main__":
+    process_emails()