Update app.py

app.py

@@ -1,48 +1,63 @@
 import gradio as gr
-from datetime import datetime
+from datetime import datetime, timedelta
 import requests
 import json
 
 def wayback(website):
     if not website:
-        return '😭 Error: introduce una url correcta'
+        return '<p>😭 Error: introduce una url correcta</p>'
 
-    # URL de la Wayback CDX Server API
-    api_url = f"http://web.archive.org/cdx/search/cdx?url={website}&output=json&limit=10&fl=timestamp,original"
+    # Intentar primero con la Wayback CDX Server API
+    end_date = datetime.now()
+    start_date = end_date - timedelta(days=365)
+    datefrom = start_date.strftime('%Y%m%d')
+    dateto = end_date.strftime('%Y%m%d')
+    cdx_api_url = f"http://web.archive.org/cdx/search/cdx?url={website}&output=json&from={datefrom}&to={dateto}&limit=3000"
 
     try:
-        response = requests.get(api_url)
-        if response.status_code != 200:
-            return f'😭 Error: Respuesta no exitosa con código de estado {response.status_code}'
-        
-        content = json.loads(response.text)
-
-        if not content or len(content) < 2:
-            return '😭 Error: No hay instantáneas disponibles para esta URL'
-
-        # Procesar los resultados y devolverlos en forma de tabla HTML
-        results = ["<table style='width:100%; border-collapse: collapse;'><tr><th>Fecha</th><th>URL</th></tr>"]
-        for row in content[1:]:  # Ignorar la primera fila, que es el encabezado
-            date, original_url = row
-            formatted_date = datetime.strptime(date, '%Y%m%d%H%M%S').strftime('%d/%m/%Y')
-            snapshot_url = f'https://web.archive.org/web/{date}/{original_url}'
-            results.append(f"<tr><td>{formatted_date}</td><td><a href='{snapshot_url}' target='_blank'>{original_url}</a></td></tr>")
-        results.append("</table>")
-        return "".join(results)
+        response = requests.get(cdx_api_url)
+        if response.status_code == 200:
+            content = json.loads(response.text)
+            if len(content) > 1:
+                # Procesar y mostrar los resultados
+                results = []
+                for row in content[1:]:
+                    date, page, status = [row[i] for i in [1, 2, 4]]
+                    formatted_date = datetime.strptime(date, '%Y%m%d%H%M%S').strftime('%d/%m/%Y')
+                    formatted_wayback_url = f"https://web.archive.org/web/{date}/{page}"
+                    results.append({'date': date, 'formatted_date': formatted_date, 'link': formatted_wayback_url})
+                results.sort(key=lambda x: x['date'], reverse=True)
+                formatted_results = [f"<tr><td>{item['formatted_date']}</td><td><a href='{item['link']}' target='_blank'>{item['link']}</a></td></tr>" for item in results]
+                return "<table><tr><th>Fecha</th><th>URL</th></tr>" + "".join(formatted_results) + "</table>"
+    except Exception as e:
+        pass  # Falla silenciosa, intentar con el siguiente método
 
-    except json.JSONDecodeError as e:
-        return f'😭 Error al analizar JSON: {e}'
+    # Si falla, intentar con la Wayback Availability JSON API
+    availability_api_url = f"http://archive.org/wayback/available?url={website}"
+    try:
+        response = requests.get(availability_api_url)
+        if response.status_code == 200:
+            data = json.loads(response.text)
+            if data["archived_snapshots"]:
+                closest_snapshot = data["archived_snapshots"]["closest"]
+                if closest_snapshot and closest_snapshot["available"]:
+                    snapshot_url = closest_snapshot["url"]
+                    timestamp = closest_snapshot["timestamp"]
+                    formatted_date = datetime.strptime(timestamp, '%Y%m%d%H%M%S').strftime('%d/%m/%Y')
+                    return f'<table><tr><th>Fecha</th><th>URL</th></tr><tr><td>{formatted_date}</td><td><a href="{snapshot_url}" target="_blank">{snapshot_url}</a></td></tr></table>'
     except Exception as e:
-        return f"😭 Error: {e}"
+        return f"<p>😭 Error: {e}</p>"
+
+    return '<p>😭 Error: No se encontraron datos archivados para esta URL.</p>'
 
 # Crear la interfaz de Gradio
 iface = gr.Interface(
     fn=wayback,
     inputs="text",
     outputs="html",
-    title="Wayback Machine CDX Server Lookup",
+    title="Wayback Machine Combined Lookup",
     description="Busca instantáneas archivadas de una página web en la Wayback Machine. Introduce la URL."
 )
 
 # Lanzar la aplicación
-iface.launch()
+iface.launch()