Informe detallado de S3 con coste y detalle del contenido para cada bucket.

claude_prompt.md

User prompt 1: Solicitud

  ¿Me podrías dar un código python q haga lo siguiente?
  A partir de las credenciales AWS en memoria (no pedirlas directamente), hacer un listado de buckets y un ls/scan por cada bucket de una cuenta de S3 para imprimir en forma de informe html (un único fichero llamado s3-report-<account_ID>.html) con una estética más o menos limpia y responsive (todo loq que utilice que sea por CDN).

  Las tablas serán:
  h1 informe S3 cuenta XXXXX

  h2 Listado de buckets
  
  a) listado de buckets con nombre, región, tamaño ocupado y coste mensual estimado
  Ejemplo de línea:
  bucket_1 | irlanda | 4Gb | 9.99 USD/m

  h2 Contenido de los buckets
  h3 Bucket X
  
  b) una tabla por cada bucket con todos sus ficheros de la siguiente forma: ruta, tamaño y tipo de almacenamiento

  Ejemplo de líneas:
  /archivo1.png | 1 Gb | Glacier Deep Archive
  /folder1/archivo500.docx | 215 kb | Standard

User prompt 2: Depurado por los errores multi-región

(py38) ➜  Workspace ./s3-report.py
Error: An error occurred (IllegalLocationConstraintException) when calling the ListObjects operation: The eu-south-2 location constraint is incompatible for the region specific endpoint this request was sent to.

S3-report-bucket-detail-and-cost.py

#!/usr/bin/env python3
import boto3
import datetime
from pathlib import Path
from typing import Dict, List, Tuple
import humanize
import logging

logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)

class S3Reporter:
    def __init__(self):
        # Cliente inicial para operaciones básicas
        self.default_client = boto3.client('s3')
        self.account_id = boto3.client('sts').get_caller_identity().get('Account')
        self.region_clients = {}
        
    def get_s3_client(self, region: str = None) -> boto3.client:
        """Obtiene un cliente S3 para una región específica"""
        if not region:
            return self.default_client
        
        if region not in self.region_clients:
            self.region_clients[region] = boto3.client('s3', region_name=region)
        return self.region_clients[region]

    def get_bucket_size_and_cost(self, bucket_name: str, region: str) -> Tuple[int, float]:
        """Calcula el tamaño total y coste estimado mensual de un bucket"""
        total_size = 0
        s3_client = self.get_s3_client(region)
        
        try:
            paginator = s3_client.get_paginator('list_objects_v2')
            for page in paginator.paginate(Bucket=bucket_name):
                if 'Contents' in page:
                    for obj in page['Contents']:
                        total_size += obj.get('Size', 0)
                        
            # Cálculo aproximado del coste mensual (simplificación)
            cost_per_gb_month = 0.023  # USD por GB/mes para primeros 50TB
            cost = (total_size / (1024**3)) * cost_per_gb_month
            
            return total_size, cost
        except Exception as e:
            logger.error(f"Error al obtener tamaño del bucket {bucket_name}: {str(e)}")
            return 0, 0

    def get_bucket_region(self, bucket_name: str) -> str:
        """Obtiene la región de un bucket"""
        try:
            location = self.default_client.get_bucket_location(Bucket=bucket_name)
            region = location['LocationConstraint']
            # None significa us-east-1
            return region if region else 'us-east-1'
        except Exception as e:
            logger.error(f"Error al obtener región del bucket {bucket_name}: {str(e)}")
            return "desconocida"

    def get_bucket_contents(self, bucket_name: str, region: str) -> List[Dict]:
        """Obtiene el contenido de un bucket"""
        contents = []
        s3_client = self.get_s3_client(region)
        
        try:
            paginator = s3_client.get_paginator('list_objects_v2')
            for page in paginator.paginate(Bucket=bucket_name):
                if 'Contents' in page:
                    for obj in page['Contents']:
                        try:
                            obj_info = s3_client.head_object(
                                Bucket=bucket_name, 
                                Key=obj['Key']
                            )
                            storage_class = obj_info.get('StorageClass', 'STANDARD')
                        except:
                            storage_class = obj.get('StorageClass', 'UNKNOWN')
                            
                        contents.append({
                            'path': obj['Key'],
                            'size': obj['Size'],
                            'storage_class': storage_class
                        })
                        
        except Exception as e:
            logger.error(f"Error al listar contenido del bucket {bucket_name}: {str(e)}")
            
        return contents

    def generate_html_report(self):
        """Genera el informe HTML"""
        buckets_info = []
        buckets_contents = {}
        
        # Listar todos los buckets
        try:
            response = self.default_client.list_buckets()
            buckets = response['Buckets']
        except Exception as e:
            logger.error(f"Error al listar buckets: {str(e)}")
            return
        
        # Recopilar información de todos los buckets
        total_buckets = len(buckets)
        for i, bucket in enumerate(buckets, 1):
            bucket_name = bucket['Name']
            logger.info(f"Procesando bucket {i}/{total_buckets}: {bucket_name}")
            
            # Obtener región del bucket
            region = self.get_bucket_region(bucket_name)
            logger.info(f"Región del bucket {bucket_name}: {region}")
            
            # Obtener tamaño y coste
            size, cost = self.get_bucket_size_and_cost(bucket_name, region)
            
            buckets_info.append({
                'name': bucket_name,
                'region': region,
                'size': size,
                'cost': cost
            })
            
            # Obtener contenido del bucket
            buckets_contents[bucket_name] = self.get_bucket_contents(bucket_name, region)

        # Generar HTML
        html = self._generate_html_content(buckets_info, buckets_contents)
        
        # Guardar el informe
        filename = f"s3-report-{self.account_id}.html"
        with open(filename, 'w', encoding='utf-8') as f:
            f.write(html)
            
        logger.info(f"Informe generado: {filename}")

    def _generate_html_content(self, buckets_info: List[Dict], buckets_contents: Dict) -> str:
        """Genera el contenido HTML del informe"""
        html = f"""<!DOCTYPE html>
<html lang="es">
<head>
    <meta charset="UTF-8">
    <meta name="viewport" content="width=device-width, initial-scale=1.0">
    <title>Informe S3 - Cuenta {self.account_id}</title>
    <link href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" rel="stylesheet">
    <link href="https://cdn.jsdelivr.net/npm/[email protected]/font/bootstrap-icons.css" rel="stylesheet">
    <style>
        .bucket-section {{ margin-top: 2rem; }}
        .table-responsive {{ margin-top: 1rem; }}
        .storage-class {{
            padding: 0.2em 0.6em;
            border-radius: 0.25rem;
            font-size: 0.875em;
        }}
        .storage-class-STANDARD {{ background-color: #e3f2fd; }}
        .storage-class-GLACIER {{ background-color: #f3e5f5; }}
        .storage-class-DEEP_ARCHIVE {{ background-color: #efebe9; }}
        .storage-class-INTELLIGENT_TIERING {{ background-color: #e8f5e9; }}
    </style>
</head>
<body class="container-fluid py-4">
    <h1 class="mb-4">
        <i class="bi bi-cloud"></i> 
        Informe S3 - Cuenta {self.account_id}
    </h1>
    
    <h2 class="mt-5">
        <i class="bi bi-bucket"></i> 
        Listado de Buckets
    </h2>
    <div class="table-responsive">
        <table class="table table-striped table-hover">
            <thead class="table-dark">
                <tr>
                    <th>Nombre del Bucket</th>
                    <th>Región</th>
                    <th>Tamaño Total</th>
                    <th>Coste Mensual Estimado</th>
                </tr>
            </thead>
            <tbody>
"""
        
        # Agregar información de buckets
        for bucket in buckets_info:
            html += f"""
                <tr>
                    <td>{bucket['name']}</td>
                    <td>{bucket['region']}</td>
                    <td>{humanize.naturalsize(bucket['size'])}</td>
                    <td>${bucket['cost']:.2f} USD/mes</td>
                </tr>"""

        html += """
            </tbody>
        </table>
    </div>

    <h2 class="mt-5">
        <i class="bi bi-folder"></i> 
        Contenido de los Buckets
    </h2>
"""

        # Agregar contenido de cada bucket
        for bucket_name, contents in buckets_contents.items():
            html += f"""
    <div class="bucket-section">
        <h3>
            <i class="bi bi-folder2-open"></i> 
            Bucket: {bucket_name}
        </h3>
        <div class="table-responsive">
            <table class="table table-striped table-hover">
                <thead class="table-dark">
                    <tr>
                        <th>Ruta</th>
                        <th>Tamaño</th>
                        <th>Tipo de Almacenamiento</th>
                    </tr>
                </thead>
                <tbody>
"""
            
            for item in contents:
                storage_class = item['storage_class']
                html += f"""
                    <tr>
                        <td>{item['path']}</td>
                        <td>{humanize.naturalsize(item['size'])}</td>
                        <td><span class="storage-class storage-class-{storage_class}">{storage_class}</span></td>
                    </tr>"""

            html += """
                </tbody>
            </table>
        </div>
    </div>
"""

        html += f"""
    <footer class="mt-5 text-muted">
        <hr>
        <p>
            <i class="bi bi-clock"></i> 
            Informe generado el {datetime.datetime.now().strftime('%Y-%m-%d %H:%M:%S')}
        </p>
    </footer>

    <script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/bootstrap.bundle.min.js"></script>
</body>
</html>"""

        return html

def main():
    try:
        reporter = S3Reporter()
        reporter.generate_html_report()
    except Exception as e:
        logger.error(f"Error: {str(e)}")

if __name__ == "__main__":
    main()