ejemplo_automatizacion.py

import click
import os
from dotenv import load_dotenv
from openai import OpenAI
import requests
from bs4 import BeautifulSoup

load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")

client = OpenAI(api_key=OPENAI_API_KEY)

@click.command()
@click.option('--url', default='https://news.ycombinator.com', help='URL to get a summary from')
@click.option('--about', default='', help='Description of the page to summarize,  e.g., "This is a news website about technology.". It helps the AI to understand the context better.')
@click.option('--output-file', default='output.txt', help='Path to the output summary file')
def process_file(url, about, output_file):
  print("Starting the process...")
  info = scrap_url(url)
  # print(f"Scraped info from {url}:\n{info[:500]}...")  # Print first 500 characters for debugging
  print(f"Scraped info from {url} successfully.")
  r = summarize_info(info,url, about)
  print(f"Summary generated successfully.")
  with open(output_file, 'w', encoding='utf-8') as f:
    f.write(r)
    print(f"Summary written to {output_file} successfully.")          

def summarize_info(info,url,about):
  input= """
    Por favor, resume las siguiente información de la página web:
    {url}
    Si la información es muy extensa, por favor, resume las líneas más importantes.
    Si la información es corta, por favor, resume todo.
    Aquí está el cuerpo de la información:
    {info}
    """.format(info=info, url=url)
  if about:
    input += f"\n\nContexto: {about}"
  # print(f"Input: {input}")
  response = client.responses.create(
    model="gpt-4.1",
    input=input
  )

  return response.output_text
def scrap_url(url):
    """
    Scrapes the main text content from the given URL.
    Returns the extracted text as a string.
    """
    try:
        response = requests.get(url, timeout=10)
        response.raise_for_status()
        soup = BeautifulSoup(response.text, 'html.parser')
        # Remove script and style elements
        for script in soup(["script", "style"]):
            script.decompose()
        # Get text and clean up whitespace
        text = soup.get_text(separator=' ', strip=True)
        lines = [line.strip() for line in text.splitlines() if line.strip()]
        return '\n'.join(lines)
    except Exception as e:
        return f"Error scraping URL: {e}"

if __name__ == '__main__':
    process_file()