# Puppeteer Web Scraper

Puppeteer es una biblioteca de Node.js que controla Chrome/Chromium a través del DevTools Protocol en modo headless. Ten en cuenta que al hacer scraping de sitios web, **siempre debes revisar y cumplir con los términos de servicio y políticas del sitio web para asegurar un uso ético y legal de los datos**.

## Scraping de Una URL

1. *(Opcional)* Conecta [**Text Splitter**](https://docs.flowiseai.com/espanol/documentacion-oficial/integraciones/langchain/text-splitters).
2. Ingresa la URL deseada para hacer scraping.

## Crawl y Scraping de Múltiples URLs

Visita la guía de [**Web Crawl**](https://github.com/FlowiseAI/FlowiseDocs/blob/main/esp/integraciones/use-cases/web-crawl.md) para permitir el scraping de múltiples páginas.

## Salida

Carga el contenido de la URL como Documento

## Recursos

* [LangChain JS Puppeteer](https://js.langchain.com/docs/integrations/document_loaders/web_loaders/web_puppeteer)
* [Puppeteer](https://pptr.dev/)


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.flowiseai.com/espanol/documentacion-oficial/integraciones/langchain/document-loaders/puppeteer-web-scraper.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.