0aff31e2d3
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
40 lines
828 B
Markdown
40 lines
828 B
Markdown
---
|
|
layout: default
|
|
---
|
|
|
|
# CheerioWebBaseLoader
|
|
|
|
<v-clicks>
|
|
|
|
Carga páginas web como documentos (sin ejecutar JavaScript)
|
|
|
|
### Instalación
|
|
|
|
```bash
|
|
npm install @langchain/community cheerio
|
|
```
|
|
|
|
### Uso
|
|
|
|
```typescript
|
|
import "cheerio";
|
|
import { CheerioWebBaseLoader } from
|
|
"@langchain/community/document_loaders/web/cheerio";
|
|
|
|
const loader = new CheerioWebBaseLoader(
|
|
"https://blog.langchain.dev/what-is-an-agent/",
|
|
{ selector: "article" } // selector CSS para filtrar contenido
|
|
);
|
|
const docs = await loader.load();
|
|
|
|
console.log(docs[0].pageContent.substring(0, 300));
|
|
console.log(docs[0].metadata);
|
|
// { source: 'https://blog.langchain.dev/...', title: '...' }
|
|
```
|
|
|
|
<div class="mt-4 p-4 bg-yellow-500/10 rounded">
|
|
⚠️ Para SPAs o páginas con JS dinámico, usa <b>Playwright</b> o <b>Puppeteer</b>
|
|
</div>
|
|
|
|
</v-clicks>
|