Files
browser-use/docs/legacy/code-agent/example-products.mdx
ShawnPana 96f39b3c75 Move Code Agent, Actor, and Sandbox docs to Legacy section
Relocate deprecated doc sections from customize/ to legacy/ under
Customize OS nav. Add redirects for all old paths and update
cross-references in AGENTS.md and related mdx files.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 15:30:39 -08:00

60 lines
1.6 KiB
Plaintext

---
title: "Example: Extract Products"
description: "Collect thousands of products and save to CSV"
icon: "database"
---
This example shows how to extract large amounts of product data from an e-commerce site and save it to files.
## Use Case
Extract 1000s of products from multiple categories with:
- Product URLs
- Names and descriptions
- Original and sale prices
- Discount percentages
Save everything to a CSV file for further analysis.
## Code
```python
import asyncio
from browser_use.code_use import CodeAgent
async def main():
task = """
Go to https://www.flipkart.com.
Collect approximately 50 products from:
1. Books & Media - 15 products
2. Sports & Fitness - 15 products
3. Beauty & Personal Care - 10 products
Save to products.csv
"""
agent = CodeAgent(task=task)
await agent.run()
asyncio.run(main())
```
## How It Works
1. **Agent navigates** to the e-commerce site
2. **Writes JavaScript** to extract product data from each page
3. **Loops through categories** collecting products
4. **Stores in variables** that persist across steps
5. **Saves to CSV** using pandas or csv module
6. **Returns deterministic code** you can modify and rerun
## Key Benefits
- **Function reuse:** Extraction code is written once, used many times
- **Scale:** Easily collect 100s or 1000s of items
- **Deterministic:** The generated Python code can be saved and rerun
- **Data processing:** Built-in pandas support for cleaning and transforming data
[View full example on GitHub →](https://github.com/browser-use/browser-use/blob/main/examples/code_agent/extract_products.py)