Skip to main content

The official Python library for the Browser Use API

Project description

Browser Use Python

BrowserUse Python Library

fern shield pypi

The BrowserUse Python library provides convenient access to the BrowserUse APIs from Python.

Three-Step QuickStart

  1. 📦 Install Browser Use SDK

    # PIP
    pip install browser-use-sdk
    
    # Poetry
    poetry add browser-use-sdk
    
    # UV
    uv add browser-use-sdk
    
  2. 🔑 Get your API Key at Browser Use Cloud!

  3. 🦄 Automate the Internet!

    from browser_use_sdk import BrowserUse
    
    client = BrowserUse(api_key="bu_...")
    
    task = client.tasks.create_task(
        task="Search for the top 10 Hacker News posts and return the title and url.",
        llm="gpt-4.1"
    )
    
    result = task.complete()
    
    result.output
    

The full API of this library can be found in api.md.

Structured Output with Pydantic

Browser Use Python SDK provides first class support for Pydantic models.

from browser_use_sdk import AsyncBrowserUse

client = AsyncBrowserUse(api_key=API_KEY)

class HackerNewsPost(BaseModel):
    title: str
    url: str

class SearchResult(BaseModel):
    posts: List[HackerNewsPost]

async def main() -> None:
    task = await client.tasks.create_task(
        task="""
        Find top 10 Hacker News articles and return the title and url.
        """,
        schema=SearchResult,
    )

    result = await task.complete()

    if result.parsed_output is not None:
        print("Top HackerNews Posts:")
        for post in result.parsed_output.posts:
            print(f" - {post.title} - {post.url}")

asyncio.run(main())

Streaming Updates with Async Iterators

When presenting a long running task you might want to show updates as they happen.

Browser Use SDK exposes a .stream method that lets you subscribe to a sync or an async generator that automatically polls Browser Use Cloud servers and emits a new event when an update happens (e.g., live url becomes available, agent takes a new step, or agent completes the task).

class HackerNewsPost(BaseModel):
    title: str
    url: str

class SearchResult(BaseModel):
    posts: List[HackerNewsPost]


async def main() -> None:
    task = await client.tasks.create_task(
        task="""
        Find top 10 Hacker News articles and return the title and url.
        """,
        schema=SearchResult,
    )

    async for step in task.stream():
        print(f"Step {step.number}: {step.url} ({step.next_goal})")

    result = await task.complete()

    if result.parsed_output is not None:
        print("Top HackerNews Posts:")
        for post in result.parsed_output.posts:
            print(f" - {post.title} - {post.url}")

asyncio.run(main())

Verifying Webhook Events

You can configure Browser Use Cloud to emit Webhook events and process them easily with Browser Use Python SDK.

Browser Use SDK lets you easily verify the signature and structure of the payload you receive in the webhook.

import uvicorn
import os
from browser_use_sdk import Webhook, verify_webhook_event_signature

from fastapi import FastAPI, Request, HTTPException

app = FastAPI()

SECRET_KEY = os.environ['SECRET_KEY']

@app.post('/webhook')
async def webhook(request: Request):
    body = await request.json()

    timestamp = request.headers.get('X-Browser-Use-Timestamp')
    signature = request.headers.get('X-Browser-Use-Signature')

    verified_webhook: Webhook = verify_webhook_event_signature(
        body=body,
        timestamp=timestamp,
        secret=SECRET_KEY,
        expected_signature=signature,
    )

    if verified_webhook is not None:
        print('Webhook received:', verified_webhook)
    else:
        print('Invalid webhook received')

    return {'status': 'success', 'message': 'Webhook received'}

if __name__ == '__main__':
    uvicorn.run(app, host='0.0.0.0', port=8080)

Async usage

Simply import AsyncBrowserUse instead of BrowserUse and use await with each API call:

import os
import asyncio
from browser_use_sdk import AsyncBrowserUse

client = AsyncBrowserUse(
    api_key=os.environ.get("BROWSER_USE_API_KEY"),  # This is the default and can be omitted
)


async def main() -> None:
    task = await client.tasks.create_task(
        task="Search for the top 10 Hacker News posts and return the title and url.",
    )

    print(task.id)


asyncio.run(main())

Requirements

Python 3.8 or higher.

Contributing

While we value open-source contributions to this SDK, this library is generated programmatically. Additions made directly to this library would have to be moved over to our generation code, otherwise they would be overwritten upon the next generated release. Feel free to open a PR as a proof of concept, but know that we will not be able to merge it as-is. We suggest opening an issue first to discuss with us!

On the other hand, contributions to the README are always very welcome!

Reference

A full reference for this library is available here.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

browser_use_sdk-2.0.13.tar.gz (68.1 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

browser_use_sdk-2.0.13-py3-none-any.whl (147.9 kB view details)

Uploaded Python 3

File details

Details for the file browser_use_sdk-2.0.13.tar.gz.

File metadata

  • Download URL: browser_use_sdk-2.0.13.tar.gz
  • Upload date:
  • Size: 68.1 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.7.21

File hashes

Hashes for browser_use_sdk-2.0.13.tar.gz
Algorithm Hash digest
SHA256 58b25a92a045470f9482a1a06fabe092dec8506f5c6f20c00a60028a9f963ef6
MD5 09b5fdc5d8543a01c8c069624a125068
BLAKE2b-256 3a5807b08bec515d1bc43bb5e7a1cd4b788aee9c477ffbe2053c956857fa70af

See more details on using hashes here.

File details

Details for the file browser_use_sdk-2.0.13-py3-none-any.whl.

File metadata

File hashes

Hashes for browser_use_sdk-2.0.13-py3-none-any.whl
Algorithm Hash digest
SHA256 db0b48ed936b494c4bfc94361c91ed11ef48a6bc8e3fd5c0c68ff50e404ed6ca
MD5 22d963afc36be5ccecc1b2d91a2a9004
BLAKE2b-256 1b4c47a207b76e41567cfe4eb593c553fdf0c5ff908de0f308e27ae72eaca899

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page