wehub-resource-sync
229 lines
7.5 KiB
Plaintext
229 lines
7.5 KiB
Plaintext
---
|
|
title: "Python headless browser web crawler example"
|
|
sidebarTitle: "Headless web crawler"
|
|
description: "Learn how to use Python, Crawl4AI and Playwright to create a headless browser web crawler with Trigger.dev."
|
|
---
|
|
|
|
import ScrapingWarning from "/snippets/web-scraping-warning.mdx";
|
|
import PythonLearnMore from "/snippets/python-learn-more.mdx";
|
|
|
|
## Overview
|
|
|
|
This demo showcases how to use Trigger.dev with Python to build a web crawler that uses a headless browser to navigate websites and extract content.
|
|
|
|
## Prerequisites
|
|
|
|
- A project with [Trigger.dev initialized](/quick-start)
|
|
- [Python](https://www.python.org/) installed on your local machine
|
|
|
|
## Features
|
|
|
|
- [Trigger.dev](https://trigger.dev) for background task orchestration
|
|
- Our [Python build extension](/config/extensions/pythonExtension) to install the dependencies and run the Python script
|
|
- [Crawl4AI](https://github.com/unclecode/crawl4ai), an open source LLM friendly web crawler
|
|
- A custom [Playwright extension](https://playwright.dev/) to create a headless chromium browser
|
|
- Proxy support
|
|
|
|
## Using Proxies
|
|
|
|
<ScrapingWarning />
|
|
|
|
Some popular proxy services are:
|
|
|
|
- [Smartproxy](https://smartproxy.com/)
|
|
- [Bright Data](https://brightdata.com/)
|
|
- [Browserbase](https://browserbase.com/)
|
|
- [Oxylabs](https://oxylabs.io/)
|
|
- [ScrapingBee](https://scrapingbee.com/)
|
|
|
|
Once you have a proxy service, set the following environment variables in your Trigger.dev .env file, and add them in the Trigger.dev dashboard:
|
|
|
|
- `PROXY_URL`: The URL of your proxy server (e.g., `http://proxy.example.com:8080`)
|
|
- `PROXY_USERNAME`: Username for authenticated proxies (optional)
|
|
- `PROXY_PASSWORD`: Password for authenticated proxies (optional)
|
|
|
|
## GitHub repo
|
|
|
|
<Card
|
|
title="View the project on GitHub"
|
|
icon="GitHub"
|
|
href="https://github.com/triggerdotdev/examples/tree/main/python-crawl4ai"
|
|
>
|
|
Click here to view the full code for this project in our examples repository on GitHub. You can
|
|
fork it and use it as a starting point for your own project.
|
|
</Card>
|
|
|
|
## The code
|
|
|
|
### Build configuration
|
|
|
|
After you've initialized your project with Trigger.dev, add these build settings to your `trigger.config.ts` file:
|
|
|
|
```ts trigger.config.ts
|
|
import { defineConfig } from "@trigger.dev/sdk";
|
|
import { pythonExtension } from "@trigger.dev/python/extension";
|
|
import type { BuildContext, BuildExtension } from "@trigger.dev/core/build";
|
|
|
|
export default defineConfig({
|
|
project: "<project ref>",
|
|
// Your other config settings...
|
|
build: {
|
|
extensions: [
|
|
// This is required to use the Python extension
|
|
pythonExtension(),
|
|
// This is required to create a headless chromium browser with Playwright
|
|
installPlaywrightChromium(),
|
|
],
|
|
},
|
|
});
|
|
|
|
// This is a custom build extension to install Playwright and Chromium
|
|
export function installPlaywrightChromium(): BuildExtension {
|
|
return {
|
|
name: "InstallPlaywrightChromium",
|
|
onBuildComplete(context: BuildContext) {
|
|
const instructions = [
|
|
// Base and Chromium dependencies
|
|
`RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
curl unzip npm libnspr4 libatk1.0-0 libatk-bridge2.0-0 libatspi2.0-0 \
|
|
libasound2 libnss3 libxcomposite1 libxdamage1 libxfixes3 libxrandr2 \
|
|
libgbm1 libxkbcommon0 \
|
|
&& apt-get clean && rm -rf /var/lib/apt/lists/*`,
|
|
|
|
// Install Playwright and Chromium
|
|
`RUN npm install -g playwright`,
|
|
`RUN mkdir -p /ms-playwright`,
|
|
`RUN PLAYWRIGHT_BROWSERS_PATH=/ms-playwright python -m playwright install --with-deps chromium`,
|
|
];
|
|
|
|
context.addLayer({
|
|
id: "playwright",
|
|
image: { instructions },
|
|
deploy: {
|
|
env: {
|
|
PLAYWRIGHT_BROWSERS_PATH: "/ms-playwright",
|
|
PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD: "1",
|
|
PLAYWRIGHT_SKIP_BROWSER_VALIDATION: "1",
|
|
},
|
|
override: true,
|
|
},
|
|
});
|
|
},
|
|
};
|
|
}
|
|
```
|
|
|
|
<Info>
|
|
Learn more about executing scripts in your Trigger.dev project using our Python build extension
|
|
[here](/config/extensions/pythonExtension).
|
|
</Info>
|
|
|
|
### Task code
|
|
|
|
This task uses the `python.runScript` method to run the `crawl-url.py` script with the given URL as an argument. You can see the original task in our examples repository [here](https://github.com/triggerdotdev/examples/blob/main/python-crawl4ai/src/trigger/pythonTasks.ts).
|
|
|
|
```ts src/trigger/pythonTasks.ts
|
|
import { logger, schemaTask, task } from "@trigger.dev/sdk";
|
|
import { python } from "@trigger.dev/python";
|
|
import { z } from "zod";
|
|
|
|
export const convertUrlToMarkdown = schemaTask({
|
|
id: "convert-url-to-markdown",
|
|
schema: z.object({
|
|
url: z.string().url(),
|
|
}),
|
|
run: async (payload) => {
|
|
// Pass through any proxy environment variables
|
|
const env = {
|
|
PROXY_URL: process.env.PROXY_URL,
|
|
PROXY_USERNAME: process.env.PROXY_USERNAME,
|
|
PROXY_PASSWORD: process.env.PROXY_PASSWORD,
|
|
};
|
|
|
|
const result = await python.runScript("./src/python/crawl-url.py", [payload.url], { env });
|
|
|
|
logger.debug("convert-url-to-markdown", {
|
|
url: payload.url,
|
|
result,
|
|
});
|
|
|
|
return result.stdout;
|
|
},
|
|
});
|
|
```
|
|
|
|
### Add a requirements.txt file
|
|
|
|
Add the following to your `requirements.txt` file. This is required in Python projects to install the dependencies.
|
|
|
|
```txt requirements.txt
|
|
crawl4ai
|
|
playwright
|
|
urllib3<2.0.0
|
|
```
|
|
|
|
### The Python script
|
|
|
|
The Python script is a simple script using Crawl4AI that takes a URL and returns the markdown content of the page. You can see the original script in our examples repository [here](https://github.com/triggerdotdev/examples/blob/main/python-crawl4ai/src/python/crawl-url.py).
|
|
|
|
```python src/python/crawl-url.py
|
|
import asyncio
|
|
import sys
|
|
import os
|
|
from crawl4ai import *
|
|
from crawl4ai.async_configs import BrowserConfig
|
|
|
|
async def main(url: str):
|
|
# Get proxy configuration from environment variables
|
|
proxy_url = os.environ.get("PROXY_URL")
|
|
proxy_username = os.environ.get("PROXY_USERNAME")
|
|
proxy_password = os.environ.get("PROXY_PASSWORD")
|
|
|
|
# Configure the proxy
|
|
browser_config = None
|
|
if proxy_url:
|
|
if proxy_username and proxy_password:
|
|
# Use authenticated proxy
|
|
proxy_config = {
|
|
"server": proxy_url,
|
|
"username": proxy_username,
|
|
"password": proxy_password
|
|
}
|
|
browser_config = BrowserConfig(proxy_config=proxy_config)
|
|
else:
|
|
# Use simple proxy
|
|
browser_config = BrowserConfig(proxy=proxy_url)
|
|
else:
|
|
browser_config = BrowserConfig()
|
|
|
|
async with AsyncWebCrawler(config=browser_config) as crawler:
|
|
result = await crawler.arun(
|
|
url=url,
|
|
)
|
|
print(result.markdown)
|
|
|
|
if __name__ == "__main__":
|
|
if len(sys.argv) < 2:
|
|
print("Usage: python crawl-url.py <url>")
|
|
sys.exit(1)
|
|
url = sys.argv[1]
|
|
asyncio.run(main(url))
|
|
```
|
|
|
|
## Testing your task
|
|
|
|
1. Create a virtual environment `python -m venv venv`
|
|
2. Activate the virtual environment, depending on your OS: On Mac/Linux: `source venv/bin/activate`, on Windows: `venv\Scripts\activate`
|
|
3. Install the Python dependencies `pip install -r requirements.txt`
|
|
4. If you haven't already, copy your project ref from your [Trigger.dev dashboard](https://cloud.trigger.dev) and add it to the `trigger.config.ts` file.
|
|
5. Run the Trigger.dev CLI `dev` command (it may ask you to authorize the CLI if you haven't already).
|
|
6. Test the task in the dashboard, using a URL of your choice.
|
|
|
|
<ScrapingWarning />
|
|
|
|
## Deploying your task
|
|
|
|
Deploy the task to production using the Trigger.dev CLI `deploy` command.
|
|
|
|
<PythonLearnMore />
|