Python headless browser web crawler example

import { defineConfig } from "@trigger.dev/sdk/v3";
import { pythonExtension } from "@trigger.dev/python/extension";
import type { BuildContext, BuildExtension } from "@trigger.dev/core/v3/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,
        },
      });
    },
  };
}

import { logger, schemaTask, task } from "@trigger.dev/sdk/v3";
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;
  },
});

crawl4ai
playwright
urllib3<2.0.0

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))