PDFs

With Browserbase, you can work with PDFs in a few ways:

1. Generate: Create PDFs from web pages with Playwright’s page.pdf() method.
2. Download: Auto-download PDFs to Browserbase’s cloud storage by opening a PDF URL. To retrieve them, see the Downloads documentation.
3. View: Display PDFs in the browser, instead of downloading them, by setting the enablePdfViewer property in your browser settings.

Generate PDFs

After creating and connecting to a session, here’s how to generate a PDF from a web page using Playwright:

Node.js

Playwright

import { chromium } from "playwright-core";
import { Browserbase } from "@browserbasehq/sdk";

(async () => {
  console.log("Starting remote browser...");
  const bb = new Browserbase({ apiKey: process.env.BROWSERBASE_API_KEY });
  const session = await bb.sessions.create();

  const browser = await chromium.connectOverCDP(session.connectUrl);
  const defaultContext = browser.contexts()[0];
  const page = defaultContext.pages()[0];

  await page.goto("https://news.ycombinator.com");

  console.log("Generating PDF...");

  await page.pdf({
    path: "webpage.pdf",
    format: "A4",
  });

  console.log("Shutting down...");
  await page.close();
  await browser.close();
})().catch((error) => {
  console.error(error);
});

Download PDFs

When you navigate to a PDF URL, Browserbase automatically downloads the PDF and cancels the navigation. Browserbase stores the file in cloud storage for later retrieval.

Node.js

Playwright

import { chromium } from "playwright-core";
import { Browserbase } from "@browserbasehq/sdk";

(async () => {
  console.log("Starting remote browser...");
  const bb = new Browserbase({ apiKey: process.env.BROWSERBASE_API_KEY });
  const session = await bb.sessions.create();

  const browser = await chromium.connectOverCDP(session.connectUrl);
  const defaultContext = browser.contexts()[0];
  const page = defaultContext.pages()[0];

  // Configure download behavior
  const client = await defaultContext.newCDPSession(page);
  await client.send("Browser.setDownloadBehavior", {
    behavior: "allow",
    downloadPath: "downloads",
    eventsEnabled: true,
  });

  // Navigate to PDF and trigger download
  console.log("Attempting to download PDF...");
  const [download] = await Promise.all([
    page.waitForEvent("download"),
    page.goto("https://constitutioncenter.org/media/files/constitution.pdf").catch(() => {
      console.log("Navigation cancelled due to download (expected behavior)");
    })
  ]);

  let downloadError = await download.failure();
  if (downloadError !== null) {
    console.log("Error happened on download:", downloadError);
    throw new Error(downloadError);
  }

  console.log("PDF download completed successfully");

  console.log("Shutting down...");
  await page.close();
  await browser.close();
})().catch((error) => {
  console.error(error);
});

import puppeteer from "puppeteer-core";
import { Browserbase } from "@browserbasehq/sdk";

(async () => {
  console.log("Starting remote browser...");
  const bb = new Browserbase({ apiKey: process.env.BROWSERBASE_API_KEY });
  const session = await bb.sessions.create();

  const browser = await puppeteer.connect({
    browserWSEndpoint: session.connectUrl,
  });
  const pages = await browser.pages();
  const page = pages[0];

  // Configure download behavior
  const client = await page.createCDPSession();
  await client.send("Browser.setDownloadBehavior", {
    behavior: "allow",
    downloadPath: "downloads",
    eventsEnabled: true,
  });

  console.log("Attempting to download PDF...");

  // Navigate to PDF URL
  await page.goto("https://constitutioncenter.org/media/files/constitution.pdf").catch(() => {
    console.log("Navigation cancelled due to download (expected behavior)");
  });

  // Wait a moment for download to complete
  await new Promise(resolve => setTimeout(resolve, 3000));

  console.log("PDF download completed successfully");

  console.log("Shutting down...");
  await page.close();
  await browser.close();
})().catch((error) => {
  console.error(error);
});

Python

Playwright

from playwright.sync_api import sync_playwright, Playwright
import os
from browserbase import Browserbase

def main(p: Playwright):
    print("Starting remote browser...")
    bb = Browserbase(api_key=os.environ["BROWSERBASE_API_KEY"])
    session = bb.sessions.create()

    browser = p.chromium.connect_over_cdp(session.connect_url)
    context = browser.contexts[0]
    page = context.pages[0]

    # Configure download behavior
    client = context.new_cdp_session(page)
    client.send("Browser.setDownloadBehavior", {
        "behavior": "allow",
        "downloadPath": "downloads",
        "eventsEnabled": True,
    })

    print("Attempting to download PDF...")

    # Set up download handling and navigate to PDF
    with page.expect_download() as download_info:
        try:
            page.goto("https://constitutioncenter.org/media/files/constitution.pdf")
        except Exception:
            print("Navigation cancelled due to download (expected behavior)")

    download = download_info.value

    # Check for download errors
    if download.failure():
        print(f"Error happened on download: {download.failure()}")
        raise Exception(download.failure())

    print("PDF download completed successfully")

    print("Shutting down...")
    page.close()
    browser.close()

with sync_playwright() as playwright:
    main(playwright)

from selenium import webdriver
from selenium.webdriver.remote.remote_connection import RemoteConnection
import os
import time
from browserbase import Browserbase

def run():
    bb = Browserbase(api_key=os.environ["BROWSERBASE_API_KEY"])
    session = bb.sessions.create()

    # Create a custom connection with the session details
    class CustomRemoteConnection(RemoteConnection):
        def get_remote_connection_headers(self, parsed_url, keep_alive=False):
            headers = super().get_remote_connection_headers(parsed_url, keep_alive)
            headers["x-bb-api-key"] = os.environ["BROWSERBASE_API_KEY"]
            headers["session-id"] = session.id
            return headers

    custom_conn = CustomRemoteConnection(session.selenium_remote_url)

    # Configure Chrome options for downloads
    options = webdriver.ChromeOptions()
    prefs = {
        "download.default_directory": "downloads",
        "download.prompt_for_download": False,
        "plugins.always_open_pdf_externally": True
    }
    options.add_experimental_option("prefs", prefs)

    driver = webdriver.Remote(custom_conn, options=options)

    print("Attempting to download PDF...")

    # Navigate to PDF URL
    driver.get("https://constitutioncenter.org/media/files/constitution.pdf")

    # Wait for download to complete
    time.sleep(5)

    print("PDF download completed successfully")

    # Make sure to quit the driver so your session is ended!
    driver.quit()

run()

Retrieve the downloaded PDF from Browserbase’s cloud storage. See Downloads for details on accessing your files.

View or run the example template here

View PDFs

To view a PDF in the browser tab instead of downloading it, set enablePdfViewer to true:

Node.js

SDK

const bb = new Browserbase({ apiKey: process.env.BROWSERBASE_API_KEY });
const session = await bb.sessions.create({
  browserSettings: {
    enablePdfViewer: true,
  },
});

Python

SDK

bb = Browserbase(api_key=os.environ["BROWSERBASE_API_KEY"])
session = bb.sessions.create(
  browser_settings={
      "enablePdfViewer": True,
  },
)