5. Browser Automation

Module 05: Browser Automation

Filling Forms, Clicking Buttons, and Automating User Flows

Browser automation goes beyond data extraction — it replicates complete user journeys. Login flows, form submissions, multi-step checkout processes, file uploads, dropdown navigation — anything a human can do in a browser, Playwright can automate. This is the foundation of RPA (Robotic Process Automation), end-to-end testing, and complex site interactions that require authentication.

🖱️ Core Interaction Patterns

from playwright.sync_api import sync_playwright
import time

with sync_playwright() as p:
    browser = p.chromium.launch(headless=False)  # visible for debugging
    page = browser.new_page()
    
    page.goto('https://example-form.com/register')
    
    # Fill text inputs
    page.fill('#username', 'automation_user')
    page.fill('#email', 'user@example.com')
    page.fill('#password', 'SecurePass123!')
    
    # Handle dropdowns
    page.select_option('#country', 'Ghana')  # by value
    page.select_option('#timezone', label='Africa/Accra')  # by visible text
    
    # Handle checkboxes and radio buttons
    page.check('#terms-checkbox')
    page.click('input[type="radio"][value="monthly"]')
    
    # Click buttons
    page.click('button[type="submit"]')
    
    # Wait for navigation after form submit
    page.wait_for_url('**/dashboard**', timeout=10000)
    print('Registration successful, now on dashboard')
    
    # Take a screenshot for verification
    page.screenshot(path='dashboard.png', full_page=True)
    
    browser.close()

🔐 Login Automation and Session Management

import json
from pathlib import Path
from playwright.sync_api import sync_playwright

COOKIE_FILE = Path('session_cookies.json')

def login_and_save_session(email: str, password: str):
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        context = browser.new_context()
        page = context.new_page()
        
        page.goto('https://example.com/login')
        page.fill('input[name="email"]', email)
        page.fill('input[name="password"]', password)
        page.click('button[type="submit"]')
        page.wait_for_url('**/dashboard', timeout=15000)
        
        # Save cookies and local storage
        cookies = context.cookies()
        COOKIE_FILE.write_text(json.dumps(cookies, indent=2))
        print(f'Session saved with {len(cookies)} cookies')
        browser.close()

def use_saved_session():
    if not COOKIE_FILE.exists():
        raise RuntimeError('No saved session. Run login_and_save_session first.')
    
    cookies = json.loads(COOKIE_FILE.read_text())
    
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        context = browser.new_context()
        context.add_cookies(cookies)  # restore session
        page = context.new_page()
        
        # Go directly to protected page — already authenticated
        page.goto('https://example.com/dashboard/orders')
        page.wait_for_selector('table.orders-table')
        
        # Now scrape the authenticated content
        orders = page.eval_on_selector_all(
            'tr.order-row',
            'rows => rows.map(r => ({ id: r.dataset.orderId, status: r.querySelector(".status").innerText }))'
        )
        return orders

📂 File Upload and Download Automation

from playwright.sync_api import sync_playwright
from pathlib import Path

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    context = browser.new_context(accept_downloads=True)
    page = context.new_page()
    
    # --- FILE UPLOAD ---
    page.goto('https://example.com/upload')
    
    # Use set_input_files to upload without triggering a file dialog
    page.set_input_files('input[type="file"]', 'report.csv')
    
    # Upload multiple files
    page.set_input_files('input[type="file"][multiple]', ['file1.csv', 'file2.csv'])
    
    page.click('button#upload-btn')
    page.wait_for_selector('div.upload-success')
    print('Upload complete')
    
    # --- FILE DOWNLOAD ---
    with page.expect_download() as download_info:
        page.click('a#export-csv-btn')
    
    download = download_info.value
    save_path = Path('downloads') / download.suggested_filename
    save_path.parent.mkdir(exist_ok=True)
    download.save_as(str(save_path))
    print(f'Downloaded: {save_path}')
    
    browser.close()

⚡ Handling Dynamic Content and Waits

from playwright.sync_api import sync_playwright, expect

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    page = browser.new_page()
    page.goto('https://dynamic-app.com')
    
    # Wait for element to be visible
    page.wait_for_selector('div#results', state='visible', timeout=15000)
    
    # Wait for element to disappear (e.g., loading spinner)
    page.wait_for_selector('div.loading-spinner', state='hidden', timeout=20000)
    
    # Wait for a network request to complete
    with page.expect_response('**/api/search**') as response_info:
        page.fill('input#search', 'automation tools')
        page.click('button#search-btn')
    response = response_info.value
    data = response.json()
    
    # Use Playwright's built-in assertions
    expect(page.locator('h1')).to_contain_text('Search Results')
    expect(page.locator('ul.results li')).to_have_count(10)
    
    browser.close()

Automation Arena: Target Practice

VOID MART.

CyberDeck Keyboard

$149.99

In Stock

Neural-Link Headset

$899.00

Low Stock

Haptic Gloves v2

$245.50

Out of Stock

Quantum SSD (2TB)

$120.00

In Stock

Target Selector

Scraper Output0 matches

No elements matched.

5. Browser Automation

Module 05: Browser Automation

Filling Forms, Clicking Buttons, and Automating User Flows

🖱️ Core Interaction Patterns

from playwright.sync_api import sync_playwright
import time

with sync_playwright() as p:
    browser = p.chromium.launch(headless=False)  # visible for debugging
    page = browser.new_page()
    
    page.goto('https://example-form.com/register')
    
    # Fill text inputs
    page.fill('#username', 'automation_user')
    page.fill('#email', 'user@example.com')
    page.fill('#password', 'SecurePass123!')
    
    # Handle dropdowns
    page.select_option('#country', 'Ghana')  # by value
    page.select_option('#timezone', label='Africa/Accra')  # by visible text
    
    # Handle checkboxes and radio buttons
    page.check('#terms-checkbox')
    page.click('input[type="radio"][value="monthly"]')
    
    # Click buttons
    page.click('button[type="submit"]')
    
    # Wait for navigation after form submit
    page.wait_for_url('**/dashboard**', timeout=10000)
    print('Registration successful, now on dashboard')
    
    # Take a screenshot for verification
    page.screenshot(path='dashboard.png', full_page=True)
    
    browser.close()

🔐 Login Automation and Session Management

import json
from pathlib import Path
from playwright.sync_api import sync_playwright

COOKIE_FILE = Path('session_cookies.json')

def login_and_save_session(email: str, password: str):
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        context = browser.new_context()
        page = context.new_page()
        
        page.goto('https://example.com/login')
        page.fill('input[name="email"]', email)
        page.fill('input[name="password"]', password)
        page.click('button[type="submit"]')
        page.wait_for_url('**/dashboard', timeout=15000)
        
        # Save cookies and local storage
        cookies = context.cookies()
        COOKIE_FILE.write_text(json.dumps(cookies, indent=2))
        print(f'Session saved with {len(cookies)} cookies')
        browser.close()

def use_saved_session():
    if not COOKIE_FILE.exists():
        raise RuntimeError('No saved session. Run login_and_save_session first.')
    
    cookies = json.loads(COOKIE_FILE.read_text())
    
    with sync_playwright() as p:
        browser = p.chromium.launch(headless=True)
        context = browser.new_context()
        context.add_cookies(cookies)  # restore session
        page = context.new_page()
        
        # Go directly to protected page — already authenticated
        page.goto('https://example.com/dashboard/orders')
        page.wait_for_selector('table.orders-table')
        
        # Now scrape the authenticated content
        orders = page.eval_on_selector_all(
            'tr.order-row',
            'rows => rows.map(r => ({ id: r.dataset.orderId, status: r.querySelector(".status").innerText }))'
        )
        return orders

📂 File Upload and Download Automation

from playwright.sync_api import sync_playwright
from pathlib import Path

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    context = browser.new_context(accept_downloads=True)
    page = context.new_page()
    
    # --- FILE UPLOAD ---
    page.goto('https://example.com/upload')
    
    # Use set_input_files to upload without triggering a file dialog
    page.set_input_files('input[type="file"]', 'report.csv')
    
    # Upload multiple files
    page.set_input_files('input[type="file"][multiple]', ['file1.csv', 'file2.csv'])
    
    page.click('button#upload-btn')
    page.wait_for_selector('div.upload-success')
    print('Upload complete')
    
    # --- FILE DOWNLOAD ---
    with page.expect_download() as download_info:
        page.click('a#export-csv-btn')
    
    download = download_info.value
    save_path = Path('downloads') / download.suggested_filename
    save_path.parent.mkdir(exist_ok=True)
    download.save_as(str(save_path))
    print(f'Downloaded: {save_path}')
    
    browser.close()

⚡ Handling Dynamic Content and Waits

from playwright.sync_api import sync_playwright, expect

with sync_playwright() as p:
    browser = p.chromium.launch(headless=True)
    page = browser.new_page()
    page.goto('https://dynamic-app.com')
    
    # Wait for element to be visible
    page.wait_for_selector('div#results', state='visible', timeout=15000)
    
    # Wait for element to disappear (e.g., loading spinner)
    page.wait_for_selector('div.loading-spinner', state='hidden', timeout=20000)
    
    # Wait for a network request to complete
    with page.expect_response('**/api/search**') as response_info:
        page.fill('input#search', 'automation tools')
        page.click('button#search-btn')
    response = response_info.value
    data = response.json()
    
    # Use Playwright's built-in assertions
    expect(page.locator('h1')).to_contain_text('Search Results')
    expect(page.locator('ul.results li')).to_have_count(10)
    
    browser.close()

Automation Arena: Target Practice

VOID MART.

CyberDeck Keyboard

$149.99

In Stock

Neural-Link Headset

$899.00

Low Stock

Haptic Gloves v2

$245.50

Out of Stock

Quantum SSD (2TB)

$120.00

In Stock

Target Selector

Scraper Output0 matches

No elements matched.

5. Browser Automation

Filling Forms, Clicking Buttons, and Automating User Flows

🖱️ Core Interaction Patterns

🔐 Login Automation and Session Management

📂 File Upload and Download Automation

⚡ Handling Dynamic Content and Waits

VOID MART.

CyberDeck Keyboard

Neural-Link Headset

Haptic Gloves v2

Quantum SSD (2TB)

Knowledge Check

5. Browser Automation

Filling Forms, Clicking Buttons, and Automating User Flows

🖱️ Core Interaction Patterns

🔐 Login Automation and Session Management

📂 File Upload and Download Automation

⚡ Handling Dynamic Content and Waits

VOID MART.

CyberDeck Keyboard

Neural-Link Headset

Haptic Gloves v2

Quantum SSD (2TB)

Knowledge Check