Playwright tips and trick

Cature request with playwright

When web scraping using Playwright and Python to capture background requests and responses we can use the page.on() method to add middleware callbacks on request and response events:

from playwright.sync_api import sync_playwright
 
def intercept_request(request):
    # we can update requests with custom headers
    if "secret" in request.url :
        request.headers['x-secret-token'] = "123"
        print("patched headers of a secret request")
    # or adjust sent data
    if request.method == "POST":
        request.post_data = "patched"
        print("patched POST request")
    return request
 
def intercept_response(response):
    # we can extract details from background requests
    if response.request.resource_type == "xhr":
        print(response.headers.get('cookie'))
    return response
 
with sync_playwright() as pw:
    browser = pw.chromium.launch(headless=False)
    context = browser.new_context(viewport={"width": 1920, "height": 1080})
    page = context.new_page()
    # enable intercepting for this page
    page.on("request", intercept_request)
    page.on("response", intercept_response)
 
    page.goto("https://google.com/")