Chrome Devtools Protocol with BiDi API

These examples are currently implemented with CDP, but the same code should work when the functionality is re-implemented with WebDriver-BiDi.

Usage

The following list of APIs will be growing as the Selenium project works through supporting real world use cases. If there is additional functionality you’d like to see, please raise a feature request.

As these examples are re-implemented with the WebDriver-Bidi protocol, they will be moved to the WebDriver Bidi pages.

Examples

Basic authentication

Some applications make use of browser authentication to secure pages. It used to be common to handle them in the URL, but browser stopped supporting this. With BiDi, you can now provide the credentials when necessary

Alternate implementations can be found at CDP Endpoint Basic Authentication and CDP API Basic Authentication

    Predicate<URI> uriPredicate = uri -> uri.toString().contains("herokuapp.com");
    Supplier<Credentials> authentication = UsernameAndPassword.of("admin", "admin");

    ((HasAuthentication) driver).register(uriPredicate, authentication);

An alternate implementation may be found at CDP Endpoint Basic Authentication

Implementation Missing

            var handler = new NetworkAuthenticationHandler()
            {
                UriMatcher = uri => uri.AbsoluteUri.Contains("herokuapp"),
                Credentials = new PasswordCredentials("admin", "admin")
            };

            var networkInterceptor = driver.Manage().Network;
            networkInterceptor.AddAuthenticationHandler(handler);

            await networkInterceptor.StartMonitoring();
    driver.register(username: 'admin',
                    password: 'admin',
                    uri: /herokuapp/)

Move Code

const {Builder} = require('selenium-webdriver');

(async function example() {
  try {
    let driver = await new Builder()
      .forBrowser('chrome')
      .build();

    const pageCdpConnection = await driver.createCDPConnection('page');
    await driver.register('username', 'password', pageCdpConnection);
    await driver.get('https://the-internet.herokuapp.com/basic_auth');
    await driver.quit();
  }catch (e){
    console.log(e)
  }
}())

Move Code

val uriPredicate = Predicate { uri: URI ->
        uri.host.contains("your-domain.com")
    }
(driver as HasAuthentication).register(uriPredicate, UsernameAndPassword.of("admin", "password"))
driver.get("https://your-domain.com/login")

Pin scripts

This can be especially useful when executing on a remote server. For example, whenever you check the visibility of an element, or whenever you use the classic get attribute method, Selenium is sending the contents of a js file to the script execution endpoint. These files are each about 50kB, which adds up.

            var key = await new JavaScriptEngine(driver).PinScript("return arguments;");

            var arguments = ((WebDriver)driver).ExecuteScript(key, 1, true, element);
    key = driver.pin_script('return arguments;')
    arguments = driver.execute_script(key, 1, true, element)

Mutation observation

Mutation Observation is the ability to capture events via WebDriver BiDi when there are DOM mutations on a specific element in the DOM.

    CopyOnWriteArrayList<WebElement> mutations = new CopyOnWriteArrayList<>();
    ((HasLogEvents) driver).onLogEvent(domMutation(e -> mutations.add(e.getElement())));
    async with driver.bidi_connection() as session:
        log = Log(driver, session)
            var mutations = new List<IWebElement>();
            using IJavaScriptEngine monitor = new JavaScriptEngine(driver);
            monitor.DomMutated += (_, e) =>
            {
                var locator = By.CssSelector($"*[data-__webdriver_id='{e.AttributeData.TargetId}']");
                mutations.Add(driver.FindElement(locator));
            };

            await monitor.StartEventMonitoring();
            await monitor.EnableDomMutationMonitoring();
    mutations = []
    driver.on_log_event(:mutation) { |mutation| mutations << mutation.element }

Move Code

const {Builder, until} = require('selenium-webdriver');
const assert = require("assert");

(async function example() {
  try {
    let driver = await new Builder()
      .forBrowser('chrome')
      .build();

    const cdpConnection = await driver.createCDPConnection('page');
    await driver.logMutationEvents(cdpConnection, event => {
      assert.deepStrictEqual(event['attribute_name'], 'style');
      assert.deepStrictEqual(event['current_value'], "");
      assert.deepStrictEqual(event['old_value'], "display:none;");
    });

    await driver.get('dynamic.html');
    await driver.findElement({id: 'reveal'}).click();
    let revealed = driver.findElement({id: 'revealed'});
    await driver.wait(until.elementIsVisible(revealed), 5000);
    await driver.quit();
  }catch (e){
    console.log(e)
  }
}())

Console logs and errors

Listen to the console.log events and register callbacks to process the event.

CDP API Console logs and WebDriver BiDi Console logs

Use the WebDriver BiDi Console logs implementation. HasLogEvents will likely end up deprecated because it does not implement Closeable.

    CopyOnWriteArrayList<String> messages = new CopyOnWriteArrayList<>();
    ((HasLogEvents) driver).onLogEvent(consoleEvent(e -> messages.add(e.getMessages().get(0))));
    async with driver.bidi_connection() as session:
        log = Log(driver, session)

        async with log.add_listener(Console.ALL) as messages:
            using IJavaScriptEngine monitor = new JavaScriptEngine(driver);
            var messages = new List<string>();
            monitor.JavaScriptConsoleApiCalled += (_, e) =>
            {
                messages.Add(e.MessageContent);
            };

            await monitor.StartEventMonitoring();
    logs = []
    driver.on_log_event(:console) { |log| logs << log.args.first }

Move Code

const {Builder} = require('selenium-webdriver');
(async () => {
  try {
    let driver = new Builder()
      .forBrowser('chrome')
      .build();

    const cdpConnection = await driver.createCDPConnection('page');
    await driver.onLogEvent(cdpConnection, function (event) {
      console.log(event['args'][0]['value']);
    });
    await driver.executeScript('console.log("here")');
    await driver.quit();
  }catch (e){
    console.log(e);
  }
})()

Move Code

fun kotlinConsoleLogExample() {
    val driver = ChromeDriver()
    val devTools = driver.devTools
    devTools.createSession()

    val logConsole = { c: ConsoleEvent -> print("Console log message is: " + c.messages)}
    devTools.domains.events().addConsoleListener(logConsole)

    driver.get("https://www.google.com")

    val executor = driver as JavascriptExecutor
    executor.executeScript("console.log('Hello World')")

    val input = driver.findElement(By.name("q"))
    input.sendKeys("Selenium 4")
    input.sendKeys(Keys.RETURN)
    driver.quit()
}

JavaScript exceptions

Listen to the JS Exceptions and register callbacks to process the exception details.

    async with driver.bidi_connection() as session:
        log = Log(driver, session)

        async with log.add_js_error_listener() as messages:
            using IJavaScriptEngine monitor = new JavaScriptEngine(driver);
            var messages = new List<string>();
            monitor.JavaScriptExceptionThrown += (_, e) =>
            {
                messages.Add(e.Message);
            };

            await monitor.StartEventMonitoring();
    exceptions = []
    driver.on_log_event(:exception) { |exception| exceptions << exception }

Network Interception

Both requests and responses can be recorded or transformed.

Response information

    CopyOnWriteArrayList<String> contentType = new CopyOnWriteArrayList<>();

    try (NetworkInterceptor ignored =
        new NetworkInterceptor(
            driver,
            (Filter)
                next ->
                    req -> {
                      HttpResponse res = next.execute(req);
                      contentType.add(res.getHeader("Content-Type"));
                      return res;
                    })) {
            var contentType = new List<string>();

            INetwork networkInterceptor = driver.Manage().Network;
            networkInterceptor.NetworkResponseReceived += (_, e)  =>
            {
                contentType.Add(e.ResponseHeaders["content-type"]);
            };

            await networkInterceptor.StartMonitoring();
    content_type = []
    driver.intercept do |request, &continue|
      continue.call(request) do |response|
        content_type << response.headers['content-type']
      end
    end

Response transformation

    try (NetworkInterceptor ignored =
        new NetworkInterceptor(
            driver,
            Route.matching(req -> true)
                .to(
                    () ->
                        req ->
                            new HttpResponse()
                                .setStatus(200)
                                .addHeader("Content-Type", MediaType.HTML_UTF_8.toString())
                                .setContent(Contents.utf8String("Creamy, delicious cheese!"))))) {
            var handler = new NetworkResponseHandler()
            {
                ResponseMatcher = _ => true,
                ResponseTransformer = _ => new HttpResponseData
                {
                    StatusCode = 200,
                    Body = "Creamy, delicious cheese!"
                }
            };

            INetwork networkInterceptor = driver.Manage().Network;
            networkInterceptor.AddResponseHandler(handler);

            await networkInterceptor.StartMonitoring();
    driver.intercept do |request, &continue|
      continue.call(request) do |response|
        response.body = 'Creamy, delicious cheese!' if request.url.include?('blank')
      end
    end

Move Code

const connection = await driver.createCDPConnection('page')
let url = fileServer.whereIs("/cheese")
let httpResponse = new HttpResponse(url)
httpResponse.addHeaders("Content-Type", "UTF-8")
httpResponse.body = "sausages"
await driver.onIntercept(connection, httpResponse, async function () {
  let body = await driver.getPageSource()
  assert.strictEqual(body.includes("sausages"), true, `Body contains: ${body}`)
})
driver.get(url)

Move Code

val driver = ChromeDriver()
val interceptor = new NetworkInterceptor(
      driver,
      Route.matching(req -> true)
        .to(() -> req -> new HttpResponse()
          .setStatus(200)
          .addHeader("Content-Type", MediaType.HTML_UTF_8.toString())
          .setContent(utf8String("Creamy, delicious cheese!"))))

    driver.get(appServer.whereIs("/cheese"))

    String source = driver.getPageSource()

Request interception

            var handler = new NetworkRequestHandler
            {
                RequestMatcher = request => request.Url.Contains("one.js"),
                RequestTransformer = request =>
                {
                    request.Url = request.Url.Replace("one", "two");

                    return request;
                }
            };

            INetwork networkInterceptor = driver.Manage().Network;
            networkInterceptor.AddRequestHandler(handler);

            await networkInterceptor.StartMonitoring();
    driver.intercept do |request, &continue|
      uri = URI(request.url)
      request.url = uri.to_s.gsub('one', 'two') if uri.path&.end_with?('one.js')
      continue.call(request)
    end
Last modified November 17, 2023: Upgrade to Docsy 0 7 2 (#1529) (48f43616907)