Automating Gestures

Appium supports automating complex pointer, touch, key, and wheel interactions through the W3C WebDriver Perform Actions API (W3C Specification). Alternatively, many drivers provide platform-native gesture Execute Methods for common interactions.

In the W3C Actions API, interactions are defined by creating one or more virtual input sources (such as pointer with pointerType: "touch", key, wheel, or none) and queuing a sequence of synchronized ticks (pointerMove, pointerDown, pointerUp, pause). See the Selenium Actions API documentation for a general overview of input sources and tick synchronization.

Below are examples of common single-finger and multi-touch gestures implemented using the W3C Actions API across client languages.

Double Tap

Performs two quick touch taps at (x, y) with a short pause between them:

JS (WebDriverIO)JavaPythonRubyC#

await driver
  .action('pointer', {parameters: {pointerType: 'touch'}})
  .move({x: 200, y: 300, duration: 0})
  .down()
  .up()
  .pause(100)
  .down()
  .up()
  .perform();

PointerInput finger = new PointerInput(PointerInput.Kind.TOUCH, "finger");
Sequence doubleTap = new Sequence(finger, 1)
    .addAction(finger.createPointerMove(Duration.ZERO, PointerInput.Origin.viewport(), 200, 300))
    .addAction(finger.createPointerDown(PointerInput.MouseButton.LEFT.asArg()))
    .addAction(finger.createPointerUp(PointerInput.MouseButton.LEFT.asArg()))
    .addAction(new Pause(finger, Duration.ofMillis(100)))
    .addAction(finger.createPointerDown(PointerInput.MouseButton.LEFT.asArg()))
    .addAction(finger.createPointerUp(PointerInput.MouseButton.LEFT.asArg()));
driver.perform(Collections.singletonList(doubleTap));

actions = ActionChains(driver)
actions.w3c_actions = ActionBuilder(driver, mouse=PointerInput(interaction.POINTER_TOUCH, "finger"))
actions.w3c_actions.pointer_action.move_to_location(200, 300)
actions.w3c_actions.pointer_action.pointer_down()
actions.w3c_actions.pointer_action.pointer_up()
actions.w3c_actions.pointer_action.pause(0.1)
actions.w3c_actions.pointer_action.pointer_down()
actions.w3c_actions.pointer_action.pointer_up()
actions.perform()

f1 = driver.action.add_pointer_input(:touch, 'finger')
f1.create_pointer_move(duration: 0, x: 200, y: 300, origin: :viewport)
f1.create_pointer_down(:left)
f1.create_pointer_up(:left)
f1.create_pause(0.1)
f1.create_pointer_down(:left)
f1.create_pointer_up(:left)
driver.perform_actions([f1])

var finger = new PointerInputDevice(PointerKind.Touch, "finger");
var doubleTap = new ActionSequence(finger, 0);
doubleTap.AddAction(finger.CreatePointerMove(CoordinateOrigin.Viewport, 200, 300, TimeSpan.Zero));
doubleTap.AddAction(finger.CreatePointerDown(MouseButton.Touch));
doubleTap.AddAction(finger.CreatePointerUp(MouseButton.Touch));
doubleTap.AddAction(finger.CreatePause(TimeSpan.FromMilliseconds(100)));
doubleTap.AddAction(finger.CreatePointerDown(MouseButton.Touch));
doubleTap.AddAction(finger.CreatePointerUp(MouseButton.Touch));
driver.PerformActions(new List<ActionSequence> { doubleTap });

Long Press

Presses and holds a touch pointer at (x, y) for 1000ms before releasing:

JS (WebDriverIO)JavaPythonRubyC#

await driver
  .action('pointer', {parameters: {pointerType: 'touch'}})
  .move({x: 200, y: 300, duration: 0})
  .down()
  .pause(1000)
  .up()
  .perform();

PointerInput finger = new PointerInput(PointerInput.Kind.TOUCH, "finger");
Sequence longPress = new Sequence(finger, 1)
    .addAction(finger.createPointerMove(Duration.ZERO, PointerInput.Origin.viewport(), 200, 300))
    .addAction(finger.createPointerDown(PointerInput.MouseButton.LEFT.asArg()))
    .addAction(new Pause(finger, Duration.ofMillis(1000)))
    .addAction(finger.createPointerUp(PointerInput.MouseButton.LEFT.asArg()));
driver.perform(Collections.singletonList(longPress));

actions = ActionChains(driver)
actions.w3c_actions = ActionBuilder(driver, mouse=PointerInput(interaction.POINTER_TOUCH, "finger"))
actions.w3c_actions.pointer_action.move_to_location(200, 300)
actions.w3c_actions.pointer_action.pointer_down()
actions.w3c_actions.pointer_action.pause(1.0)
actions.w3c_actions.pointer_action.pointer_up()
actions.perform()

f1 = driver.action.add_pointer_input(:touch, 'finger')
f1.create_pointer_move(duration: 0, x: 200, y: 300, origin: :viewport)
f1.create_pointer_down(:left)
f1.create_pause(1.0)
f1.create_pointer_up(:left)
driver.perform_actions([f1])

var finger = new PointerInputDevice(PointerKind.Touch, "finger");
var longPress = new ActionSequence(finger, 0);
longPress.AddAction(finger.CreatePointerMove(CoordinateOrigin.Viewport, 200, 300, TimeSpan.Zero));
longPress.AddAction(finger.CreatePointerDown(MouseButton.Touch));
longPress.AddAction(finger.CreatePause(TimeSpan.FromMilliseconds(1000)));
longPress.AddAction(finger.CreatePointerUp(MouseButton.Touch));
driver.PerformActions(new List<ActionSequence> { longPress });

Drag and Drop / Swipe

Moves a touch pointer from (200, 600) to (200, 200) over 600ms:

JS (WebDriverIO)JavaPythonRubyC#

await driver
  .action('pointer', {parameters: {pointerType: 'touch'}})
  .move({x: 200, y: 600, duration: 0})
  .down()
  .pause(100)
  .move({x: 200, y: 200, duration: 600})
  .up()
  .perform();

PointerInput finger = new PointerInput(PointerInput.Kind.TOUCH, "finger");
Sequence dragAndDrop = new Sequence(finger, 1)
    .addAction(finger.createPointerMove(Duration.ZERO, PointerInput.Origin.viewport(), 200, 600))
    .addAction(finger.createPointerDown(PointerInput.MouseButton.LEFT.asArg()))
    .addAction(new Pause(finger, Duration.ofMillis(100)))
    .addAction(finger.createPointerMove(Duration.ofMillis(600), PointerInput.Origin.viewport(), 200, 200))
    .addAction(finger.createPointerUp(PointerInput.MouseButton.LEFT.asArg()));
driver.perform(Collections.singletonList(dragAndDrop));

actions = ActionChains(driver)
actions.w3c_actions = ActionBuilder(driver, mouse=PointerInput(interaction.POINTER_TOUCH, "finger"))
actions.w3c_actions.pointer_action.move_to_location(200, 600)
actions.w3c_actions.pointer_action.pointer_down()
actions.w3c_actions.pointer_action.pause(0.1)
actions.w3c_actions.pointer_action.move_to_location(200, 200)
actions.w3c_actions.pointer_action.pointer_up()
actions.perform()

f1 = driver.action.add_pointer_input(:touch, 'finger')
f1.create_pointer_move(duration: 0, x: 200, y: 600, origin: :viewport)
f1.create_pointer_down(:left)
f1.create_pause(0.1)
f1.create_pointer_move(duration: 0.6, x: 200, y: 200, origin: :viewport)
f1.create_pointer_up(:left)
driver.perform_actions([f1])

var finger = new PointerInputDevice(PointerKind.Touch, "finger");
var dragAndDrop = new ActionSequence(finger, 0);
dragAndDrop.AddAction(finger.CreatePointerMove(CoordinateOrigin.Viewport, 200, 600, TimeSpan.Zero));
dragAndDrop.AddAction(finger.CreatePointerDown(MouseButton.Touch));
dragAndDrop.AddAction(finger.CreatePause(TimeSpan.FromMilliseconds(100)));
dragAndDrop.AddAction(finger.CreatePointerMove(CoordinateOrigin.Viewport, 200, 200, TimeSpan.FromMilliseconds(600)));
dragAndDrop.AddAction(finger.CreatePointerUp(MouseButton.Touch));
driver.PerformActions(new List<ActionSequence> { dragAndDrop });

Pinch and Zoom (Multi-Touch)

Uses two concurrent touch pointer sequences (finger1 and finger2) moving apart to zoom in (or toward each other to pinch):

JS (WebDriverIO)JavaPythonRubyC#

await driver.performActions([
  {
    type: 'pointer',
    id: 'finger1',
    parameters: {pointerType: 'touch'},
    actions: [
      {type: 'pointerMove', duration: 0, x: 200, y: 400},
      {type: 'pointerDown', button: 0},
      {type: 'pause', duration: 100},
      {type: 'pointerMove', duration: 500, x: 200, y: 200},
      {type: 'pointerUp', button: 0},
    ],
  },
  {
    type: 'pointer',
    id: 'finger2',
    parameters: {pointerType: 'touch'},
    actions: [
      {type: 'pointerMove', duration: 0, x: 200, y: 450},
      {type: 'pointerDown', button: 0},
      {type: 'pause', duration: 100},
      {type: 'pointerMove', duration: 500, x: 200, y: 650},
      {type: 'pointerUp', button: 0},
    ],
  },
]);

PointerInput finger1 = new PointerInput(PointerInput.Kind.TOUCH, "finger1");
Sequence seq1 = new Sequence(finger1, 1)
    .addAction(finger1.createPointerMove(Duration.ZERO, PointerInput.Origin.viewport(), 200, 400))
    .addAction(finger1.createPointerDown(PointerInput.MouseButton.LEFT.asArg()))
    .addAction(new Pause(finger1, Duration.ofMillis(100)))
    .addAction(finger1.createPointerMove(Duration.ofMillis(500), PointerInput.Origin.viewport(), 200, 200))
    .addAction(finger1.createPointerUp(PointerInput.MouseButton.LEFT.asArg()));

PointerInput finger2 = new PointerInput(PointerInput.Kind.TOUCH, "finger2");
Sequence seq2 = new Sequence(finger2, 1)
    .addAction(finger2.createPointerMove(Duration.ZERO, PointerInput.Origin.viewport(), 200, 450))
    .addAction(finger2.createPointerDown(PointerInput.MouseButton.LEFT.asArg()))
    .addAction(new Pause(finger2, Duration.ofMillis(100)))
    .addAction(finger2.createPointerMove(Duration.ofMillis(500), PointerInput.Origin.viewport(), 200, 650))
    .addAction(finger2.createPointerUp(PointerInput.MouseButton.LEFT.asArg()));

driver.perform(Arrays.asList(seq1, seq2));

action_builder = ActionBuilder(driver)
finger1 = action_builder.add_pointer_input(interaction.POINTER_TOUCH, "finger1")
finger2 = action_builder.add_pointer_input(interaction.POINTER_TOUCH, "finger2")

finger1.create_pointer_move(duration=0, x=200, y=400)
finger1.create_pointer_down(button=MouseButton.LEFT)
finger1.create_pause(0.1)
finger1.create_pointer_move(duration=500, x=200, y=200)
finger1.create_pointer_up(button=MouseButton.LEFT)

finger2.create_pointer_move(duration=0, x=200, y=450)
finger2.create_pointer_down(button=MouseButton.LEFT)
finger2.create_pause(0.1)
finger2.create_pointer_move(duration=500, x=200, y=650)
finger2.create_pointer_up(button=MouseButton.LEFT)

action_builder.perform()

f1 = driver.action.add_pointer_input(:touch, 'finger1')
f1.create_pointer_move(duration: 0, x: 200, y: 400, origin: :viewport)
f1.create_pointer_down(:left)
f1.create_pause(0.1)
f1.create_pointer_move(duration: 0.5, x: 200, y: 200, origin: :viewport)
f1.create_pointer_up(:left)

f2 = driver.action.add_pointer_input(:touch, 'finger2')
f2.create_pointer_move(duration: 0, x: 200, y: 450, origin: :viewport)
f2.create_pointer_down(:left)
f2.create_pause(0.1)
f2.create_pointer_move(duration: 0.5, x: 200, y: 650, origin: :viewport)
f2.create_pointer_up(:left)

driver.perform_actions([f1, f2])

var finger1 = new PointerInputDevice(PointerKind.Touch, "finger1");
var seq1 = new ActionSequence(finger1, 0);
seq1.AddAction(finger1.CreatePointerMove(CoordinateOrigin.Viewport, 200, 400, TimeSpan.Zero));
seq1.AddAction(finger1.CreatePointerDown(MouseButton.Touch));
seq1.AddAction(finger1.CreatePause(TimeSpan.FromMilliseconds(100)));
seq1.AddAction(finger1.CreatePointerMove(CoordinateOrigin.Viewport, 200, 200, TimeSpan.FromMilliseconds(500)));
seq1.AddAction(finger1.CreatePointerUp(MouseButton.Touch));

var finger2 = new PointerInputDevice(PointerKind.Touch, "finger2");
var seq2 = new ActionSequence(finger2, 0);
seq2.AddAction(finger2.CreatePointerMove(CoordinateOrigin.Viewport, 200, 450, TimeSpan.Zero));
seq2.AddAction(finger2.CreatePointerDown(MouseButton.Touch));
seq2.AddAction(finger2.CreatePause(TimeSpan.FromMilliseconds(100)));
seq2.AddAction(finger2.CreatePointerMove(CoordinateOrigin.Viewport, 200, 650, TimeSpan.FromMilliseconds(500)));
seq2.AddAction(finger2.CreatePointerUp(MouseButton.Touch));

driver.PerformActions(new List<ActionSequence> { seq1, seq2 });