autogen_ext.agents.web_surfer.playwright_controller#

class PlaywrightController(downloads_folder: str | None = None, animate_actions: bool = False, viewport_width: int = 1440, viewport_height: int = 900, _download_handler: Callable[[Download], None] | None = None, to_resize_viewport: bool = True)[source]#

Bases: object

A helper class to allow Playwright to interact with web pages to perform actions such as clicking, filling, and scrolling.

Parameters:

  • downloads_folder (str | None) – The folder to save downloads to. If None, downloads are not saved.

  • animate_actions (bool) – Whether to animate the actions (create fake cursor to click).

  • viewport_width (int) – The width of the viewport.

  • viewport_height (int) – The height of the viewport.

  • _download_handler (Optional[Callable[[Download], None]]) – A function to handle downloads.

  • to_resize_viewport (bool) – Whether to resize the viewport

async sleep(page: Page, duration: int | float) → None[source]#

Pause the execution for a specified duration.

Parameters:

  • page (Page) – The Playwright page object.

  • duration (Union[int, float]) – The duration to sleep in milliseconds.

async get_interactive_rects(page: Page) → Dict[str, InteractiveRegion][source]#

Retrieve interactive regions from the web page.

Parameters:

page (Page) – The Playwright page object.

Returns:

Dict[str, InteractiveRegion] – A dictionary of interactive regions.

async get_visual_viewport(page: Page) → VisualViewport[source]#

Retrieve the visual viewport of the web page.

Parameters:

page (Page) – The Playwright page object.

Returns:

VisualViewport – The visual viewport of the page.

async get_focused_rect_id(page: Page) → str | None[source]#

Retrieve the ID of the currently focused element.

Parameters:

page (Page) – The Playwright page object.

Returns:

str – The ID of the focused element or None if no control has focus.

async get_page_metadata(page: Page) → Dict[str, Any][source]#

Retrieve metadata from the web page.

Parameters:

page (Page) – The Playwright page object.

Returns:

Dict[str, Any] – A dictionary of page metadata.

async on_new_page(page: Page) → None[source]#

Handle actions to perform on a new page.

Parameters:

page (Page) – The Playwright page object.

async back(page: Page) → None[source]#

Navigate back to the previous page.

Parameters:

page (Page) – The Playwright page object.

async visit_page(page: Page, url: str) → Tuple[bool, bool][source]#

Visit a specified URL.

Parameters:

  • page (Page) – The Playwright page object.

  • url (str) – The URL to visit.

Returns:

Tuple[bool, bool] – A tuple indicating whether to reset prior metadata hash and last download.

async page_down(page: Page) → None[source]#

Scroll the page down by one viewport height minus 50 pixels.

Parameters:

page (Page) – The Playwright page object.

async page_up(page: Page) → None[source]#

Scroll the page up by one viewport height minus 50 pixels.

Parameters:

page (Page) – The Playwright page object.

async gradual_cursor_animation(page: Page, start_x: float, start_y: float, end_x: float, end_y: float) → None[source]#

Animate the cursor movement gradually from start to end coordinates.

Parameters:

  • page (Page) – The Playwright page object.

  • start_x (float) – The starting x-coordinate.

  • start_y (float) – The starting y-coordinate.

  • end_x (float) – The ending x-coordinate.

  • end_y (float) – The ending y-coordinate.

async add_cursor_box(page: Page, identifier: str) → None[source]#

Add a red cursor box around the element with the given identifier.

Parameters:

  • page (Page) – The Playwright page object.

  • identifier (str) – The element identifier.

async remove_cursor_box(page: Page, identifier: str) → None[source]#

Remove the red cursor box around the element with the given identifier.

Parameters:

  • page (Page) – The Playwright page object.

  • identifier (str) – The element identifier.

async click_id(page: Page, identifier: str) → Page | None[source]#

Click the element with the given identifier.

Parameters:

  • page (Page) – The Playwright page object.

  • identifier (str) – The element identifier.

Returns:

Page | None – The new page if a new page is opened, otherwise None.

async hover_id(page: Page, identifier: str) → None[source]#

Hover the mouse over the element with the given identifier.

Parameters:

  • page (Page) – The Playwright page object.

  • identifier (str) – The element identifier.

async fill_id(page: Page, identifier: str, value: str, press_enter: bool = True) → None[source]#

Fill the element with the given identifier with the specified value.

Parameters:

  • page (Page) – The Playwright page object.

  • identifier (str) – The element identifier.

  • value (str) – The value to fill.

async scroll_id(page: Page, identifier: str, direction: str) → None[source]#

Scroll the element with the given identifier in the specified direction.

Parameters:

  • page (Page) – The Playwright page object.

  • identifier (str) – The element identifier.

  • direction (str) – The direction to scroll (“up” or “down”).

async get_webpage_text(page: Page, n_lines: int = 50) → str[source]#

Retrieve the text content of the web page.

Parameters:

  • page (Page) – The Playwright page object.

  • n_lines (int) – The number of lines to return from the page inner text.

Returns:

str – The text content of the page.

async get_visible_text(page: Page) → str[source]#

Retrieve the text content of the browser viewport (approximately).

Parameters:

page (Page) – The Playwright page object.

Returns:

str – The text content of the page.

async get_page_markdown(page: Page) → str[source]#

Retrieve the markdown content of the web page. Currently not implemented.

Parameters:

page (Page) – The Playwright page object.

Returns:

str – The markdown content of the page.