BrowserOperator API Reference

April 2, 2026 · View on GitHub

T

T = TypeVar("T", bound=BaseModel)

ERROR_ACT_START_FAIL

ERROR_ACT_START_FAIL = 9000

ERROR_ACT_TASK_FAILED

ERROR_ACT_TASK_FAILED = 9001

ERROR_ACT_TIMEOUT

ERROR_ACT_TIMEOUT = 9002

ERROR_OBSERVE_FAIL

ERROR_OBSERVE_FAIL = 9020

ERROR_EXTRACT_FAIL

ERROR_EXTRACT_FAIL = 9040

ERROR_EXTRACT_START_FAIL

ERROR_EXTRACT_START_FAIL = 9041

ERROR_EXTRACT_TIMEOUT

ERROR_EXTRACT_TIMEOUT = 9042

BrowserOperator

class BrowserOperator(BaseService)

BrowserOperator handles browser automation and small parts of agentic logic.

⚠️ Note: Currently, for agent services (including ComputerUseAgent, BrowserUseAgent, and MobileUseAgent), we do not provide services for overseas users registered with alibabacloud.com.

init

def __init__(self, session, browser)

def navigate(url: str) -> str

Navigates a specific page to the given URL.

Arguments:

url: The URL to navigate to.

Returns:

A string indicating the result of the navigation.

screenshot

def screenshot(page=None,
               full_page: bool = True,
               quality: int = 80,
               clip: Optional[Dict[str, float]] = None,
               timeout: Optional[int] = None) -> str

Synchronously takes a screenshot of the specified page.

Arguments:

  • page Optional[Page] - The Playwright Page object to take a screenshot of. If None, the operator's currently focused page will be used.
  • full_page bool - Whether to capture the full scrollable page.
  • quality int - The quality of the image (0-100), for JPEG format.
  • clip Optional[Dict[str, float]] - An object specifying the clipping region {x, y, width, height}.
  • timeout Optional[int] - Custom timeout for the operation in seconds.

Returns:

str: A base64 encoded data URL of the screenshot, or an error message.

close

def close() -> bool

Synchronously closes the remote browser operator session. This will terminate the browser process managed by the operator.

act

def act(action_input: Union[ObserveResult, ActOptions],
        page=None) -> "ActResult"

Synchronously perform an action on a web page.

Arguments:

  • page Optional[Page] - The Playwright Page object to act on. If None, the operator's currently focused page will be used automatically.
  • action_input Union[ObserveResult, ActOptions] - The action to perform.

Returns:

ActResult: The result of the action.

observe

def observe(options: ObserveOptions,
            page=None) -> Tuple[bool, List[ObserveResult]]

Synchronously observe elements or state on a web page.

Arguments:

  • page Optional[Page] - The Playwright Page object to observe. If None, the operator's currently focused page will be used.
  • options ObserveOptions - Options to configure the observation behavior.

Returns:

Tuple[bool, List[ObserveResult]]: A tuple containing a success boolean and a list of observation results.

extract

def extract(options: ExtractOptions, page=None) -> Tuple[bool, T]

Synchronously extract information from a web page.

Arguments:

  • page Optional[Page] - The Playwright Page object to extract from. If None, the operator's currently focused page will be used.
  • options ExtractOptions - Options to configure the extraction, including schema.

Returns:

Tuple[bool, T]: A tuple containing a success boolean and the extracted data as a Pydantic model instance, or None on failure.

login

def login(login_config: str,
          page=None,
          use_vision: Optional[bool] = False) -> "ActResult"

Synchronously perform a login operation on a web page.

Arguments:

  • login_config str - A JSON string containing login configuration, e.g., '{"api_key": "xxx", "skill_id": "yyy"}'
  • page Optional[Page] - The Playwright Page object to login on. If None, the agent's currently focused page will be used.
  • use_vision Optional[bool] - Whether to use vision-based capabilities during login.

Returns:

ActResult: The result of the login operation.

See Also

Documentation generated automatically from source code using pydoc-markdown.