Class Configuration

src/crawlee/configuration.py:20–230

Configuration settings for the Crawlee project. This class stores common configurable parameters for Crawlee. Default values are provided for all settings, so typically, no adjustments are necessary. However, you may modify settings for specific use cases, such as changing the default s

@docs_group('Configuration')
class Configuration(BaseSettings):
    """Configuration settings for the Crawlee project.

    This class stores common configurable parameters for Crawlee. Default values are provided for all settings,
    so typically, no adjustments are necessary. However, you may modify settings for specific use cases,
    such as changing the default storage directory, the default storage IDs, the timeout for internal
    operations, and more.

    Settings can also be configured via environment variables, prefixed with `CRAWLEE_`.
    """

    # TODO: https://github.com/pydantic/pydantic-settings/issues/706
    # Use `SettingsConfigDict(validate_by_name=True, validate_by_alias=True)` when issue is resolved.
    model_config = SettingsConfigDict(populate_by_name=True)

    internal_timeout: Annotated[timedelta | None, Field(alias='crawlee_internal_timeout')] = None
    """Timeout for the internal asynchronous operations."""

    default_browser_path: Annotated[
        str | None,
        Field(
            validation_alias=AliasChoices(
                'apify_default_browser_path',
                'crawlee_default_browser_path',
            )
        ),
    ] = None
    """Specifies the path to the browser executable. Currently primarily for Playwright-based features. This option
    is passed directly to Playwright's `browser_type.launch` method as `executable_path` argument. For more details,
    refer to the Playwright documentation:
    https://playwright.dev/docs/api/class-browsertype#browser-type-launch.
    """

    disable_browser_sandbox: Annotated[
        bool,
        Field(
            validation_alias=AliasChoices(
                'apify_disable_browser_sandbox',
                'crawlee_disable_browser_sandbox',
            )
        ),
    ] = False
    """Disables the sandbox for the browser. Currently primarily for Playwright-based features. This option
    is passed directly to Playwright's `browser_type.launch` method as `chromium_sandbox`. For more details,
    refer to the Playwright documentation:
    https://playwright.dev/docs/api/class-browsertype#browser-type-launch."""

    log_level: Annotated[
        LogLevel,
        Field(
            validation_alias=AliasChoices(
                'apify_log_level',
                'crawlee_log_level',
            )
        ),
        BeforeValidator(lambda value: str(value).upper()),
    ] = 'INFO'
    """The logging level."""