GlobalScrapeRequest

export type GlobalScrapeRequest = {
    /**
     * Solve Captchas
     *
     * Whether to try to automatically solve captchas
     */
    solve_captchas?: boolean;
    /**
     * Max Duration Minutes
     *
     * Maximum session lifetime in minutes (absolute maximum, not affected by activity).
     */
    max_duration_minutes?: number;
    /**
     * Idle Timeout Minutes
     *
     * Idle timeout in minutes. Session closes after this period of inactivity (resets on each operation).
     */
    idle_timeout_minutes?: number;
    /**
     * Proxies
     *
     * List of custom proxies to use for the session. If True, the default proxies will be used.
     */
    proxies?: Array<NotteProxy | ExternalProxy | TailnetProxy> | boolean;
    /**
     * Browser Type
     *
     * The browser type to use. Supported values are chromium and chrome. chrome-nightly and chrome-turbo are legacy aliases for chrome.
     */
    browser_type?: 'chromium' | 'chrome' | 'chrome-nightly' | 'chrome-turbo';
    /**
     * User Agent
     *
     * The user agent to use for the session
     */
    user_agent?: string | null;
    /**
     * Chrome Args
     *
     * Overwrite the chrome instance arguments
     */
    chrome_args?: Array<string> | null;
    /**
     * Viewport Width
     *
     * The width of the viewport
     */
    viewport_width?: number | null;
    /**
     * Viewport Height
     *
     * The height of the viewport
     */
    viewport_height?: number | null;
    /**
     * Aspect Ratio
     *
     * Viewport shape preset. When set, the backend fits the largest rectangle of this aspect ratio inside the sampled available screen area. Cannot be combined with explicit viewport_width/viewport_height.
     */
    aspect_ratio?: '5:4' | '16:9' | null;
    /**
     * Cdp Url
     *
     * The CDP URL of another remote session provider.
     */
    cdp_url?: string | null;
    /**
     * Screenshot Type
     *
     * The type of screenshot to use for the session.
     */
    screenshot_type?: 'raw' | 'full' | 'last_action';
    /**
     * Browser profile configuration for state persistence
     */
    profile?: SessionProfile | null;
    /**
     * Web Bot Auth
     *
     * Whether to use web bot authentication.
     */
    web_bot_auth?: boolean;
    /**
     * Extra Http Headers
     *
     * Extra HTTP headers to be sent with every request.
     */
    extra_http_headers?: {
        [key: string]: string;
    } | null;
    /**
     * Vault Id
     *
     * The vault to use for the session
     */
    vault_id?: string | null;
    /**
     * Auth Ids
     *
     * Managed Auth connection IDs to verify and, when necessary, authenticate inside this session before it is returned.
     */
    auth_ids?: Array<string>;
    /**
     * Wait For Authentication
     *
     * Whether to wait for Managed Auth before returning the session. Defaults to true. When true, authentication failure or timeout fails session creation; when false, authentication continues in the background after the browser is ready.
     */
    wait_for_authentication?: boolean;
    /**
     * Advanced Stealth
     *
     * Enable Notte's highest-fidelity browser environment for sites with sophisticated bot detection. Available to approved workspaces.
     */
    advanced_stealth?: boolean;
    /**
     * Selector
     *
     * Playwright selector to scope the scrape to. Only content inside this selector will be scraped.
     */
    selector?: string | null;
    /**
     * Scrape Links
     *
     * Whether to scrape links from the page. Links are scraped by default.
     */
    scrape_links?: boolean;
    /**
     * Scrape Images
     *
     * Whether to scrape images from the page. Images are scraped by default.
     */
    scrape_images?: boolean;
    /**
     * Ignored Tags
     *
     * HTML tags to ignore from the page
     */
    ignored_tags?: Array<string> | null;
    /**
     * Only Main Content
     *
     * Whether to only scrape the main content of the page. If True, navbars, footers, etc. are excluded.
     */
    only_main_content?: boolean;
    /**
     * Only Images
     *
     * Whether to only scrape images from the page. If True, the page content is excluded.
     */
    only_images?: boolean;
    /**
     * Response Format
     *
     * The response format to use for the scrape. Use a JSON Schema object; high-level Node agent and scrape methods also accept a Zod schema
     */
    response_format?: unknown | null;
    /**
     * Instructions
     *
     * Additional instructions to use for the scrape. E.g. 'Extract only the title, date and content of the articles.'
     */
    instructions?: string | null;
    /**
     * Use Link Placeholders
     *
     * Whether to use link/image placeholders to reduce the number of tokens in the prompt and hallucinations. However this is an experimental feature and might not work as expected.
     */
    use_link_placeholders?: boolean;
    /**
     * Url
     */
    url: string;
};