ScrapeRequest

export type ScrapeRequest = {
    /**
     * 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;
};