@mendable/firecrawl-js/dist/index.d.cts

JavaScript SDK for Firecrawl API

import * as zt from 'zod';
import { ZodTypeAny } from 'zod';
import { AxiosResponse, AxiosRequestHeaders } from 'axios';
import { EventEmitter } from 'events';
import { TypedEventTarget } from 'typescript-event-target';

type FormatString = 'markdown' | 'html' | 'rawHtml' | 'links' | 'images' | 'screenshot' | 'summary' | 'changeTracking' | 'json' | 'attributes' | 'branding';
interface Viewport {
    width: number;
    height: number;
}
interface Format {
    type: FormatString;
}
interface JsonFormat extends Format {
    type: 'json';
    prompt?: string;
    schema?: Record<string, unknown> | ZodTypeAny;
}
interface ScreenshotFormat {
    type: 'screenshot';
    fullPage?: boolean;
    quality?: number;
    viewport?: Viewport | {
        width: number;
        height: number;
    };
}
interface ChangeTrackingFormat extends Format {
    type: 'changeTracking';
    modes: ('git-diff' | 'json')[];
    schema?: Record<string, unknown>;
    prompt?: string;
    tag?: string;
}
interface AttributesFormat extends Format {
    type: 'attributes';
    selectors: Array<{
        selector: string;
        attribute: string;
    }>;
}
type FormatOption = FormatString | Format | JsonFormat | ChangeTrackingFormat | ScreenshotFormat | AttributesFormat;
interface LocationConfig$1 {
    country?: string;
    languages?: string[];
}
interface WaitAction {
    type: 'wait';
    milliseconds?: number;
    selector?: string;
}
interface ScreenshotAction {
    type: 'screenshot';
    fullPage?: boolean;
    quality?: number;
    viewport?: Viewport | {
        width: number;
        height: number;
    };
}
interface ClickAction {
    type: 'click';
    selector: string;
}
interface WriteAction {
    type: 'write';
    text: string;
}
interface PressAction {
    type: 'press';
    key: string;
}
interface ScrollAction {
    type: 'scroll';
    direction: 'up' | 'down';
    selector?: string;
}
interface ScrapeAction {
    type: 'scrape';
}
interface ExecuteJavascriptAction {
    type: 'executeJavascript';
    script: string;
}
interface PDFAction {
    type: 'pdf';
    format?: 'A0' | 'A1' | 'A2' | 'A3' | 'A4' | 'A5' | 'A6' | 'Letter' | 'Legal' | 'Tabloid' | 'Ledger';
    landscape?: boolean;
    scale?: number;
}
type ActionOption = WaitAction | ScreenshotAction | ClickAction | WriteAction | PressAction | ScrollAction | ScrapeAction | ExecuteJavascriptAction | PDFAction;
interface ScrapeOptions {
    formats?: FormatOption[];
    headers?: Record<string, string>;
    includeTags?: string[];
    excludeTags?: string[];
    onlyMainContent?: boolean;
    timeout?: number;
    waitFor?: number;
    mobile?: boolean;
    parsers?: Array<string | {
        type: 'pdf';
        maxPages?: number;
    }>;
    actions?: ActionOption[];
    location?: LocationConfig$1;
    skipTlsVerification?: boolean;
    removeBase64Images?: boolean;
    fastMode?: boolean;
    useMock?: string;
    blockAds?: boolean;
    proxy?: 'basic' | 'stealth' | 'auto' | string;
    maxAge?: number;
    minAge?: number;
    storeInCache?: boolean;
    integration?: string;
}
interface WebhookConfig {
    url: string;
    headers?: Record<string, string>;
    metadata?: Record<string, string>;
    events?: Array<'completed' | 'failed' | 'page' | 'started'>;
}
interface BrandingProfile {
    colorScheme?: 'light' | 'dark';
    logo?: string | null;
    fonts?: Array<{
        family: string;
        [key: string]: unknown;
    }>;
    colors?: {
        primary?: string;
        secondary?: string;
        accent?: string;
        background?: string;
        textPrimary?: string;
        textSecondary?: string;
        link?: string;
        success?: string;
        warning?: string;
        error?: string;
        [key: string]: string | undefined;
    };
    typography?: {
        fontFamilies?: {
            primary?: string;
            heading?: string;
            code?: string;
            [key: string]: string | undefined;
        };
        fontStacks?: {
            primary?: string[];
            heading?: string[];
            body?: string[];
            paragraph?: string[];
            [key: string]: string[] | undefined;
        };
        fontSizes?: {
            h1?: string;
            h2?: string;
            h3?: string;
            body?: string;
            small?: string;
            [key: string]: string | undefined;
        };
        lineHeights?: {
            heading?: number;
            body?: number;
            [key: string]: number | undefined;
        };
        fontWeights?: {
            light?: number;
            regular?: number;
            medium?: number;
            bold?: number;
            [key: string]: number | undefined;
        };
    };
    spacing?: {
        baseUnit?: number;
        padding?: Record<string, number>;
        margins?: Record<string, number>;
        gridGutter?: number;
        borderRadius?: string;
        [key: string]: number | string | Record<string, number> | undefined;
    };
    components?: {
        buttonPrimary?: {
            background?: string;
            textColor?: string;
            borderColor?: string;
            borderRadius?: string;
            [key: string]: string | undefined;
        };
        buttonSecondary?: {
            background?: string;
            textColor?: string;
            borderColor?: string;
            borderRadius?: string;
            [key: string]: string | undefined;
        };
        input?: {
            borderColor?: string;
            focusBorderColor?: string;
            borderRadius?: string;
            [key: string]: string | undefined;
        };
        [key: string]: unknown;
    };
    icons?: {
        style?: string;
        primaryColor?: string;
        [key: string]: string | undefined;
    };
    images?: {
        logo?: string | null;
        favicon?: string | null;
        ogImage?: string | null;
        [key: string]: string | null | undefined;
    };
    animations?: {
        transitionDuration?: string;
        easing?: string;
        [key: string]: string | undefined;
    };
    layout?: {
        grid?: {
            columns?: number;
            maxWidth?: string;
            [key: string]: number | string | undefined;
        };
        headerHeight?: string;
        footerHeight?: string;
        [key: string]: number | string | Record<string, number | string | undefined> | undefined;
    };
    tone?: {
        voice?: string;
        emojiUsage?: string;
        [key: string]: string | undefined;
    };
    personality?: {
        tone: 'professional' | 'playful' | 'modern' | 'traditional' | 'minimalist' | 'bold';
        energy: 'low' | 'medium' | 'high';
        targetAudience: string;
    };
    [key: string]: unknown;
}
interface DocumentMetadata {
    title?: string;
    description?: string;
    url?: string;
    language?: string;
    keywords?: string | string[];
    robots?: string;
    ogTitle?: string;
    ogDescription?: string;
    ogUrl?: string;
    ogImage?: string;
    ogAudio?: string;
    ogDeterminer?: string;
    ogLocale?: string;
    ogLocaleAlternate?: string[];
    ogSiteName?: string;
    ogVideo?: string;
    favicon?: string;
    dcTermsCreated?: string;
    dcDateCreated?: string;
    dcDate?: string;
    dcTermsType?: string;
    dcType?: string;
    dcTermsAudience?: string;
    dcTermsSubject?: string;
    dcSubject?: string;
    dcDescription?: string;
    dcTermsKeywords?: string;
    modifiedTime?: string;
    publishedTime?: string;
    articleTag?: string;
    articleSection?: string;
    sourceURL?: string;
    statusCode?: number;
    scrapeId?: string;
    numPages?: number;
    contentType?: string;
    timezone?: string;
    proxyUsed?: 'basic' | 'stealth';
    cacheState?: 'hit' | 'miss';
    cachedAt?: string;
    creditsUsed?: number;
    concurrencyLimited?: boolean;
    concurrencyQueueDurationMs?: number;
    error?: string;
    [key: string]: unknown;
}
interface Document {
    markdown?: string;
    html?: string;
    rawHtml?: string;
    json?: unknown;
    summary?: string;
    metadata?: DocumentMetadata;
    links?: string[];
    images?: string[];
    screenshot?: string;
    attributes?: Array<{
        selector: string;
        attribute: string;
        values: string[];
    }>;
    actions?: Record<string, unknown>;
    warning?: string;
    changeTracking?: Record<string, unknown>;
    branding?: BrandingProfile;
}
interface PaginationConfig {
    /** When true (default), automatically follow `next` links and aggregate all documents. */
    autoPaginate?: boolean;
    /** Maximum number of additional pages to fetch after the first response. */
    maxPages?: number;
    /** Maximum total number of documents to return across all pages. */
    maxResults?: number;
    /** Maximum time to spend fetching additional pages (in seconds). */
    maxWaitTime?: number;
}
interface SearchResultWeb {
    url: string;
    title?: string;
    description?: string;
    category?: string;
}
interface SearchResultNews {
    title?: string;
    url?: string;
    snippet?: string;
    date?: string;
    imageUrl?: string;
    position?: number;
    category?: string;
}
interface SearchResultImages {
    title?: string;
    imageUrl?: string;
    imageWidth?: number;
    imageHeight?: number;
    url?: string;
    position?: number;
}
interface SearchData {
    web?: Array<SearchResultWeb | Document>;
    news?: Array<SearchResultNews | Document>;
    images?: Array<SearchResultImages | Document>;
}
interface CategoryOption {
    type: 'github' | 'research' | 'pdf';
}
interface SearchRequest {
    query: string;
    sources?: Array<'web' | 'news' | 'images' | {
        type: 'web' | 'news' | 'images';
    }>;
    categories?: Array<'github' | 'research' | 'pdf' | CategoryOption>;
    limit?: number;
    tbs?: string;
    location?: string;
    ignoreInvalidURLs?: boolean;
    timeout?: number;
    scrapeOptions?: ScrapeOptions;
    integration?: string;
}
interface CrawlOptions {
    prompt?: string | null;
    excludePaths?: string[] | null;
    includePaths?: string[] | null;
    maxDiscoveryDepth?: number | null;
    sitemap?: 'skip' | 'include';
    ignoreQueryParameters?: boolean;
    limit?: number | null;
    crawlEntireDomain?: boolean;
    allowExternalLinks?: boolean;
    allowSubdomains?: boolean;
    delay?: number | null;
    maxConcurrency?: number | null;
    webhook?: string | WebhookConfig | null;
    scrapeOptions?: ScrapeOptions | null;
    zeroDataRetention?: boolean;
    integration?: string;
}
interface CrawlResponse$1 {
    id: string;
    url: string;
}
interface CrawlJob {
    id: string;
    status: 'scraping' | 'completed' | 'failed' | 'cancelled';
    total: number;
    completed: number;
    creditsUsed?: number;
    expiresAt?: string;
    next?: string | null;
    data: Document[];
}
interface BatchScrapeOptions {
    options?: ScrapeOptions;
    webhook?: string | WebhookConfig;
    appendToId?: string;
    ignoreInvalidURLs?: boolean;
    maxConcurrency?: number;
    zeroDataRetention?: boolean;
    idempotencyKey?: string;
    integration?: string;
}
interface BatchScrapeResponse$1 {
    id: string;
    url: string;
    invalidURLs?: string[];
}
interface BatchScrapeJob {
    id: string;
    status: 'scraping' | 'completed' | 'failed' | 'cancelled';
    completed: number;
    total: number;
    creditsUsed?: number;
    expiresAt?: string;
    next?: string | null;
    data: Document[];
}
interface MapData {
    links: SearchResultWeb[];
}
interface MapOptions {
    search?: string;
    sitemap?: 'only' | 'include' | 'skip';
    includeSubdomains?: boolean;
    ignoreQueryParameters?: boolean;
    limit?: number;
    timeout?: number;
    integration?: string;
    location?: LocationConfig$1;
}
interface ExtractResponse$1 {
    success?: boolean;
    id?: string;
    status?: 'processing' | 'completed' | 'failed' | 'cancelled';
    data?: unknown;
    error?: string;
    warning?: string;
    sources?: Record<string, unknown>;
    expiresAt?: string;
    creditsUsed?: number;
}
interface AgentResponse {
    success: boolean;
    id: string;
    error?: string;
}
interface AgentStatusResponse {
    success: boolean;
    status: 'processing' | 'completed' | 'failed';
    error?: string;
    data?: unknown;
    expiresAt: string;
    creditsUsed?: number;
}
interface AgentOptions$1 {
    model: 'FIRE-1' | 'v3-beta';
}
interface ConcurrencyCheck {
    concurrency: number;
    maxConcurrency: number;
}
interface CreditUsage {
    remainingCredits: number;
    planCredits?: number;
    billingPeriodStart?: string | null;
    billingPeriodEnd?: string | null;
}
interface TokenUsage {
    remainingTokens: number;
    planTokens?: number;
    billingPeriodStart?: string | null;
    billingPeriodEnd?: string | null;
}
interface CreditUsageHistoricalPeriod {
    startDate: string | null;
    endDate: string | null;
    apiKey?: string;
    creditsUsed: number;
}
interface CreditUsageHistoricalResponse {
    success: boolean;
    periods: CreditUsageHistoricalPeriod[];
}
interface TokenUsageHistoricalPeriod {
    startDate: string | null;
    endDate: string | null;
    apiKey?: string;
    tokensUsed: number;
}
interface TokenUsageHistoricalResponse {
    success: boolean;
    periods: TokenUsageHistoricalPeriod[];
}
interface CrawlErrorsResponse$1 {
    errors: {
        id: string;
        timestamp?: string;
        url: string;
        code?: string;
        error: string;
    }[];
    robotsBlocked: string[];
}
interface ActiveCrawl {
    id: string;
    teamId: string;
    url: string;
    options?: Record<string, unknown> | null;
}
interface ActiveCrawlsResponse {
    success: boolean;
    crawls: ActiveCrawl[];
}
interface ErrorDetails {
    code?: string;
    message: string;
    details?: Record<string, unknown>;
    status?: number;
}
declare class SdkError extends Error {
    status?: number;
    code?: string;
    details?: unknown;
    jobId?: string;
    constructor(message: string, status?: number, code?: string, details?: unknown, jobId?: string);
}
declare class JobTimeoutError extends SdkError {
    timeoutSeconds: number;
    constructor(jobId: string, timeoutSeconds: number, jobType?: 'batch' | 'crawl');
}
interface QueueStatusResponse$1 {
    success: boolean;
    jobsInQueue: number;
    activeJobsInQueue: number;
    waitingJobsInQueue: number;
    maxConcurrency: number;
    mostRecentSuccess: string | null;
}

interface HttpClientOptions {
    apiKey: string;
    apiUrl: string;
    timeoutMs?: number;
    maxRetries?: number;
    backoffFactor?: number;
}
declare class HttpClient {
    private instance;
    private readonly apiKey;
    private readonly apiUrl;
    private readonly maxRetries;
    private readonly backoffFactor;
    constructor(options: HttpClientOptions);
    getApiUrl(): string;
    getApiKey(): string;
    private request;
    private sleep;
    post<T = any>(endpoint: string, body: Record<string, unknown>, headers?: Record<string, string>): Promise<AxiosResponse<T, any, {}>>;
    get<T = any>(endpoint: string, headers?: Record<string, string>): Promise<AxiosResponse<T, any, {}>>;
    delete<T = any>(endpoint: string, headers?: Record<string, string>): Promise<AxiosResponse<T, any, {}>>;
    prepareHeaders(idempotencyKey?: string): Record<string, string>;
}

declare function prepareExtractPayload(args: {
    urls?: string[];
    prompt?: string;
    schema?: Record<string, unknown> | ZodTypeAny;
    systemPrompt?: string;
    allowExternalLinks?: boolean;
    enableWebSearch?: boolean;
    showSources?: boolean;
    scrapeOptions?: ScrapeOptions;
    ignoreInvalidURLs?: boolean;
    integration?: string;
    agent?: AgentOptions$1;
}): Record<string, unknown>;
declare function startExtract(http: HttpClient, args: Parameters<typeof prepareExtractPayload>[0]): Promise<ExtractResponse$1>;

declare function prepareAgentPayload(args: {
    urls?: string[];
    prompt: string;
    schema?: Record<string, unknown> | ZodTypeAny;
    integration?: string;
    maxCredits?: number;
    strictConstrainToURLs?: boolean;
}): Record<string, unknown>;
declare function startAgent(http: HttpClient, args: Parameters<typeof prepareAgentPayload>[0]): Promise<AgentResponse>;

type JobKind = "crawl" | "batch";
interface WatcherOptions {
    kind?: JobKind;
    pollInterval?: number;
    timeout?: number;
}
declare class Watcher extends EventEmitter {
    private readonly http;
    private readonly jobId;
    private readonly kind;
    private readonly pollInterval;
    private readonly timeout?;
    private ws?;
    private closed;
    private readonly emittedDocumentKeys;
    constructor(http: HttpClient, jobId: string, opts?: WatcherOptions);
    private buildWsUrl;
    start(): Promise<void>;
    private attachWsHandlers;
    private documentKey;
    private emitDocuments;
    private emitSnapshot;
    private pollLoop;
    close(): void;
}

type ExtractJsonSchemaFromFormats<Formats> = Formats extends readonly any[] ? Extract<Formats[number], {
    type: "json";
    schema?: unknown;
}>["schema"] : never;
type InferredJsonFromOptions<Opts> = Opts extends {
    formats?: infer Fmts;
} ? ExtractJsonSchemaFromFormats<Fmts> extends zt.ZodTypeAny ? zt.infer<ExtractJsonSchemaFromFormats<Fmts>> : unknown : unknown;
/**
 * Configuration for the v2 client transport.
 */
interface FirecrawlClientOptions {
    /** API key (falls back to FIRECRAWL_API_KEY). */
    apiKey?: string | null;
    /** API base URL (falls back to FIRECRAWL_API_URL or https://api.firecrawl.dev). */
    apiUrl?: string | null;
    /** Per-request timeout in milliseconds (optional). */
    timeoutMs?: number;
    /** Max automatic retries for transient failures (optional). */
    maxRetries?: number;
    /** Exponential backoff factor for retries (optional). */
    backoffFactor?: number;
}
/**
 * Firecrawl v2 client. Provides typed access to all v2 endpoints and utilities.
 */
declare class FirecrawlClient {
    private readonly http;
    private isCloudService;
    /**
     * Create a v2 client.
     * @param options Transport configuration (API key, base URL, timeouts, retries).
     */
    constructor(options?: FirecrawlClientOptions);
    /**
     * Scrape a single URL.
     * @param url Target URL.
     * @param options Optional scrape options (formats, headers, etc.).
     * @returns Resolved document with requested formats.
     */
    scrape<Opts extends ScrapeOptions>(url: string, options: Opts): Promise<Omit<Document, "json"> & {
        json?: InferredJsonFromOptions<Opts>;
    }>;
    scrape(url: string, options?: ScrapeOptions): Promise<Document>;
    /**
     * Search the web and optionally scrape each result.
     * @param query Search query string.
     * @param req Additional search options (sources, limit, scrapeOptions, etc.).
     * @returns Structured search results.
     */
    search(query: string, req?: Omit<SearchRequest, "query">): Promise<SearchData>;
    /**
     * Map a site to discover URLs (sitemap-aware).
     * @param url Root URL to map.
     * @param options Mapping options (sitemap mode, includeSubdomains, limit, timeout).
     * @returns Discovered links.
     */
    map(url: string, options?: MapOptions): Promise<MapData>;
    /**
     * Start a crawl job (async).
     * @param url Root URL to crawl.
     * @param req Crawl configuration (paths, limits, scrapeOptions, webhook, etc.).
     * @returns Job id and url.
     */
    startCrawl(url: string, req?: CrawlOptions): Promise<CrawlResponse$1>;
    /**
     * Get the status and partial data of a crawl job.
     * @param jobId Crawl job id.
     */
    getCrawlStatus(jobId: string, pagination?: PaginationConfig): Promise<CrawlJob>;
    /**
     * Cancel a crawl job.
     * @param jobId Crawl job id.
     * @returns True if cancelled.
     */
    cancelCrawl(jobId: string): Promise<boolean>;
    /**
     * Convenience waiter: start a crawl and poll until it finishes.
     * @param url Root URL to crawl.
     * @param req Crawl configuration plus waiter controls (pollInterval, timeout seconds).
     * @returns Final job snapshot.
     */
    crawl(url: string, req?: CrawlOptions & {
        pollInterval?: number;
        timeout?: number;
    }): Promise<CrawlJob>;
    /**
     * Retrieve crawl errors and robots.txt blocks.
     * @param crawlId Crawl job id.
     */
    getCrawlErrors(crawlId: string): Promise<CrawlErrorsResponse$1>;
    /**
     * List active crawls for the authenticated team.
     */
    getActiveCrawls(): Promise<ActiveCrawlsResponse>;
    /**
     * Preview normalized crawl parameters produced by a natural-language prompt.
     * @param url Root URL.
     * @param prompt Natural-language instruction.
     */
    crawlParamsPreview(url: string, prompt: string): Promise<Record<string, unknown>>;
    /**
     * Start a batch scrape job for multiple URLs (async).
     * @param urls URLs to scrape.
     * @param opts Batch options (scrape options, webhook, concurrency, idempotency key, etc.).
     * @returns Job id and url.
     */
    startBatchScrape(urls: string[], opts?: BatchScrapeOptions): Promise<BatchScrapeResponse$1>;
    /**
     * Get the status and partial data of a batch scrape job.
     * @param jobId Batch job id.
     */
    getBatchScrapeStatus(jobId: string, pagination?: PaginationConfig): Promise<BatchScrapeJob>;
    /**
     * Retrieve batch scrape errors and robots.txt blocks.
     * @param jobId Batch job id.
     */
    getBatchScrapeErrors(jobId: string): Promise<CrawlErrorsResponse$1>;
    /**
     * Cancel a batch scrape job.
     * @param jobId Batch job id.
     * @returns True if cancelled.
     */
    cancelBatchScrape(jobId: string): Promise<boolean>;
    /**
     * Convenience waiter: start a batch scrape and poll until it finishes.
     * @param urls URLs to scrape.
     * @param opts Batch options plus waiter controls (pollInterval, timeout seconds).
     * @returns Final job snapshot.
     */
    batchScrape(urls: string[], opts?: BatchScrapeOptions & {
        pollInterval?: number;
        timeout?: number;
    }): Promise<BatchScrapeJob>;
    /**
     * Start an extract job (async).
     * @param args Extraction request (urls, schema or prompt, flags).
     * @returns Job id or processing state.
     */
    startExtract(args: Parameters<typeof startExtract>[1]): Promise<ExtractResponse$1>;
    /**
     * Get extract job status/data.
     * @param jobId Extract job id.
     */
    getExtractStatus(jobId: string): Promise<ExtractResponse$1>;
    /**
     * Convenience waiter: start an extract and poll until it finishes.
     * @param args Extraction request plus waiter controls (pollInterval, timeout seconds).
     * @returns Final extract response.
     */
    extract(args: Parameters<typeof startExtract>[1] & {
        pollInterval?: number;
        timeout?: number;
    }): Promise<ExtractResponse$1>;
    /**
     * Start an agent job (async).
     * @param args Agent request (urls, prompt, schema).
     * @returns Job id or processing state.
     */
    startAgent(args: Parameters<typeof startAgent>[1]): Promise<AgentResponse>;
    /**
     * Get agent job status/data.
     * @param jobId Agent job id.
     */
    getAgentStatus(jobId: string): Promise<AgentStatusResponse>;
    /**
     * Convenience waiter: start an agent and poll until it finishes.
     * @param args Agent request plus waiter controls (pollInterval, timeout seconds).
     * @returns Final agent response.
     */
    agent(args: Parameters<typeof startAgent>[1] & {
        pollInterval?: number;
        timeout?: number;
    }): Promise<AgentStatusResponse>;
    /**
     * Cancel an agent job.
     * @param jobId Agent job id.
     * @returns True if cancelled.
     */
    cancelAgent(jobId: string): Promise<boolean>;
    /** Current concurrency usage. */
    getConcurrency(): Promise<ConcurrencyCheck>;
    /** Current credit usage. */
    getCreditUsage(): Promise<CreditUsage>;
    /** Recent token usage. */
    getTokenUsage(): Promise<TokenUsage>;
    /** Historical credit usage by month; set byApiKey to true to break down by API key. */
    getCreditUsageHistorical(byApiKey?: boolean): Promise<CreditUsageHistoricalResponse>;
    /** Historical token usage by month; set byApiKey to true to break down by API key. */
    getTokenUsageHistorical(byApiKey?: boolean): Promise<TokenUsageHistoricalResponse>;
    /** Metrics about the team's scrape queue. */
    getQueueStatus(): Promise<QueueStatusResponse$1>;
    /**
     * Create a watcher for a crawl or batch job. Emits: `document`, `snapshot`, `done`, `error`.
     * @param jobId Job id.
     * @param opts Watcher options (kind, pollInterval, timeout seconds).
     */
    watcher(jobId: string, opts?: WatcherOptions): Watcher;
}

/**
 * Configuration interface for FirecrawlApp.
 * @param apiKey - Optional API key for authentication.
 * @param apiUrl - Optional base URL of the API; defaults to 'https://api.firecrawl.dev'.
 */
interface FirecrawlAppConfig {
    apiKey?: string | null;
    apiUrl?: string | null;
}
/**
 * Metadata for a Firecrawl document.
 * Includes various optional properties for document metadata.
 */
interface FirecrawlDocumentMetadata {
    title?: string;
    description?: string;
    language?: string;
    keywords?: string;
    robots?: string;
    ogTitle?: string;
    ogDescription?: string;
    ogUrl?: string;
    ogImage?: string;
    ogAudio?: string;
    ogDeterminer?: string;
    ogLocale?: string;
    ogLocaleAlternate?: string[];
    ogSiteName?: string;
    ogVideo?: string;
    dctermsCreated?: string;
    dcDateCreated?: string;
    dcDate?: string;
    dctermsType?: string;
    dcType?: string;
    dctermsAudience?: string;
    dctermsSubject?: string;
    dcSubject?: string;
    dcDescription?: string;
    dctermsKeywords?: string;
    modifiedTime?: string;
    publishedTime?: string;
    articleTag?: string;
    articleSection?: string;
    sourceURL?: string;
    statusCode?: number;
    timezone?: string;
    error?: string;
    proxyUsed?: "basic" | "stealth";
    cacheState?: "miss" | "hit";
    cachedAt?: string;
    creditsUsed?: number;
    concurrencyLimited?: boolean;
    concurrencyQueueDurationMs?: number;
    [key: string]: any;
}
/**
 * Document interface for Firecrawl.
 * Represents a document retrieved or processed by Firecrawl.
 */
interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult | never) = never> {
    url?: string;
    markdown?: string;
    html?: string;
    rawHtml?: string;
    links?: string[];
    extract?: T;
    json?: T;
    screenshot?: string;
    metadata?: FirecrawlDocumentMetadata;
    actions: ActionsSchema;
    changeTracking?: {
        previousScrapeAt: string | null;
        changeStatus: "new" | "same" | "changed" | "removed";
        visibility: "visible" | "hidden";
        diff?: {
            text: string;
            json: {
                files: Array<{
                    from: string | null;
                    to: string | null;
                    chunks: Array<{
                        content: string;
                        changes: Array<{
                            type: string;
                            normal?: boolean;
                            ln?: number;
                            ln1?: number;
                            ln2?: number;
                            content: string;
                        }>;
                    }>;
                }>;
            };
        };
        json?: any;
    };
    title?: string;
    description?: string;
}
/**
 * Location configuration for proxy location
 */
interface LocationConfig {
    country?: string;
    languages?: string[];
}
/**
 * Parameters for scraping operations.
 * Defines the options and configurations available for scraping web content.
 */
interface CrawlScrapeOptions {
    formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json" | "changeTracking")[];
    headers?: Record<string, string>;
    includeTags?: string[];
    excludeTags?: string[];
    onlyMainContent?: boolean;
    waitFor?: number;
    timeout?: number;
    location?: LocationConfig;
    mobile?: boolean;
    skipTlsVerification?: boolean;
    removeBase64Images?: boolean;
    blockAds?: boolean;
    proxy?: "basic" | "stealth" | "auto";
    storeInCache?: boolean;
    maxAge?: number;
    parsePDF?: boolean;
}
type Action = {
    type: "wait";
    milliseconds?: number;
    selector?: string;
} | {
    type: "click";
    selector: string;
    all?: boolean;
} | {
    type: "screenshot";
    fullPage?: boolean;
    quality?: number;
} | {
    type: "write";
    text: string;
} | {
    type: "press";
    key: string;
} | {
    type: "scroll";
    direction?: "up" | "down";
    selector?: string;
} | {
    type: "scrape";
} | {
    type: "executeJavascript";
    script: string;
};
interface ScrapeParams<LLMSchema extends zt.ZodSchema = any, ActionsSchema extends (Action[] | undefined) = undefined> extends CrawlScrapeOptions {
    extract?: {
        prompt?: string;
        schema?: LLMSchema;
        systemPrompt?: string;
    };
    jsonOptions?: {
        prompt?: string;
        schema?: LLMSchema;
        systemPrompt?: string;
    };
    changeTrackingOptions?: {
        prompt?: string;
        schema?: any;
        modes?: ("json" | "git-diff")[];
        tag?: string | null;
    };
    actions?: ActionsSchema;
    agent?: AgentOptions;
    zeroDataRetention?: boolean;
}
interface ActionsResult {
    screenshots: string[];
    scrapes: ({
        url: string;
        html: string;
    })[];
    javascriptReturns: {
        type: string;
        value: unknown;
    }[];
}
/**
 * Response interface for scraping operations.
 * Defines the structure of the response received after a scraping operation.
 */
interface ScrapeResponse<LLMResult = any, ActionsSchema extends (ActionsResult | never) = never> extends FirecrawlDocument<LLMResult, ActionsSchema> {
    success: true;
    warning?: string;
    error?: string;
}
/**
 * Parameters for crawling operations.
 * Includes options for both scraping and mapping during a crawl.
 */
interface CrawlParams {
    includePaths?: string[];
    excludePaths?: string[];
    maxDepth?: number;
    maxDiscoveryDepth?: number;
    limit?: number;
    allowBackwardLinks?: boolean;
    crawlEntireDomain?: boolean;
    allowExternalLinks?: boolean;
    ignoreSitemap?: boolean;
    scrapeOptions?: CrawlScrapeOptions;
    webhook?: string | {
        url: string;
        headers?: Record<string, string>;
        metadata?: Record<string, string>;
        events?: ["completed", "failed", "page", "started"][number][];
    };
    deduplicateSimilarURLs?: boolean;
    ignoreQueryParameters?: boolean;
    regexOnFullURL?: boolean;
    /**
     * Delay in seconds between scrapes. This helps respect website rate limits.
     * If not provided, the crawler may use the robots.txt crawl delay if available.
     */
    delay?: number;
    allowSubdomains?: boolean;
    maxConcurrency?: number;
    zeroDataRetention?: boolean;
}
/**
 * Response interface for crawling operations.
 * Defines the structure of the response received after initiating a crawl.
 */
interface CrawlResponse {
    id?: string;
    url?: string;
    success: true;
    error?: string;
}
/**
 * Response interface for batch scrape operations.
 * Defines the structure of the response received after initiating a crawl.
 */
interface BatchScrapeResponse {
    id?: string;
    url?: string;
    success: true;
    error?: string;
    invalidURLs?: string[];
}
/**
 * Response interface for job status checks.
 * Provides detailed status of a crawl job including progress and results.
 */
interface CrawlStatusResponse {
    success: true;
    status: "scraping" | "completed" | "failed" | "cancelled";
    completed: number;
    total: number;
    creditsUsed: number;
    expiresAt: Date;
    next?: string;
    data: FirecrawlDocument<undefined>[];
}
/**
 * Response interface for batch scrape job status checks.
 * Provides detailed status of a batch scrape job including progress and results.
 */
interface BatchScrapeStatusResponse {
    success: true;
    status: "scraping" | "completed" | "failed" | "cancelled";
    completed: number;
    total: number;
    creditsUsed: number;
    expiresAt: Date;
    next?: string;
    data: FirecrawlDocument<undefined>[];
}
/**
 * Parameters for mapping operations.
 * Defines options for mapping URLs during a crawl.
 */
interface MapParams {
    search?: string;
    ignoreSitemap?: boolean;
    includeSubdomains?: boolean;
    sitemapOnly?: boolean;
    limit?: number;
    timeout?: number;
    useIndex?: boolean;
    location?: LocationConfig;
}
/**
 * Response interface for mapping operations.
 * Defines the structure of the response received after a mapping operation.
 */
interface MapResponse {
    success: true;
    links?: string[];
    error?: string;
}
/**
 * Parameters for extracting information from URLs.
 * Defines options for extracting information from URLs.
 */
interface AgentOptions {
    model?: string;
    prompt?: string;
    sessionId?: string;
}
/**
 * Parameters for extracting information from URLs.
 * Defines options for extracting information from URLs.
 */
interface AgentOptionsExtract {
    model?: string;
    sessionId?: string;
}
interface ExtractParams<LLMSchema extends zt.ZodSchema = any> {
    prompt?: string;
    schema?: LLMSchema | object;
    systemPrompt?: string;
    allowExternalLinks?: boolean;
    enableWebSearch?: boolean;
    includeSubdomains?: boolean;
    origin?: string;
    showSources?: boolean;
    scrapeOptions?: CrawlScrapeOptions;
    agent?: AgentOptionsExtract;
}
/**
 * Response interface for extracting information from URLs.
 * Defines the structure of the response received after extracting information from URLs.
 */
interface ExtractResponse<LLMSchema extends zt.ZodSchema = any> {
    success: boolean;
    data: LLMSchema;
    error?: string;
    warning?: string;
    sources?: string[];
    creditsUsed?: number;
}
/**
 * Error response interface.
 * Defines the structure of the response received when an error occurs.
 */
interface ErrorResponse {
    success: false;
    error: string;
}
/**
 * Parameters for search operations.
 * Defines options for searching and scraping search results.
 */
interface SearchParams {
    limit?: number;
    tbs?: string;
    filter?: string;
    lang?: string;
    country?: string;
    location?: string;
    origin?: string;
    timeout?: number;
    scrapeOptions?: ScrapeParams;
}
/**
 * Response interface for search operations.
 * Defines the structure of the response received after a search operation.
 */
interface SearchResponse {
    success: boolean;
    data: FirecrawlDocument<undefined>[];
    warning?: string;
    error?: string;
}
/**
 * Response interface for crawl/batch scrape error monitoring.
 */
interface CrawlErrorsResponse {
    /**
     * Scrapes that errored out + error details
     */
    errors: {
        id: string;
        timestamp?: string;
        url: string;
        code?: string;
        error: string;
    }[];
    /**
     * URLs blocked by robots.txt
     */
    robotsBlocked: string[];
}
/**
 * Parameters for deep research operations.
 * Defines options for conducting deep research on a query.
 */
interface DeepResearchParams<LLMSchema extends zt.ZodSchema = any> {
    /**
     * Maximum depth of research iterations (1-10)
     * @default 7
     */
    maxDepth?: number;
    /**
     * Time limit in seconds (30-300)
     * @default 270
     */
    timeLimit?: number;
    /**
     * Maximum number of URLs to analyze (1-1000)
     * @default 20
     */
    maxUrls?: number;
    /**
     * The prompt to use for the final analysis
     */
    analysisPrompt?: string;
    /**
     * The system prompt to use for the research agent
     */
    systemPrompt?: string;
    /**
     * The formats to use for the final analysis
     */
    formats?: ("markdown" | "json")[];
    /**
     * The JSON options to use for the final analysis
     */
    jsonOptions?: {
        prompt?: string;
        schema?: LLMSchema;
        systemPrompt?: string;
    };
}
/**
 * Response interface for deep research operations.
 */
interface DeepResearchResponse {
    success: boolean;
    id: string;
}
/**
 * Status response interface for deep research operations.
 */
interface DeepResearchStatusResponse {
    success: boolean;
    data: {
        finalAnalysis: string;
        activities: Array<{
            type: string;
            status: string;
            message: string;
            timestamp: string;
            depth: number;
        }>;
        sources: Array<{
            url: string;
            title: string;
            description: string;
        }>;
    };
    status: "processing" | "completed" | "failed";
    error?: string;
    expiresAt: string;
    currentDepth: number;
    maxDepth: number;
    activities: Array<{
        type: string;
        status: string;
        message: string;
        timestamp: string;
        depth: number;
    }>;
    sources: Array<{
        url: string;
        title: string;
        description: string;
    }>;
    summaries: string[];
}
/**
 * Parameters for LLMs.txt generation operations.
 */
interface GenerateLLMsTextParams {
    /**
     * Maximum number of URLs to process (1-100)
     * @default 10
     */
    maxUrls?: number;
    /**
     * Whether to show the full LLMs-full.txt in the response
     * @default false
     */
    showFullText?: boolean;
    /**
     * Whether to use cached content if available
     * @default true
     */
    cache?: boolean;
    /**
     * Experimental flag for streaming
     */
    __experimental_stream?: boolean;
}
/**
 * Response interface for LLMs.txt generation operations.
 */
interface GenerateLLMsTextResponse {
    success: boolean;
    id: string;
}
/**
 * Status response interface for LLMs.txt generation operations.
 */
interface GenerateLLMsTextStatusResponse {
    success: boolean;
    data: {
        llmstxt: string;
        llmsfulltxt?: string;
    };
    status: "processing" | "completed" | "failed";
    error?: string;
    expiresAt: string;
}
/**
 * Response interface for queue status operations.
 */
interface QueueStatusResponse {
    success: boolean;
    jobsInQueue: number;
    activeJobsInQueue: number;
    waitingJobsInQueue: number;
    maxConcurrency: number;
    /**
     * ISO timestamp of the most recent successful scrape in the past 24 hours. Will be null if no successful scrape has occurred in the past 24 hours.
     */
    mostRecentSuccess: string | null;
}
/** Credit usage for v1 API (snake_case fields as returned by API). */
interface CreditUsageResponseV1 {
    success: boolean;
    data: {
        remaining_credits: number;
        plan_credits: number;
        billing_period_start: string | null;
        billing_period_end: string | null;
    };
}
/** Token usage for v1 API (snake_case fields as returned by API). */
interface TokenUsageResponseV1 {
    success: boolean;
    data: {
        remaining_tokens: number;
        plan_tokens: number;
        billing_period_start: string | null;
        billing_period_end: string | null;
    };
}
interface CreditUsageHistoricalResponseV1 {
    success: boolean;
    periods: {
        startDate: string | null;
        endDate: string | null;
        apiKey?: string;
        creditsUsed: number;
    }[];
}
interface TokenUsageHistoricalResponseV1 {
    success: boolean;
    periods: {
        startDate: string | null;
        endDate: string | null;
        apiKey?: string;
        tokensUsed: number;
    }[];
}
/**
 * Main class for interacting with the Firecrawl API.
 * Provides methods for scraping, searching, crawling, and mapping web content.
 */
declare class FirecrawlApp {
    apiKey: string;
    apiUrl: string;
    version: string;
    private isCloudService;
    private getVersion;
    private init;
    /**
     * Initializes a new instance of the FirecrawlApp class.
     * @param config - Configuration options for the FirecrawlApp instance.
     */
    constructor({ apiKey, apiUrl }: FirecrawlAppConfig);
    /**
     * Scrapes a URL using the Firecrawl API.
     * @param url - The URL to scrape.
     * @param params - Additional parameters for the scrape request.
     * @returns The response from the scrape operation.
     */
    scrapeUrl<T extends zt.ZodSchema, ActionsSchema extends (Action[] | undefined) = undefined>(url: string, params?: ScrapeParams<T, ActionsSchema>): Promise<ScrapeResponse<zt.infer<T>, ActionsSchema extends Action[] ? ActionsResult : never> | ErrorResponse>;
    /**
     * Searches using the Firecrawl API and optionally scrapes the results.
     * @param query - The search query string.
     * @param params - Optional parameters for the search request.
     * @returns The response from the search operation.
     */
    search(query: string, params?: SearchParams | Record<string, any>): Promise<SearchResponse>;
    /**
     * Initiates a crawl job for a URL using the Firecrawl API.
     * @param url - The URL to crawl.
     * @param params - Additional parameters for the crawl request.
     * @param pollInterval - Time in seconds for job status checks.
     * @param idempotencyKey - Optional idempotency key for the request.
     * @returns The response from the crawl operation.
     */
    crawlUrl(url: string, params?: CrawlParams, pollInterval?: number, idempotencyKey?: string): Promise<CrawlStatusResponse | ErrorResponse>;
    asyncCrawlUrl(url: string, params?: CrawlParams, idempotencyKey?: string): Promise<CrawlResponse | ErrorResponse>;
    /**
     * Checks the status of a crawl job using the Firecrawl API.
     * @param id - The ID of the crawl operation.
     * @param getAllData - Paginate through all the pages of documents, returning the full list of all documents. (default: `false`)
     * @param nextURL - The `next` URL from the previous crawl status. Only required if you're not manually increasing `skip`. Only used when `getAllData = false`.
     * @param skip - How many entries to skip to paginate. Only required if you're not providing `nextURL`. Only used when `getAllData = false`.
     * @param limit - How many entries to return. Only used when `getAllData = false`.
     * @returns The response containing the job status.
     */
    checkCrawlStatus(id?: string, getAllData?: boolean, nextURL?: string, skip?: number, limit?: number): Promise<CrawlStatusResponse | ErrorResponse>;
    /**
     * Returns information about crawl errors.
     * @param id - The ID of the crawl operation.
     * @returns Information about crawl errors.
     */
    checkCrawlErrors(id: string): Promise<CrawlErrorsResponse | ErrorResponse>;
    /**
     * Cancels a crawl job using the Firecrawl API.
     * @param id - The ID of the crawl operation.
     * @returns The response from the cancel crawl operation.
     */
    cancelCrawl(id: string): Promise<ErrorResponse>;
    /**
     * Initiates a crawl job and returns a CrawlWatcher to monitor the job via WebSocket.
     * @param url - The URL to crawl.
     * @param params - Additional parameters for the crawl request.
     * @param idempotencyKey - Optional idempotency key for the request.
     * @returns A CrawlWatcher instance to monitor the crawl job.
     */
    crawlUrlAndWatch(url: string, params?: CrawlParams, idempotencyKey?: string): Promise<CrawlWatcher>;
    /**
     * Maps a URL using the Firecrawl API.
     * @param url - The URL to map.
     * @param params - Additional parameters for the map request.
     * @returns The response from the map operation.
     */
    mapUrl(url: string, params?: MapParams): Promise<MapResponse | ErrorResponse>;
    /**
     * Initiates a batch scrape job for multiple URLs using the Firecrawl API.
     * @param url - The URLs to scrape.
     * @param params - Additional parameters for the scrape request.
     * @param pollInterval - Time in seconds for job status checks.
     * @param idempotencyKey - Optional idempotency key for the request.
     * @param webhook - Optional webhook for the batch scrape.
     * @param ignoreInvalidURLs - Optional flag to ignore invalid URLs.
     * @returns The response from the crawl operation.
     */
    batchScrapeUrls(urls: string[], params?: ScrapeParams, pollInterval?: number, idempotencyKey?: string, webhook?: CrawlParams["webhook"], ignoreInvalidURLs?: boolean, maxConcurrency?: number): Promise<BatchScrapeStatusResponse | ErrorResponse>;
    asyncBatchScrapeUrls(urls: string[], params?: ScrapeParams, idempotencyKey?: string, webhook?: CrawlParams["webhook"], ignoreInvalidURLs?: boolean): Promise<BatchScrapeResponse | ErrorResponse>;
    /**
     * Initiates a batch scrape job and returns a CrawlWatcher to monitor the job via WebSocket.
     * @param urls - The URL to scrape.
     * @param params - Additional parameters for the scrape request.
     * @param idempotencyKey - Optional idempotency key for the request.
     * @returns A CrawlWatcher instance to monitor the crawl job.
     */
    batchScrapeUrlsAndWatch(urls: string[], params?: ScrapeParams, idempotencyKey?: string, webhook?: CrawlParams["webhook"], ignoreInvalidURLs?: boolean): Promise<CrawlWatcher>;
    /**
     * Checks the status of a batch scrape job using the Firecrawl API.
     * @param id - The ID of the batch scrape operation.
     * @param getAllData - Paginate through all the pages of documents, returning the full list of all documents. (default: `false`)
     * @param nextURL - The `next` URL from the previous batch scrape status. Only required if you're not manually increasing `skip`. Only used when `getAllData = false`.
     * @param skip - How many entries to skip to paginate. Only used when `getAllData = false`.
     * @param limit - How many entries to return. Only used when `getAllData = false`.
     * @returns The response containing the job status.
     */
    checkBatchScrapeStatus(id?: string, getAllData?: boolean, nextURL?: string, skip?: number, limit?: number): Promise<BatchScrapeStatusResponse | ErrorResponse>;
    /**
     * Returns information about batch scrape errors.
     * @param id - The ID of the batch scrape operation.
     * @returns Information about batch scrape errors.
     */
    checkBatchScrapeErrors(id: string): Promise<CrawlErrorsResponse | ErrorResponse>;
    /**
     * Extracts information from URLs using the Firecrawl API.
     * Currently in Beta. Expect breaking changes on future minor versions.
     * @param urls - The URLs to extract information from. Optional if using other methods for data extraction.
     * @param params - Additional parameters for the extract request.
     * @returns The response from the extract operation.
     */
    extract<T extends zt.ZodSchema = any>(urls?: string[], params?: ExtractParams<T>): Promise<ExtractResponse<zt.infer<T>> | ErrorResponse>;
    /**
     * Initiates an asynchronous extract job for a URL using the Firecrawl API.
     * @param url - The URL to extract data from.
     * @param params - Additional parameters for the extract request.
     * @param idempotencyKey - Optional idempotency key for the request.
     * @returns The response from the extract operation.
     */
    asyncExtract(urls: string[], params?: ExtractParams, idempotencyKey?: string): Promise<ExtractResponse | ErrorResponse>;
    /**
     * Retrieves the status of an extract job.
     * @param jobId - The ID of the extract job.
     * @returns The status of the extract job.
     */
    getExtractStatus(jobId: string): Promise<any>;
    /**
     * Prepares the headers for an API request.
     * @param idempotencyKey - Optional key to ensure idempotency.
     * @returns The prepared headers.
     */
    prepareHeaders(idempotencyKey?: string): AxiosRequestHeaders;
    /**
     * Sends a POST request to the specified URL.
     * @param url - The URL to send the request to.
     * @param data - The data to send in the request.
     * @param headers - The headers for the request.
     * @returns The response from the POST request.
     */
    postRequest(url: string, data: any, headers: AxiosRequestHeaders): Promise<AxiosResponse>;
    /**
     * Sends a GET request to the specified URL.
     * @param url - The URL to send the request to.
     * @param headers - The headers for the request.
     * @returns The response from the GET request.
     */
    getRequest(url: string, headers: AxiosRequestHeaders): Promise<AxiosResponse>;
    /**
     * Sends a DELETE request to the specified URL.
     * @param url - The URL to send the request to.
     * @param headers - The headers for the request.
     * @returns The response from the DELETE request.
     */
    deleteRequest(url: string, headers: AxiosRequestHeaders): Promise<AxiosResponse>;
    /**
     * Monitors the status of a crawl job until completion or failure.
     * @param id - The ID of the crawl operation.
     * @param headers - The headers for the request.
     * @param checkInterval - Interval in seconds for job status checks.
     * @param checkUrl - Optional URL to check the status (used for v1 API)
     * @returns The final job status or data.
     */
    monitorJobStatus(id: string, headers: AxiosRequestHeaders, checkInterval: number): Promise<CrawlStatusResponse | ErrorResponse>;
    /**
     * Determines if an error is retryable (transient network error)
     * @param error - The error to check
     * @returns True if the error should be retried
     */
    private isRetryableError;
    /**
     * Handles errors from API responses.
     * @param {AxiosResponse} response - The response from the API.
     * @param {string} action - The action being performed when the error occurred.
     */
    handleError(response: AxiosResponse, action: string): never;
    /**
     * Initiate