@mendable/firecrawl 4.13.0 → 4.13.2

package/dist/{chunk-22A4MB4F.js → chunk-YMCI3PLP.js}

@@ -8,7 +8,7 @@ var require_package = __commonJS({
   "package.json"(exports, module) {
     module.exports = {
       name: "@mendable/firecrawl-js",
-      version: "4.13.0",
+      version: "4.13.2",
       description: "JavaScript SDK for Firecrawl API",
       main: "dist/index.js",
       types: "dist/index.d.ts",
@@ -71,7 +71,8 @@ var require_package = __commonJS({
       },
       pnpm: {
         overrides: {
-          "@isaacs/brace-expansion@<=5.0.0": ">=5.0.1"
+          "@isaacs/brace-expansion@<=5.0.0": ">=5.0.1",
+          "minimatch@<10.2.1": ">=10.2.1"
         }
       }
     };

package/dist/index.cjs

@@ -35,7 +35,7 @@ var require_package = __commonJS({
   "package.json"(exports2, module2) {
     module2.exports = {
       name: "@mendable/firecrawl-js",
-      version: "4.13.0",
+      version: "4.13.2",
       description: "JavaScript SDK for Firecrawl API",
       main: "dist/index.js",
       types: "dist/index.d.ts",
@@ -98,7 +98,8 @@ var require_package = __commonJS({
       },
       pnpm: {
         overrides: {
-          "@isaacs/brace-expansion@<=5.0.0": ">=5.0.1"
+          "@isaacs/brace-expansion@<=5.0.0": ">=5.0.1",
+          "minimatch@<10.2.1": ">=10.2.1"
         }
       }
     };
@@ -539,12 +540,14 @@ function prepareCrawlPayload(request) {
   if (request.maxDiscoveryDepth != null) data.maxDiscoveryDepth = request.maxDiscoveryDepth;
   if (request.sitemap != null) data.sitemap = request.sitemap;
   if (request.ignoreQueryParameters != null) data.ignoreQueryParameters = request.ignoreQueryParameters;
+  if (request.deduplicateSimilarURLs != null) data.deduplicateSimilarURLs = request.deduplicateSimilarURLs;
   if (request.limit != null) data.limit = request.limit;
   if (request.crawlEntireDomain != null) data.crawlEntireDomain = request.crawlEntireDomain;
   if (request.allowExternalLinks != null) data.allowExternalLinks = request.allowExternalLinks;
   if (request.allowSubdomains != null) data.allowSubdomains = request.allowSubdomains;
   if (request.delay != null) data.delay = request.delay;
   if (request.maxConcurrency != null) data.maxConcurrency = request.maxConcurrency;
+  if (request.regexOnFullURL != null) data.regexOnFullURL = request.regexOnFullURL;
   if (request.webhook != null) data.webhook = request.webhook;
   if (request.integration != null && request.integration.trim()) data.integration = request.integration.trim();
   if (request.scrapeOptions) {
@@ -1428,6 +1431,8 @@ var FirecrawlClient = class {
    * Start an extract job (async).
    * @param args Extraction request (urls, schema or prompt, flags).
    * @returns Job id or processing state.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async startExtract(args) {
     return startExtract(this.http, args);
@@ -1435,6 +1440,8 @@ var FirecrawlClient = class {
   /**
    * Get extract job status/data.
    * @param jobId Extract job id.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async getExtractStatus(jobId) {
     return getExtractStatus(this.http, jobId);
@@ -1443,6 +1450,8 @@ var FirecrawlClient = class {
    * Convenience waiter: start an extract and poll until it finishes.
    * @param args Extraction request plus waiter controls (pollInterval, timeout seconds).
    * @returns Final extract response.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async extract(args) {
     return extract(this.http, args);
@@ -2122,10 +2131,11 @@ var FirecrawlApp = class {
   }
   /**
    * 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.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async extract(urls, params) {
     const headers = this.prepareHeaders();
@@ -2177,6 +2187,8 @@ var FirecrawlApp = class {
    * @param params - Additional parameters for the extract request.
    * @param idempotencyKey - Optional idempotency key for the request.
    * @returns The response from the extract operation.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async asyncExtract(urls, params, idempotencyKey) {
     const headers = this.prepareHeaders(idempotencyKey);
@@ -2202,6 +2214,8 @@ var FirecrawlApp = class {
    * Retrieves the status of an extract job.
    * @param jobId - The ID of the extract job.
    * @returns The status of the extract job.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async getExtractStatus(jobId) {
     try {

package/dist/index.d.cts

@@ -382,6 +382,7 @@ interface CrawlOptions {
     maxDiscoveryDepth?: number | null;
     sitemap?: 'skip' | 'include' | 'only';
     ignoreQueryParameters?: boolean;
+    deduplicateSimilarURLs?: boolean;
     limit?: number | null;
     crawlEntireDomain?: boolean;
     allowExternalLinks?: boolean;
@@ -390,6 +391,7 @@ interface CrawlOptions {
     maxConcurrency?: number | null;
     webhook?: string | WebhookConfig | null;
     scrapeOptions?: ScrapeOptions | null;
+    regexOnFullURL?: boolean;
     zeroDataRetention?: boolean;
     integration?: string;
 }
@@ -629,6 +631,10 @@ declare function prepareExtractPayload(args: {
     integration?: string;
     agent?: AgentOptions$1;
 }): Record<string, unknown>;
+/**
+ * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+ * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
+ */
 declare function startExtract(http: HttpClient, args: Parameters<typeof prepareExtractPayload>[0]): Promise<ExtractResponse$1>;
 
 declare function prepareAgentPayload(args: {
@@ -820,17 +826,23 @@ declare class FirecrawlClient {
      * Start an extract job (async).
      * @param args Extraction request (urls, schema or prompt, flags).
      * @returns Job id or processing state.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     startExtract(args: Parameters<typeof startExtract>[1]): Promise<ExtractResponse$1>;
     /**
      * Get extract job status/data.
      * @param jobId Extract job id.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     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.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     extract(args: Parameters<typeof startExtract>[1] & {
         pollInterval?: number;
@@ -1599,10 +1611,11 @@ declare class FirecrawlApp {
     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.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     extract<T extends zt.ZodSchema = any>(urls?: string[], params?: ExtractParams<T>): Promise<ExtractResponse<zt.infer<T>> | ErrorResponse>;
     /**
@@ -1611,12 +1624,16 @@ declare class FirecrawlApp {
      * @param params - Additional parameters for the extract request.
      * @param idempotencyKey - Optional idempotency key for the request.
      * @returns The response from the extract operation.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     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.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     getExtractStatus(jobId: string): Promise<any>;
     /**

package/dist/index.d.ts

@@ -382,6 +382,7 @@ interface CrawlOptions {
     maxDiscoveryDepth?: number | null;
     sitemap?: 'skip' | 'include' | 'only';
     ignoreQueryParameters?: boolean;
+    deduplicateSimilarURLs?: boolean;
     limit?: number | null;
     crawlEntireDomain?: boolean;
     allowExternalLinks?: boolean;
@@ -390,6 +391,7 @@ interface CrawlOptions {
     maxConcurrency?: number | null;
     webhook?: string | WebhookConfig | null;
     scrapeOptions?: ScrapeOptions | null;
+    regexOnFullURL?: boolean;
     zeroDataRetention?: boolean;
     integration?: string;
 }
@@ -629,6 +631,10 @@ declare function prepareExtractPayload(args: {
     integration?: string;
     agent?: AgentOptions$1;
 }): Record<string, unknown>;
+/**
+ * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+ * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
+ */
 declare function startExtract(http: HttpClient, args: Parameters<typeof prepareExtractPayload>[0]): Promise<ExtractResponse$1>;
 
 declare function prepareAgentPayload(args: {
@@ -820,17 +826,23 @@ declare class FirecrawlClient {
      * Start an extract job (async).
      * @param args Extraction request (urls, schema or prompt, flags).
      * @returns Job id or processing state.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     startExtract(args: Parameters<typeof startExtract>[1]): Promise<ExtractResponse$1>;
     /**
      * Get extract job status/data.
      * @param jobId Extract job id.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     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.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     extract(args: Parameters<typeof startExtract>[1] & {
         pollInterval?: number;
@@ -1599,10 +1611,11 @@ declare class FirecrawlApp {
     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.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     extract<T extends zt.ZodSchema = any>(urls?: string[], params?: ExtractParams<T>): Promise<ExtractResponse<zt.infer<T>> | ErrorResponse>;
     /**
@@ -1611,12 +1624,16 @@ declare class FirecrawlApp {
      * @param params - Additional parameters for the extract request.
      * @param idempotencyKey - Optional idempotency key for the request.
      * @returns The response from the extract operation.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     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.
+     * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+     * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
      */
     getExtractStatus(jobId: string): Promise<any>;
     /**

package/dist/index.js

@@ -1,6 +1,6 @@
 import {
   require_package
-} from "./chunk-22A4MB4F.js";
+} from "./chunk-YMCI3PLP.js";
 
 // src/v2/utils/httpClient.ts
 import axios from "axios";
@@ -423,12 +423,14 @@ function prepareCrawlPayload(request) {
   if (request.maxDiscoveryDepth != null) data.maxDiscoveryDepth = request.maxDiscoveryDepth;
   if (request.sitemap != null) data.sitemap = request.sitemap;
   if (request.ignoreQueryParameters != null) data.ignoreQueryParameters = request.ignoreQueryParameters;
+  if (request.deduplicateSimilarURLs != null) data.deduplicateSimilarURLs = request.deduplicateSimilarURLs;
   if (request.limit != null) data.limit = request.limit;
   if (request.crawlEntireDomain != null) data.crawlEntireDomain = request.crawlEntireDomain;
   if (request.allowExternalLinks != null) data.allowExternalLinks = request.allowExternalLinks;
   if (request.allowSubdomains != null) data.allowSubdomains = request.allowSubdomains;
   if (request.delay != null) data.delay = request.delay;
   if (request.maxConcurrency != null) data.maxConcurrency = request.maxConcurrency;
+  if (request.regexOnFullURL != null) data.regexOnFullURL = request.regexOnFullURL;
   if (request.webhook != null) data.webhook = request.webhook;
   if (request.integration != null && request.integration.trim()) data.integration = request.integration.trim();
   if (request.scrapeOptions) {
@@ -1312,6 +1314,8 @@ var FirecrawlClient = class {
    * Start an extract job (async).
    * @param args Extraction request (urls, schema or prompt, flags).
    * @returns Job id or processing state.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async startExtract(args) {
     return startExtract(this.http, args);
@@ -1319,6 +1323,8 @@ var FirecrawlClient = class {
   /**
    * Get extract job status/data.
    * @param jobId Extract job id.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async getExtractStatus(jobId) {
     return getExtractStatus(this.http, jobId);
@@ -1327,6 +1333,8 @@ var FirecrawlClient = class {
    * Convenience waiter: start an extract and poll until it finishes.
    * @param args Extraction request plus waiter controls (pollInterval, timeout seconds).
    * @returns Final extract response.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async extract(args) {
     return extract(this.http, args);
@@ -1465,7 +1473,7 @@ var FirecrawlApp = class {
       if (typeof process !== "undefined" && process.env && process.env.npm_package_version) {
         return process.env.npm_package_version;
       }
-      const packageJson = await import("./package-5SIMNZMX.js");
+      const packageJson = await import("./package-HWPUIS3T.js");
       return packageJson.default.version;
     } catch (error) {
       const isTest = typeof process !== "undefined" && (process.env.JEST_WORKER_ID != null || false);
@@ -2006,10 +2014,11 @@ var FirecrawlApp = class {
   }
   /**
    * 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.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async extract(urls, params) {
     const headers = this.prepareHeaders();
@@ -2061,6 +2070,8 @@ var FirecrawlApp = class {
    * @param params - Additional parameters for the extract request.
    * @param idempotencyKey - Optional idempotency key for the request.
    * @returns The response from the extract operation.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async asyncExtract(urls, params, idempotencyKey) {
     const headers = this.prepareHeaders(idempotencyKey);
@@ -2086,6 +2097,8 @@ var FirecrawlApp = class {
    * Retrieves the status of an extract job.
    * @param jobId - The ID of the extract job.
    * @returns The status of the extract job.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async getExtractStatus(jobId) {
     try {

package/dist/{package-5SIMNZMX.js → package-HWPUIS3T.js}

@@ -1,4 +1,4 @@
 import {
   require_package
-} from "./chunk-22A4MB4F.js";
+} from "./chunk-YMCI3PLP.js";
 export default require_package();

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mendable/firecrawl",
-  "version": "4.13.0",
+  "version": "4.13.2",
   "description": "JavaScript SDK for Firecrawl API",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

package/src/v1/index.ts

@@ -1278,10 +1278,11 @@ export default class FirecrawlApp {
 
   /**
    * 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.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async extract<T extends zt.ZodSchema = any>(urls?: string[], params?: ExtractParams<T>): Promise<ExtractResponse<zt.infer<T>> | ErrorResponse> {
     const headers = this.prepareHeaders();
@@ -1337,6 +1338,8 @@ export default class FirecrawlApp {
    * @param params - Additional parameters for the extract request.
    * @param idempotencyKey - Optional idempotency key for the request.
    * @returns The response from the extract operation.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async asyncExtract(
     urls: string[],
@@ -1369,6 +1372,8 @@ export default class FirecrawlApp {
    * Retrieves the status of an extract job.
    * @param jobId - The ID of the extract job.
    * @returns The status of the extract job.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async getExtractStatus(jobId: string): Promise<any> {
     try {

package/src/v2/client.ts

@@ -255,6 +255,8 @@ export class FirecrawlClient {
    * Start an extract job (async).
    * @param args Extraction request (urls, schema or prompt, flags).
    * @returns Job id or processing state.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async startExtract(args: Parameters<typeof startExtract>[1]): Promise<ExtractResponse> {
     return startExtract(this.http, args);
@@ -262,6 +264,8 @@ export class FirecrawlClient {
   /**
    * Get extract job status/data.
    * @param jobId Extract job id.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async getExtractStatus(jobId: string): Promise<ExtractResponse> {
     return getExtractStatus(this.http, jobId);
@@ -270,6 +274,8 @@ export class FirecrawlClient {
    * Convenience waiter: start an extract and poll until it finishes.
    * @param args Extraction request plus waiter controls (pollInterval, timeout seconds).
    * @returns Final extract response.
+   * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+   * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
    */
   async extract(args: Parameters<typeof startExtract>[1] & { pollInterval?: number; timeout?: number }): Promise<ExtractResponse> {
     return extractWaiter(this.http, args);

package/src/v2/methods/crawl.ts

@@ -28,12 +28,14 @@ function prepareCrawlPayload(request: CrawlRequest): Record<string, unknown> {
   if (request.maxDiscoveryDepth != null) data.maxDiscoveryDepth = request.maxDiscoveryDepth;
   if (request.sitemap != null) data.sitemap = request.sitemap;
   if (request.ignoreQueryParameters != null) data.ignoreQueryParameters = request.ignoreQueryParameters;
+  if (request.deduplicateSimilarURLs != null) data.deduplicateSimilarURLs = request.deduplicateSimilarURLs;
   if (request.limit != null) data.limit = request.limit;
   if (request.crawlEntireDomain != null) data.crawlEntireDomain = request.crawlEntireDomain;
   if (request.allowExternalLinks != null) data.allowExternalLinks = request.allowExternalLinks;
   if (request.allowSubdomains != null) data.allowSubdomains = request.allowSubdomains;
   if (request.delay != null) data.delay = request.delay;
   if (request.maxConcurrency != null) data.maxConcurrency = request.maxConcurrency;
+  if (request.regexOnFullURL != null) data.regexOnFullURL = request.regexOnFullURL;
   if (request.webhook != null) data.webhook = request.webhook;
   if (request.integration != null && request.integration.trim()) data.integration = request.integration.trim();
   if (request.scrapeOptions) {

package/src/v2/methods/extract.ts

@@ -38,6 +38,10 @@ function prepareExtractPayload(args: {
   return body;
 }
 
+/**
+ * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+ * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
+ */
 export async function startExtract(http: HttpClient, args: Parameters<typeof prepareExtractPayload>[0]): Promise<ExtractResponse> {
   const payload = prepareExtractPayload(args);
   try {
@@ -50,6 +54,10 @@ export async function startExtract(http: HttpClient, args: Parameters<typeof pre
   }
 }
 
+/**
+ * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+ * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
+ */
 export async function getExtractStatus(http: HttpClient, jobId: string): Promise<ExtractResponse> {
   try {
     const res = await http.get<ExtractResponse>(`/v2/extract/${jobId}`);
@@ -61,6 +69,10 @@ export async function getExtractStatus(http: HttpClient, jobId: string): Promise
   }
 }
 
+/**
+ * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+ * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
+ */
 export async function waitExtract(
   http: HttpClient,
   jobId: string,
@@ -76,6 +88,10 @@ export async function waitExtract(
   }
 }
 
+/**
+ * @deprecated The extract endpoint is in maintenance mode and its use is discouraged.
+ * Review https://docs.firecrawl.dev/developer-guides/usage-guides/choosing-the-data-extractor to find a replacement.
+ */
 export async function extract(
   http: HttpClient,
   args: Parameters<typeof prepareExtractPayload>[0] & { pollInterval?: number; timeout?: number }

package/src/v2/types.ts

@@ -462,6 +462,7 @@ export interface CrawlOptions {
   maxDiscoveryDepth?: number | null;
   sitemap?: 'skip' | 'include' | 'only';
   ignoreQueryParameters?: boolean;
+  deduplicateSimilarURLs?: boolean;
   limit?: number | null;
   crawlEntireDomain?: boolean;
   allowExternalLinks?: boolean;
@@ -470,6 +471,7 @@ export interface CrawlOptions {
   maxConcurrency?: number | null;
   webhook?: string | WebhookConfig | null;
   scrapeOptions?: ScrapeOptions | null;
+  regexOnFullURL?: boolean;
   zeroDataRetention?: boolean;
   integration?: string;
 }