@mendable/firecrawl 1.27.0 → 1.29.1

package/dist/index.cjs

@@ -35,7 +35,7 @@ var require_package = __commonJS({
   "package.json"(exports2, module2) {
     module2.exports = {
       name: "@mendable/firecrawl-js",
-      version: "1.27.0",
+      version: "1.29.1",
       description: "JavaScript SDK for Firecrawl API",
       main: "dist/index.js",
       types: "dist/index.d.ts",

package/dist/index.d.cts

@@ -120,6 +120,7 @@ interface CrawlScrapeOptions {
     proxy?: "basic" | "stealth" | "auto";
     storeInCache?: boolean;
     maxAge?: number;
+    parsePDF?: boolean;
 }
 type Action = {
     type: "wait";
@@ -132,6 +133,7 @@ type Action = {
 } | {
     type: "screenshot";
     fullPage?: boolean;
+    quality?: number;
 } | {
     type: "write";
     text: string;
@@ -167,6 +169,7 @@ interface ScrapeParams<LLMSchema extends zt.ZodSchema = any, ActionsSchema exten
     };
     actions?: ActionsSchema;
     agent?: AgentOptions;
+    zeroDataRetention?: boolean;
 }
 interface ActionsResult {
     screenshots: string[];
@@ -217,7 +220,9 @@ interface CrawlParams {
      * 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.

package/dist/index.d.ts

@@ -120,6 +120,7 @@ interface CrawlScrapeOptions {
     proxy?: "basic" | "stealth" | "auto";
     storeInCache?: boolean;
     maxAge?: number;
+    parsePDF?: boolean;
 }
 type Action = {
     type: "wait";
@@ -132,6 +133,7 @@ type Action = {
 } | {
     type: "screenshot";
     fullPage?: boolean;
+    quality?: number;
 } | {
     type: "write";
     text: string;
@@ -167,6 +169,7 @@ interface ScrapeParams<LLMSchema extends zt.ZodSchema = any, ActionsSchema exten
     };
     actions?: ActionsSchema;
     agent?: AgentOptions;
+    zeroDataRetention?: boolean;
 }
 interface ActionsResult {
     screenshots: string[];
@@ -217,7 +220,9 @@ interface CrawlParams {
      * 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.

package/dist/index.js

@@ -29,7 +29,7 @@ var FirecrawlApp = class {
   }
   async getVersion() {
     try {
-      const packageJson = await import("./package-STCQBHTG.js");
+      const packageJson = await import("./package-TKKTR5R7.js");
       return packageJson.default.version;
     } catch (error) {
       console.error("Error getting version:", error);

package/dist/{package-STCQBHTG.js → package-TKKTR5R7.js}

@@ -1,6 +1,6 @@
 // package.json
 var name = "@mendable/firecrawl-js";
-var version = "1.27.0";
+var version = "1.29.1";
 var description = "JavaScript SDK for Firecrawl API";
 var main = "dist/index.js";
 var types = "dist/index.d.ts";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mendable/firecrawl",
-  "version": "1.27.0",
+  "version": "1.29.1",
   "description": "JavaScript SDK for Firecrawl API",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",

package/src/__tests__/v1/e2e_withAuth/index.test.ts

@@ -103,6 +103,32 @@ describe('FirecrawlApp E2E Tests', () => {
     expect(response?.markdown).toContain('We present spectrophotometric observations of the Broad Line Radio Galaxy');
   }, 30000); // 30 seconds timeout
 
+  test.concurrent('should return successful response for valid scrape with PDF file and parsePDF true', async () => {
+    const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
+    const response = await app.scrapeUrl('https://arxiv.org/pdf/astro-ph/9301001.pdf', {
+      parsePDF: true
+    });
+    if (!response.success) {
+      throw new Error(response.error);
+    }
+
+    expect(response).not.toBeNull();
+    expect(response?.markdown).toContain('We present spectrophotometric observations of the Broad Line Radio Galaxy');
+  }, 30000); // 30 seconds timeout
+
+  test.concurrent('should return successful response for valid scrape with PDF file and parsePDF false', async () => {
+    const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
+    const response = await app.scrapeUrl('https://arxiv.org/pdf/astro-ph/9301001.pdf', {
+      parsePDF: false
+    });
+    if (!response.success) {
+      throw new Error(response.error);
+    }
+
+    expect(response).not.toBeNull();
+    expect(response?.markdown).toMatch(/^[A-Za-z0-9+/]+=*$/);
+  }, 30000); // 30 seconds timeout
+
   test.concurrent('should throw error for invalid API key on crawl', async () => {
     if (API_URL.includes('api.firecrawl.dev')) {
       const invalidApp = new FirecrawlApp({ apiKey: "invalid_api_key", apiUrl: API_URL });

package/src/index.ts

@@ -125,6 +125,7 @@ export interface CrawlScrapeOptions {
   proxy?: "basic" | "stealth" | "auto";
   storeInCache?: boolean;
   maxAge?: number;
+  parsePDF?: boolean;
 }
 
 export type Action = {
@@ -138,6 +139,7 @@ export type Action = {
 } | {
   type: "screenshot",
   fullPage?: boolean,
+  quality?: number,
 } | {
   type: "write",
   text: string,
@@ -174,6 +176,7 @@ export interface ScrapeParams<LLMSchema extends zt.ZodSchema = any, ActionsSchem
   }
   actions?: ActionsSchema;
   agent?: AgentOptions;
+  zeroDataRetention?: boolean;
 }
 
 export interface ActionsResult {
@@ -227,7 +230,9 @@ export interface CrawlParams {
    * If not provided, the crawler may use the robots.txt crawl delay if available.
    */
   delay?: number;
+  allowSubdomains?: boolean;
   maxConcurrency?: number;
+  zeroDataRetention?: boolean;
 }
 
 /**