firecrawl 1.1.0 → 1.3.0

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

@@ -1,4 +1,4 @@
-import FirecrawlApp, { CrawlParams, CrawlResponse, CrawlStatusResponse, MapResponse, ScrapeParams, ScrapeResponse } from '../../../index';
+import FirecrawlApp, { type CrawlParams, type CrawlResponse, type CrawlStatusResponse, type MapResponse, type ScrapeResponse } from '../../../index';
 import { v4 as uuidv4 } from 'uuid';
 import dotenv from 'dotenv';
 import { describe, test, expect } from '@jest/globals';
@@ -6,7 +6,7 @@ import { describe, test, expect } from '@jest/globals';
 dotenv.config();
 
 const TEST_API_KEY = process.env.TEST_API_KEY;
-const API_URL = "http://127.0.0.1:3002";
+const API_URL = process.env.API_URL ?? "https://api.firecrawl.dev";
 
 describe('FirecrawlApp E2E Tests', () => {
   test.concurrent('should throw error for no API key', async () => {
@@ -71,6 +71,7 @@ describe('FirecrawlApp E2E Tests', () => {
     expect(response.links?.length).toBeGreaterThan(0);
     expect(response.links?.[0]).toContain("https://");
     expect(response.metadata).not.toBeNull();
+    expect(response.metadata).not.toBeUndefined();
     expect(response.metadata).toHaveProperty("title");
     expect(response.metadata).toHaveProperty("description");
     expect(response.metadata).toHaveProperty("keywords");
@@ -85,19 +86,21 @@ describe('FirecrawlApp E2E Tests', () => {
     expect(response.metadata).not.toHaveProperty("pageStatusCode");
     expect(response.metadata).toHaveProperty("statusCode");
     expect(response.metadata).not.toHaveProperty("pageError");
-    expect(response.metadata.error).toBeUndefined();
-    expect(response.metadata.title).toBe("Roast My Website");
-    expect(response.metadata.description).toBe("Welcome to Roast My Website, the ultimate tool for putting your website through the wringer! This repository harnesses the power of Firecrawl to scrape and capture screenshots of websites, and then unleashes the latest LLM vision models to mercilessly roast them. 🌶️");
-    expect(response.metadata.keywords).toBe("Roast My Website,Roast,Website,GitHub,Firecrawl");
-    expect(response.metadata.robots).toBe("follow, index");
-    expect(response.metadata.ogTitle).toBe("Roast My Website");
-    expect(response.metadata.ogDescription).toBe("Welcome to Roast My Website, the ultimate tool for putting your website through the wringer! This repository harnesses the power of Firecrawl to scrape and capture screenshots of websites, and then unleashes the latest LLM vision models to mercilessly roast them. 🌶️");
-    expect(response.metadata.ogUrl).toBe("https://www.roastmywebsite.ai");
-    expect(response.metadata.ogImage).toBe("https://www.roastmywebsite.ai/og.png");
-    expect(response.metadata.ogLocaleAlternate).toStrictEqual([]);
-    expect(response.metadata.ogSiteName).toBe("Roast My Website");
-    expect(response.metadata.sourceURL).toBe("https://roastmywebsite.ai");
-    expect(response.metadata.statusCode).toBe(200);
+    if (response.metadata !== undefined) {
+      expect(response.metadata.error).toBeUndefined();
+      expect(response.metadata.title).toBe("Roast My Website");
+      expect(response.metadata.description).toBe("Welcome to Roast My Website, the ultimate tool for putting your website through the wringer! This repository harnesses the power of Firecrawl to scrape and capture screenshots of websites, and then unleashes the latest LLM vision models to mercilessly roast them. 🌶️");
+      expect(response.metadata.keywords).toBe("Roast My Website,Roast,Website,GitHub,Firecrawl");
+      expect(response.metadata.robots).toBe("follow, index");
+      expect(response.metadata.ogTitle).toBe("Roast My Website");
+      expect(response.metadata.ogDescription).toBe("Welcome to Roast My Website, the ultimate tool for putting your website through the wringer! This repository harnesses the power of Firecrawl to scrape and capture screenshots of websites, and then unleashes the latest LLM vision models to mercilessly roast them. 🌶️");
+      expect(response.metadata.ogUrl).toBe("https://www.roastmywebsite.ai");
+      expect(response.metadata.ogImage).toBe("https://www.roastmywebsite.ai/og.png");
+      expect(response.metadata.ogLocaleAlternate).toStrictEqual([]);
+      expect(response.metadata.ogSiteName).toBe("Roast My Website");
+      expect(response.metadata.sourceURL).toBe("https://roastmywebsite.ai");
+      expect(response.metadata.statusCode).toBe(200);
+    }
   }, 30000); // 30 seconds timeout
 
   test.concurrent('should return successful response for valid scrape with PDF file', async () => {
@@ -127,7 +130,7 @@ describe('FirecrawlApp E2E Tests', () => {
 
   test.concurrent('should return successful response for crawl and wait for completion', async () => {
     const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
-    const response = await app.crawlUrl('https://roastmywebsite.ai', {}, true, 30) as CrawlStatusResponse;
+    const response = await app.crawlUrl('https://roastmywebsite.ai', {}, 30) as CrawlStatusResponse;
     expect(response).not.toBeNull();
     expect(response).toHaveProperty("total");
     expect(response.total).toBeGreaterThan(0);
@@ -138,21 +141,25 @@ describe('FirecrawlApp E2E Tests', () => {
     expect(response).toHaveProperty("status");
     expect(response.status).toBe("completed");
     expect(response).not.toHaveProperty("next"); // wait until done
-    expect(response.data?.length).toBeGreaterThan(0);
-    expect(response.data?.[0]).toHaveProperty("markdown");
-    expect(response.data?.[0].markdown).toContain("_Roast_");
-    expect(response.data?.[0]).not.toHaveProperty('content'); // v0
-    expect(response.data?.[0]).not.toHaveProperty("html");
-    expect(response.data?.[0]).not.toHaveProperty("rawHtml");
-    expect(response.data?.[0]).not.toHaveProperty("screenshot");
-    expect(response.data?.[0]).not.toHaveProperty("links");
-    expect(response.data?.[0]).toHaveProperty("metadata");
-    expect(response.data?.[0].metadata).toHaveProperty("title");
-    expect(response.data?.[0].metadata).toHaveProperty("description");
-    expect(response.data?.[0].metadata).toHaveProperty("language");
-    expect(response.data?.[0].metadata).toHaveProperty("sourceURL");
-    expect(response.data?.[0].metadata).toHaveProperty("statusCode");
-    expect(response.data?.[0].metadata).not.toHaveProperty("error");
+    expect(response.data.length).toBeGreaterThan(0);
+    expect(response.data[0]).not.toBeNull();
+    expect(response.data[0]).not.toBeUndefined();
+    if (response.data[0]) {
+      expect(response.data[0]).toHaveProperty("markdown");
+      expect(response.data[0].markdown).toContain("_Roast_");
+      expect(response.data[0]).not.toHaveProperty('content'); // v0
+      expect(response.data[0]).not.toHaveProperty("html");
+      expect(response.data[0]).not.toHaveProperty("rawHtml");
+      expect(response.data[0]).not.toHaveProperty("screenshot");
+      expect(response.data[0]).not.toHaveProperty("links");
+      expect(response.data[0]).toHaveProperty("metadata");
+      expect(response.data[0].metadata).toHaveProperty("title");
+      expect(response.data[0].metadata).toHaveProperty("description");
+      expect(response.data[0].metadata).toHaveProperty("language");
+      expect(response.data[0].metadata).toHaveProperty("sourceURL");
+      expect(response.data[0].metadata).toHaveProperty("statusCode");
+      expect(response.data[0].metadata).not.toHaveProperty("error");
+    }
   }, 60000); // 60 seconds timeout
 
   test.concurrent('should return successful response for crawl with options and wait for completion', async () => {    
@@ -173,7 +180,7 @@ describe('FirecrawlApp E2E Tests', () => {
         onlyMainContent: true,
         waitFor: 1000
       }
-    } as CrawlParams, true, 30) as CrawlStatusResponse;
+    } as CrawlParams, 30) as CrawlStatusResponse;
     expect(response).not.toBeNull();
     expect(response).toHaveProperty("total");
     expect(response.total).toBeGreaterThan(0);
@@ -184,41 +191,45 @@ describe('FirecrawlApp E2E Tests', () => {
     expect(response).toHaveProperty("status");
     expect(response.status).toBe("completed");
     expect(response).not.toHaveProperty("next");
-    expect(response.data?.length).toBeGreaterThan(0);
-    expect(response.data?.[0]).toHaveProperty("markdown");
-    expect(response.data?.[0].markdown).toContain("_Roast_");
-    expect(response.data?.[0]).not.toHaveProperty('content'); // v0
-    expect(response.data?.[0]).toHaveProperty("html");
-    expect(response.data?.[0].html).toContain("<h1");
-    expect(response.data?.[0]).toHaveProperty("rawHtml");
-    expect(response.data?.[0].rawHtml).toContain("<h1");
-    expect(response.data?.[0]).toHaveProperty("screenshot");
-    expect(response.data?.[0].screenshot).toContain("https://");
-    expect(response.data?.[0]).toHaveProperty("links");
-    expect(response.data?.[0].links).not.toBeNull();
-    expect(response.data?.[0].links?.length).toBeGreaterThan(0);
-    expect(response.data?.[0]).toHaveProperty("metadata");
-    expect(response.data?.[0].metadata).toHaveProperty("title");
-    expect(response.data?.[0].metadata).toHaveProperty("description");
-    expect(response.data?.[0].metadata).toHaveProperty("language");
-    expect(response.data?.[0].metadata).toHaveProperty("sourceURL");
-    expect(response.data?.[0].metadata).toHaveProperty("statusCode");
-    expect(response.data?.[0].metadata).not.toHaveProperty("error");
+    expect(response.data.length).toBeGreaterThan(0);
+    expect(response.data[0]).not.toBeNull();
+    expect(response.data[0]).not.toBeUndefined();
+    if (response.data[0]) {
+      expect(response.data[0]).toHaveProperty("markdown");
+      expect(response.data[0].markdown).toContain("_Roast_");
+      expect(response.data[0]).not.toHaveProperty('content'); // v0
+      expect(response.data[0]).toHaveProperty("html");
+      expect(response.data[0].html).toContain("<h1");
+      expect(response.data[0]).toHaveProperty("rawHtml");
+      expect(response.data[0].rawHtml).toContain("<h1");
+      expect(response.data[0]).toHaveProperty("screenshot");
+      expect(response.data[0].screenshot).toContain("https://");
+      expect(response.data[0]).toHaveProperty("links");
+      expect(response.data[0].links).not.toBeNull();
+      expect(response.data[0].links?.length).toBeGreaterThan(0);
+      expect(response.data[0]).toHaveProperty("metadata");
+      expect(response.data[0].metadata).toHaveProperty("title");
+      expect(response.data[0].metadata).toHaveProperty("description");
+      expect(response.data[0].metadata).toHaveProperty("language");
+      expect(response.data[0].metadata).toHaveProperty("sourceURL");
+      expect(response.data[0].metadata).toHaveProperty("statusCode");
+      expect(response.data[0].metadata).not.toHaveProperty("error");
+    }
   }, 60000); // 60 seconds timeout
 
   test.concurrent('should handle idempotency key for crawl', async () => {
     const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
     const uniqueIdempotencyKey = uuidv4();
-    const response = await app.crawlUrl('https://roastmywebsite.ai', {}, false, 2, uniqueIdempotencyKey) as CrawlResponse;
+    const response = await app.asyncCrawlUrl('https://roastmywebsite.ai', {}, uniqueIdempotencyKey) as CrawlResponse;
     expect(response).not.toBeNull();
     expect(response.id).toBeDefined();
 
-    await expect(app.crawlUrl('https://roastmywebsite.ai', {}, true, 2, uniqueIdempotencyKey)).rejects.toThrow("Request failed with status code 409");
+    await expect(app.crawlUrl('https://roastmywebsite.ai', {}, 2, uniqueIdempotencyKey)).rejects.toThrow("Request failed with status code 409");
   });
 
   test.concurrent('should check crawl status', async () => {
     const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
-    const response = await app.crawlUrl('https://firecrawl.dev', { scrapeOptions: { formats: ['markdown', 'html', 'rawHtml', 'screenshot', 'links']}} as CrawlParams, false) as CrawlResponse;
+    const response = await app.asyncCrawlUrl('https://firecrawl.dev', { scrapeOptions: { formats: ['markdown', 'html', 'rawHtml', 'screenshot', 'links']}} as CrawlParams) as CrawlResponse;
     expect(response).not.toBeNull();
     expect(response.id).toBeDefined();
 
@@ -226,7 +237,8 @@ describe('FirecrawlApp E2E Tests', () => {
     const maxChecks = 15;
     let checks = 0;
 
-    while (statusResponse.status === 'scraping' && checks < maxChecks) {
+    expect(statusResponse.success).toBe(true);
+    while ((statusResponse as any).status === 'scraping' && checks < maxChecks) {
       await new Promise(resolve => setTimeout(resolve, 5000));
       expect(statusResponse).not.toHaveProperty("partial_data"); // v0
       expect(statusResponse).not.toHaveProperty("current"); // v0
@@ -236,44 +248,55 @@ describe('FirecrawlApp E2E Tests', () => {
       expect(statusResponse).toHaveProperty("expiresAt");
       expect(statusResponse).toHaveProperty("status");
       expect(statusResponse).toHaveProperty("next");
-      expect(statusResponse.total).toBeGreaterThan(0);
-      expect(statusResponse.creditsUsed).toBeGreaterThan(0);
-      expect(statusResponse.expiresAt.getTime()).toBeGreaterThan(Date.now());
-      expect(statusResponse.status).toBe("scraping");
-      expect(statusResponse.next).toContain("/v1/crawl/");
+      expect(statusResponse.success).toBe(true);
+      if (statusResponse.success === true) {
+        expect(statusResponse.total).toBeGreaterThan(0);
+        expect(statusResponse.creditsUsed).toBeGreaterThan(0);
+        expect(statusResponse.expiresAt.getTime()).toBeGreaterThan(Date.now());
+        expect(statusResponse.status).toBe("scraping");
+        expect(statusResponse.next).toContain("/v1/crawl/");
+      }
       statusResponse = await app.checkCrawlStatus(response.id) as CrawlStatusResponse;
+      expect(statusResponse.success).toBe(true);
       checks++;
     }
 
     expect(statusResponse).not.toBeNull();
     expect(statusResponse).toHaveProperty("total");
-    expect(statusResponse.total).toBeGreaterThan(0);
-    expect(statusResponse).toHaveProperty("creditsUsed");
-    expect(statusResponse.creditsUsed).toBeGreaterThan(0);
-    expect(statusResponse).toHaveProperty("expiresAt");
-    expect(statusResponse.expiresAt.getTime()).toBeGreaterThan(Date.now());
-    expect(statusResponse).toHaveProperty("status");
-    expect(statusResponse.status).toBe("completed");
-    expect(statusResponse.data?.length).toBeGreaterThan(0);
-    expect(statusResponse.data?.[0]).toHaveProperty("markdown");
-    expect(statusResponse.data?.[0].markdown?.length).toBeGreaterThan(10);
-    expect(statusResponse.data?.[0]).not.toHaveProperty('content'); // v0
-    expect(statusResponse.data?.[0]).toHaveProperty("html");
-    expect(statusResponse.data?.[0].html).toContain("<div");
-    expect(statusResponse.data?.[0]).toHaveProperty("rawHtml");
-    expect(statusResponse.data?.[0].rawHtml).toContain("<div");
-    expect(statusResponse.data?.[0]).toHaveProperty("screenshot");
-    expect(statusResponse.data?.[0].screenshot).toContain("https://");
-    expect(statusResponse.data?.[0]).toHaveProperty("links");
-    expect(statusResponse.data?.[0].links).not.toBeNull();
-    expect(statusResponse.data?.[0].links?.length).toBeGreaterThan(0);
-    expect(statusResponse.data?.[0]).toHaveProperty("metadata");
-    expect(statusResponse.data?.[0].metadata).toHaveProperty("title");
-    expect(statusResponse.data?.[0].metadata).toHaveProperty("description");
-    expect(statusResponse.data?.[0].metadata).toHaveProperty("language");
-    expect(statusResponse.data?.[0].metadata).toHaveProperty("sourceURL");
-    expect(statusResponse.data?.[0].metadata).toHaveProperty("statusCode");
-    expect(statusResponse.data?.[0].metadata).not.toHaveProperty("error");
+    expect(statusResponse.success).toBe(true);
+    if (statusResponse.success === true) {
+      expect(statusResponse.total).toBeGreaterThan(0);
+      expect(statusResponse).toHaveProperty("creditsUsed");
+      expect(statusResponse.creditsUsed).toBeGreaterThan(0);
+      expect(statusResponse).toHaveProperty("expiresAt");
+      expect(statusResponse.expiresAt.getTime()).toBeGreaterThan(Date.now());
+      expect(statusResponse).toHaveProperty("status");
+      expect(statusResponse.status).toBe("completed");
+      expect(statusResponse.data.length).toBeGreaterThan(0);
+      expect(statusResponse.data[0]).not.toBeNull();
+      expect(statusResponse.data[0]).not.toBeUndefined();
+      if (statusResponse.data[0]) {
+        expect(statusResponse.data[0]).toHaveProperty("markdown");
+        expect(statusResponse.data[0].markdown?.length).toBeGreaterThan(10);
+        expect(statusResponse.data[0]).not.toHaveProperty('content'); // v0
+        expect(statusResponse.data[0]).toHaveProperty("html");
+        expect(statusResponse.data[0].html).toContain("<div");
+        expect(statusResponse.data[0]).toHaveProperty("rawHtml");
+        expect(statusResponse.data[0].rawHtml).toContain("<div");
+        expect(statusResponse.data[0]).toHaveProperty("screenshot");
+        expect(statusResponse.data[0].screenshot).toContain("https://");
+        expect(statusResponse.data[0]).toHaveProperty("links");
+        expect(statusResponse.data[0].links).not.toBeNull();
+        expect(statusResponse.data[0].links?.length).toBeGreaterThan(0);
+        expect(statusResponse.data[0]).toHaveProperty("metadata");
+        expect(statusResponse.data[0].metadata).toHaveProperty("title");
+        expect(statusResponse.data[0].metadata).toHaveProperty("description");
+        expect(statusResponse.data[0].metadata).toHaveProperty("language");
+        expect(statusResponse.data[0].metadata).toHaveProperty("sourceURL");
+        expect(statusResponse.data[0].metadata).toHaveProperty("statusCode");
+        expect(statusResponse.data[0].metadata).not.toHaveProperty("error");
+      }
+    }
   }, 60000); // 60 seconds timeout
 
   test.concurrent('should throw error for invalid API key on map', async () => {

package/src/index.ts

@@ -1,5 +1,5 @@
-import axios, { AxiosResponse, AxiosRequestHeaders } from "axios";
-import { z } from "zod";
+import axios, { type AxiosResponse, type AxiosRequestHeaders } from "axios";
+import type { ZodSchema } from "zod";
 import { zodToJsonSchema } from "zod-to-json-schema";
 import { WebSocket } from "isows";
 import { TypedEventTarget } from "typescript-event-target";
@@ -64,6 +64,7 @@ export interface FirecrawlDocument {
   html?: string;
   rawHtml?: string;
   links?: string[];
+  extract?: Record<any, any>;
   screenshot?: string;
   metadata?: FirecrawlDocumentMetadata;
 }
@@ -73,12 +74,17 @@ export interface FirecrawlDocument {
  * Defines the options and configurations available for scraping web content.
  */
 export interface ScrapeParams {
-  formats: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "full@scrennshot")[];
+  formats: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "extract" | "full@scrennshot")[];
   headers?: Record<string, string>;
   includeTags?: string[];
   excludeTags?: string[];
   onlyMainContent?: boolean;
-    waitFor?: number;
+  extract?: {
+    prompt?: string;
+    schema?: ZodSchema | any;
+    systemPrompt?: string;
+  };
+  waitFor?: number;
   timeout?: number;
 }
 
@@ -105,6 +111,7 @@ export interface CrawlParams {
   allowExternalLinks?: boolean;
   ignoreSitemap?: boolean;
   scrapeOptions?: ScrapeParams;
+  webhook?: string;
 }
 
 /**
@@ -124,15 +131,14 @@ export interface CrawlResponse {
  */
 export interface CrawlStatusResponse {
   success: true;
-  total: number;
+  status: "scraping" | "completed" | "failed" | "cancelled";
   completed: number;
+  total: number;
   creditsUsed: number;
   expiresAt: Date;
-  status: "scraping" | "completed" | "failed";
-  next: string;
-  data?: FirecrawlDocument[];
-  error?: string;
-}
+  next?: string;
+  data: FirecrawlDocument[];
+};
 
 /**
  * Parameters for mapping operations.
@@ -177,7 +183,11 @@ export default class FirecrawlApp {
    * @param config - Configuration options for the FirecrawlApp instance.
    */
   constructor({ apiKey = null, apiUrl = null }: FirecrawlAppConfig) {
-    this.apiKey = apiKey || "";
+    if (typeof apiKey !== "string") {
+      throw new Error("No API key provided");
+    }
+
+    this.apiKey = apiKey;
     this.apiUrl = apiUrl || "https://api.firecrawl.dev";
   }
 
@@ -196,18 +206,20 @@ export default class FirecrawlApp {
       Authorization: `Bearer ${this.apiKey}`,
     } as AxiosRequestHeaders;
     let jsonData: any = { url, ...params };
-    if (jsonData?.extractorOptions?.extractionSchema) {
-      let schema = jsonData.extractorOptions.extractionSchema;
-      // Check if schema is an instance of ZodSchema to correctly identify Zod schemas
-      if (schema instanceof z.ZodSchema) {
+    if (jsonData?.extract?.schema) {
+      let schema = jsonData.extract.schema;
+
+      // Try parsing the schema as a Zod schema
+      try {
         schema = zodToJsonSchema(schema);
+      } catch (error) {
+        
       }
       jsonData = {
         ...jsonData,
-        extractorOptions: {
-          ...jsonData.extractorOptions,
-          extractionSchema: schema,
-          mode: jsonData.extractorOptions.mode || "llm-extraction",
+        extract: {
+          ...jsonData.extract,
+          schema: schema,
         },
       };
     }
@@ -320,9 +332,10 @@ export default class FirecrawlApp {
   /**
    * 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`)
    * @returns The response containing the job status.
    */
-  async checkCrawlStatus(id?: string): Promise<CrawlStatusResponse | ErrorResponse> {
+  async checkCrawlStatus(id?: string, getAllData = false): Promise<CrawlStatusResponse | ErrorResponse> {
     if (!id) {
       throw new Error("No crawl ID provided");
     }
@@ -334,16 +347,28 @@ export default class FirecrawlApp {
         headers
       );
       if (response.status === 200) {
+        let allData = response.data.data;
+        if (getAllData && response.data.status === "completed") {
+          let statusData = response.data
+          if ("data" in statusData) {
+            let data = statusData.data;
+            while ('next' in statusData) {
+              statusData = (await this.getRequest(statusData.next, headers)).data;
+              data = data.concat(statusData.data);
+            }
+            allData = data;
+          }
+        }
         return ({
-          success: true,
+          success: response.data.success,
           status: response.data.status,
           total: response.data.total,
           completed: response.data.completed,
           creditsUsed: response.data.creditsUsed,
           expiresAt: new Date(response.data.expiresAt),
           next: response.data.next,
-          data: response.data.data,
-          error: response.data.error
+          data: allData,
+          error: response.data.error,
         })
       } else {
         this.handleError(response, "check crawl status");
@@ -443,22 +468,29 @@ export default class FirecrawlApp {
     id: string,
     headers: AxiosRequestHeaders,
     checkInterval: number
-  ): Promise<CrawlStatusResponse> {
+  ): Promise<CrawlStatusResponse | ErrorResponse> {
     while (true) {
-      const statusResponse: AxiosResponse = await this.getRequest(
+      let statusResponse: AxiosResponse = await this.getRequest(
         `${this.apiUrl}/v1/crawl/${id}`,
         headers
       );
       if (statusResponse.status === 200) {
-        const statusData = statusResponse.data;
-        if (statusData.status === "completed") {
-          if ("data" in statusData) {
-            return statusData;
-          } else {
-            throw new Error("Crawl job completed but no data was returned");
-          }
-        } else if (
-          ["active", "paused", "pending", "queued", "scraping"].includes(statusData.status)
+        let statusData = statusResponse.data;
+          if (statusData.status === "completed") {
+            if ("data" in statusData) {
+              let data = statusData.data;
+              while ('next' in statusData) {
+                statusResponse = await this.getRequest(statusData.next, headers);
+                statusData = statusResponse.data;
+                data = data.concat(statusData.data);
+              }
+              statusData.data = data;
+              return statusData;
+            } else {
+              throw new Error("Crawl job completed but no data was returned");
+            }
+          } else if (
+          ["active", "paused", "pending", "queued", "waiting", "scraping"].includes(statusData.status)
         ) {
           checkInterval = Math.max(checkInterval, 2);
           await new Promise((resolve) =>

package/tsconfig.json

@@ -1,110 +1,24 @@
 {
   "compilerOptions": {
-    /* Visit https://aka.ms/tsconfig to read more about this file */
-
-    /* Projects */
-    // "incremental": true,                              /* Save .tsbuildinfo files to allow for incremental compilation of projects. */
-    // "composite": true,                                /* Enable constraints that allow a TypeScript project to be used with project references. */
-    // "tsBuildInfoFile": "./.tsbuildinfo",              /* Specify the path to .tsbuildinfo incremental compilation file. */
-    // "disableSourceOfProjectReferenceRedirect": true,  /* Disable preferring source files instead of declaration files when referencing composite projects. */
-    // "disableSolutionSearching": true,                 /* Opt a project out of multi-project reference checking when editing. */
-    // "disableReferencedProjectLoad": true,             /* Reduce the number of projects loaded automatically by TypeScript. */
-
-    /* Language and Environment */
-    "target": "es2020",                                  /* Set the JavaScript language version for emitted JavaScript and include compatible library declarations. */
-    // "lib": [],                                        /* Specify a set of bundled library declaration files that describe the target runtime environment. */
-    // "jsx": "preserve",                                /* Specify what JSX code is generated. */
-    // "experimentalDecorators": true,                   /* Enable experimental support for legacy experimental decorators. */
-    // "emitDecoratorMetadata": true,                    /* Emit design-type metadata for decorated declarations in source files. */
-    // "jsxFactory": "",                                 /* Specify the JSX factory function used when targeting React JSX emit, e.g. 'React.createElement' or 'h'. */
-    // "jsxFragmentFactory": "",                         /* Specify the JSX Fragment reference used for fragments when targeting React JSX emit e.g. 'React.Fragment' or 'Fragment'. */
-    // "jsxImportSource": "",                            /* Specify module specifier used to import the JSX factory functions when using 'jsx: react-jsx*'. */
-    // "reactNamespace": "",                             /* Specify the object invoked for 'createElement'. This only applies when targeting 'react' JSX emit. */
-    // "noLib": true,                                    /* Disable including any library files, including the default lib.d.ts. */
-    // "useDefineForClassFields": true,                  /* Emit ECMAScript-standard-compliant class fields. */
-    // "moduleDetection": "auto",                        /* Control what method is used to detect module-format JS files. */
-
-    /* Modules */
-    "module": "commonjs",                                /* Specify what module code is generated. */
-    "rootDir": "./src",                                  /* Specify the root folder within your source files. */
-    "moduleResolution": "node",                     /* Specify how TypeScript looks up a file from a given module specifier. */
-    // "baseUrl": "./",                                  /* Specify the base directory to resolve non-relative module names. */
-    // "paths": {},                                      /* Specify a set of entries that re-map imports to additional lookup locations. */
-    // "rootDirs": [],                                   /* Allow multiple folders to be treated as one when resolving modules. */
-    // "typeRoots": [],                                  /* Specify multiple folders that act like './node_modules/@types'. */
-    // "types": [],                                      /* Specify type package names to be included without being referenced in a source file. */
-    // "allowUmdGlobalAccess": true,                     /* Allow accessing UMD globals from modules. */
-    // "moduleSuffixes": [],                             /* List of file name suffixes to search when resolving a module. */
-    // "allowImportingTsExtensions": true,               /* Allow imports to include TypeScript file extensions. Requires '--moduleResolution bundler' and either '--noEmit' or '--emitDeclarationOnly' to be set. */
-    // "resolvePackageJsonExports": true,                /* Use the package.json 'exports' field when resolving package imports. */
-    // "resolvePackageJsonImports": true,                /* Use the package.json 'imports' field when resolving imports. */
-    // "customConditions": [],                           /* Conditions to set in addition to the resolver-specific defaults when resolving imports. */
-    // "resolveJsonModule": true,                        /* Enable importing .json files. */
-    // "allowArbitraryExtensions": true,                 /* Enable importing files with any extension, provided a declaration file is present. */
-    // "noResolve": true,                                /* Disallow 'import's, 'require's or '<reference>'s from expanding the number of files TypeScript should add to a project. */
-
-    /* JavaScript Support */
-    // "allowJs": true,                                  /* Allow JavaScript files to be a part of your program. Use the 'checkJS' option to get errors from these files. */
-    // "checkJs": true,                                  /* Enable error reporting in type-checked JavaScript files. */
-    // "maxNodeModuleJsDepth": 1,                        /* Specify the maximum folder depth used for checking JavaScript files from 'node_modules'. Only applicable with 'allowJs'. */
-
-    /* Emit */
-    "declaration": true,                              /* Generate .d.ts files from TypeScript and JavaScript files in your project. */
-    // "declarationMap": true,                           /* Create sourcemaps for d.ts files. */
-    // "emitDeclarationOnly": true,                      /* Only output d.ts files and not JavaScript files. */
-    // "sourceMap": true,                                /* Create source map files for emitted JavaScript files. */
-    // "inlineSourceMap": true,                          /* Include sourcemap files inside the emitted JavaScript. */
-    // "outFile": "./",                                  /* Specify a file that bundles all outputs into one JavaScript file. If 'declaration' is true, also designates a file that bundles all .d.ts output. */
-    "outDir": "./build",                                   /* Specify an output folder for all emitted files. */
-    // "removeComments": true,                           /* Disable emitting comments. */
-    // "noEmit": true,                                   /* Disable emitting files from a compilation. */
-    // "importHelpers": true,                            /* Allow importing helper functions from tslib once per project, instead of including them per-file. */
-    // "importsNotUsedAsValues": "remove",               /* Specify emit/checking behavior for imports that are only used for types. */
-    // "downlevelIteration": true,                       /* Emit more compliant, but verbose and less performant JavaScript for iteration. */
-    // "sourceRoot": "",                                 /* Specify the root path for debuggers to find the reference source code. */
-    // "mapRoot": "",                                    /* Specify the location where debugger should locate map files instead of generated locations. */
-    // "inlineSources": true,                            /* Include source code in the sourcemaps inside the emitted JavaScript. */
-    // "emitBOM": true,                                  /* Emit a UTF-8 Byte Order Mark (BOM) in the beginning of output files. */
-    // "newLine": "crlf",                                /* Set the newline character for emitting files. */
-    // "stripInternal": true,                            /* Disable emitting declarations that have '@internal' in their JSDoc comments. */
-    // "noEmitHelpers": true,                            /* Disable generating custom helper functions like '__extends' in compiled output. */
-    // "noEmitOnError": true,                            /* Disable emitting files if any type checking errors are reported. */
-    // "preserveConstEnums": true,                       /* Disable erasing 'const enum' declarations in generated code. */
-    "declarationDir": "./types",                           /* Specify the output directory for generated declaration files. */
-    // "preserveValueImports": true,                     /* Preserve unused imported values in the JavaScript output that would otherwise be removed. */
-
-    /* Interop Constraints */
-    // "isolatedModules": true,                          /* Ensure that each file can be safely transpiled without relying on other imports. */
-    // "verbatimModuleSyntax": true,                     /* Do not transform or elide any imports or exports not marked as type-only, ensuring they are written in the output file's format based on the 'module' setting. */
-    // "allowSyntheticDefaultImports": true,             /* Allow 'import x from y' when a module doesn't have a default export. */
-    "esModuleInterop": true,                             /* Emit additional JavaScript to ease support for importing CommonJS modules. This enables 'allowSyntheticDefaultImports' for type compatibility. */
-    // "preserveSymlinks": true,                         /* Disable resolving symlinks to their realpath. This correlates to the same flag in node. */
-    "forceConsistentCasingInFileNames": true,            /* Ensure that casing is correct in imports. */
-
-    /* Type Checking */
-    "strict": true,                                      /* Enable all strict type-checking options. */
-    // "noImplicitAny": true,                            /* Enable error reporting for expressions and declarations with an implied 'any' type. */
-    // "strictNullChecks": true,                         /* When type checking, take into account 'null' and 'undefined'. */
-    // "strictFunctionTypes": true,                      /* When assigning functions, check to ensure parameters and the return values are subtype-compatible. */
-    // "strictBindCallApply": true,                      /* Check that the arguments for 'bind', 'call', and 'apply' methods match the original function. */
-    // "strictPropertyInitialization": true,             /* Check for class properties that are declared but not set in the constructor. */
-    // "noImplicitThis": true,                           /* Enable error reporting when 'this' is given the type 'any'. */
-    // "useUnknownInCatchVariables": true,               /* Default catch clause variables as 'unknown' instead of 'any'. */
-    // "alwaysStrict": true,                             /* Ensure 'use strict' is always emitted. */
-    // "noUnusedLocals": true,                           /* Enable error reporting when local variables aren't read. */
-    // "noUnusedParameters": true,                       /* Raise an error when a function parameter isn't read. */
-    // "exactOptionalPropertyTypes": true,               /* Interpret optional property types as written, rather than adding 'undefined'. */
-    // "noImplicitReturns": true,                        /* Enable error reporting for codepaths that do not explicitly return in a function. */
-    // "noFallthroughCasesInSwitch": true,               /* Enable error reporting for fallthrough cases in switch statements. */
-    // "noUncheckedIndexedAccess": true,                 /* Add 'undefined' to a type when accessed using an index. */
-    // "noImplicitOverride": true,                       /* Ensure overriding members in derived classes are marked with an override modifier. */
-    // "noPropertyAccessFromIndexSignature": true,       /* Enforces using indexed accessors for keys declared using an indexed type. */
-    // "allowUnusedLabels": true,                        /* Disable error reporting for unused labels. */
-    // "allowUnreachableCode": true,                     /* Disable error reporting for unreachable code. */
-
-    /* Completeness */
-    // "skipDefaultLibCheck": true,                      /* Skip type checking .d.ts files that are included with TypeScript. */
-    "skipLibCheck": true                                 /* Skip type checking all .d.ts files. */
+    // See https://www.totaltypescript.com/tsconfig-cheat-sheet
+    /* Base Options: */
+    "esModuleInterop": true,
+    "skipLibCheck": true,
+    "target": "es2022",
+    "allowJs": true,
+    "resolveJsonModule": true,
+    "moduleDetection": "force",
+    "isolatedModules": true,
+    "verbatimModuleSyntax": true,
+
+    /* Strictness */
+    "strict": true,
+    "noUncheckedIndexedAccess": true,
+    "noImplicitOverride": true,
+
+    /* If NOT transpiling with TypeScript: */
+    "module": "NodeNext",
+    "noEmit": true,
   },
   "include": ["src/**/*"],
   "exclude": ["node_modules", "dist", "**/__tests__/*"]

package/tsup.config.ts

@@ -0,0 +1,9 @@
+import { defineConfig } from "tsup";
+
+export default defineConfig({
+  entryPoints: ["src/index.ts"],
+  format: ["cjs", "esm"],
+  dts: true,
+  outDir: "dist",
+  clean: true,
+});