@mendable/firecrawl-js 1.1.0 → 1.2.1

package/build/cjs/index.js

@@ -5,7 +5,6 @@ var __importDefault = (this && this.__importDefault) || function (mod) {
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.CrawlWatcher = void 0;
 const axios_1 = __importDefault(require("axios"));
-const zod_1 = require("zod");
 const zod_to_json_schema_1 = require("zod-to-json-schema");
 const isows_1 = require("isows");
 const typescript_event_target_1 = require("typescript-event-target");
@@ -34,18 +33,19 @@ class FirecrawlApp {
             Authorization: `Bearer ${this.apiKey}`,
         };
         let jsonData = { 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 zod_1.z.ZodSchema) {
+        if (jsonData?.extract?.schema) {
+            let schema = jsonData.extract.schema;
+            // Try parsing the schema as a Zod schema
+            try {
                 schema = (0, zod_to_json_schema_1.zodToJsonSchema)(schema);
             }
+            catch (error) {
+            }
             jsonData = {
                 ...jsonData,
-                extractorOptions: {
-                    ...jsonData.extractorOptions,
-                    extractionSchema: schema,
-                    mode: jsonData.extractorOptions.mode || "llm-extraction",
+                extract: {
+                    ...jsonData.extract,
+                    schema: schema,
                 },
             };
         }

package/build/esm/index.js

@@ -1,5 +1,4 @@
 import axios from "axios";
-import { z } from "zod";
 import { zodToJsonSchema } from "zod-to-json-schema";
 import { WebSocket } from "isows";
 import { TypedEventTarget } from "typescript-event-target";
@@ -28,18 +27,19 @@ export default class FirecrawlApp {
             Authorization: `Bearer ${this.apiKey}`,
         };
         let jsonData = { 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,
                 },
             };
         }

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mendable/firecrawl-js",
-  "version": "1.1.0",
+  "version": "1.2.1",
   "description": "JavaScript SDK for Firecrawl API",
   "main": "build/cjs/index.js",
   "types": "types/index.d.ts",

package/src/index.ts

@@ -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?: z.ZodSchema | any;
+    systemPrompt?: string;
+  };
+  waitFor?: number;
   timeout?: number;
 }
 
@@ -105,6 +111,7 @@ export interface CrawlParams {
   allowExternalLinks?: boolean;
   ignoreSitemap?: boolean;
   scrapeOptions?: ScrapeParams;
+  webhook?: string;
 }
 
 /**
@@ -196,18 +203,20 @@ 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,
         },
       };
     }

package/types/index.d.ts

@@ -1,4 +1,5 @@
 import { AxiosResponse, AxiosRequestHeaders } from "axios";
+import { z } from "zod";
 import { TypedEventTarget } from "typescript-event-target";
 /**
  * Configuration interface for FirecrawlApp.
@@ -58,6 +59,7 @@ export interface FirecrawlDocument {
     html?: string;
     rawHtml?: string;
     links?: string[];
+    extract?: Record<any, any>;
     screenshot?: string;
     metadata?: FirecrawlDocumentMetadata;
 }
@@ -66,11 +68,16 @@ 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;
+    extract?: {
+        prompt?: string;
+        schema?: z.ZodSchema | any;
+        systemPrompt?: string;
+    };
     waitFor?: number;
     timeout?: number;
 }
@@ -96,6 +103,7 @@ export interface CrawlParams {
     allowExternalLinks?: boolean;
     ignoreSitemap?: boolean;
     scrapeOptions?: ScrapeParams;
+    webhook?: string;
 }
 /**
  * Response interface for crawling operations.