firecrawl 4.3.8 → 4.4.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/{chunk-I2FDKS37.js → chunk-J3BEBX3Y.js} +1 -1
- package/dist/index.cjs +6 -3
- package/dist/index.d.cts +3 -2
- package/dist/index.d.ts +3 -2
- package/dist/index.js +7 -4
- package/dist/{package-O3Y6ICGR.js → package-SYKCM5JT.js} +1 -1
- package/package.json +1 -1
- package/src/__tests__/e2e/v1/index.test.ts +14 -14
- package/src/v2/client.ts +9 -2
- package/src/v2/types.ts +2 -2
|
@@ -8,7 +8,7 @@ var require_package = __commonJS({
|
|
|
8
8
|
"package.json"(exports, module) {
|
|
9
9
|
module.exports = {
|
|
10
10
|
name: "@mendable/firecrawl-js",
|
|
11
|
-
version: "4.
|
|
11
|
+
version: "4.4.1",
|
|
12
12
|
description: "JavaScript SDK for Firecrawl API",
|
|
13
13
|
main: "dist/index.js",
|
|
14
14
|
types: "dist/index.d.ts",
|
package/dist/index.cjs
CHANGED
|
@@ -35,7 +35,7 @@ var require_package = __commonJS({
|
|
|
35
35
|
"package.json"(exports2, module2) {
|
|
36
36
|
module2.exports = {
|
|
37
37
|
name: "@mendable/firecrawl-js",
|
|
38
|
-
version: "4.
|
|
38
|
+
version: "4.4.1",
|
|
39
39
|
description: "JavaScript SDK for Firecrawl API",
|
|
40
40
|
main: "dist/index.js",
|
|
41
41
|
types: "dist/index.d.ts",
|
|
@@ -953,6 +953,9 @@ var Watcher = class extends import_events.EventEmitter {
|
|
|
953
953
|
var zt = require("zod");
|
|
954
954
|
var FirecrawlClient = class {
|
|
955
955
|
http;
|
|
956
|
+
isCloudService(url) {
|
|
957
|
+
return url.includes("api.firecrawl.dev");
|
|
958
|
+
}
|
|
956
959
|
/**
|
|
957
960
|
* Create a v2 client.
|
|
958
961
|
* @param options Transport configuration (API key, base URL, timeouts, retries).
|
|
@@ -960,8 +963,8 @@ var FirecrawlClient = class {
|
|
|
960
963
|
constructor(options = {}) {
|
|
961
964
|
const apiKey = options.apiKey ?? process.env.FIRECRAWL_API_KEY ?? "";
|
|
962
965
|
const apiUrl = (options.apiUrl ?? process.env.FIRECRAWL_API_URL ?? "https://api.firecrawl.dev").replace(/\/$/, "");
|
|
963
|
-
if (!apiKey) {
|
|
964
|
-
throw new Error("API key is required. Set FIRECRAWL_API_KEY env or pass apiKey.");
|
|
966
|
+
if (this.isCloudService(apiUrl) && !apiKey) {
|
|
967
|
+
throw new Error("API key is required for the cloud API. Set FIRECRAWL_API_KEY env or pass apiKey.");
|
|
965
968
|
}
|
|
966
969
|
this.http = new HttpClient({
|
|
967
970
|
apiKey,
|
package/dist/index.d.cts
CHANGED
|
@@ -223,14 +223,14 @@ interface SearchData {
|
|
|
223
223
|
images?: Array<SearchResultImages | Document>;
|
|
224
224
|
}
|
|
225
225
|
interface CategoryOption {
|
|
226
|
-
type: 'github' | 'research';
|
|
226
|
+
type: 'github' | 'research' | 'pdf';
|
|
227
227
|
}
|
|
228
228
|
interface SearchRequest {
|
|
229
229
|
query: string;
|
|
230
230
|
sources?: Array<'web' | 'news' | 'images' | {
|
|
231
231
|
type: 'web' | 'news' | 'images';
|
|
232
232
|
}>;
|
|
233
|
-
categories?: Array<'github' | 'research' | CategoryOption>;
|
|
233
|
+
categories?: Array<'github' | 'research' | 'pdf' | CategoryOption>;
|
|
234
234
|
limit?: number;
|
|
235
235
|
tbs?: string;
|
|
236
236
|
location?: string;
|
|
@@ -486,6 +486,7 @@ interface FirecrawlClientOptions {
|
|
|
486
486
|
*/
|
|
487
487
|
declare class FirecrawlClient {
|
|
488
488
|
private readonly http;
|
|
489
|
+
private isCloudService;
|
|
489
490
|
/**
|
|
490
491
|
* Create a v2 client.
|
|
491
492
|
* @param options Transport configuration (API key, base URL, timeouts, retries).
|
package/dist/index.d.ts
CHANGED
|
@@ -223,14 +223,14 @@ interface SearchData {
|
|
|
223
223
|
images?: Array<SearchResultImages | Document>;
|
|
224
224
|
}
|
|
225
225
|
interface CategoryOption {
|
|
226
|
-
type: 'github' | 'research';
|
|
226
|
+
type: 'github' | 'research' | 'pdf';
|
|
227
227
|
}
|
|
228
228
|
interface SearchRequest {
|
|
229
229
|
query: string;
|
|
230
230
|
sources?: Array<'web' | 'news' | 'images' | {
|
|
231
231
|
type: 'web' | 'news' | 'images';
|
|
232
232
|
}>;
|
|
233
|
-
categories?: Array<'github' | 'research' | CategoryOption>;
|
|
233
|
+
categories?: Array<'github' | 'research' | 'pdf' | CategoryOption>;
|
|
234
234
|
limit?: number;
|
|
235
235
|
tbs?: string;
|
|
236
236
|
location?: string;
|
|
@@ -486,6 +486,7 @@ interface FirecrawlClientOptions {
|
|
|
486
486
|
*/
|
|
487
487
|
declare class FirecrawlClient {
|
|
488
488
|
private readonly http;
|
|
489
|
+
private isCloudService;
|
|
489
490
|
/**
|
|
490
491
|
* Create a v2 client.
|
|
491
492
|
* @param options Transport configuration (API key, base URL, timeouts, retries).
|
package/dist/index.js
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
import {
|
|
2
2
|
require_package
|
|
3
|
-
} from "./chunk-
|
|
3
|
+
} from "./chunk-J3BEBX3Y.js";
|
|
4
4
|
|
|
5
5
|
// src/v2/utils/httpClient.ts
|
|
6
6
|
import axios from "axios";
|
|
@@ -837,6 +837,9 @@ var Watcher = class extends EventEmitter {
|
|
|
837
837
|
import "zod";
|
|
838
838
|
var FirecrawlClient = class {
|
|
839
839
|
http;
|
|
840
|
+
isCloudService(url) {
|
|
841
|
+
return url.includes("api.firecrawl.dev");
|
|
842
|
+
}
|
|
840
843
|
/**
|
|
841
844
|
* Create a v2 client.
|
|
842
845
|
* @param options Transport configuration (API key, base URL, timeouts, retries).
|
|
@@ -844,8 +847,8 @@ var FirecrawlClient = class {
|
|
|
844
847
|
constructor(options = {}) {
|
|
845
848
|
const apiKey = options.apiKey ?? process.env.FIRECRAWL_API_KEY ?? "";
|
|
846
849
|
const apiUrl = (options.apiUrl ?? process.env.FIRECRAWL_API_URL ?? "https://api.firecrawl.dev").replace(/\/$/, "");
|
|
847
|
-
if (!apiKey) {
|
|
848
|
-
throw new Error("API key is required. Set FIRECRAWL_API_KEY env or pass apiKey.");
|
|
850
|
+
if (this.isCloudService(apiUrl) && !apiKey) {
|
|
851
|
+
throw new Error("API key is required for the cloud API. Set FIRECRAWL_API_KEY env or pass apiKey.");
|
|
849
852
|
}
|
|
850
853
|
this.http = new HttpClient({
|
|
851
854
|
apiKey,
|
|
@@ -1068,7 +1071,7 @@ var FirecrawlApp = class {
|
|
|
1068
1071
|
if (typeof process !== "undefined" && process.env && process.env.npm_package_version) {
|
|
1069
1072
|
return process.env.npm_package_version;
|
|
1070
1073
|
}
|
|
1071
|
-
const packageJson = await import("./package-
|
|
1074
|
+
const packageJson = await import("./package-SYKCM5JT.js");
|
|
1072
1075
|
return packageJson.default.version;
|
|
1073
1076
|
} catch (error) {
|
|
1074
1077
|
const isTest = typeof process !== "undefined" && (process.env.JEST_WORKER_ID != null || false);
|
package/package.json
CHANGED
|
@@ -36,7 +36,7 @@ describe('FirecrawlApp E2E Tests', () => {
|
|
|
36
36
|
test.concurrent('should throw error for blocklisted URL on scrape', async () => {
|
|
37
37
|
const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
|
|
38
38
|
const blocklistedUrl = "https://facebook.com/fake-test";
|
|
39
|
-
await expect(app.scrapeUrl(blocklistedUrl)).rejects.toThrow("This website is
|
|
39
|
+
await expect(app.scrapeUrl(blocklistedUrl)).rejects.toThrow("This website is not currently supported");
|
|
40
40
|
});
|
|
41
41
|
|
|
42
42
|
test.concurrent('should return successful response for valid scrape', async () => {
|
|
@@ -52,13 +52,13 @@ describe('FirecrawlApp E2E Tests', () => {
|
|
|
52
52
|
const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
|
|
53
53
|
const response = await app.scrapeUrl(
|
|
54
54
|
'https://roastmywebsite.ai', {
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
55
|
+
formats: ['markdown', 'html', 'rawHtml', 'screenshot', 'links'],
|
|
56
|
+
headers: { "x-key": "test" },
|
|
57
|
+
includeTags: ['h1'],
|
|
58
|
+
excludeTags: ['h2'],
|
|
59
|
+
onlyMainContent: true,
|
|
60
|
+
timeout: 30000,
|
|
61
|
+
waitFor: 1000
|
|
62
62
|
});
|
|
63
63
|
|
|
64
64
|
if (!response.success) {
|
|
@@ -70,7 +70,7 @@ describe('FirecrawlApp E2E Tests', () => {
|
|
|
70
70
|
const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
|
|
71
71
|
const response = await app.scrapeUrl(
|
|
72
72
|
'https://roastmywebsite.ai', {
|
|
73
|
-
|
|
73
|
+
formats: ['screenshot@fullPage'],
|
|
74
74
|
});
|
|
75
75
|
if (!response.success) {
|
|
76
76
|
throw new Error(response.error);
|
|
@@ -149,7 +149,7 @@ describe('FirecrawlApp E2E Tests', () => {
|
|
|
149
149
|
}
|
|
150
150
|
}, 60000); // 60 seconds timeout
|
|
151
151
|
|
|
152
|
-
test.concurrent('should return successful response for crawl with options and wait for completion', async () => {
|
|
152
|
+
test.concurrent('should return successful response for crawl with options and wait for completion', async () => {
|
|
153
153
|
const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
|
|
154
154
|
const response = await app.crawlUrl('https://roastmywebsite.ai', {
|
|
155
155
|
excludePaths: ['blog/*'],
|
|
@@ -192,7 +192,7 @@ describe('FirecrawlApp E2E Tests', () => {
|
|
|
192
192
|
|
|
193
193
|
test.concurrent('should check crawl status', async () => {
|
|
194
194
|
const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
|
|
195
|
-
const response = await app.asyncCrawlUrl('https://firecrawl.dev', { limit: 20, scrapeOptions: { formats: ['markdown', 'html', 'rawHtml', 'screenshot', 'links']}} as CrawlParams) as CrawlResponse;
|
|
195
|
+
const response = await app.asyncCrawlUrl('https://firecrawl.dev', { limit: 20, scrapeOptions: { formats: ['markdown', 'html', 'rawHtml', 'screenshot', 'links'] } } as CrawlParams) as CrawlResponse;
|
|
196
196
|
expect(response).not.toBeNull();
|
|
197
197
|
expect(response.id).toBeDefined();
|
|
198
198
|
|
|
@@ -250,16 +250,16 @@ describe('FirecrawlApp E2E Tests', () => {
|
|
|
250
250
|
});
|
|
251
251
|
|
|
252
252
|
test.concurrent('should return successful response for valid map', async () => {
|
|
253
|
-
const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL });
|
|
253
|
+
const app = new FirecrawlApp({ apiKey: TEST_API_KEY, apiUrl: API_URL }); const response = await app.mapUrl('https://roastmywebsite.ai') as MapResponse;
|
|
254
254
|
expect(response).not.toBeNull();
|
|
255
|
-
|
|
255
|
+
|
|
256
256
|
expect(response.links?.length).toBeGreaterThan(0);
|
|
257
257
|
expect(response.links?.[0]).toContain("https://");
|
|
258
258
|
const filteredLinks = response.links?.filter((link: string) => link.includes("roastmywebsite.ai"));
|
|
259
259
|
expect(filteredLinks?.length).toBeGreaterThan(0);
|
|
260
260
|
}, 30000); // 30 seconds timeout
|
|
261
261
|
|
|
262
|
-
|
|
262
|
+
|
|
263
263
|
|
|
264
264
|
test('should search with string query', async () => {
|
|
265
265
|
const app = new FirecrawlApp({ apiUrl: API_URL, apiKey: TEST_API_KEY });
|
package/src/v2/client.ts
CHANGED
|
@@ -72,9 +72,14 @@ export interface FirecrawlClientOptions {
|
|
|
72
72
|
/**
|
|
73
73
|
* Firecrawl v2 client. Provides typed access to all v2 endpoints and utilities.
|
|
74
74
|
*/
|
|
75
|
+
|
|
75
76
|
export class FirecrawlClient {
|
|
76
77
|
private readonly http: HttpClient;
|
|
77
78
|
|
|
79
|
+
private isCloudService(url: string): boolean {
|
|
80
|
+
return url.includes('api.firecrawl.dev');
|
|
81
|
+
}
|
|
82
|
+
|
|
78
83
|
/**
|
|
79
84
|
* Create a v2 client.
|
|
80
85
|
* @param options Transport configuration (API key, base URL, timeouts, retries).
|
|
@@ -82,9 +87,11 @@ export class FirecrawlClient {
|
|
|
82
87
|
constructor(options: FirecrawlClientOptions = {}) {
|
|
83
88
|
const apiKey = options.apiKey ?? process.env.FIRECRAWL_API_KEY ?? "";
|
|
84
89
|
const apiUrl = (options.apiUrl ?? process.env.FIRECRAWL_API_URL ?? "https://api.firecrawl.dev").replace(/\/$/, "");
|
|
85
|
-
|
|
86
|
-
|
|
90
|
+
|
|
91
|
+
if (this.isCloudService(apiUrl) && !apiKey) {
|
|
92
|
+
throw new Error("API key is required for the cloud API. Set FIRECRAWL_API_KEY env or pass apiKey.");
|
|
87
93
|
}
|
|
94
|
+
|
|
88
95
|
this.http = new HttpClient({
|
|
89
96
|
apiKey,
|
|
90
97
|
apiUrl,
|
package/src/v2/types.ts
CHANGED
|
@@ -286,7 +286,7 @@ export interface SearchData {
|
|
|
286
286
|
}
|
|
287
287
|
|
|
288
288
|
export interface CategoryOption {
|
|
289
|
-
type: 'github' | 'research';
|
|
289
|
+
type: 'github' | 'research' | 'pdf';
|
|
290
290
|
}
|
|
291
291
|
|
|
292
292
|
export interface SearchRequest {
|
|
@@ -294,7 +294,7 @@ export interface SearchRequest {
|
|
|
294
294
|
sources?: Array<
|
|
295
295
|
'web' | 'news' | 'images' | { type: 'web' | 'news' | 'images' }
|
|
296
296
|
>;
|
|
297
|
-
categories?: Array<'github' | 'research' | CategoryOption>;
|
|
297
|
+
categories?: Array<'github' | 'research' | 'pdf' | CategoryOption>;
|
|
298
298
|
limit?: number;
|
|
299
299
|
tbs?: string;
|
|
300
300
|
location?: string;
|