n8n-nodes-firecrawl-latest 1.0.0

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.
Files changed (24) hide show
  1. package/LICENSE.md +19 -0
  2. package/README.md +232 -0
  3. package/dist/credentials/FirecrawlApi.credentials.js +22 -0
  4. package/dist/icons/flames-icon.svg +144 -0
  5. package/dist/nodes/Firecrawl/FireCrawlScraper.node.js +156 -0
  6. package/dist/nodes/Firecrawl/resources/batchScrape/batchScrape.methods.js +253 -0
  7. package/dist/nodes/Firecrawl/resources/batchScrape/batchScrape.properties.js +205 -0
  8. package/dist/nodes/Firecrawl/resources/crawler/crawler.methods.js +281 -0
  9. package/dist/nodes/Firecrawl/resources/crawler/crawler.properties.js +313 -0
  10. package/dist/nodes/Firecrawl/resources/deepResearch/deepResearch.methods.js +171 -0
  11. package/dist/nodes/Firecrawl/resources/deepResearch/deepResearch.properties.js +200 -0
  12. package/dist/nodes/Firecrawl/resources/extract/extract.methods.js +424 -0
  13. package/dist/nodes/Firecrawl/resources/extract/extract.properties.js +339 -0
  14. package/dist/nodes/Firecrawl/resources/llmsText/llmsText.methods.js +124 -0
  15. package/dist/nodes/Firecrawl/resources/llmsText/llmsText.properties.js +87 -0
  16. package/dist/nodes/Firecrawl/resources/map/map.methods.js +52 -0
  17. package/dist/nodes/Firecrawl/resources/map/map.properties.js +22 -0
  18. package/dist/nodes/Firecrawl/resources/scrape/scrape.methods.js +203 -0
  19. package/dist/nodes/Firecrawl/resources/scrape/scrape.properties.js +348 -0
  20. package/dist/nodes/HttpBin/HttpBin.node.js +59 -0
  21. package/dist/nodes/HttpBin/HttpVerbDescription.js +246 -0
  22. package/dist/nodes/HttpBin/httpbin.svg +18 -0
  23. package/index.js +7 -0
  24. package/package.json +58 -0
package/dist/nodes/Firecrawl/resources/extract/extract.methods.js ADDED
@@ -0,0 +1,424 @@
1
+ "use strict";
2
+ var __importDefault = (this && this.__importDefault) || function (mod) {
3
+ return (mod && mod.__esModule) ? mod : { "default": mod };
4
+ };
5
+ Object.defineProperty(exports, "__esModule", { value: true });
6
+ exports.extractMethods = void 0;
7
+ const firecrawl_js_1 = __importDefault(require("@mendable/firecrawl-js"));
8
+ const n8n_workflow_1 = require("n8n-workflow");
9
+ // Helper function to parse URLs input
10
+ function parseUrlsInput(urlsInput) {
11
+ if (!urlsInput)
12
+ return [];
13
+ // Check if input is already a JSON array
14
+ if (urlsInput.trim().startsWith('[') && urlsInput.trim().endsWith(']')) {
15
+ try {
16
+ const parsed = JSON.parse(urlsInput);
17
+ if (Array.isArray(parsed)) {
18
+ return parsed.map((url) => url.toString().trim());
19
+ }
20
+ }
21
+ catch (e) {
22
+ // If JSON parsing fails, continue with other methods
23
+ }
24
+ }
25
+ // Split by comma if it's a comma-separated list
26
+ if (urlsInput.includes(',')) {
27
+ return urlsInput.split(',').map((url) => url.trim());
28
+ }
29
+ // Single URL case
30
+ return [urlsInput.trim()];
31
+ }
32
+ // Helper function to generate schema from JSON example
33
+ function generateSchemaFromExample(jsonExample) {
34
+ if (jsonExample === null) {
35
+ return { type: 'null' };
36
+ }
37
+ if (typeof jsonExample === 'string') {
38
+ return { type: 'string' };
39
+ }
40
+ if (typeof jsonExample === 'number') {
41
+ return { type: 'number' };
42
+ }
43
+ if (typeof jsonExample === 'boolean') {
44
+ return { type: 'boolean' };
45
+ }
46
+ if (Array.isArray(jsonExample)) {
47
+ if (jsonExample.length === 0) {
48
+ return {
49
+ type: 'array',
50
+ items: { type: 'string' }, // Default to string items for empty arrays
51
+ };
52
+ }
53
+ // Use the first item as a sample for the items schema
54
+ const itemSchema = generateSchemaFromExample(jsonExample[0]);
55
+ return {
56
+ type: 'array',
57
+ items: itemSchema,
58
+ };
59
+ }
60
+ if (typeof jsonExample === 'object') {
61
+ const properties = {};
62
+ for (const [key, value] of Object.entries(jsonExample)) {
63
+ properties[key] = generateSchemaFromExample(value);
64
+ }
65
+ return {
66
+ type: 'object',
67
+ properties,
68
+ required: Object.keys(properties),
69
+ };
70
+ }
71
+ // Default fallback
72
+ return { type: 'string' };
73
+ }
74
+ exports.extractMethods = {
75
+ async execute() {
76
+ const items = this.getInputData();
77
+ const returnData = [];
78
+ // Get credentials
79
+ const credentials = await this.getCredentials('firecrawlApi');
80
+ const apiKey = credentials.apiKey;
81
+ // Initialize Firecrawl app
82
+ const firecrawl = new firecrawl_js_1.default({ apiKey });
83
+ // Process each item
84
+ for (let i = 0; i < items.length; i++) {
85
+ try {
86
+ // Get API version
87
+ const version = this.getNodeParameter('version', i, 'v1');
88
+ const operationMode = this.getNodeParameter('operationMode', i);
89
+ const extractionMethod = this.getNodeParameter('extractionMethod', i);
90
+ const enableDebugLogs = this.getNodeParameter('enableDebugLogs', i, false);
91
+ const trackChanges = this.getNodeParameter('trackChanges', i, false);
92
+ // Get URLs (except for URL-less mode)
93
+ let urls = [];
94
+ if (operationMode !== 'urlless') {
95
+ const urlsInput = this.getNodeParameter('urls', i);
96
+ urls = parseUrlsInput(urlsInput);
97
+ if (urls.length === 0) {
98
+ throw new n8n_workflow_1.NodeOperationError(this.getNode(), 'No valid URLs provided', {
99
+ itemIndex: i,
100
+ });
101
+ }
102
+ }
103
+ // Optional parameters
104
+ const enableWebSearch = this.getNodeParameter('enableWebSearch', i, false);
105
+ // Create extraction options
106
+ const extractionOptions = {
107
+ enableWebSearch,
108
+ };
109
+ // Add change tracking options if enabled
110
+ if (trackChanges) {
111
+ const changeTrackingModes = this.getNodeParameter('changeTrackingMode', i, ['git-diff']);
112
+ extractionOptions.changeTracking = {
113
+ modes: changeTrackingModes,
114
+ };
115
+ }
116
+ // Handle extraction method
117
+ if (extractionMethod === 'simple') {
118
+ const extractionPrompt = this.getNodeParameter('extractionPrompt', i, '');
119
+ const systemPrompt = this.getNodeParameter('systemPrompt', i, '');
120
+ extractionOptions.prompt = extractionPrompt;
121
+ if (systemPrompt) {
122
+ extractionOptions.systemPrompt = systemPrompt;
123
+ }
124
+ }
125
+ else if (extractionMethod === 'schema') {
126
+ const schemaPrompt = this.getNodeParameter('schemaPrompt', i, '');
127
+ const systemPrompt = this.getNodeParameter('systemPrompt', i, '');
128
+ const schemaDefinitionType = this.getNodeParameter('schemaDefinitionType', i);
129
+ if (schemaPrompt) {
130
+ extractionOptions.prompt = schemaPrompt;
131
+ }
132
+ if (systemPrompt) {
133
+ extractionOptions.systemPrompt = systemPrompt;
134
+ }
135
+ let schema;
136
+ if (schemaDefinitionType === 'example') {
137
+ const jsonExample = JSON.parse(this.getNodeParameter('jsonExample', i));
138
+ schema = generateSchemaFromExample(jsonExample);
139
+ }
140
+ else {
141
+ // Manual schema definition
142
+ schema = JSON.parse(this.getNodeParameter('schemaDefinition', i));
143
+ }
144
+ extractionOptions.schema = schema;
145
+ }
146
+ // Add FIRE-1 agent options for v2
147
+ if (version === 'v2') {
148
+ const useFire1Agent = this.getNodeParameter('useFire1Agent', i, true);
149
+ if (useFire1Agent) {
150
+ extractionOptions.agent = {
151
+ model: 'FIRE-1',
152
+ };
153
+ // Check if page actions are enabled
154
+ const enablePageActions = this.getNodeParameter('enablePageActions', i, false);
155
+ if (enablePageActions) {
156
+ const pageActions = JSON.parse(this.getNodeParameter('pageActions', i, '[]'));
157
+ extractionOptions.agent.actions = pageActions;
158
+ }
159
+ }
160
+ }
161
+ // Log the extraction parameters if debug is enabled
162
+ if (enableDebugLogs) {
163
+ console.log('URLs:', urls);
164
+ console.log('Extraction options:', JSON.stringify(extractionOptions, null, 2));
165
+ }
166
+ // Handle different operation modes
167
+ if (operationMode === 'urlless') {
168
+ // URL-less extraction - use search-based extraction
169
+ // This fixes the error on line 195 by passing an object instead of using urls parameter
170
+ const extractionResult = await firecrawl.extract({
171
+ ...extractionOptions,
172
+ enableWebSearch: true, // Always enable web search for URL-less mode
173
+ });
174
+ // Log the results if debug is enabled
175
+ if (enableDebugLogs) {
176
+ console.log('Extraction results:', JSON.stringify(extractionResult, null, 2));
177
+ }
178
+ // Add results to return data
179
+ if (!extractionResult.success && 'error' in extractionResult) {
180
+ returnData.push({
181
+ json: {
182
+ success: false,
183
+ error: extractionResult.error,
184
+ debug: enableDebugLogs ? { options: extractionOptions } : undefined,
185
+ },
186
+ });
187
+ }
188
+ else {
189
+ returnData.push({
190
+ json: {
191
+ success: true,
192
+ data: 'data' in extractionResult ? extractionResult.data : undefined,
193
+ status: 'status' in extractionResult ? extractionResult.status : 'completed',
194
+ expiresAt: 'expiresAt' in extractionResult ? extractionResult.expiresAt : undefined,
195
+ debug: enableDebugLogs ? { options: extractionOptions } : undefined,
196
+ },
197
+ });
198
+ }
199
+ }
200
+ else if (operationMode === 'single' || urls.length === 1) {
201
+ // Check if using async mode
202
+ const useAsyncMode = this.getNodeParameter('useAsyncMode', i, false);
203
+ if (useAsyncMode) {
204
+ // Get job ID if provided
205
+ const jobId = this.getNodeParameter('jobId', i, '');
206
+ if (jobId && jobId.trim() !== '') {
207
+ // Check status of an existing job
208
+ const status = await firecrawl.getExtractStatus(jobId);
209
+ if (!status.success && 'error' in status) {
210
+ returnData.push({
211
+ json: {
212
+ success: false,
213
+ error: status.error,
214
+ jobId,
215
+ debug: enableDebugLogs ? { jobId } : undefined,
216
+ },
217
+ });
218
+ }
219
+ else {
220
+ returnData.push({
221
+ json: {
222
+ success: true,
223
+ status: 'status' in status ? status.status : 'unknown',
224
+ progress: 'progress' in status ? status.progress : undefined,
225
+ results: 'results' in status ? status.results : undefined,
226
+ jobId,
227
+ debug: enableDebugLogs ? { jobId } : undefined,
228
+ },
229
+ });
230
+ }
231
+ }
232
+ else {
233
+ // Start a new asynchronous job
234
+ // Use the appropriate endpoint based on version
235
+ let extractJob;
236
+ if (version === 'v2') {
237
+ extractJob = await firecrawl.asyncExtract(urls, {
238
+ ...extractionOptions,
239
+ v2: true,
240
+ });
241
+ }
242
+ else {
243
+ extractJob = await firecrawl.asyncExtract(urls, extractionOptions);
244
+ }
245
+ if (!extractJob.success && 'error' in extractJob) {
246
+ returnData.push({
247
+ json: {
248
+ success: false,
249
+ error: extractJob.error,
250
+ debug: enableDebugLogs ? { urls, options: extractionOptions } : undefined,
251
+ },
252
+ });
253
+ }
254
+ else {
255
+ returnData.push({
256
+ json: {
257
+ success: true,
258
+ status: 'started',
259
+ jobId: 'jobId' in extractJob ? extractJob.jobId : undefined,
260
+ message: 'Extraction started successfully. Use the job ID to check status.',
261
+ debug: enableDebugLogs ? { urls, options: extractionOptions } : undefined,
262
+ },
263
+ });
264
+ }
265
+ }
266
+ }
267
+ else {
268
+ // Synchronous extraction - wait for the result
269
+ // Use the appropriate endpoint based on version
270
+ let extractionResult;
271
+ if (version === 'v2') {
272
+ extractionResult = await firecrawl.extract(urls, {
273
+ ...extractionOptions,
274
+ v2: true,
275
+ });
276
+ }
277
+ else {
278
+ extractionResult = await firecrawl.extract(urls, extractionOptions);
279
+ }
280
+ if (!extractionResult.success && 'error' in extractionResult) {
281
+ returnData.push({
282
+ json: {
283
+ success: false,
284
+ error: extractionResult.error,
285
+ debug: enableDebugLogs ? { urls, options: extractionOptions } : undefined,
286
+ },
287
+ });
288
+ }
289
+ else {
290
+ returnData.push({
291
+ json: {
292
+ success: true,
293
+ data: 'data' in extractionResult ? extractionResult.data : undefined,
294
+ status: 'status' in extractionResult ? extractionResult.status : 'completed',
295
+ expiresAt: 'expiresAt' in extractionResult ? extractionResult.expiresAt : undefined,
296
+ debug: enableDebugLogs ? { urls, options: extractionOptions } : undefined,
297
+ },
298
+ });
299
+ }
300
+ }
301
+ }
302
+ else {
303
+ // Batch mode - check if async or sync is needed
304
+ const useAsyncMode = this.getNodeParameter('useAsyncMode', i, false);
305
+ if (useAsyncMode) {
306
+ // Get job ID if provided
307
+ const jobId = this.getNodeParameter('jobId', i, '');
308
+ if (jobId && jobId.trim() !== '') {
309
+ // Check status of an existing job
310
+ const status = await firecrawl.getExtractStatus(jobId);
311
+ if (!status.success && 'error' in status) {
312
+ returnData.push({
313
+ json: {
314
+ success: false,
315
+ error: status.error,
316
+ jobId,
317
+ debug: enableDebugLogs ? { jobId } : undefined,
318
+ },
319
+ });
320
+ }
321
+ else {
322
+ returnData.push({
323
+ json: {
324
+ success: true,
325
+ status: 'status' in status ? status.status : 'unknown',
326
+ progress: 'progress' in status ? status.progress : undefined,
327
+ results: 'results' in status ? status.results : undefined,
328
+ jobId,
329
+ debug: enableDebugLogs ? { jobId } : undefined,
330
+ },
331
+ });
332
+ }
333
+ }
334
+ else {
335
+ // Start a new asynchronous job
336
+ // Use the appropriate endpoint based on version
337
+ let extractJob;
338
+ if (version === 'v2') {
339
+ extractJob = await firecrawl.asyncExtract(urls, {
340
+ ...extractionOptions,
341
+ v2: true,
342
+ });
343
+ }
344
+ else {
345
+ extractJob = await firecrawl.asyncExtract(urls, extractionOptions);
346
+ }
347
+ if (!extractJob.success && 'error' in extractJob) {
348
+ returnData.push({
349
+ json: {
350
+ success: false,
351
+ error: extractJob.error,
352
+ debug: enableDebugLogs ? { urls, options: extractionOptions } : undefined,
353
+ },
354
+ });
355
+ }
356
+ else {
357
+ returnData.push({
358
+ json: {
359
+ success: true,
360
+ status: 'started',
361
+ jobId: 'jobId' in extractJob ? extractJob.jobId : undefined,
362
+ message: 'Extraction started successfully. Use the job ID to check status.',
363
+ debug: enableDebugLogs ? { urls, options: extractionOptions } : undefined,
364
+ },
365
+ });
366
+ }
367
+ }
368
+ }
369
+ else {
370
+ // Synchronous batch extraction - wait for all results
371
+ // Use the appropriate endpoint based on version
372
+ let extractionResult;
373
+ if (version === 'v2') {
374
+ extractionResult = await firecrawl.extract(urls, {
375
+ ...extractionOptions,
376
+ v2: true,
377
+ });
378
+ }
379
+ else {
380
+ extractionResult = await firecrawl.extract(urls, extractionOptions);
381
+ }
382
+ if (!extractionResult.success && 'error' in extractionResult) {
383
+ returnData.push({
384
+ json: {
385
+ success: false,
386
+ error: extractionResult.error,
387
+ debug: enableDebugLogs ? { urls, options: extractionOptions } : undefined,
388
+ },
389
+ });
390
+ }
391
+ else {
392
+ returnData.push({
393
+ json: {
394
+ success: true,
395
+ data: 'data' in extractionResult ? extractionResult.data : undefined,
396
+ status: 'status' in extractionResult ? extractionResult.status : 'completed',
397
+ expiresAt: 'expiresAt' in extractionResult ? extractionResult.expiresAt : undefined,
398
+ debug: enableDebugLogs ? { urls, options: extractionOptions } : undefined,
399
+ },
400
+ });
401
+ }
402
+ }
403
+ }
404
+ }
405
+ catch (error) {
406
+ const errorMessage = error instanceof Error ? error.message : String(error);
407
+ console.error('Extraction error:', errorMessage);
408
+ if (this.continueOnFail()) {
409
+ returnData.push({
410
+ json: {
411
+ success: false,
412
+ error: errorMessage,
413
+ },
414
+ });
415
+ continue;
416
+ }
417
+ throw new n8n_workflow_1.NodeOperationError(this.getNode(), error, {
418
+ itemIndex: i,
419
+ });
420
+ }
421
+ }
422
+ return [returnData];
423
+ },
424
+ };