n8n-nodes-firecrawl-latest 1.0.0

package/dist/nodes/Firecrawl/resources/extract/extract.properties.js

@@ -0,0 +1,339 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.extractProperties = void 0;
+// Fields for the Extract resource
+const extractFields = [
+    {
+        displayName: 'URL(s)',
+        name: 'urls',
+        type: 'string',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+            },
+        },
+        default: '',
+        required: true,
+        description: 'The URL(s) to extract data from. For multiple URLs, use comma-separated values or JSON array format. You can use wildcards (e.g., "https://example.com/*") to crawl all pages within a domain.',
+        placeholder: 'https://example.com or https://example.com/* or [https://example1.com, https://example2.com]',
+    },
+    {
+        displayName: 'Version',
+        name: 'version',
+        type: 'options',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+            },
+        },
+        options: [
+            {
+                name: 'V1 (Original)',
+                value: 'v1',
+                description: 'Use the original extract endpoint',
+            },
+            {
+                name: 'V2 (New with FIRE-1)',
+                value: 'v2',
+                description: 'Use the new extract v2 with FIRE-1 agent integration',
+            },
+        ],
+        default: 'v1',
+        description: 'The extraction API version to use',
+    },
+    {
+        displayName: 'Extraction Method',
+        name: 'extractionMethod',
+        type: 'options',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+            },
+        },
+        options: [
+            {
+                name: 'Simple Extraction',
+                value: 'simple',
+                description: 'Extract data using a prompt',
+            },
+            {
+                name: 'Schema Based Extraction',
+                value: 'schema',
+                description: 'Extract data using a defined schema',
+            },
+        ],
+        default: 'simple',
+        description: 'The method to use for extraction',
+    },
+    {
+        displayName: 'Extraction Prompt',
+        name: 'extractionPrompt',
+        type: 'string',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                extractionMethod: ['simple'],
+            },
+        },
+        default: '',
+        required: true,
+        description: 'The prompt to guide the extraction process (e.g., "Extract the company mission from the page")',
+        placeholder: 'Extract the main content from this website',
+    },
+    {
+        displayName: 'System Prompt',
+        name: 'systemPrompt',
+        type: 'string',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                extractionMethod: ['simple', 'schema'],
+            },
+        },
+        default: '',
+        description: 'Optional system prompt to provide additional context for the extraction',
+        placeholder: 'You are a data extraction assistant that extracts specific information from web content.',
+    },
+    {
+        displayName: 'Schema Definition Type',
+        name: 'schemaDefinitionType',
+        type: 'options',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                extractionMethod: ['schema'],
+            },
+        },
+        options: [
+            {
+                name: 'Generate From JSON Example',
+                value: 'example',
+                description: 'Generate schema from a JSON example',
+            },
+            {
+                name: 'Define Below',
+                value: 'manual',
+                description: 'Define schema manually in JSON Schema format',
+            },
+        ],
+        default: 'manual',
+        description: 'How to define the schema for extraction',
+    },
+    {
+        displayName: 'Extraction Prompt for Schema',
+        name: 'schemaPrompt',
+        type: 'string',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                extractionMethod: ['schema'],
+            },
+        },
+        default: '',
+        description: 'Optional prompt to guide the schema-based extraction process',
+        placeholder: 'Extract the structured data according to the provided schema',
+    },
+    {
+        displayName: 'JSON Example',
+        name: 'jsonExample',
+        type: 'json',
+        typeOptions: {
+            alwaysOpenEditWindow: true,
+            rows: 8,
+        },
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                extractionMethod: ['schema'],
+                schemaDefinitionType: ['example'],
+            },
+        },
+        default: '{\n  "company_mission": "Our mission is to...",\n  "supports_sso": true,\n  "is_open_source": false,\n  "links": ["https://example.com/docs", "https://example.com/about"]\n}',
+        description: 'A JSON example that represents the data structure you want to extract',
+        hint: 'Provide a JSON object that represents the structure you want to extract',
+    },
+    {
+        displayName: 'Schema Definition',
+        name: 'schemaDefinition',
+        type: 'json',
+        typeOptions: {
+            alwaysOpenEditWindow: true,
+            rows: 12,
+        },
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                extractionMethod: ['schema'],
+                schemaDefinitionType: ['manual'],
+            },
+        },
+        default: '{\n  "type": "object",\n  "properties": {\n    "company_mission": {\n      "type": "string",\n      "description": "The mission statement of the company"\n    },\n    "supports_sso": {\n      "type": "boolean",\n      "description": "Whether the product supports Single Sign-On"\n    },\n    "is_open_source": {\n      "type": "boolean",\n      "description": "Whether the product is open source"\n    },\n    "links": {\n      "type": "array",\n      "items": {\n        "type": "string"\n      },\n      "description": "Important links found on the page"\n    }\n  },\n  "required": ["company_mission"]\n}',
+        description: 'The schema definition in standard JSON Schema format. Define the structure you want to extract.',
+        hint: 'Use standard JSON Schema format with "type", "properties", and optional "required" fields',
+    },
+    {
+        displayName: 'Operation Mode',
+        name: 'operationMode',
+        type: 'options',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+            },
+        },
+        options: [
+            {
+                name: 'Single',
+                value: 'single',
+                description: 'Extract from a single URL at a time',
+            },
+            {
+                name: 'Batch',
+                value: 'batch',
+                description: 'Extract from multiple URLs in batch mode',
+            },
+            {
+                name: 'URL-Less',
+                value: 'urlless',
+                description: 'Extract data without providing specific URLs (search-based)',
+            },
+        ],
+        default: 'single',
+        description: 'The operation mode for extraction',
+    },
+    {
+        displayName: 'Use Asynchronous Mode',
+        name: 'useAsyncMode',
+        type: 'boolean',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                operationMode: ['batch', 'single'],
+            },
+        },
+        default: false,
+        description: 'Whether to process the extraction asynchronously for larger batches',
+    },
+    {
+        displayName: 'Job ID',
+        name: 'jobId',
+        type: 'string',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                operationMode: ['batch', 'single'],
+                useAsyncMode: [true],
+            },
+        },
+        default: '',
+        description: 'Job ID for checking the status of an existing extraction job (leave empty to start a new job)',
+    },
+    {
+        displayName: 'Enable Web Search',
+        name: 'enableWebSearch',
+        type: 'boolean',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+            },
+        },
+        default: false,
+        description: 'Whether to enable web search to follow links outside the specified domain for better context',
+    },
+    {
+        displayName: 'Use FIRE-1 Agent',
+        name: 'useFire1Agent',
+        type: 'boolean',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                version: ['v2'],
+            },
+        },
+        default: true,
+        description: 'Whether to use the FIRE-1 agent for advanced extraction capabilities',
+    },
+    {
+        displayName: 'Enable Page Actions',
+        name: 'enablePageActions',
+        type: 'boolean',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                version: ['v2'],
+                useFire1Agent: [true],
+            },
+        },
+        default: false,
+        description: 'Whether to define specific page actions for the FIRE-1 agent to perform',
+    },
+    {
+        displayName: 'Page Actions',
+        name: 'pageActions',
+        type: 'json',
+        typeOptions: {
+            alwaysOpenEditWindow: true,
+            rows: 10,
+        },
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                version: ['v2'],
+                useFire1Agent: [true],
+                enablePageActions: [true],
+            },
+        },
+        default: '[\n  { "type": "wait", "milliseconds": 2000 },\n  { "type": "click", "selector": "button.accept-cookies" },\n  { "type": "wait", "milliseconds": 1000 }\n]',
+        description: 'Define specific actions for the FIRE-1 agent to perform on pages',
+    },
+    {
+        displayName: 'Track Changes',
+        name: 'trackChanges',
+        type: 'boolean',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+            },
+        },
+        default: false,
+        description: 'Whether to track changes between the current extraction and previous ones',
+    },
+    {
+        displayName: 'Change Tracking Mode',
+        name: 'changeTrackingMode',
+        type: 'multiOptions',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+                trackChanges: [true],
+            },
+        },
+        options: [
+            {
+                name: 'Git-Diff',
+                value: 'git-diff',
+                description: 'Track changes using Git-style diff format',
+            },
+            {
+                name: 'JSON',
+                value: 'json',
+                description: 'Track changes in structured JSON format',
+            },
+        ],
+        default: ['git-diff'],
+        description: 'The modes to use for change tracking',
+    },
+    {
+        displayName: 'Enable Debug Logs',
+        name: 'enableDebugLogs',
+        type: 'boolean',
+        displayOptions: {
+            show: {
+                resource: ['extract'],
+            },
+        },
+        default: false,
+        description: 'Whether to enable debug logs in the output',
+    },
+];
+// Export all properties for the Extract resource
+exports.extractProperties = [...extractFields];

package/dist/nodes/Firecrawl/resources/llmsText/llmsText.methods.js

@@ -0,0 +1,124 @@
+"use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.llmsTextMethods = void 0;
+const firecrawl_js_1 = __importDefault(require("@mendable/firecrawl-js"));
+const n8n_workflow_1 = require("n8n-workflow");
+exports.llmsTextMethods = {
+    async execute() {
+        const items = this.getInputData();
+        const returnData = [];
+        // Get credentials
+        const credentials = await this.getCredentials('firecrawlApi');
+        const apiKey = credentials.apiKey;
+        // Initialize Firecrawl app
+        const firecrawl = new firecrawl_js_1.default({ apiKey });
+        // Process each item
+        for (let i = 0; i < items.length; i++) {
+            try {
+                // Get parameters
+                const url = this.getNodeParameter('url', i);
+                const maxUrls = this.getNodeParameter('maxUrls', i, 10);
+                const showFullText = this.getNodeParameter('showFullText', i, false);
+                const operationMode = this.getNodeParameter('operationMode', i);
+                // Prepare parameters for the API call
+                const params = {
+                    maxUrls,
+                    showFullText,
+                };
+                // Handle different operation modes
+                if (operationMode === 'sync') {
+                    // Synchronous mode - wait for the generation to complete
+                    const results = await firecrawl.generateLLMsText(url, params);
+                    if (!results.success && 'error' in results) {
+                        returnData.push({
+                            json: {
+                                success: false,
+                                error: results.error,
+                            },
+                        });
+                    }
+                    else {
+                        returnData.push({
+                            json: {
+                                success: results.success,
+                                status: 'status' in results ? results.status : 'completed',
+                                data: 'data' in results ? results.data : undefined,
+                                expiresAt: 'expiresAt' in results ? results.expiresAt : undefined,
+                            },
+                        });
+                    }
+                }
+                else {
+                    // Asynchronous mode - start the process or check status
+                    const jobId = this.getNodeParameter('jobId', i, '');
+                    if (jobId && jobId.trim() !== '') {
+                        // Check status of an existing job
+                        const status = await firecrawl.checkGenerateLLMsTextStatus(jobId);
+                        if (!status.success && 'error' in status) {
+                            returnData.push({
+                                json: {
+                                    success: false,
+                                    error: status.error,
+                                    jobId,
+                                },
+                            });
+                        }
+                        else {
+                            returnData.push({
+                                json: {
+                                    success: status.success,
+                                    status: 'status' in status ? status.status : 'unknown',
+                                    data: 'data' in status ? status.data : undefined,
+                                    expiresAt: 'expiresAt' in status ? status.expiresAt : undefined,
+                                    jobId,
+                                },
+                            });
+                        }
+                    }
+                    else {
+                        // Start a new asynchronous job
+                        const job = await firecrawl.asyncGenerateLLMsText(url, params);
+                        if (!job.success && 'error' in job) {
+                            returnData.push({
+                                json: {
+                                    success: false,
+                                    error: job.error,
+                                },
+                            });
+                        }
+                        else {
+                            returnData.push({
+                                json: {
+                                    success: true,
+                                    status: 'started',
+                                    jobId: 'jobId' in job ? job.jobId : undefined,
+                                    message: 'LLMs.txt generation started successfully. Use the job ID to check status.',
+                                },
+                            });
+                        }
+                    }
+                }
+            }
+            catch (error) {
+                const errorMessage = error instanceof Error ? error.message : String(error);
+                console.error('LLMs.txt generation error:', errorMessage);
+                if (this.continueOnFail()) {
+                    returnData.push({
+                        json: {
+                            success: false,
+                            error: errorMessage,
+                        },
+                    });
+                    continue;
+                }
+                throw new n8n_workflow_1.NodeOperationError(this.getNode(), error, {
+                    itemIndex: i,
+                });
+            }
+        }
+        return [returnData];
+    },
+};

package/dist/nodes/Firecrawl/resources/llmsText/llmsText.properties.js

@@ -0,0 +1,87 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.llmsTextProperties = void 0;
+// Fields for the LLMsText resource
+const llmsTextFields = [
+    {
+        displayName: 'URL',
+        name: 'url',
+        type: 'string',
+        displayOptions: {
+            show: {
+                resource: ['llmsText'],
+            },
+        },
+        default: '',
+        required: true,
+        description: 'The URL to generate LLMs.txt files from',
+        placeholder: 'https://example.com',
+    },
+    {
+        displayName: 'Max URLs',
+        name: 'maxUrls',
+        type: 'number',
+        typeOptions: {
+            minValue: 1,
+            maxValue: 100,
+        },
+        displayOptions: {
+            show: {
+                resource: ['llmsText'],
+            },
+        },
+        default: 10,
+        description: 'Maximum number of pages to crawl (1-100)',
+    },
+    {
+        displayName: 'Generate Full Text',
+        name: 'showFullText',
+        type: 'boolean',
+        displayOptions: {
+            show: {
+                resource: ['llmsText'],
+            },
+        },
+        default: false,
+        description: 'Whether to generate llms-full.txt in addition to llms.txt',
+    },
+    {
+        displayName: 'Operation Mode',
+        name: 'operationMode',
+        type: 'options',
+        displayOptions: {
+            show: {
+                resource: ['llmsText'],
+            },
+        },
+        options: [
+            {
+                name: 'Synchronous',
+                value: 'sync',
+                description: 'Wait for the generation to complete (suitable for small websites)',
+            },
+            {
+                name: 'Asynchronous',
+                value: 'async',
+                description: 'Start the generation process and return the job ID (suitable for larger websites)',
+            },
+        ],
+        default: 'sync',
+        description: 'Whether to wait for the generation to complete or just start the process',
+    },
+    {
+        displayName: 'Job ID',
+        name: 'jobId',
+        type: 'string',
+        displayOptions: {
+            show: {
+                resource: ['llmsText'],
+                operationMode: ['async'],
+            },
+        },
+        default: '',
+        description: 'Job ID for checking the status of an existing LLMs.txt generation (leave empty to start a new job)',
+    },
+];
+// Export all properties for the LLMsText resource
+exports.llmsTextProperties = [...llmsTextFields];

package/dist/nodes/Firecrawl/resources/map/map.methods.js

@@ -0,0 +1,52 @@
+"use strict";
+var __importDefault = (this && this.__importDefault) || function (mod) {
+    return (mod && mod.__esModule) ? mod : { "default": mod };
+};
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.mapMethods = void 0;
+const firecrawl_js_1 = __importDefault(require("@mendable/firecrawl-js"));
+const n8n_workflow_1 = require("n8n-workflow");
+exports.mapMethods = {
+    async execute() {
+        const items = this.getInputData();
+        const returnData = [];
+        // Get credentials
+        const credentials = await this.getCredentials('firecrawlApi');
+        const apiKey = credentials.apiKey;
+        // Initialize Firecrawl app
+        const firecrawl = new firecrawl_js_1.default({ apiKey });
+        // Process each item
+        for (let i = 0; i < items.length; i++) {
+            try {
+                // Get parameters
+                const url = this.getNodeParameter('url', i);
+                // Prepare map parameters
+                const mapParams = {};
+                // Map URL
+                const mapResponse = await firecrawl.mapUrl(url, mapParams);
+                // Add result to return data
+                returnData.push({
+                    json: {
+                        success: true,
+                        data: mapResponse,
+                    },
+                });
+            }
+            catch (error) {
+                if (this.continueOnFail()) {
+                    returnData.push({
+                        json: {
+                            success: false,
+                            error: error instanceof Error ? error.message : String(error),
+                        },
+                    });
+                    continue;
+                }
+                throw new n8n_workflow_1.NodeOperationError(this.getNode(), error, {
+                    itemIndex: i,
+                });
+            }
+        }
+        return [returnData];
+    },
+};

package/dist/nodes/Firecrawl/resources/map/map.properties.js

@@ -0,0 +1,22 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.mapProperties = void 0;
+// Fields for the Map resource
+const mapFields = [
+    {
+        displayName: 'URL',
+        name: 'url',
+        type: 'string',
+        displayOptions: {
+            show: {
+                resource: ['map'],
+            },
+        },
+        default: '',
+        required: true,
+        description: 'The starting URL to map',
+        placeholder: 'https://example.com',
+    },
+];
+// Export all properties for the Map resource
+exports.mapProperties = [...mapFields];