AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-12 04:29:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Nick:

Browse Source
This commit is contained in:
Nicolas 2024-08-28 15:59:20 -03:00
parent 8be75accb8
commit 70bff7f8fb
4 changed files with 706 additions and 378 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

69
apps/api/src/lib/map-cosine.ts
View File

@ -1,35 +1,46 @@
import { Logger } from "./logger";
export function performCosineSimilarity(links: string[], searchQuery: string) {
// Function to calculate cosine similarity
const cosineSimilarity = (vec1: number[], vec2: number[]): number => {
const dotProduct = vec1.reduce((sum, val, i) => sum + val * vec2[i], 0);
const magnitude1 = Math.sqrt(vec1.reduce((sum, val) => sum + val * val, 0));
const magnitude2 = Math.sqrt(vec2.reduce((sum, val) => sum + val * val, 0));
if (magnitude1 === 0 || magnitude2 === 0) return 0;
return dotProduct / (magnitude1 * magnitude2);
};
try {
// Function to calculate cosine similarity
const cosineSimilarity = (vec1: number[], vec2: number[]): number => {
const dotProduct = vec1.reduce((sum, val, i) => sum + val * vec2[i], 0);
const magnitude1 = Math.sqrt(
vec1.reduce((sum, val) => sum + val * val, 0)
);
const magnitude2 = Math.sqrt(
vec2.reduce((sum, val) => sum + val * val, 0)
);
if (magnitude1 === 0 || magnitude2 === 0) return 0;
return dotProduct / (magnitude1 * magnitude2);
};
// Function to convert text to vector
const textToVector = (text: string): number[] => {
const words = searchQuery.toLowerCase().split(/\W+/);
return words.map((word) => {
const count = (text.toLowerCase().match(new RegExp(word, "g")) || [])
.length;
return count / text.length;
// Function to convert text to vector
const textToVector = (text: string): number[] => {
const words = searchQuery.toLowerCase().split(/\W+/);
return words.map((word) => {
const count = (text.toLowerCase().match(new RegExp(word, "g")) || [])
.length;
return count / text.length;
});
};
// Calculate similarity scores
const similarityScores = links.map((link) => {
const linkVector = textToVector(link);
const searchVector = textToVector(searchQuery);
return cosineSimilarity(linkVector, searchVector);
});
};
// Calculate similarity scores
const similarityScores = links.map((link) => {
const linkVector = textToVector(link);
const searchVector = textToVector(searchQuery);
return cosineSimilarity(linkVector, searchVector);
});
// Sort links based on similarity scores and print scores
const a = links
.map((link, index) => ({ link, score: similarityScores[index] }))
.sort((a, b) => b.score - a.score);
// Sort links based on similarity scores and print scores
const a = links
.map((link, index) => ({ link, score: similarityScores[index] }))
.sort((a, b) => b.score - a.score);
links = a.map((item) => item.link);
return links;
links = a.map((item) => item.link);
return links;
} catch (error) {
Logger.error(`Error performing cosine similarity: ${error}`);
return links;
}
}

363
apps/js-sdk/firecrawl/build/cjs/index.js
View File

@ -1,13 +1,4 @@
"use strict";
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
return new (P || (P = Promise))(function (resolve, reject) {
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
step((generator = generator.apply(thisArg, _arguments || [])).next());
});
};
var __importDefault = (this && this.__importDefault) || function (mod) {
return (mod && mod.__esModule) ? mod : { "default": mod };
};
@ -17,148 +8,179 @@ const zod_1 = require("zod");
const zod_to_json_schema_1 = require("zod-to-json-schema");
/**
* Main class for interacting with the Firecrawl API.
* Provides methods for scraping, searching, crawling, and mapping web content.
*/
class FirecrawlApp {
/**
* Initializes a new instance of the FirecrawlApp class.
* @param {FirecrawlAppConfig} config - Configuration options for the FirecrawlApp instance.
* @param config - Configuration options for the FirecrawlApp instance.
*/
constructor({ apiKey = null, apiUrl = null }) {
constructor({ apiKey = null, apiUrl = null, version = "v1" }) {
this.apiKey = apiKey || "";
this.apiUrl = apiUrl || "https://api.firecrawl.dev";
this.version = version;
if (!this.apiKey) {
throw new Error("No API key provided");
}
}
/**
* Scrapes a URL using the Firecrawl API.
* @param {string} url - The URL to scrape.
* @param {Params | null} params - Additional parameters for the scrape request.
* @returns {Promise<ScrapeResponse>} The response from the scrape operation.
* @param url - The URL to scrape.
* @param params - Additional parameters for the scrape request.
* @returns The response from the scrape operation.
*/
scrapeUrl(url_1) {
return __awaiter(this, arguments, void 0, function* (url, params = null) {
var _a;
const headers = {
"Content-Type": "application/json",
Authorization: `Bearer ${this.apiKey}`,
};
let jsonData = Object.assign({ url }, params);
if ((_a = params === null || params === void 0 ? void 0 : params.extractorOptions) === null || _a === void 0 ? void 0 : _a.extractionSchema) {
let schema = params.extractorOptions.extractionSchema;
// Check if schema is an instance of ZodSchema to correctly identify Zod schemas
if (schema instanceof zod_1.z.ZodSchema) {
schema = (0, zod_to_json_schema_1.zodToJsonSchema)(schema);
}
jsonData = Object.assign(Object.assign({}, jsonData), { extractorOptions: Object.assign(Object.assign({}, params.extractorOptions), { extractionSchema: schema, mode: params.extractorOptions.mode || "llm-extraction" }) });
async scrapeUrl(url, params) {
const headers = {
"Content-Type": "application/json",
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) {
schema = (0, zod_to_json_schema_1.zodToJsonSchema)(schema);
}
try {
const response = yield axios_1.default.post(this.apiUrl + "/v0/scrape", jsonData, { headers });
if (response.status === 200) {
const responseData = response.data;
if (responseData.success) {
return responseData;
}
else {
throw new Error(`Failed to scrape URL. Error: ${responseData.error}`);
}
jsonData = {
...jsonData,
extractorOptions: {
...jsonData.extractorOptions,
extractionSchema: schema,
mode: jsonData.extractorOptions.mode || "llm-extraction",
},
};
}
try {
const response = await axios_1.default.post(this.apiUrl + `/${this.version}/scrape`, jsonData, { headers });
if (response.status === 200) {
const responseData = response.data;
if (responseData.success) {
return (this.version === 'v0' ? responseData : {
success: true,
warning: responseData.warning,
error: responseData.error,
...responseData.data
});
}
else {
this.handleError(response, "scrape URL");
throw new Error(`Failed to scrape URL. Error: ${responseData.error}`);
}
}
catch (error) {
throw new Error(error.message);
else {
this.handleError(response, "scrape URL");
}
return { success: false, error: "Internal server error." };
});
}
catch (error) {
throw new Error(error.message);
}
return { success: false, error: "Internal server error." };
}
/**
* Searches for a query using the Firecrawl API.
* @param {string} query - The query to search for.
* @param {Params | null} params - Additional parameters for the search request.
* @returns {Promise<SearchResponse>} The response from the search operation.
* @param query - The query to search for.
* @param params - Additional parameters for the search request.
* @returns The response from the search operation.
*/
search(query_1) {
return __awaiter(this, arguments, void 0, function* (query, params = null) {
const headers = {
"Content-Type": "application/json",
Authorization: `Bearer ${this.apiKey}`,
};
let jsonData = { query };
if (params) {
jsonData = Object.assign(Object.assign({}, jsonData), params);
}
try {
const response = yield axios_1.default.post(this.apiUrl + "/v0/search", jsonData, { headers });
if (response.status === 200) {
const responseData = response.data;
if (responseData.success) {
return responseData;
}
else {
throw new Error(`Failed to search. Error: ${responseData.error}`);
}
async search(query, params) {
if (this.version === "v1") {
throw new Error("Search is not supported in v1, please update FirecrawlApp() initialization to use v0.");
}
const headers = {
"Content-Type": "application/json",
Authorization: `Bearer ${this.apiKey}`,
};
let jsonData = { query };
if (params) {
jsonData = { ...jsonData, ...params };
}
try {
const response = await axios_1.default.post(this.apiUrl + "/v0/search", jsonData, { headers });
if (response.status === 200) {
const responseData = response.data;
if (responseData.success) {
return responseData;
}
else {
this.handleError(response, "search");
throw new Error(`Failed to search. Error: ${responseData.error}`);
}
}
catch (error) {
throw new Error(error.message);
else {
this.handleError(response, "search");
}
return { success: false, error: "Internal server error." };
});
}
catch (error) {
throw new Error(error.message);
}
return { success: false, error: "Internal server error." };
}
/**
* Initiates a crawl job for a URL using the Firecrawl API.
* @param {string} url - The URL to crawl.
* @param {Params | null} params - Additional parameters for the crawl request.
* @param {boolean} waitUntilDone - Whether to wait for the crawl job to complete.
* @param {number} pollInterval - Time in seconds for job status checks.
* @param {string} idempotencyKey - Optional idempotency key for the request.
* @returns {Promise<CrawlResponse | any>} The response from the crawl operation.
* @param url - The URL to crawl.
* @param params - Additional parameters for the crawl request.
* @param waitUntilDone - Whether to wait for the crawl job to complete.
* @param pollInterval - Time in seconds for job status checks.
* @param idempotencyKey - Optional idempotency key for the request.
* @returns The response from the crawl operation.
*/
crawlUrl(url_1) {
return __awaiter(this, arguments, void 0, function* (url, params = null, waitUntilDone = true, pollInterval = 2, idempotencyKey) {
const headers = this.prepareHeaders(idempotencyKey);
let jsonData = { url };
if (params) {
jsonData = Object.assign(Object.assign({}, jsonData), params);
}
try {
const response = yield this.postRequest(this.apiUrl + "/v0/crawl", jsonData, headers);
if (response.status === 200) {
const jobId = response.data.jobId;
if (waitUntilDone) {
return this.monitorJobStatus(jobId, headers, pollInterval);
}
else {
return { success: true, jobId };
async crawlUrl(url, params, waitUntilDone = true, pollInterval = 2, idempotencyKey) {
const headers = this.prepareHeaders(idempotencyKey);
let jsonData = { url, ...params };
try {
const response = await this.postRequest(this.apiUrl + `/${this.version}/crawl`, jsonData, headers);
if (response.status === 200) {
const id = this.version === 'v0' ? response.data.jobId : response.data.id;
let checkUrl = undefined;
if (waitUntilDone) {
if (this.version === 'v1') {
checkUrl = response.data.url;
}
return this.monitorJobStatus(id, headers, pollInterval, checkUrl);
}
else {
this.handleError(response, "start crawl job");
if (this.version === 'v0') {
return {
success: true,
jobId: id
};
}
else {
return {
success: true,
id: id
};
}
}
}
catch (error) {
console.log(error);
else {
this.handleError(response, "start crawl job");
}
}
catch (error) {
if (error.response?.data?.error) {
throw new Error(`Request failed with status code ${error.response.status}. Error: ${error.response.data.error} ${error.response.data.details ? ` - ${JSON.stringify(error.response.data.details)}` : ''}`);
}
else {
throw new Error(error.message);
}
return { success: false, error: "Internal server error." };
});
}
return { success: false, error: "Internal server error." };
}
/**
* Checks the status of a crawl job using the Firecrawl API.
* @param {string} jobId - The job ID of the crawl operation.
* @returns {Promise<JobStatusResponse>} The response containing the job status.
* @param id - The ID of the crawl operation.
* @returns The response containing the job status.
*/
checkCrawlStatus(jobId) {
return __awaiter(this, void 0, void 0, function* () {
const headers = this.prepareHeaders();
try {
const response = yield this.getRequest(this.apiUrl + `/v0/crawl/status/${jobId}`, headers);
if (response.status === 200) {
async checkCrawlStatus(id) {
if (!id) {
throw new Error("No crawl ID provided");
}
const headers = this.prepareHeaders();
try {
const response = await this.getRequest(this.version === 'v1' ?
`${this.apiUrl}/${this.version}/crawl/${id}` :
`${this.apiUrl}/${this.version}/crawl/status/${id}`, headers);
if (response.status === 200) {
if (this.version === 'v0') {
return {
success: true,
status: response.data.status,
@ -173,13 +195,28 @@ class FirecrawlApp {
};
}
else {
this.handleError(response, "check crawl status");
return {
success: true,
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
};
}
}
catch (error) {
throw new Error(error.message);
else {
this.handleError(response, "check crawl status");
}
return {
}
catch (error) {
throw new Error(error.message);
}
return this.version === 'v0' ?
{
success: false,
status: "unknown",
current: 0,
@ -187,71 +224,103 @@ class FirecrawlApp {
current_step: "",
total: 0,
error: "Internal server error.",
} :
{
success: false,
error: "Internal server error.",
};
});
}
async mapUrl(url, params) {
if (this.version == 'v0') {
throw new Error("Map is not supported in v0");
}
const headers = this.prepareHeaders();
let jsonData = { url, ...params };
try {
const response = await this.postRequest(this.apiUrl + `/${this.version}/map`, jsonData, headers);
if (response.status === 200) {
return response.data;
}
else {
this.handleError(response, "map");
}
}
catch (error) {
throw new Error(error.message);
}
return { success: false, error: "Internal server error." };
}
/**
* Prepares the headers for an API request.
* @returns {AxiosRequestHeaders} The prepared headers.
* @param idempotencyKey - Optional key to ensure idempotency.
* @returns The prepared headers.
*/
prepareHeaders(idempotencyKey) {
return Object.assign({ "Content-Type": "application/json", Authorization: `Bearer ${this.apiKey}` }, (idempotencyKey ? { "x-idempotency-key": idempotencyKey } : {}));
return {
"Content-Type": "application/json",
Authorization: `Bearer ${this.apiKey}`,
...(idempotencyKey ? { "x-idempotency-key": idempotencyKey } : {}),
};
}
/**
* Sends a POST request to the specified URL.
* @param {string} url - The URL to send the request to.
* @param {Params} data - The data to send in the request.
* @param {AxiosRequestHeaders} headers - The headers for the request.
* @returns {Promise<AxiosResponse>} The response from the POST request.
* @param url - The URL to send the request to.
* @param data - The data to send in the request.
* @param headers - The headers for the request.
* @returns The response from the POST request.
*/
postRequest(url, data, headers) {
return axios_1.default.post(url, data, { headers });
}
/**
* Sends a GET request to the specified URL.
* @param {string} url - The URL to send the request to.
* @param {AxiosRequestHeaders} headers - The headers for the request.
* @returns {Promise<AxiosResponse>} The response from the GET request.
* @param url - The URL to send the request to.
* @param headers - The headers for the request.
* @returns The response from the GET request.
*/
getRequest(url, headers) {
return axios_1.default.get(url, { headers });
}
/**
* Monitors the status of a crawl job until completion or failure.
* @param {string} jobId - The job ID of the crawl operation.
* @param {AxiosRequestHeaders} headers - The headers for the request.
* @param {number} timeout - Timeout in seconds for job status checks.
* @returns {Promise<any>} The final job status or data.
* @param id - The ID of the crawl operation.
* @param headers - The headers for the request.
* @param checkInterval - Interval in seconds for job status checks.
* @param checkUrl - Optional URL to check the status (used for v1 API)
* @returns The final job status or data.
*/
monitorJobStatus(jobId, headers, checkInterval) {
return __awaiter(this, void 0, void 0, function* () {
while (true) {
const statusResponse = yield this.getRequest(this.apiUrl + `/v0/crawl/status/${jobId}`, headers);
if (statusResponse.status === 200) {
const statusData = statusResponse.data;
if (statusData.status === "completed") {
if ("data" in statusData) {
return statusData.data;
}
else {
throw new Error("Crawl job completed but no data was returned");
}
}
else if (["active", "paused", "pending", "queued"].includes(statusData.status)) {
if (checkInterval < 2) {
checkInterval = 2;
}
yield new Promise((resolve) => setTimeout(resolve, checkInterval * 1000)); // Wait for the specified timeout before checking again
async monitorJobStatus(id, headers, checkInterval, checkUrl) {
let apiUrl = '';
while (true) {
if (this.version === 'v1') {
apiUrl = checkUrl ?? `${this.apiUrl}/v1/crawl/${id}`;
}
else if (this.version === 'v0') {
apiUrl = `${this.apiUrl}/v0/crawl/status/${id}`;
}
const statusResponse = await this.getRequest(apiUrl, headers);
if (statusResponse.status === 200) {
const statusData = statusResponse.data;
if (statusData.status === "completed") {
if ("data" in statusData) {
return this.version === 'v0' ? statusData.data : statusData;
}
else {
throw new Error(`Crawl job failed or was stopped. Status: ${statusData.status}`);
throw new Error("Crawl job completed but no data was returned");
}
}
else if (["active", "paused", "pending", "queued", "scraping"].includes(statusData.status)) {
checkInterval = Math.max(checkInterval, 2);
await new Promise((resolve) => setTimeout(resolve, checkInterval * 1000));
}
else {
this.handleError(statusResponse, "check crawl status");
throw new Error(`Crawl job failed or was stopped. Status: ${statusData.status}`);
}
}
});
else {
this.handleError(statusResponse, "check crawl status");
}
}
}
/**
* Handles errors from API responses.

363
apps/js-sdk/firecrawl/build/esm/index.js
View File

@ -1,159 +1,181 @@
var __awaiter = (this && this.__awaiter) || function (thisArg, _arguments, P, generator) {
function adopt(value) { return value instanceof P ? value : new P(function (resolve) { resolve(value); }); }
return new (P || (P = Promise))(function (resolve, reject) {
function fulfilled(value) { try { step(generator.next(value)); } catch (e) { reject(e); } }
function rejected(value) { try { step(generator["throw"](value)); } catch (e) { reject(e); } }
function step(result) { result.done ? resolve(result.value) : adopt(result.value).then(fulfilled, rejected); }
step((generator = generator.apply(thisArg, _arguments || [])).next());
});
};
import axios from "axios";
import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";
/**
* Main class for interacting with the Firecrawl API.
* Provides methods for scraping, searching, crawling, and mapping web content.
*/
export default class FirecrawlApp {
/**
* Initializes a new instance of the FirecrawlApp class.
* @param {FirecrawlAppConfig} config - Configuration options for the FirecrawlApp instance.
* @param config - Configuration options for the FirecrawlApp instance.
*/
constructor({ apiKey = null, apiUrl = null }) {
constructor({ apiKey = null, apiUrl = null, version = "v1" }) {
this.apiKey = apiKey || "";
this.apiUrl = apiUrl || "https://api.firecrawl.dev";
this.version = version;
if (!this.apiKey) {
throw new Error("No API key provided");
}
}
/**
* Scrapes a URL using the Firecrawl API.
* @param {string} url - The URL to scrape.
* @param {Params | null} params - Additional parameters for the scrape request.
* @returns {Promise<ScrapeResponse>} The response from the scrape operation.
* @param url - The URL to scrape.
* @param params - Additional parameters for the scrape request.
* @returns The response from the scrape operation.
*/
scrapeUrl(url_1) {
return __awaiter(this, arguments, void 0, function* (url, params = null) {
var _a;
const headers = {
"Content-Type": "application/json",
Authorization: `Bearer ${this.apiKey}`,
};
let jsonData = Object.assign({ url }, params);
if ((_a = params === null || params === void 0 ? void 0 : params.extractorOptions) === null || _a === void 0 ? void 0 : _a.extractionSchema) {
let schema = params.extractorOptions.extractionSchema;
// Check if schema is an instance of ZodSchema to correctly identify Zod schemas
if (schema instanceof z.ZodSchema) {
schema = zodToJsonSchema(schema);
}
jsonData = Object.assign(Object.assign({}, jsonData), { extractorOptions: Object.assign(Object.assign({}, params.extractorOptions), { extractionSchema: schema, mode: params.extractorOptions.mode || "llm-extraction" }) });
async scrapeUrl(url, params) {
const headers = {
"Content-Type": "application/json",
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) {
schema = zodToJsonSchema(schema);
}
try {
const response = yield axios.post(this.apiUrl + "/v0/scrape", jsonData, { headers });
if (response.status === 200) {
const responseData = response.data;
if (responseData.success) {
return responseData;
}
else {
throw new Error(`Failed to scrape URL. Error: ${responseData.error}`);
}
jsonData = {
...jsonData,
extractorOptions: {
...jsonData.extractorOptions,
extractionSchema: schema,
mode: jsonData.extractorOptions.mode || "llm-extraction",
},
};
}
try {
const response = await axios.post(this.apiUrl + `/${this.version}/scrape`, jsonData, { headers });
if (response.status === 200) {
const responseData = response.data;
if (responseData.success) {
return (this.version === 'v0' ? responseData : {
success: true,
warning: responseData.warning,
error: responseData.error,
...responseData.data
});
}
else {
this.handleError(response, "scrape URL");
throw new Error(`Failed to scrape URL. Error: ${responseData.error}`);
}
}
catch (error) {
throw new Error(error.message);
else {
this.handleError(response, "scrape URL");
}
return { success: false, error: "Internal server error." };
});
}
catch (error) {
throw new Error(error.message);
}
return { success: false, error: "Internal server error." };
}
/**
* Searches for a query using the Firecrawl API.
* @param {string} query - The query to search for.
* @param {Params | null} params - Additional parameters for the search request.
* @returns {Promise<SearchResponse>} The response from the search operation.
* @param query - The query to search for.
* @param params - Additional parameters for the search request.
* @returns The response from the search operation.
*/
search(query_1) {
return __awaiter(this, arguments, void 0, function* (query, params = null) {
const headers = {
"Content-Type": "application/json",
Authorization: `Bearer ${this.apiKey}`,
};
let jsonData = { query };
if (params) {
jsonData = Object.assign(Object.assign({}, jsonData), params);
}
try {
const response = yield axios.post(this.apiUrl + "/v0/search", jsonData, { headers });
if (response.status === 200) {
const responseData = response.data;
if (responseData.success) {
return responseData;
}
else {
throw new Error(`Failed to search. Error: ${responseData.error}`);
}
async search(query, params) {
if (this.version === "v1") {
throw new Error("Search is not supported in v1, please update FirecrawlApp() initialization to use v0.");
}
const headers = {
"Content-Type": "application/json",
Authorization: `Bearer ${this.apiKey}`,
};
let jsonData = { query };
if (params) {
jsonData = { ...jsonData, ...params };
}
try {
const response = await axios.post(this.apiUrl + "/v0/search", jsonData, { headers });
if (response.status === 200) {
const responseData = response.data;
if (responseData.success) {
return responseData;
}
else {
this.handleError(response, "search");
throw new Error(`Failed to search. Error: ${responseData.error}`);
}
}
catch (error) {
throw new Error(error.message);
else {
this.handleError(response, "search");
}
return { success: false, error: "Internal server error." };
});
}
catch (error) {
throw new Error(error.message);
}
return { success: false, error: "Internal server error." };
}
/**
* Initiates a crawl job for a URL using the Firecrawl API.
* @param {string} url - The URL to crawl.
* @param {Params | null} params - Additional parameters for the crawl request.
* @param {boolean} waitUntilDone - Whether to wait for the crawl job to complete.
* @param {number} pollInterval - Time in seconds for job status checks.
* @param {string} idempotencyKey - Optional idempotency key for the request.
* @returns {Promise<CrawlResponse | any>} The response from the crawl operation.
* @param url - The URL to crawl.
* @param params - Additional parameters for the crawl request.
* @param waitUntilDone - Whether to wait for the crawl job to complete.
* @param pollInterval - Time in seconds for job status checks.
* @param idempotencyKey - Optional idempotency key for the request.
* @returns The response from the crawl operation.
*/
crawlUrl(url_1) {
return __awaiter(this, arguments, void 0, function* (url, params = null, waitUntilDone = true, pollInterval = 2, idempotencyKey) {
const headers = this.prepareHeaders(idempotencyKey);
let jsonData = { url };
if (params) {
jsonData = Object.assign(Object.assign({}, jsonData), params);
}
try {
const response = yield this.postRequest(this.apiUrl + "/v0/crawl", jsonData, headers);
if (response.status === 200) {
const jobId = response.data.jobId;
if (waitUntilDone) {
return this.monitorJobStatus(jobId, headers, pollInterval);
}
else {
return { success: true, jobId };
async crawlUrl(url, params, waitUntilDone = true, pollInterval = 2, idempotencyKey) {
const headers = this.prepareHeaders(idempotencyKey);
let jsonData = { url, ...params };
try {
const response = await this.postRequest(this.apiUrl + `/${this.version}/crawl`, jsonData, headers);
if (response.status === 200) {
const id = this.version === 'v0' ? response.data.jobId : response.data.id;
let checkUrl = undefined;
if (waitUntilDone) {
if (this.version === 'v1') {
checkUrl = response.data.url;
}
return this.monitorJobStatus(id, headers, pollInterval, checkUrl);
}
else {
this.handleError(response, "start crawl job");
if (this.version === 'v0') {
return {
success: true,
jobId: id
};
}
else {
return {
success: true,
id: id
};
}
}
}
catch (error) {
console.log(error);
else {
this.handleError(response, "start crawl job");
}
}
catch (error) {
if (error.response?.data?.error) {
throw new Error(`Request failed with status code ${error.response.status}. Error: ${error.response.data.error} ${error.response.data.details ? ` - ${JSON.stringify(error.response.data.details)}` : ''}`);
}
else {
throw new Error(error.message);
}
return { success: false, error: "Internal server error." };
});
}
return { success: false, error: "Internal server error." };
}
/**
* Checks the status of a crawl job using the Firecrawl API.
* @param {string} jobId - The job ID of the crawl operation.
* @returns {Promise<JobStatusResponse>} The response containing the job status.
* @param id - The ID of the crawl operation.
* @returns The response containing the job status.
*/
checkCrawlStatus(jobId) {
return __awaiter(this, void 0, void 0, function* () {
const headers = this.prepareHeaders();
try {
const response = yield this.getRequest(this.apiUrl + `/v0/crawl/status/${jobId}`, headers);
if (response.status === 200) {
async checkCrawlStatus(id) {
if (!id) {
throw new Error("No crawl ID provided");
}
const headers = this.prepareHeaders();
try {
const response = await this.getRequest(this.version === 'v1' ?
`${this.apiUrl}/${this.version}/crawl/${id}` :
`${this.apiUrl}/${this.version}/crawl/status/${id}`, headers);
if (response.status === 200) {
if (this.version === 'v0') {
return {
success: true,
status: response.data.status,
@ -168,13 +190,28 @@ export default class FirecrawlApp {
};
}
else {
this.handleError(response, "check crawl status");
return {
success: true,
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
};
}
}
catch (error) {
throw new Error(error.message);
else {
this.handleError(response, "check crawl status");
}
return {
}
catch (error) {
throw new Error(error.message);
}
return this.version === 'v0' ?
{
success: false,
status: "unknown",
current: 0,
@ -182,71 +219,103 @@ export default class FirecrawlApp {
current_step: "",
total: 0,
error: "Internal server error.",
} :
{
success: false,
error: "Internal server error.",
};
});
}
async mapUrl(url, params) {
if (this.version == 'v0') {
throw new Error("Map is not supported in v0");
}
const headers = this.prepareHeaders();
let jsonData = { url, ...params };
try {
const response = await this.postRequest(this.apiUrl + `/${this.version}/map`, jsonData, headers);
if (response.status === 200) {
return response.data;
}
else {
this.handleError(response, "map");
}
}
catch (error) {
throw new Error(error.message);
}
return { success: false, error: "Internal server error." };
}
/**
* Prepares the headers for an API request.
* @returns {AxiosRequestHeaders} The prepared headers.
* @param idempotencyKey - Optional key to ensure idempotency.
* @returns The prepared headers.
*/
prepareHeaders(idempotencyKey) {
return Object.assign({ "Content-Type": "application/json", Authorization: `Bearer ${this.apiKey}` }, (idempotencyKey ? { "x-idempotency-key": idempotencyKey } : {}));
return {
"Content-Type": "application/json",
Authorization: `Bearer ${this.apiKey}`,
...(idempotencyKey ? { "x-idempotency-key": idempotencyKey } : {}),
};
}
/**
* Sends a POST request to the specified URL.
* @param {string} url - The URL to send the request to.
* @param {Params} data - The data to send in the request.
* @param {AxiosRequestHeaders} headers - The headers for the request.
* @returns {Promise<AxiosResponse>} The response from the POST request.
* @param url - The URL to send the request to.
* @param data - The data to send in the request.
* @param headers - The headers for the request.
* @returns The response from the POST request.
*/
postRequest(url, data, headers) {
return axios.post(url, data, { headers });
}
/**
* Sends a GET request to the specified URL.
* @param {string} url - The URL to send the request to.
* @param {AxiosRequestHeaders} headers - The headers for the request.
* @returns {Promise<AxiosResponse>} The response from the GET request.
* @param url - The URL to send the request to.
* @param headers - The headers for the request.
* @returns The response from the GET request.
*/
getRequest(url, headers) {
return axios.get(url, { headers });
}
/**
* Monitors the status of a crawl job until completion or failure.
* @param {string} jobId - The job ID of the crawl operation.
* @param {AxiosRequestHeaders} headers - The headers for the request.
* @param {number} timeout - Timeout in seconds for job status checks.
* @returns {Promise<any>} The final job status or data.
* @param id - The ID of the crawl operation.
* @param headers - The headers for the request.
* @param checkInterval - Interval in seconds for job status checks.
* @param checkUrl - Optional URL to check the status (used for v1 API)
* @returns The final job status or data.
*/
monitorJobStatus(jobId, headers, checkInterval) {
return __awaiter(this, void 0, void 0, function* () {
while (true) {
const statusResponse = yield this.getRequest(this.apiUrl + `/v0/crawl/status/${jobId}`, headers);
if (statusResponse.status === 200) {
const statusData = statusResponse.data;
if (statusData.status === "completed") {
if ("data" in statusData) {
return statusData.data;
}
else {
throw new Error("Crawl job completed but no data was returned");
}
}
else if (["active", "paused", "pending", "queued"].includes(statusData.status)) {
if (checkInterval < 2) {
checkInterval = 2;
}
yield new Promise((resolve) => setTimeout(resolve, checkInterval * 1000)); // Wait for the specified timeout before checking again
async monitorJobStatus(id, headers, checkInterval, checkUrl) {
let apiUrl = '';
while (true) {
if (this.version === 'v1') {
apiUrl = checkUrl ?? `${this.apiUrl}/v1/crawl/${id}`;
}
else if (this.version === 'v0') {
apiUrl = `${this.apiUrl}/v0/crawl/status/${id}`;
}
const statusResponse = await this.getRequest(apiUrl, headers);
if (statusResponse.status === 200) {
const statusData = statusResponse.data;
if (statusData.status === "completed") {
if ("data" in statusData) {
return this.version === 'v0' ? statusData.data : statusData;
}
else {
throw new Error(`Crawl job failed or was stopped. Status: ${statusData.status}`);
throw new Error("Crawl job completed but no data was returned");
}
}
else if (["active", "paused", "pending", "queued", "scraping"].includes(statusData.status)) {
checkInterval = Math.max(checkInterval, 2);
await new Promise((resolve) => setTimeout(resolve, checkInterval * 1000));
}
else {
this.handleError(statusResponse, "check crawl status");
throw new Error(`Crawl job failed or was stopped. Status: ${statusData.status}`);
}
}
});
else {
this.handleError(statusResponse, "check crawl status");
}
}
}
/**
* Handles errors from API responses.

289
apps/js-sdk/firecrawl/types/index.d.ts vendored
View File

@ -2,13 +2,18 @@ import { AxiosResponse, AxiosRequestHeaders } from "axios";
import { z } from "zod";
/**
* Configuration interface for FirecrawlApp.
* @param apiKey - Optional API key for authentication.
* @param apiUrl - Optional base URL of the API; defaults to 'https://api.firecrawl.dev'.
* @param version - API version, either 'v0' or 'v1'.
*/
export interface FirecrawlAppConfig {
apiKey?: string | null;
apiUrl?: string | null;
version?: "v0" | "v1";
}
/**
* Metadata for a Firecrawl document.
* Includes various optional properties for document metadata.
*/
export interface FirecrawlDocumentMetadata {
title?: string;
@ -41,14 +46,37 @@ export interface FirecrawlDocumentMetadata {
articleTag?: string;
articleSection?: string;
sourceURL?: string;
statusCode?: number;
error?: string;
[key: string]: any;
}
/**
* Metadata for a Firecrawl document on v0.
* Similar to FirecrawlDocumentMetadata but includes properties specific to API version v0.
*/
export interface FirecrawlDocumentMetadataV0 {
pageStatusCode?: number;
pageError?: string;
[key: string]: any;
}
/**
* Document interface for Firecrawl.
* Represents a document retrieved or processed by Firecrawl.
*/
export interface FirecrawlDocument {
url?: string;
markdown?: string;
html?: string;
rawHtml?: string;
links?: string[];
screenshot?: string;
metadata: FirecrawlDocumentMetadata;
}
/**
* Document interface for Firecrawl on v0.
* Represents a document specifically for API version v0 with additional properties.
*/
export interface FirecrawlDocumentV0 {
id?: string;
url?: string;
content: string;
@ -58,132 +86,283 @@ export interface FirecrawlDocument {
createdAt?: Date;
updatedAt?: Date;
type?: string;
metadata: FirecrawlDocumentMetadata;
metadata: FirecrawlDocumentMetadataV0;
childrenLinks?: string[];
provider?: string;
warning?: string;
index?: number;
}
/**
* Response interface for scraping operations.
* Parameters for scraping operations.
* Defines the options and configurations available for scraping web content.
*/
export interface ScrapeResponse {
export interface ScrapeParams {
formats: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot")[];
headers?: Record<string, string>;
includeTags?: string[];
excludeTags?: string[];
onlyMainContent?: boolean;
screenshotMode?: "desktop" | "full-desktop" | "mobile" | "full-mobile";
waitFor?: number;
timeout?: number;
}
/**
* Parameters for scraping operations on v0.
* Includes page and extractor options specific to API version v0.
*/
export interface ScrapeParamsV0 {
pageOptions?: {
headers?: Record<string, string>;
includeHtml?: boolean;
includeRawHtml?: boolean;
onlyIncludeTags?: string[];
onlyMainContent?: boolean;
removeTags?: string[];
replaceAllPathsWithAbsolutePaths?: boolean;
screenshot?: boolean;
fullPageScreenshot?: boolean;
waitFor?: number;
};
extractorOptions?: {
mode?: "markdown" | "llm-extraction" | "llm-extraction-from-raw-html" | "llm-extraction-from-markdown";
extractionPrompt?: string;
extractionSchema?: Record<string, any> | z.ZodSchema | any;
};
timeout?: number;
}
/**
* Response interface for scraping operations.
* Defines the structure of the response received after a scraping operation.
*/
export interface ScrapeResponse extends FirecrawlDocument {
success: boolean;
data?: FirecrawlDocument;
warning?: string;
error?: string;
}
/**
* Response interface for searching operations.
* Response interface for scraping operations on v0.
* Similar to ScrapeResponse but tailored for responses from API version v0.
*/
export interface SearchResponse {
export interface ScrapeResponseV0 {
success: boolean;
data?: FirecrawlDocument[];
data?: FirecrawlDocumentV0;
error?: string;
}
/**
* Parameters for crawling operations.
* Includes options for both scraping and mapping during a crawl.
*/
export interface CrawlParams {
scrapeOptions?: ScrapeParams;
crawlerOptions?: {
includePaths?: string[];
excludePaths?: string[];
maxDepth?: number;
limit?: number;
allowBackwardLinks?: boolean;
allowExternalLinks?: boolean;
ignoreSitemap?: boolean;
};
}
/**
* Parameters for crawling operations on v0.
* Tailored for API version v0, includes specific options for crawling.
*/
export interface CrawlParamsV0 {
crawlerOptions?: {
includes?: string[];
excludes?: string[];
generateImgAltText?: boolean;
returnOnlyUrls?: boolean;
maxDepth?: number;
mode?: "default" | "fast";
ignoreSitemap?: boolean;
limit?: number;
allowBackwardCrawling?: boolean;
allowExternalContentLinks?: boolean;
};
pageOptions?: {
headers?: Record<string, string>;
includeHtml?: boolean;
includeRawHtml?: boolean;
onlyIncludeTags?: string[];
onlyMainContent?: boolean;
removeTags?: string[];
replaceAllPathsWithAbsolutePaths?: boolean;
screenshot?: boolean;
fullPageScreenshot?: boolean;
waitFor?: number;
};
}
/**
* Response interface for crawling operations.
* Defines the structure of the response received after initiating a crawl.
*/
export interface CrawlResponse {
id?: string;
url?: string;
success: boolean;
error?: string;
}
/**
* Response interface for crawling operations on v0.
* Similar to CrawlResponse but tailored for responses from API version v0.
*/
export interface CrawlResponseV0 {
jobId?: string;
data?: FirecrawlDocument[];
success: boolean;
error?: string;
}
/**
* Response interface for job status checks.
* Provides detailed status of a crawl job including progress and results.
*/
export interface JobStatusResponse {
export interface CrawlStatusResponse {
success: boolean;
total: number;
completed: number;
creditsUsed: number;
expiresAt: Date;
status: "scraping" | "completed" | "failed";
next: string;
data?: FirecrawlDocument[];
error?: string;
}
/**
* Response interface for job status checks on v0.
* Tailored for API version v0, provides status and partial data of a crawl job.
*/
export interface CrawlStatusResponseV0 {
success: boolean;
status: string;
current?: number;
current_url?: string;
current_step?: string;
total?: number;
jobId?: string;
data?: FirecrawlDocument[];
partial_data?: FirecrawlDocument[];
data?: FirecrawlDocumentV0[];
partial_data?: FirecrawlDocumentV0[];
error?: string;
}
/**
* Generic parameter interface.
* Parameters for mapping operations.
* Defines options for mapping URLs during a crawl.
*/
export interface Params {
[key: string]: any;
extractorOptions?: {
extractionSchema: z.ZodSchema | any;
mode?: "llm-extraction";
extractionPrompt?: string;
export interface MapParams {
includePaths?: string[];
excludePaths?: string[];
maxDepth?: number;
limit?: number;
allowBackwardLinks?: boolean;
allowExternalLinks?: boolean;
ignoreSitemap?: boolean;
}
/**
* Response interface for mapping operations.
* Defines the structure of the response received after a mapping operation.
*/
export interface MapResponse {
success: boolean;
links?: string[];
error?: string;
}
/**
* Parameters for searching operations on v0.
* Tailored for API version v0, includes specific options for searching content.
*/
export interface SearchParamsV0 {
pageOptions?: {
onlyMainContent?: boolean;
fetchPageContent?: boolean;
includeHtml?: boolean;
includeRawHtml?: boolean;
};
searchOptions?: {
limit?: number;
};
}
/**
* Main class for interacting with the Firecrawl API.
* Response interface for searching operations on v0.
* Defines the structure of the response received after a search operation on v0.
*/
export default class FirecrawlApp {
export interface SearchResponseV0 {
success: boolean;
data?: FirecrawlDocumentV0[];
error?: string;
}
/**
* Main class for interacting with the Firecrawl API.
* Provides methods for scraping, searching, crawling, and mapping web content.
*/
export default class FirecrawlApp<T extends "v0" | "v1"> {
private apiKey;
private apiUrl;
version: T;
/**
* Initializes a new instance of the FirecrawlApp class.
* @param {FirecrawlAppConfig} config - Configuration options for the FirecrawlApp instance.
* @param config - Configuration options for the FirecrawlApp instance.
*/
constructor({ apiKey, apiUrl }: FirecrawlAppConfig);
constructor({ apiKey, apiUrl, version }: FirecrawlAppConfig);
/**
* Scrapes a URL using the Firecrawl API.
* @param {string} url - The URL to scrape.
* @param {Params | null} params - Additional parameters for the scrape request.
* @returns {Promise<ScrapeResponse>} The response from the scrape operation.
* @param url - The URL to scrape.
* @param params - Additional parameters for the scrape request.
* @returns The response from the scrape operation.
*/
scrapeUrl(url: string, params?: Params | null): Promise<ScrapeResponse>;
scrapeUrl(url: string, params?: ScrapeParams | ScrapeParamsV0): Promise<this['version'] extends 'v0' ? ScrapeResponseV0 : ScrapeResponse>;
/**
* Searches for a query using the Firecrawl API.
* @param {string} query - The query to search for.
* @param {Params | null} params - Additional parameters for the search request.
* @returns {Promise<SearchResponse>} The response from the search operation.
* @param query - The query to search for.
* @param params - Additional parameters for the search request.
* @returns The response from the search operation.
*/
search(query: string, params?: Params | null): Promise<SearchResponse>;
search(query: string, params?: SearchParamsV0): Promise<SearchResponseV0>;
/**
* Initiates a crawl job for a URL using the Firecrawl API.
* @param {string} url - The URL to crawl.
* @param {Params | null} params - Additional parameters for the crawl request.
* @param {boolean} waitUntilDone - Whether to wait for the crawl job to complete.
* @param {number} pollInterval - Time in seconds for job status checks.
* @param {string} idempotencyKey - Optional idempotency key for the request.
* @returns {Promise<CrawlResponse | any>} The response from the crawl operation.
* @param url - The URL to crawl.
* @param params - Additional parameters for the crawl request.
* @param waitUntilDone - Whether to wait for the crawl job to complete.
* @param pollInterval - Time in seconds for job status checks.
* @param idempotencyKey - Optional idempotency key for the request.
* @returns The response from the crawl operation.
*/
crawlUrl(url: string, params?: Params | null, waitUntilDone?: boolean, pollInterval?: number, idempotencyKey?: string): Promise<CrawlResponse | any>;
crawlUrl(url: string, params?: this['version'] extends 'v0' ? CrawlParamsV0 : CrawlParams, waitUntilDone?: boolean, pollInterval?: number, idempotencyKey?: string): Promise<this['version'] extends 'v0' ? CrawlResponseV0 | CrawlStatusResponseV0 | FirecrawlDocumentV0[] : CrawlResponse | CrawlStatusResponse>;
/**
* Checks the status of a crawl job using the Firecrawl API.
* @param {string} jobId - The job ID of the crawl operation.
* @returns {Promise<JobStatusResponse>} The response containing the job status.
* @param id - The ID of the crawl operation.
* @returns The response containing the job status.
*/
checkCrawlStatus(jobId: string): Promise<JobStatusResponse>;
checkCrawlStatus(id?: string): Promise<this['version'] extends 'v0' ? CrawlStatusResponseV0 : CrawlStatusResponse>;
mapUrl(url: string, params?: MapParams): Promise<MapResponse>;
/**
* Prepares the headers for an API request.
* @returns {AxiosRequestHeaders} The prepared headers.
* @param idempotencyKey - Optional key to ensure idempotency.
* @returns The prepared headers.
*/
prepareHeaders(idempotencyKey?: string): AxiosRequestHeaders;
/**
* Sends a POST request to the specified URL.
* @param {string} url - The URL to send the request to.
* @param {Params} data - The data to send in the request.
* @param {AxiosRequestHeaders} headers - The headers for the request.
* @returns {Promise<AxiosResponse>} The response from the POST request.
* @param url - The URL to send the request to.
* @param data - The data to send in the request.
* @param headers - The headers for the request.
* @returns The response from the POST request.
*/
postRequest(url: string, data: Params, headers: AxiosRequestHeaders): Promise<AxiosResponse>;
postRequest(url: string, data: any, headers: AxiosRequestHeaders): Promise<AxiosResponse>;
/**
* Sends a GET request to the specified URL.
* @param {string} url - The URL to send the request to.
* @param {AxiosRequestHeaders} headers - The headers for the request.
* @returns {Promise<AxiosResponse>} The response from the GET request.
* @param url - The URL to send the request to.
* @param headers - The headers for the request.
* @returns The response from the GET request.
*/
getRequest(url: string, headers: AxiosRequestHeaders): Promise<AxiosResponse>;
/**
* Monitors the status of a crawl job until completion or failure.
* @param {string} jobId - The job ID of the crawl operation.
* @param {AxiosRequestHeaders} headers - The headers for the request.
* @param {number} timeout - Timeout in seconds for job status checks.
* @returns {Promise<any>} The final job status or data.
* @param id - The ID of the crawl operation.
* @param headers - The headers for the request.
* @param checkInterval - Interval in seconds for job status checks.
* @param checkUrl - Optional URL to check the status (used for v1 API)
* @returns The final job status or data.
*/
monitorJobStatus(jobId: string, headers: AxiosRequestHeaders, checkInterval: number): Promise<any>;
monitorJobStatus(id: string, headers: AxiosRequestHeaders, checkInterval: number, checkUrl?: string): Promise<this['version'] extends 'v0' ? CrawlStatusResponseV0 | FirecrawlDocumentV0[] : CrawlStatusResponse>;
/**
* Handles errors from API responses.
* @param {AxiosResponse} response - The response from the API.