AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-12 20:29:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(js-sdk): add further options to checkxstatus

Browse Source
This commit is contained in:
Gergő Móricz 2025-01-15 20:16:39 +01:00
parent cbe67d89a5
commit c3937996b1
1 changed files with 28 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
apps/js-sdk/firecrawl/src/index.ts
View File

@ -545,17 +545,28 @@ export default class FirecrawlApp {
* Checks the status of a crawl job using the Firecrawl API. * Checks the status of a crawl job using the Firecrawl API.
* @param id - The ID of the crawl operation. * @param id - The ID of the crawl operation.
* @param getAllData - Paginate through all the pages of documents, returning the full list of all documents. (default: `false`) * @param getAllData - Paginate through all the pages of documents, returning the full list of all documents. (default: `false`)
* @param nextURL - The `next` URL from the previous crawl status. Only required if you're not manually increasing `skip`. Only used when `getAllData = false`.
* @param skip - How many entries to skip to paginate. Only required if you're not providing `nextURL`. Only used when `getAllData = false`.
* @param limit - How many entries to return. Only used when `getAllData = false`.
* @returns The response containing the job status. * @returns The response containing the job status.
*/ */
async checkCrawlStatus(id?: string, getAllData = false): Promise<CrawlStatusResponse | ErrorResponse> { async checkCrawlStatus(id?: string, getAllData = false, nextURL?: string, skip?: number, limit?: number): Promise<CrawlStatusResponse | ErrorResponse> {
if (!id) { if (!id) {
throw new FirecrawlError("No crawl ID provided", 400); throw new FirecrawlError("No crawl ID provided", 400);
} }
const headers: AxiosRequestHeaders = this.prepareHeaders(); const headers: AxiosRequestHeaders = this.prepareHeaders();
const targetURL = new URL(nextURL ?? `${this.apiUrl}/v1/crawl/${id}`);
if (skip !== undefined) {
targetURL.searchParams.set("skip", skip.toString());
}
if (limit !== undefined) {
targetURL.searchParams.set("skip", limit.toString());
}
try { try {
const response: AxiosResponse = await this.getRequest( const response: AxiosResponse = await this.getRequest(
`${this.apiUrl}/v1/crawl/${id}`, targetURL.href,
headers headers
); );
if (response.status === 200) { if (response.status === 200) {
@ -581,6 +592,7 @@ export default class FirecrawlApp {
total: response.data.total, total: response.data.total,
completed: response.data.completed, completed: response.data.completed,
creditsUsed: response.data.creditsUsed, creditsUsed: response.data.creditsUsed,
next: getAllData ? undefined : response.data.next,
expiresAt: new Date(response.data.expiresAt), expiresAt: new Date(response.data.expiresAt),
data: allData data: allData
} }
@ -795,17 +807,28 @@ export default class FirecrawlApp {
* Checks the status of a batch scrape job using the Firecrawl API. * Checks the status of a batch scrape job using the Firecrawl API.
* @param id - The ID of the batch scrape operation. * @param id - The ID of the batch scrape operation.
* @param getAllData - Paginate through all the pages of documents, returning the full list of all documents. (default: `false`) * @param getAllData - Paginate through all the pages of documents, returning the full list of all documents. (default: `false`)
* @param nextURL - The `next` URL from the previous batch scrape status. Only required if you're not manually increasing `skip`. Only used when `getAllData = false`.
* @param skip - How many entries to skip to paginate. Only used when `getAllData = false`.
* @param limit - How many entries to return. Only used when `getAllData = false`.
* @returns The response containing the job status. * @returns The response containing the job status.
*/ */
async checkBatchScrapeStatus(id?: string, getAllData = false): Promise<BatchScrapeStatusResponse | ErrorResponse> { async checkBatchScrapeStatus(id?: string, getAllData = false, nextURL?: string, skip?: number, limit?: number): Promise<BatchScrapeStatusResponse | ErrorResponse> {
if (!id) { if (!id) {
throw new FirecrawlError("No batch scrape ID provided", 400); throw new FirecrawlError("No batch scrape ID provided", 400);
} }
const headers: AxiosRequestHeaders = this.prepareHeaders(); const headers: AxiosRequestHeaders = this.prepareHeaders();
const targetURL = new URL(nextURL ?? `${this.apiUrl}/v1/batch/scrape/${id}`);
if (skip !== undefined) {
targetURL.searchParams.set("skip", skip.toString());
}
if (limit !== undefined) {
targetURL.searchParams.set("skip", limit.toString());
}
try { try {
const response: AxiosResponse = await this.getRequest( const response: AxiosResponse = await this.getRequest(
`${this.apiUrl}/v1/batch/scrape/${id}`, targetURL.href,
headers headers
); );
if (response.status === 200) { if (response.status === 200) {
@ -831,6 +854,7 @@ export default class FirecrawlApp {
total: response.data.total, total: response.data.total,
completed: response.data.completed, completed: response.data.completed,
creditsUsed: response.data.creditsUsed, creditsUsed: response.data.creditsUsed,
next: getAllData ? undefined : response.data.next,
expiresAt: new Date(response.data.expiresAt), expiresAt: new Date(response.data.expiresAt),
data: allData data: allData
} }