Austin/firecrawl
1
0
Fork 0
mirror of https://github.com/mendableai/firecrawl.git synced 2024-11-16 11:42:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fixed

Browse Source
This commit is contained in:
rafaelsideguide 2024-06-12 11:27:06 -03:00
parent dc6acbf1f0
commit 01c9f071fa
2 changed files with 14 additions and 26 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

36
apps/api/src/__tests__/e2e_withAuth/index.test.ts
View File

@ -624,11 +624,11 @@ describe("E2E Tests for API Routes", () => {
expect(completedResponse.body.data[0]).toHaveProperty("metadata");
expect(completedResponse.body.data[0].content).toContain("Mendable");
const childrenLinks = completedResponse.body.data.filter(doc =>
doc.sourceURL && doc.sourceURL.startsWith("https://mendable.ai/blog")
);
const childrenLinks = completedResponse.body.data.filter(doc =>
doc.metadata && doc.metadata.sourceURL && doc.metadata.sourceURL.includes("mendable.ai/blog")
);
expect(childrenLinks.length).toBe(completedResponse.body.data.length);
expect(childrenLinks.length).toBe(completedResponse.body.data.length);
}, 120000); // 120 seconds
it.concurrent('should return a successful response for a valid crawl job with PDF files without explicit .pdf extension', async () => {
@ -816,35 +816,23 @@ describe("E2E Tests for API Routes", () => {
.post("/v0/crawl")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.set("Content-Type", "application/json")
.send({ url: "https://scrapethissite.com" });
.send({ url: "https://jestjs.io" });
expect(crawlResponse.statusCode).toBe(200);
await new Promise((r) => setTimeout(r, 2000)); // Wait for 1 seconds before cancelling the job
await new Promise((r) => setTimeout(r, 20000));
const responseCancel = await request(TEST_URL)
.delete(`/v0/crawl/cancel/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(responseCancel.statusCode).toBe(200);
expect(responseCancel.body).toHaveProperty("status");
expect(responseCancel.body.status).toBe("cancelled");
let isFinished = false;
let completedResponse;
while (!isFinished) {
const response = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(response.statusCode).toBe(200);
expect(response.body).toHaveProperty("status");
console.log(response.body.status)
if (response.body.status === "failed") {
isFinished = true;
completedResponse = response;
} else {
await new Promise((r) => setTimeout(r, 1000)); // Wait for 1 second before checking again
}
}
await new Promise((r) => setTimeout(r, 10000));
const completedResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${crawlResponse.body.jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
expect(completedResponse.statusCode).toBe(200);
expect(completedResponse.body).toHaveProperty("status");

4
apps/api/src/controllers/crawl.ts
View File

@ -55,7 +55,7 @@ export async function crawlController(req: Request, res: Response) {
}
const mode = req.body.mode ?? "crawl";
const crawlerOptions = req.body.crawlerOptions ?? { allowBackwardCrawling: false, returnOnlyUrls: true };
const crawlerOptions = req.body.crawlerOptions ?? { allowBackwardCrawling: false };
const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false };
if (mode === "single_urls" && !url.includes(",")) {
@ -64,7 +64,7 @@ export async function crawlController(req: Request, res: Response) {
await a.setOptions({
mode: "single_urls",
urls: [url],
crawlerOptions: crawlerOptions,
crawlerOptions: { ...crawlerOptions, returnOnlyUrls: true },
pageOptions: pageOptions,
});