github/v-firecrawl
github/v-firecrawl
0
Fork 0
Code Actions

Update crawl.test.ts

Browse Source
This commit is contained in:
Nicolas 2024-05-15 12:50:13 -07:00
parent 58053eb423
commit 499671c87f
1 changed files with 51 additions and 101 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

152
apps/test-suite/tests/crawl.test.ts
View File

@ -27,8 +27,6 @@ describe("Crawling Checkup (E2E)", () => {
describe("Crawling website tests with a dataset", () => { describe("Crawling website tests with a dataset", () => {
it("Should crawl the website and verify the response", async () => { it("Should crawl the website and verify the response", async () => {
let passedTests = 0; let passedTests = 0;
const batchSize = 15;
const batchPromises = [];
const startTime = new Date().getTime(); const startTime = new Date().getTime();
const date = new Date(); const date = new Date();
const logsDir = `logs/${date.getMonth() + 1}-${date.getDate()}-${date.getFullYear()}`; const logsDir = `logs/${date.getMonth() + 1}-${date.getDate()}-${date.getFullYear()}`;
@ -36,113 +34,65 @@ describe("Crawling Checkup (E2E)", () => {
let errorLogFileName = `${logsDir}/run.log_${new Date().toTimeString().split(' ')[0]}`; let errorLogFileName = `${logsDir}/run.log_${new Date().toTimeString().split(' ')[0]}`;
const errorLog: WebsiteScrapeError[] = []; const errorLog: WebsiteScrapeError[] = [];
for (let i = 0; i < websitesData.length; i += batchSize) { for (const websiteData of websitesData) {
await new Promise(resolve => setTimeout(resolve, 10000)); await new Promise(resolve => setTimeout(resolve, 10000));
const batch = websitesData.slice(i, i + batchSize); try {
const batchPromise = Promise.all( const crawlResponse = await request(TEST_URL || "")
batch.map(async (websiteData: WebsiteData) => { .post("/v0/crawl")
try { .set("Content-Type", "application/json")
const crawlResponse = await request(TEST_URL || "") .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.post("/v0/crawl") .send({ url: websiteData.website, pageOptions: { onlyMainContent: true }, crawlerOptions: { limit: 100 }});
.set("Content-Type", "application/json")
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
.send({ url: websiteData.website, pageOptions: { onlyMainContent: true }, crawlerOptions: { limit: 100 }});
const jobId = crawlResponse.body.jobId; const jobId = crawlResponse.body.jobId;
let completedResponse; let completedResponse;
let isFinished = false; let isFinished = false;
while (!isFinished) { while (!isFinished) {
completedResponse = await request(TEST_URL) completedResponse = await request(TEST_URL)
.get(`/v0/crawl/status/${jobId}`) .get(`/v0/crawl/status/${jobId}`)
.set("Authorization", `Bearer ${process.env.TEST_API_KEY}`); .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`);
isFinished = completedResponse.body.status === "completed"; isFinished = completedResponse.body.status === "completed";
if (!isFinished) { if (!isFinished) {
await new Promise(resolve => setTimeout(resolve, 1000)); // Wait for 1 second before checking again await new Promise(resolve => setTimeout(resolve, 1000)); // Wait for 1 second before checking again
}
}
console.log('-------------------')
console.log(websiteData.website);
if(!completedResponse) {
// fail the test
console.log('No response');
return null;
}
if (!completedResponse.body.data) {
console.log(completedResponse.body.partial_data.length);
const urls = completedResponse.body.partial_data.map((page: any) => page.metadata?.sourceURL);
console.log(urls);
} else {
console.log(completedResponse.body.data.length);
const urls = completedResponse.body.data.map((page: any) => page.metadata?.sourceURL);
console.log(urls);
}
console.log('-------------------')
// if (!completedResponse.body || completedResponse.body.status !== "completed") {
// errorLog.push({
// website: websiteData.website,
// prompt: 'CRAWL',
// expected_output: 'SUCCESS',
// actual_output: 'FAILURE',
// error: `Crawl job did not complete successfully.`
// });
// return null;
// }
// // check how many webpages were crawled successfully
// // compares with expected_num_of_pages
// if (completedResponse.body.data.length < websiteData.expected_min_num_of_pages) {
// errorLog.push({
// website: websiteData.website,
// prompt: 'CRAWL',
// expected_output: `SUCCESS: ${websiteData.expected_min_num_of_pages}`,
// actual_output: `FAILURE: ${completedResponse.body.data.length}`,
// error: `Expected at least ${websiteData.expected_min_num_of_pages} webpages, but got ${completedResponse.body.data.length}`
// });
// return null;
// }
// // checks if crawled pages contain expected_crawled_pages
// if (websiteData.expected_crawled_pages.some(page => !completedResponse.body.data.includes(page))) {
// errorLog.push({
// website: websiteData.website,
// prompt: 'CRAWL',
// expected_output: `SUCCESS: ${websiteData.expected_crawled_pages}`,
// actual_output: `FAILURE: ${completedResponse.body.data}`,
// error: `Expected crawled pages to contain ${websiteData.expected_crawled_pages}, but got ${completedResponse.body.data}`
// });
// return null;
// }
passedTests++;
return {
website: websiteData.website,
statusCode: completedResponse.statusCode,
};
} catch (error) {
console.error(`Error processing ${websiteData.website}: ${error}`);
errorLog.push({
website: websiteData.website,
prompt: 'CRAWL',
expected_output: 'SUCCESS',
actual_output: 'FAILURE',
error: `Error processing ${websiteData.website}: ${error}`
});
return null;
} }
}) }
);
batchPromises.push(batchPromise); console.log('-------------------')
console.log(websiteData.website);
if(!completedResponse) {
// fail the test
console.log('No response');
continue;
}
if (!completedResponse.body.data) {
console.log(completedResponse.body.partial_data.length);
const urls = completedResponse.body.partial_data.map((page: any) => page.metadata?.sourceURL);
console.log(urls);
} else {
console.log(completedResponse.body.data.length);
const urls = completedResponse.body.data.map((page: any) => page.metadata?.sourceURL);
console.log(urls);
}
console.log('-------------------')
passedTests++;
} catch (error) {
console.error(`Error processing ${websiteData.website}: ${error}`);
errorLog.push({
website: websiteData.website,
prompt: 'CRAWL',
expected_output: 'SUCCESS',
actual_output: 'FAILURE',
error: `Error processing ${websiteData.website}: ${error}`
});
}
} }
(await Promise.all(batchPromises)).flat();
const score = (passedTests / websitesData.length) * 100; const score = (passedTests / websitesData.length) * 100;
const endTime = new Date().getTime(); const endTime = new Date().getTime();
const timeTaken = (endTime - startTime) / 1000; const timeTaken = (endTime - startTime) / 1000;
@ -160,4 +110,4 @@ describe("Crawling Checkup (E2E)", () => {
expect(score).toBeGreaterThanOrEqual(95); expect(score).toBeGreaterThanOrEqual(95);
}, 350000); // 150 seconds timeout }, 350000); // 150 seconds timeout
}); });
}); });