feat(scrape-status): adapt

This commit is contained in:
Gergő Móricz 2025-01-09 19:14:00 +01:00
parent 2849ce2f13
commit 29c1f126ab
3 changed files with 29 additions and 35 deletions

View File

@ -3,40 +3,30 @@ import { supabaseGetJobByIdOnlyData } from "../../lib/supabase-jobs";
import { scrapeStatusRateLimiter } from "../../services/rate-limiter";
export async function scrapeStatusController(req: any, res: any) {
try {
const rateLimiter = scrapeStatusRateLimiter;
const incomingIP = (req.headers["x-forwarded-for"] ||
req.socket.remoteAddress) as string;
const iptoken = incomingIP;
await rateLimiter.consume(iptoken);
const allowedTeams = [
"41bdbfe1-0579-4d9b-b6d5-809f16be12f5",
"511544f2-2fce-4183-9c59-6c29b02c69b5",
"1ec9a0b3-6e7d-49a9-ad6c-9c598ba824c8",
];
const job = await supabaseGetJobByIdOnlyData(req.params.jobId);
const allowedTeams = [
"41bdbfe1-0579-4d9b-b6d5-809f16be12f5",
"511544f2-2fce-4183-9c59-6c29b02c69b5",
];
if (!allowedTeams.includes(job?.team_id)) {
return res.status(403).json({
success: false,
error: "You are not allowed to access this resource.",
});
}
return res.status(200).json({
success: true,
data: job?.docs[0],
if (!allowedTeams.includes(req.auth.team_id)) {
return res.status(403).json({
success: false,
error: "Forbidden",
});
} catch (error) {
if (error instanceof Error && error.message == "Too Many Requests") {
return res.status(429).json({
success: false,
error: "Rate limit exceeded. Please try again later.",
});
} else {
return res.status(500).json({
success: false,
error: "An unexpected error occurred.",
});
}
}
const job = await supabaseGetJobByIdOnlyData(req.params.jobId);
if (!allowedTeams.includes(job?.team_id) || job?.team_id !== req.auth.team_id) {
return res.status(403).json({
success: false,
error: "You are not allowed to access this resource.",
});
}
return res.status(200).json({
success: true,
data: job?.docs[0],
});
}

View File

@ -192,7 +192,10 @@ v1Router.get(
wrap((req: any, res): any => crawlStatusController(req, res, true)),
);
v1Router.get("/scrape/:jobId", wrap(scrapeStatusController));
v1Router.get("/scrape/:jobId",
authMiddleware(RateLimiterMode.CrawlStatus),
wrap(scrapeStatusController),
);
v1Router.get(
"/concurrency-check",

View File

@ -755,6 +755,7 @@ async function processJob(job: Job & { id: string }, token: string) {
{
content: doc,
source: doc?.metadata?.sourceURL ?? doc?.metadata?.url ?? "",
id: job.id,
},
],
},