8d467c8ca7
* feat: use strictNullChecking * feat: switch logger to Winston * feat(scrapeURL): first batch * fix(scrapeURL): error swallow * fix(scrapeURL): add timeout to EngineResultsTracker * fix(scrapeURL): report unexpected error to sentry * chore: remove unused modules * feat(transfomers/coerce): warn when a format's response is missing * feat(scrapeURL): feature flag priorities, engine quality sorting, PDF and DOCX support * (add note) * feat(scrapeURL): wip readme * feat(scrapeURL): LLM extract * feat(scrapeURL): better warnings * fix(scrapeURL/engines/fire-engine;playwright): fix screenshot * feat(scrapeURL): add forceEngine internal option * feat(scrapeURL/engines): scrapingbee * feat(scrapeURL/transformars): uploadScreenshot * feat(scrapeURL): more intense tests * bunch of stuff * get rid of WebScraper (mostly) * adapt batch scrape * add staging deploy workflow * fix yaml * fix logger issues * fix v1 test schema * feat(scrapeURL/fire-engine/chrome-cdp): remove wait inserts on actions * scrapeURL: v0 backwards compat * logger fixes * feat(scrapeurl): v0 returnOnlyUrls support * fix(scrapeURL/v0): URL leniency * fix(batch-scrape): ts non-nullable * fix(scrapeURL/fire-engine/chromecdp): fix wait action * fix(logger): remove error debug key * feat(requests.http): use dotenv expression * fix(scrapeURL/extractMetadata): extract custom metadata * fix crawl option conversion * feat(scrapeURL): Add retry logic to robustFetch * fix(scrapeURL): crawl stuff * fix(scrapeURL): LLM extract * fix(scrapeURL/v0): search fix * fix(tests/v0): grant larger response size to v0 crawl status * feat(scrapeURL): basic fetch engine * feat(scrapeURL): playwright engine * feat(scrapeURL): add url-specific parameters * Update readme and examples * added e2e tests for most parameters. Still a few actions, location and iframes to be done. * fixed type * Nick: * Update scrape.ts * Update index.ts * added actions and base64 check * Nick: skipTls feature flag? * 403 * todo * todo * fixes * yeet headers from url specific params * add warning when final engine has feature deficit * expose engine results tracker for ScrapeEvents implementation * ingest scrape events * fixed some tests * comment * Update index.test.ts * fixed rawHtml * Update index.test.ts * update comments * move geolocation to global f-e option, fix removeBase64Images * Nick: * trim url-specific params * Update index.ts --------- Co-authored-by: Eric Ciarla <ericciarla@yahoo.com> Co-authored-by: rafaelmmiller <8574157+rafaelmmiller@users.noreply.github.com> Co-authored-by: Nicolas <nicolascamara29@gmail.com>
39 lines
1.2 KiB
TypeScript
39 lines
1.2 KiB
TypeScript
import { Response } from "express";
|
|
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 job = await supabaseGetJobByIdOnlyData(req.params.jobId);
|
|
|
|
if(job?.team_id !== "41bdbfe1-0579-4d9b-b6d5-809f16be12f5"){
|
|
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],
|
|
});
|
|
} 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.",
|
|
});
|
|
}
|
|
}
|
|
}
|