WebScraper refactor into scrapeURL (#714)
* 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>
This commit is contained in:
Gergő Móricz
GitHub
@@ -1,14 +1,15 @@
|
||||
import { authMiddleware } from "../../routes/v1";
|
||||
import { RateLimiterMode } from "../../types";
|
||||
import { authenticateUser } from "../auth";
|
||||
import { CrawlStatusParams, CrawlStatusResponse, Document, ErrorResponse, legacyDocumentConverter, RequestWithAuth } from "./types";
|
||||
import { CrawlStatusParams, CrawlStatusResponse, Document, ErrorResponse, RequestWithAuth } from "./types";
|
||||
import { WebSocket } from "ws";
|
||||
import { v4 as uuidv4 } from "uuid";
|
||||
import { Logger } from "../../lib/logger";
|
||||
import { logger } from "../../lib/logger";
|
||||
import { getCrawl, getCrawlExpiry, getCrawlJobs, getDoneJobsOrdered, getDoneJobsOrderedLength, getThrottledJobs, isCrawlFinished, isCrawlFinishedLocked } from "../../lib/crawl-redis";
|
||||
import { getScrapeQueue } from "../../services/queue-service";
|
||||
import { getJob, getJobs } from "./crawl-status";
|
||||
import * as Sentry from "@sentry/node";
|
||||
import { Job, JobState } from "bullmq";
|
||||
|
||||
type ErrorMessage = {
|
||||
type: "error",
|
||||
@@ -56,7 +57,7 @@ async function crawlStatusWS(ws: WebSocket, req: RequestWithAuth<CrawlStatusPara
|
||||
return close(ws, 3003, { type: "error", error: "Forbidden" });
|
||||
}
|
||||
|
||||
let doneJobIDs = [];
|
||||
let doneJobIDs: string[] = [];
|
||||
let finished = false;
|
||||
|
||||
const loop = async () => {
|
||||
@@ -70,15 +71,14 @@ async function crawlStatusWS(ws: WebSocket, req: RequestWithAuth<CrawlStatusPara
|
||||
|
||||
const notDoneJobIDs = jobIDs.filter(x => !doneJobIDs.includes(x));
|
||||
const jobStatuses = await Promise.all(notDoneJobIDs.map(async x => [x, await getScrapeQueue().getJobState(x)]));
|
||||
const newlyDoneJobIDs = jobStatuses.filter(x => x[1] === "completed" || x[1] === "failed").map(x => x[0]);
|
||||
|
||||
for (const jobID of newlyDoneJobIDs) {
|
||||
const job = await getJob(jobID);
|
||||
const newlyDoneJobIDs: string[] = jobStatuses.filter(x => x[1] === "completed" || x[1] === "failed").map(x => x[0]);
|
||||
const newlyDoneJobs: Job[] = (await Promise.all(newlyDoneJobIDs.map(x => getJob(x)))).filter(x => x !== undefined) as Job[]
|
||||
|
||||
for (const job of newlyDoneJobs) {
|
||||
if (job.returnvalue) {
|
||||
send(ws, {
|
||||
type: "document",
|
||||
data: legacyDocumentConverter(job.returnvalue),
|
||||
data: job.returnvalue,
|
||||
})
|
||||
} else {
|
||||
return close(ws, 3000, { type: "error", error: job.failedReason });
|
||||
@@ -100,8 +100,8 @@ async function crawlStatusWS(ws: WebSocket, req: RequestWithAuth<CrawlStatusPara
|
||||
|
||||
const throttledJobsSet = new Set(throttledJobs);
|
||||
|
||||
const validJobStatuses = [];
|
||||
const validJobIDs = [];
|
||||
const validJobStatuses: [string, JobState | "unknown"][] = [];
|
||||
const validJobIDs: string[] = [];
|
||||
|
||||
for (const [id, status] of jobStatuses) {
|
||||
if (!throttledJobsSet.has(id) && status !== "failed" && status !== "unknown") {
|
||||
@@ -126,7 +126,7 @@ async function crawlStatusWS(ws: WebSocket, req: RequestWithAuth<CrawlStatusPara
|
||||
completed: doneJobIDs.length,
|
||||
creditsUsed: jobIDs.length,
|
||||
expiresAt: (await getCrawlExpiry(req.params.jobId)).toISOString(),
|
||||
data: data.map(x => legacyDocumentConverter(x)),
|
||||
data: data,
|
||||
}
|
||||
});
|
||||
|
||||
@@ -139,19 +139,21 @@ async function crawlStatusWS(ws: WebSocket, req: RequestWithAuth<CrawlStatusPara
|
||||
// Basically just middleware and error wrapping
|
||||
export async function crawlStatusWSController(ws: WebSocket, req: RequestWithAuth<CrawlStatusParams, undefined, undefined>) {
|
||||
try {
|
||||
const { success, team_id, error, status, plan } = await authenticateUser(
|
||||
const auth = await authenticateUser(
|
||||
req,
|
||||
null,
|
||||
RateLimiterMode.CrawlStatus,
|
||||
);
|
||||
|
||||
if (!success) {
|
||||
if (!auth.success) {
|
||||
return close(ws, 3000, {
|
||||
type: "error",
|
||||
error,
|
||||
error: auth.error,
|
||||
});
|
||||
}
|
||||
|
||||
const { team_id, plan } = auth;
|
||||
|
||||
req.auth = { team_id, plan };
|
||||
|
||||
await crawlStatusWS(ws, req);
|
||||
@@ -170,7 +172,7 @@ export async function crawlStatusWSController(ws: WebSocket, req: RequestWithAut
|
||||
}
|
||||
}
|
||||
|
||||
Logger.error("Error occurred in WebSocket! (" + req.path + ") -- ID " + id + " -- " + verbose);
|
||||
logger.error("Error occurred in WebSocket! (" + req.path + ") -- ID " + id + " -- " + verbose);
|
||||
return close(ws, 1011, {
|
||||
type: "error",
|
||||
error: "An unexpected error occurred. Please contact hello@firecrawl.com for help. Your exception ID is " + id
|
||||
|
||||
Reference in New Issue
Block a user