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
@@ -1,10 +1,7 @@
|
||||
import { Request, Response } from "express";
|
||||
import { Logger } from "../../lib/logger";
|
||||
import { Response } from "express";
|
||||
import { logger } from "../../lib/logger";
|
||||
import {
|
||||
Document,
|
||||
legacyDocumentConverter,
|
||||
legacyExtractorOptions,
|
||||
legacyScrapeOptions,
|
||||
RequestWithAuth,
|
||||
ScrapeRequest,
|
||||
scrapeRequestSchema,
|
||||
@@ -12,7 +9,6 @@ import {
|
||||
} from "./types";
|
||||
import { billTeam } from "../../services/billing/credit_billing";
|
||||
import { v4 as uuidv4 } from "uuid";
|
||||
import { numTokensFromString } from "../../lib/LLM-extraction/helpers";
|
||||
import { addScrapeJob, waitForJob } from "../../services/queue-jobs";
|
||||
import { logJob } from "../../services/logging/log_job";
|
||||
import { getJobPriority } from "../../lib/job-priority";
|
||||
@@ -28,8 +24,6 @@ export async function scrapeController(
|
||||
|
||||
const origin = req.body.origin;
|
||||
const timeout = req.body.timeout;
|
||||
const pageOptions = legacyScrapeOptions(req.body);
|
||||
const extractorOptions = req.body.extract ? legacyExtractorOptions(req.body.extract) : undefined;
|
||||
const jobId = uuidv4();
|
||||
|
||||
const startTime = new Date().getTime();
|
||||
@@ -43,11 +37,10 @@ export async function scrapeController(
|
||||
{
|
||||
url: req.body.url,
|
||||
mode: "single_urls",
|
||||
crawlerOptions: {},
|
||||
team_id: req.auth.team_id,
|
||||
plan: req.auth.plan,
|
||||
pageOptions,
|
||||
extractorOptions,
|
||||
scrapeOptions: req.body,
|
||||
internalOptions: {},
|
||||
plan: req.auth.plan!,
|
||||
origin: req.body.origin,
|
||||
is_scrape: true,
|
||||
},
|
||||
@@ -56,13 +49,13 @@ export async function scrapeController(
|
||||
jobPriority
|
||||
);
|
||||
|
||||
const totalWait = (req.body.waitFor ?? 0) + (req.body.actions ?? []).reduce((a,x) => (x.type === "wait" ? x.milliseconds : 0) + a, 0);
|
||||
const totalWait = (req.body.waitFor ?? 0) + (req.body.actions ?? []).reduce((a,x) => (x.type === "wait" ? x.milliseconds ?? 0 : 0) + a, 0);
|
||||
|
||||
let doc: any | undefined;
|
||||
let doc: Document;
|
||||
try {
|
||||
doc = (await waitForJob(jobId, timeout + totalWait))[0];
|
||||
doc = await waitForJob<Document>(jobId, timeout + totalWait); // TODO: better types for this
|
||||
} catch (e) {
|
||||
Logger.error(`Error in scrapeController: ${e}`);
|
||||
logger.error(`Error in scrapeController: ${e}`);
|
||||
if (e instanceof Error && e.message.startsWith("Job wait")) {
|
||||
return res.status(408).json({
|
||||
success: false,
|
||||
@@ -71,34 +64,19 @@ export async function scrapeController(
|
||||
} else {
|
||||
return res.status(500).json({
|
||||
success: false,
|
||||
error: `(Internal server error) - ${e && e?.message ? e.message : e} ${
|
||||
extractorOptions && extractorOptions.mode !== "markdown"
|
||||
? " - Could be due to LLM parsing issues"
|
||||
: ""
|
||||
}`,
|
||||
error: `(Internal server error) - ${e && e?.message ? e.message : e}`,
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
await getScrapeQueue().remove(jobId);
|
||||
|
||||
if (!doc) {
|
||||
console.error("!!! PANIC DOC IS", doc);
|
||||
return res.status(200).json({
|
||||
success: true,
|
||||
warning: "No page found",
|
||||
data: doc,
|
||||
});
|
||||
}
|
||||
|
||||
delete doc.index;
|
||||
delete doc.provider;
|
||||
|
||||
const endTime = new Date().getTime();
|
||||
const timeTakenInSeconds = (endTime - startTime) / 1000;
|
||||
const numTokens =
|
||||
doc && doc.markdown
|
||||
? numTokensFromString(doc.markdown, "gpt-3.5-turbo")
|
||||
doc && doc.extract
|
||||
// ? numTokensFromString(doc.markdown, "gpt-3.5-turbo")
|
||||
? 0 // TODO: fix
|
||||
: 0;
|
||||
|
||||
let creditsToBeBilled = 1; // Assuming 1 credit per document
|
||||
@@ -111,22 +89,16 @@ export async function scrapeController(
|
||||
}
|
||||
|
||||
billTeam(req.auth.team_id, req.acuc?.sub_id, creditsToBeBilled).catch(error => {
|
||||
Logger.error(`Failed to bill team ${req.auth.team_id} for ${creditsToBeBilled} credits: ${error}`);
|
||||
logger.error(`Failed to bill team ${req.auth.team_id} for ${creditsToBeBilled} credits: ${error}`);
|
||||
// Optionally, you could notify an admin or add to a retry queue here
|
||||
});
|
||||
|
||||
if (!pageOptions || !pageOptions.includeRawHtml) {
|
||||
if (!req.body.formats.includes("rawHtml")) {
|
||||
if (doc && doc.rawHtml) {
|
||||
delete doc.rawHtml;
|
||||
}
|
||||
}
|
||||
|
||||
if(pageOptions && pageOptions.includeExtract) {
|
||||
if(!pageOptions.includeMarkdown && doc && doc.markdown) {
|
||||
delete doc.markdown;
|
||||
}
|
||||
}
|
||||
|
||||
logJob({
|
||||
job_id: jobId,
|
||||
success: true,
|
||||
@@ -137,16 +109,14 @@ export async function scrapeController(
|
||||
team_id: req.auth.team_id,
|
||||
mode: "scrape",
|
||||
url: req.body.url,
|
||||
crawlerOptions: {},
|
||||
pageOptions: pageOptions,
|
||||
scrapeOptions: req.body,
|
||||
origin: origin,
|
||||
extractor_options: extractorOptions,
|
||||
num_tokens: numTokens,
|
||||
});
|
||||
|
||||
return res.status(200).json({
|
||||
success: true,
|
||||
data: legacyDocumentConverter(doc),
|
||||
data: doc,
|
||||
scrape_id: origin?.includes("website") ? jobId : undefined,
|
||||
});
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user