Spaces:
Sleeping
Sleeping
File size: 46,926 Bytes
097eaf0 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 | import { Logger } from "winston";
import { config } from "../../config";
import * as Sentry from "@sentry/node";
import { withSpan, setSpanAttributes } from "../../lib/otel-tracer";
import { captureExceptionWithZdrCheck } from "../../services/sentry";
import {
type Document,
getPDFMaxPages,
scrapeOptions,
type ScrapeOptions,
type TeamFlags,
} from "../../controllers/v2/types";
import { ScrapeOptions as ScrapeOptionsV1 } from "../../controllers/v1/types";
import { logger as _logger } from "../../lib/logger";
import {
buildFallbackList,
Engine,
EngineScrapeResult,
FeatureFlag,
getEngineMaxReasonableTime,
scrapeURLWithEngine,
shouldUseIndex,
} from "./engines";
import { parseMarkdown } from "../../lib/html-to-markdown";
import { hasFormatOfType } from "../../lib/format-utils";
import {
ActionError,
AddFeatureError,
AgentIndexOnlyError,
EngineError,
NoEnginesLeftError,
PDFAntibotError,
DocumentAntibotError,
RemoveFeatureError,
SiteError,
UnsupportedFileError,
SSLError,
PDFInsufficientTimeError,
PDFOCRRequiredError,
IndexMissError,
NoCachedDataError,
LockdownMissError,
DNSResolutionError,
ZDRViolationError,
PDFPrefetchFailed,
DocumentPrefetchFailed,
FEPageLoadFailed,
EngineSnipedError,
WaterfallNextEngineSignal,
EngineUnsuccessfulError,
ProxySelectionError,
ScrapeRetryLimitError,
BrandingNotSupportedError,
XTwitterConfigurationError,
} from "./error";
import { ScrapeRetryTracker } from "./retryTracker";
import { executeTransformers } from "./transformers";
import { LLMRefusalError } from "./transformers/llmExtract";
import { urlSpecificParams } from "./lib/urlSpecificParams";
import { shouldCheckRobots } from "./shouldCheckRobots";
import { loadMock, MockState } from "./lib/mock";
import { CostTracking } from "../../lib/cost-tracking";
import { getEngineForUrl } from "../WebScraper/utils/engine-forcing";
import { useIndex } from "../../services/index";
import {
fetchRobotsTxt,
createRobotsChecker,
isUrlAllowedByRobots,
} from "../../lib/robots-txt";
import { getCrawl } from "../../lib/crawl-redis";
import {
AbortInstance,
AbortManager,
AbortManagerThrownError,
} from "./lib/abortManager";
import {
ScrapeJobTimeoutError,
CrawlDenialError,
ActionsNotSupportedError,
} from "../../lib/error";
import { htmlTransform } from "./lib/removeUnwantedElements";
import { postprocessors } from "./postprocessors";
import { rewriteUrl } from "./lib/rewriteUrl";
import { writeFile } from "node:fs/promises";
import path from "node:path";
import { tmpdir } from "node:os";
import { randomUUID } from "node:crypto";
export type ScrapeUrlResponse =
| {
success: true;
document: Document;
unsupportedFeatures?: Set<FeatureFlag>;
}
| {
success: false;
error: any;
};
export type BrowserCookie = {
name: string;
value: string;
domain?: string;
path?: string;
expires?: number;
httpOnly?: boolean;
secure?: boolean;
sameSite?: string;
[key: string]: unknown;
};
export type Meta = {
id: string;
url: string;
rewrittenUrl?: string;
options: ScrapeOptions & { skipTlsVerification: boolean };
internalOptions: InternalOptions;
logger: Logger;
abort: AbortManager;
featureFlags: Set<FeatureFlag>;
mock: MockState | null;
pdfPrefetch:
| {
filePath: string;
url?: string;
status: number;
proxyUsed: "basic" | "stealth";
contentType?: string;
}
| null
| undefined; // undefined: no prefetch yet, null: prefetch came back empty
documentPrefetch:
| {
filePath: string;
url?: string;
status: number;
proxyUsed: "basic" | "stealth";
contentType?: string;
}
| null
| undefined; // undefined: no prefetch yet, null: prefetch came back empty
fetchPrefetch:
| {
url?: string;
status: number;
bodyBuffer: Buffer;
proxyUsed: "basic" | "stealth";
contentType?: string;
}
| null
| undefined; // undefined: no prefetch yet, null: prefetch came back empty
costTracking: CostTracking;
winnerEngine?: Engine;
abortHandle?: NodeJS.Timeout;
audioCookies?: BrowserCookie[];
};
function buildFeatureFlags(
url: string,
options: ScrapeOptions,
internalOptions: InternalOptions,
): Set<FeatureFlag> {
const flags: Set<FeatureFlag> = new Set();
// Lockdown forces index-only engines and ignores every request-time feature.
// Return empty so the fallback threshold never filters index engines out.
if (options.lockdown) {
return flags;
}
if (options.actions !== undefined && options.actions.length > 0) {
flags.add("actions");
}
if (hasFormatOfType(options.formats, "screenshot")) {
if (hasFormatOfType(options.formats, "screenshot")?.fullPage) {
flags.add("screenshot@fullScreen");
} else {
flags.add("screenshot");
}
}
if (hasFormatOfType(options.formats, "branding")) {
flags.add("branding");
}
if (hasFormatOfType(options.formats, "audio")) {
flags.add("audio");
}
if (hasFormatOfType(options.formats, "video")) {
flags.add("video");
}
if (options.waitFor !== 0) {
flags.add("waitFor");
}
if (internalOptions.atsv) {
flags.add("atsv");
}
if (options.location) {
flags.add("location");
}
if (options.mobile) {
flags.add("mobile");
}
if (options.skipTlsVerification) {
flags.add("skipTlsVerification");
}
if (options.fastMode) {
flags.add("useFastMode");
}
if (options.proxy === "stealth" || options.proxy === "enhanced") {
flags.add("stealthProxy");
}
const urlO = new URL(url);
const lowerPath = urlO.pathname.toLowerCase();
// Check for document types first (they take precedence over PDF)
const isDocument =
lowerPath.endsWith(".docx") ||
lowerPath.endsWith(".odt") ||
lowerPath.endsWith(".rtf") ||
lowerPath.endsWith(".xlsx") ||
lowerPath.endsWith(".xls") ||
lowerPath.includes(".docx/") ||
lowerPath.includes(".odt/") ||
lowerPath.includes(".rtf/") ||
lowerPath.includes(".xlsx/") ||
lowerPath.includes(".xls/");
if (isDocument) {
flags.add("document");
} else if (lowerPath.endsWith(".pdf") || lowerPath.includes(".pdf/")) {
// Only add PDF flag if it's not a document
flags.add("pdf");
}
if (options.blockAds === false) {
flags.add("disableAdblock");
}
return flags;
}
// The meta object contains all required information to perform a scrape.
// For example, the scrape ID, URL, options, feature flags, logs that occur while scraping.
// The meta object is usually immutable, except for the logs array, and in edge cases (e.g. a new feature is suddenly required)
// Having a meta object that is treated as immutable helps the code stay clean and easily tracable,
// while also retaining the benefits that WebScraper had from its OOP design.
const DOCUMENT_EXTENSIONS = new Set([
".docx",
".doc",
".odt",
".rtf",
".xlsx",
".xls",
]);
const HTML_EXTENSIONS = new Set([".html", ".htm", ".xhtml"]);
async function writeUploadedFileToTemp(
uploadedFilename: string,
uploadedBuffer: Buffer,
fallbackExtension: string,
): Promise<string> {
const ext = path.extname(uploadedFilename).toLowerCase() || fallbackExtension;
const safeExt = ext.startsWith(".") ? ext : `.${ext}`;
const tempFilePath = path.join(
tmpdir(),
`parse-upload-${randomUUID()}${safeExt}`,
);
await writeFile(tempFilePath, uploadedBuffer);
return tempFilePath;
}
function isPdfUpload(filename: string, contentType?: string): boolean {
const ext = path.extname(filename).toLowerCase();
const normalizedType = contentType?.toLowerCase() ?? "";
return (
ext === ".pdf" ||
normalizedType === "application/pdf" ||
normalizedType.startsWith("application/pdf;")
);
}
function isDocumentUpload(filename: string, contentType?: string): boolean {
const ext = path.extname(filename).toLowerCase();
const normalizedType = contentType?.toLowerCase() ?? "";
return (
DOCUMENT_EXTENSIONS.has(ext) ||
normalizedType.includes(
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
) ||
normalizedType.includes("application/vnd.ms-excel") ||
normalizedType.includes(
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
) ||
normalizedType.includes("application/msword") ||
normalizedType.includes("application/vnd.oasis.opendocument.text") ||
normalizedType.includes("application/rtf") ||
normalizedType.includes("text/rtf")
);
}
function isHtmlUpload(filename: string, contentType?: string): boolean {
const ext = path.extname(filename).toLowerCase();
const normalizedType = contentType?.toLowerCase() ?? "";
return (
HTML_EXTENSIONS.has(ext) ||
normalizedType.includes("text/html") ||
normalizedType.includes("application/xhtml+xml")
);
}
async function buildMetaObject(
id: string,
url: string,
options: ScrapeOptions,
internalOptions: InternalOptions,
costTracking: CostTracking,
): Promise<Meta> {
const specParams =
urlSpecificParams[new URL(url).hostname.replace(/^www\./, "")];
if (specParams !== undefined) {
options = Object.assign(options, specParams.scrapeOptions);
internalOptions = Object.assign(
internalOptions,
specParams.internalOptions,
);
}
if (internalOptions.forceEngine === undefined) {
const forcedEngine = getEngineForUrl(url);
if (forcedEngine !== undefined) {
internalOptions = Object.assign(internalOptions, {
forceEngine: forcedEngine,
});
}
}
const logger = _logger.child({
module: "ScrapeURL",
scrapeId: id,
scrapeURL: url,
zeroDataRetention: internalOptions.zeroDataRetention,
teamId: internalOptions.teamId,
team_id: internalOptions.teamId,
crawlId: internalOptions.crawlId,
});
const abortController = new AbortController();
const abortHandle =
options.timeout !== undefined
? setTimeout(
() => abortController.abort(new ScrapeJobTimeoutError()),
options.timeout,
)
: undefined;
let pdfPrefetch: Meta["pdfPrefetch"] = undefined;
let documentPrefetch: Meta["documentPrefetch"] = undefined;
let fetchPrefetch: Meta["fetchPrefetch"] = undefined;
if (internalOptions.uploadedFile) {
const { filename, buffer, contentType } = internalOptions.uploadedFile;
const prefetchUrl = rewriteUrl(url) ?? url;
if (isPdfUpload(filename, contentType)) {
const filePath = await writeUploadedFileToTemp(filename, buffer, ".pdf");
pdfPrefetch = {
filePath,
status: 200,
url: prefetchUrl,
proxyUsed: "basic",
contentType: contentType || "application/pdf",
};
} else if (isDocumentUpload(filename, contentType)) {
const ext = path.extname(filename).toLowerCase();
const fallbackExtension =
ext && DOCUMENT_EXTENSIONS.has(ext) ? ext : ".docx";
const filePath = await writeUploadedFileToTemp(
filename,
buffer,
fallbackExtension,
);
documentPrefetch = {
filePath,
status: 200,
url: prefetchUrl,
proxyUsed: "basic",
contentType:
contentType ||
"application/vnd.openxmlformats-officedocument.wordprocessingml.document",
};
} else if (isHtmlUpload(filename, contentType)) {
fetchPrefetch = {
url: prefetchUrl,
status: 200,
bodyBuffer: buffer,
proxyUsed: "basic",
contentType: contentType || "text/html; charset=utf-8",
};
} else {
throw new UnsupportedFileError(
contentType || path.extname(filename) || "unknown",
);
}
}
return {
id,
url,
rewrittenUrl: rewriteUrl(url),
options: {
...options,
skipTlsVerification:
options.skipTlsVerification ??
((options.headers && Object.keys(options.headers).length > 0) ||
(options.actions && options.actions.length > 0)
? false
: true),
},
internalOptions,
logger,
abortHandle,
abort: new AbortManager(
internalOptions.externalAbort,
options.timeout !== undefined
? {
signal: abortController.signal,
tier: "scrape",
timesOutAt: new Date(Date.now() + options.timeout),
throwable() {
return new ScrapeJobTimeoutError();
},
}
: undefined,
),
featureFlags: buildFeatureFlags(url, options, internalOptions),
mock:
options.useMock !== undefined
? await loadMock(options.useMock, _logger)
: null,
pdfPrefetch,
documentPrefetch,
fetchPrefetch,
costTracking,
};
}
export type InternalOptions = {
teamId: string;
crawlId?: string;
priority?: number; // Passed along to fire-engine
forceEngine?: Engine | Engine[];
atsv?: boolean; // anti-bot solver, beta
v0CrawlOnlyUrls?: boolean;
v0DisableJsDom?: boolean;
disableSmartWaitCache?: boolean; // Passed along to fire-engine
isBackgroundIndex?: boolean;
externalAbort?: AbortInstance;
urlInvisibleInCurrentCrawl?: boolean;
unnormalizedSourceURL?: string;
saveScrapeResultToGCS?: boolean; // Passed along to fire-engine
bypassBilling?: boolean;
zeroDataRetention?: boolean;
teamFlags?: TeamFlags;
v1Agent?: ScrapeOptionsV1["agent"];
v1JSONAgent?: Exclude<ScrapeOptionsV1["jsonOptions"], undefined>["agent"];
v1JSONSystemPrompt?: string;
v1OriginalFormat?: "extract" | "json"; // Track original v1 format for backward compatibility
isPreCrawl?: boolean; // Whether this scrape is part of a precrawl job
agentIndexOnly?: boolean; // Pre-confirmation agent key: serve from index only, never touch web/Fire Engine
isParse?: boolean; // Whether this scrape originated from /v2/parse
uploadedFile?: {
buffer: Buffer;
filename: string;
contentType?: string;
kind?: "html" | "pdf" | "document";
};
};
type EngineScrapeResultWithContext = {
engine: Engine;
unsupportedFeatures: Set<FeatureFlag>;
result: EngineScrapeResult;
};
const MAX_HTML_SIZE_FOR_MARKDOWN_CHECK = 300 * 1024; // 300KB
async function scrapeURLLoopIter(
meta: Meta,
engine: Engine,
snipeAbort,
): Promise<EngineScrapeResult> {
const abort = meta.abort.child(snipeAbort);
try {
const engineResult = await scrapeURLWithEngine(
{
...meta,
abort,
},
engine,
);
const hasMarkdown = hasFormatOfType(meta.options.formats, "markdown");
const hasChangeTracking = hasFormatOfType(
meta.options.formats,
"changeTracking",
);
const hasJson = hasFormatOfType(meta.options.formats, "json");
const hasSummary = hasFormatOfType(meta.options.formats, "summary");
const hasQuestion = hasFormatOfType(meta.options.formats, "question");
const hasHighlights = hasFormatOfType(meta.options.formats, "highlights");
const hasQuery = hasFormatOfType(meta.options.formats, "query");
const needsMarkdown =
hasMarkdown ||
hasChangeTracking ||
hasJson ||
hasSummary ||
hasQuestion ||
hasHighlights ||
hasQuery;
let checkMarkdown: string;
const htmlSize = engineResult.html?.length ?? 0;
const shouldSkipMarkdownCheck = htmlSize > MAX_HTML_SIZE_FOR_MARKDOWN_CHECK;
if (
meta.internalOptions.teamId === "sitemap" ||
meta.internalOptions.teamId === "robots-txt"
) {
checkMarkdown = engineResult.html?.trim() ?? "";
} else if (!needsMarkdown) {
checkMarkdown = engineResult.html?.trim() ?? "";
} else if (shouldSkipMarkdownCheck) {
// Skip markdown conversion for large HTML to avoid slowdowns
meta.logger.debug(
"Skipping markdown conversion for quality check due to large HTML size",
{
htmlSize,
threshold: MAX_HTML_SIZE_FOR_MARKDOWN_CHECK,
},
);
checkMarkdown = engineResult.html?.trim() ?? "";
} else {
const requestId = meta.id || meta.internalOptions.crawlId;
const zeroDataRetention = meta.internalOptions.zeroDataRetention;
checkMarkdown = await parseMarkdown(
await htmlTransform(
engineResult.html,
meta.url,
scrapeOptions.parse({ onlyMainContent: true }),
),
{ logger: meta.logger, requestId, zeroDataRetention },
);
if (checkMarkdown.trim().length === 0) {
checkMarkdown = await parseMarkdown(
await htmlTransform(
engineResult.html,
meta.url,
scrapeOptions.parse({ onlyMainContent: false }),
),
{ logger: meta.logger, requestId, zeroDataRetention },
);
}
}
// Success factors
const isLongEnough = checkMarkdown.trim().length > 0;
const isGoodStatusCode =
(engineResult.statusCode >= 200 && engineResult.statusCode < 300) ||
engineResult.statusCode === 304;
const hasNoPageError = engineResult.error === undefined;
const isLikelyProxyError = [401, 403, 429].includes(
engineResult.statusCode,
);
if (
isLikelyProxyError &&
meta.options.proxy === "auto" &&
!meta.featureFlags.has("stealthProxy")
) {
meta.logger.info(
"Scrape via " +
engine +
" deemed unsuccessful due to proxy inadequacy. Adding stealthProxy flag.",
{
factors: { isLongEnough, isGoodStatusCode, hasNoPageError },
statusCode: engineResult.statusCode,
length: engineResult.html?.trim().length ?? 0,
},
);
throw new AddFeatureError(["stealthProxy"]);
}
// NOTE: TODO: what to do when status code is bad is tough...
// we cannot just rely on text because error messages can be brief and not hit the limit
// should we just use all the fallbacks and pick the one with the longest text? - mogery
if (isLongEnough || !isGoodStatusCode) {
meta.logger.info("Scrape via " + engine + " deemed successful.", {
factors: { isLongEnough, isGoodStatusCode, hasNoPageError },
});
return engineResult;
} else {
meta.logger.warn("Scrape via " + engine + " deemed unsuccessful.", {
factors: { isLongEnough, isGoodStatusCode, hasNoPageError },
length: engineResult.html?.trim().length ?? 0,
});
throw new EngineUnsuccessfulError(engine);
}
} finally {
abort?.dispose();
}
}
class WrappedEngineError extends Error {
name = "WrappedEngineError";
public engine: Engine;
public error: any;
constructor(engine: Engine, error: any) {
super("WrappedEngineError");
this.engine = engine;
this.error = error;
}
}
async function scrapeURLLoop(meta: Meta): Promise<ScrapeUrlResponse> {
return withSpan("scrape.engine_loop", async span => {
meta.logger.info(
`Scraping URL ${JSON.stringify(meta.rewrittenUrl ?? meta.url)}...`,
);
setSpanAttributes(span, {
"engine.url": meta.rewrittenUrl ?? meta.url,
"engine.features": Array.from(meta.featureFlags).join(","),
});
if (meta.internalOptions.zeroDataRetention) {
if (meta.featureFlags.has("screenshot")) {
throw new ZDRViolationError("screenshot");
}
if (meta.featureFlags.has("screenshot@fullScreen")) {
throw new ZDRViolationError("screenshot@fullScreen");
}
if (
meta.options.actions &&
meta.options.actions.find(x => x.type === "screenshot")
) {
throw new ZDRViolationError("screenshot action");
}
if (
meta.options.actions &&
meta.options.actions.find(x => x.type === "pdf")
) {
throw new ZDRViolationError("pdf action");
}
}
// TODO: handle sitemap data, see WebScraper/index.ts:280
// TODO: ScrapeEvents
const fallbackList = await buildFallbackList(meta);
// Check if actions are requested but no engines support them
if (meta.featureFlags.has("actions")) {
if (
fallbackList.length === 0 ||
fallbackList.every(engine => engine.unsupportedFeatures.has("actions"))
) {
throw new ActionsNotSupportedError(
"Actions are not supported by any available engines. Actions require Fire Engine (fire-engine) to be enabled.",
);
}
}
setSpanAttributes(span, {
"engine.fallback_list": fallbackList.map(f => f.engine).join(","),
});
const snipeAbortController = new AbortController();
const snipeAbort: AbortInstance = {
signal: snipeAbortController.signal,
tier: "engine",
throwable() {
return new EngineSnipedError();
},
};
type EngineBundlePromise = {
engine: Engine;
unsupportedFeatures: Set<FeatureFlag>;
promise: Promise<EngineScrapeResultWithContext>;
};
const remainingEngines = [...fallbackList];
let enginePromises: EngineBundlePromise[] = [];
const enginesAttempted: string[] = [];
meta.abort.throwIfAborted();
let result: EngineScrapeResultWithContext | null = null;
while (remainingEngines.length > 0) {
const { engine, unsupportedFeatures } = remainingEngines.shift()!;
enginesAttempted.push(engine);
const waitUntilWaterfall =
getEngineMaxReasonableTime(meta, engine) +
config.SCRAPEURL_ENGINE_WATERFALL_DELAY_MS;
if (
!isFinite(waitUntilWaterfall) ||
isNaN(waitUntilWaterfall) ||
waitUntilWaterfall <= 0
) {
meta.logger.warn("Invalid waitUntilWaterfall value", {
waitUntilWaterfall,
timeout: meta.options.timeout,
actions: !!meta.options.actions,
hasJson: !!meta.options.formats?.find(x => x.type === "json"),
remainingEngines: remainingEngines.length,
});
}
meta.logger.info("Scraping via " + engine + "...", {
waitUntilWaterfall,
});
enginePromises.push({
engine,
unsupportedFeatures,
promise: (async () => {
try {
return {
engine,
unsupportedFeatures,
result: await scrapeURLLoopIter(meta, engine, snipeAbort),
};
} catch (error) {
throw new WrappedEngineError(engine, error);
}
})(),
});
while (true) {
let timeouts: NodeJS.Timeout[] = [];
try {
result = await Promise.race([
...enginePromises.map(x => x.promise),
...(remainingEngines.length > 0
? [
new Promise<EngineScrapeResultWithContext>((_, reject) => {
timeouts.push(
setTimeout(() => {
reject(new WaterfallNextEngineSignal());
}, waitUntilWaterfall),
);
}),
]
: []),
new Promise<EngineScrapeResultWithContext>((_, reject) => {
timeouts.push(
setTimeout(() => {
try {
meta.abort.throwIfAborted();
// Fallback error if above doesn't throw
const usingDefaultTimeout =
meta.abort.scrapeTimeout() === undefined;
throw new ScrapeJobTimeoutError(
usingDefaultTimeout
? "Scrape timed out due to maximum length of 5 minutes"
: "Scrape timed out",
);
} catch (error) {
reject(error);
}
}, meta.abort.scrapeTimeout() ?? 300000),
);
}),
]);
break;
} catch (error) {
if (error instanceof WrappedEngineError) {
if (error.engine === "x-twitter") {
meta.logger.warn("X/Twitter scrape failed fatally.", {
error: error.error,
});
throw error.error;
} else if (error.error instanceof EngineError) {
meta.logger.warn(
"Engine " + error.engine + " could not scrape the page.",
{
error: error.error,
},
);
} else if (error.error instanceof IndexMissError) {
meta.logger.warn(
"Engine " +
error.engine +
" could not find the page in the index.",
{
error: error.error,
},
);
} else if (
error.error instanceof AddFeatureError ||
error.error instanceof RemoveFeatureError ||
error.error instanceof SiteError ||
error.error instanceof SSLError ||
error.error instanceof DNSResolutionError ||
error.error instanceof ActionError ||
error.error instanceof UnsupportedFileError ||
error.error instanceof PDFAntibotError ||
error.error instanceof PDFOCRRequiredError ||
error.error instanceof DocumentAntibotError ||
error.error instanceof PDFInsufficientTimeError ||
error.error instanceof ProxySelectionError ||
error.error instanceof NoCachedDataError ||
error.error instanceof AgentIndexOnlyError ||
error.error instanceof XTwitterConfigurationError
) {
throw error.error;
} else if (error.error instanceof LLMRefusalError) {
meta.logger.warn("LLM refusal encountered", {
error: error.error,
});
throw error.error;
} else if (error.error instanceof FEPageLoadFailed) {
// This is the internal timeout bug on f-e and should be treated as an EngineError.
meta.logger.warn("FEPageLoadFailed encountered", {
error: error.error,
});
} else if (error.error instanceof AbortManagerThrownError) {
if (error.error.tier === "engine") {
meta.logger.warn(
"Engine " + error.engine + " timed out while scraping.",
{ error: error.error },
);
} else {
throw error.error;
}
} else {
meta.logger.warn(
"An unexpected error happened while scraping with " +
error.engine +
".",
{ error },
);
}
// Filter out the failed engine
enginePromises = enginePromises.filter(
x => x.engine !== error.engine,
);
// If we don't have any engines waterfalled, let's waterfall the next engine
if (enginePromises.length === 0) {
break;
}
// Otherwise, just keep racing
} else if (
error instanceof AddFeatureError ||
error instanceof RemoveFeatureError
) {
throw error;
} else if (error instanceof WaterfallNextEngineSignal) {
// It's time to waterfall the next engine
break;
} else if (error instanceof ScrapeJobTimeoutError) {
throw error;
} else if (error instanceof AbortManagerThrownError) {
if (error.tier === "engine") {
meta.logger.warn(
"Engine-scoped timeout error received here. Weird!",
{ error },
);
}
throw error;
} else {
meta.logger.warn("Unexpected error while racing engines", {
error,
});
throw error;
}
} finally {
for (const to of timeouts) {
clearTimeout(to);
}
}
}
if (result === null) {
meta.logger.info("Waterfalling to next engine...", {
waitUntilWaterfall,
});
} else {
break;
}
}
snipeAbortController.abort();
if (result === null) {
setSpanAttributes(span, {
"engine.no_engines_left": true,
"engine.engines_attempted": enginesAttempted.join(","),
});
if (meta.options.lockdown) {
throw new LockdownMissError();
}
throw new NoEnginesLeftError(fallbackList.map(x => x.engine));
}
// Set winner engine attributes
setSpanAttributes(span, {
"engine.winner": result.engine,
"engine.engines_attempted": enginesAttempted.join(","),
"engine.unsupported_features":
result.unsupportedFeatures.size > 0
? Array.from(result.unsupportedFeatures).join(",")
: undefined,
});
meta.winnerEngine = result.engine;
let engineResult: EngineScrapeResult = result.result;
meta.audioCookies = (
engineResult as { audioCookies?: BrowserCookie[] }
).audioCookies;
for (const postprocessor of postprocessors) {
if (
postprocessor.shouldRun(
meta,
new URL(engineResult.url),
engineResult.postprocessorsUsed,
)
) {
meta.logger.info("Running postprocessor " + postprocessor.name);
try {
engineResult = await postprocessor.run(
{
...meta,
logger: meta.logger.child({
method: "postprocessors/" + postprocessor.name,
}),
},
engineResult,
);
} catch (error) {
meta.logger.warn(
"Failed to run postprocessor " + postprocessor.name,
{
error,
},
);
}
}
}
let document: Document = {
markdown: engineResult.markdown,
rawHtml: engineResult.html,
screenshot: engineResult.screenshot,
actions: engineResult.actions,
branding: engineResult.branding,
metadata: {
sourceURL: meta.internalOptions.unnormalizedSourceURL ?? meta.url,
url: engineResult.url,
statusCode: engineResult.statusCode,
error: engineResult.error,
numPages: engineResult.pdfMetadata?.numPages,
...(engineResult.pdfMetadata?.title
? { title: engineResult.pdfMetadata.title }
: {}),
contentType: engineResult.contentType,
timezone: engineResult.timezone,
proxyUsed: engineResult.proxyUsed ?? "basic",
...(fallbackList.find(x =>
["index", "index;documents"].includes(x.engine),
)
? engineResult.cacheInfo
? {
cacheState: "hit",
cachedAt: engineResult.cacheInfo.created_at.toISOString(),
}
: {
cacheState: "miss",
}
: {}),
postprocessorsUsed: engineResult.postprocessorsUsed,
},
};
if (result.unsupportedFeatures.size > 0) {
const warning = `The engine used does not support the following features: ${[...result.unsupportedFeatures].join(", ")} -- your scrape may be partial.`;
meta.logger.warn(warning, {
engine: result.engine,
unsupportedFeatures: result.unsupportedFeatures,
});
document.warning =
document.warning !== undefined
? document.warning + " " + warning
: warning;
}
// NOTE: for sitemap, we don't need all the transformers, need to skip unused ones
document = await executeTransformers(meta, document);
// Set final span attributes
setSpanAttributes(span, {
"engine.final_status_code": document.metadata.statusCode,
"engine.final_url": document.metadata.url,
"engine.content_type": document.metadata.contentType,
"engine.proxy_used": document.metadata.proxyUsed,
"engine.cache_state": document.metadata.cacheState,
"engine.postprocessors_used": engineResult.postprocessorsUsed?.join(","),
});
return {
success: true,
document,
unsupportedFeatures: result.unsupportedFeatures,
};
});
}
export async function scrapeURL(
id: string,
url: string,
options: ScrapeOptions,
internalOptions: InternalOptions,
costTracking: CostTracking,
): Promise<ScrapeUrlResponse> {
return withSpan("scrape.pipeline", async span => {
const meta = await buildMetaObject(
id,
url,
options,
internalOptions,
costTracking,
);
const startTime = Date.now();
// Set initial span attributes
setSpanAttributes(span, {
"scrape.id": id,
"scrape.url": url,
"scrape.team_id": internalOptions.teamId,
"scrape.crawl_id": internalOptions.crawlId,
"scrape.zero_data_retention": internalOptions.zeroDataRetention,
"scrape.force_engine": Array.isArray(internalOptions.forceEngine)
? internalOptions.forceEngine.join(",")
: internalOptions.forceEngine,
"scrape.features": Array.from(meta.featureFlags).join(","),
});
meta.logger.info("scrapeURL entered");
if (meta.rewrittenUrl) {
meta.logger.info("Rewriting URL");
setSpanAttributes(span, {
"scrape.rewritten_url": meta.rewrittenUrl,
});
}
if (internalOptions.isPreCrawl === true) {
setSpanAttributes(span, {
"scrape.is_precrawl": true,
});
}
if (shouldCheckRobots(options, internalOptions)) {
await withSpan("scrape.robots_check", async robotsSpan => {
const urlToCheck = meta.rewrittenUrl || meta.url;
meta.logger.info("Checking robots.txt", { url: urlToCheck });
const urlObj = new URL(urlToCheck);
const isRobotsTxtPath = urlObj.pathname === "/robots.txt";
setSpanAttributes(robotsSpan, {
"robots.url": urlToCheck,
"robots.is_robots_txt_path": isRobotsTxtPath,
});
if (!isRobotsTxtPath) {
try {
let robotsTxt: string | undefined;
if (internalOptions.crawlId) {
const crawl = await getCrawl(internalOptions.crawlId);
robotsTxt = crawl?.robots;
}
if (!robotsTxt) {
const { content } = await fetchRobotsTxt(
{
url: urlToCheck,
zeroDataRetention: internalOptions.zeroDataRetention || false,
location: options.location,
},
id,
meta.logger,
meta.abort.asSignal(),
);
robotsTxt = content;
}
const checker = createRobotsChecker(urlToCheck, robotsTxt);
const isAllowed = isUrlAllowedByRobots(urlToCheck, checker.robots);
setSpanAttributes(robotsSpan, {
"robots.allowed": isAllowed,
});
if (!isAllowed) {
meta.logger.info("URL blocked by robots.txt", {
url: urlToCheck,
});
setSpanAttributes(span, {
"scrape.blocked_by_robots": true,
});
throw new CrawlDenialError("URL blocked by robots.txt");
}
} catch (error) {
if (error instanceof CrawlDenialError) {
throw error;
}
meta.logger.debug("Failed to fetch robots.txt, allowing scrape", {
error,
url: urlToCheck,
});
setSpanAttributes(robotsSpan, {
"robots.fetch_failed": true,
});
}
}
}).catch(error => {
if (error.message === "URL blocked by robots.txt") {
return {
success: false,
error,
};
}
throw error;
});
}
// Initialize retry tracker with configured limits
const retryTracker = new ScrapeRetryTracker(
{
maxAttempts: config.SCRAPE_MAX_ATTEMPTS,
maxFeatureToggles: config.SCRAPE_MAX_FEATURE_TOGGLES,
maxFeatureRemovals: config.SCRAPE_MAX_FEATURE_REMOVALS,
maxPdfPrefetches: config.SCRAPE_MAX_PDF_PREFETCHES,
maxDocumentPrefetches: config.SCRAPE_MAX_DOCUMENT_PREFETCHES,
},
meta.logger,
);
try {
let result: ScrapeUrlResponse;
while (true) {
try {
result = await scrapeURLLoop(meta);
break;
} catch (error) {
if (
error instanceof AddFeatureError &&
(meta.internalOptions.forceEngine === undefined ||
Array.isArray(meta.internalOptions.forceEngine))
) {
retryTracker.record("feature_toggle", error);
meta.logger.debug(
"More feature flags requested by scraper: adding " +
error.featureFlags.join(", "),
{ error, existingFlags: meta.featureFlags },
);
meta.featureFlags = new Set(
[...meta.featureFlags].concat(error.featureFlags),
);
if (error.pdfPrefetch) {
meta.pdfPrefetch = error.pdfPrefetch;
}
if (error.documentPrefetch) {
meta.documentPrefetch = error.documentPrefetch;
}
} else if (
error instanceof RemoveFeatureError &&
(meta.internalOptions.forceEngine === undefined ||
Array.isArray(meta.internalOptions.forceEngine))
) {
retryTracker.record("feature_removal", error);
meta.logger.debug(
"Incorrect feature flags reported by scraper: removing " +
error.featureFlags.join(","),
{ error, existingFlags: meta.featureFlags },
);
meta.featureFlags = new Set(
[...meta.featureFlags].filter(
x => !error.featureFlags.includes(x),
),
);
} else if (
error instanceof PDFAntibotError &&
meta.internalOptions.forceEngine === undefined
) {
if (meta.pdfPrefetch !== undefined) {
meta.logger.error(
"PDF was prefetched and still blocked by antibot, failing",
);
throw error;
} else {
retryTracker.record("pdf_antibot", error);
meta.logger.debug(
"PDF was blocked by anti-bot, prefetching with chrome-cdp",
);
meta.featureFlags = new Set(
[...meta.featureFlags].filter(x => x !== "pdf"),
);
}
} else if (
error instanceof DocumentAntibotError &&
meta.internalOptions.forceEngine === undefined
) {
if (meta.documentPrefetch !== undefined) {
meta.logger.error(
"Document was prefetched and still blocked by antibot, failing",
);
throw error;
} else {
retryTracker.record("document_antibot", error);
meta.logger.debug(
"Document was blocked by anti-bot, prefetching with chrome-cdp",
);
meta.featureFlags = new Set(
[...meta.featureFlags].filter(x => x !== "document"),
);
}
} else {
throw error;
}
}
}
meta.logger.debug("scrapeURL metrics", {
module: "scrapeURL/metrics",
timeTaken: Date.now() - startTime,
maxAgeValid: (meta.options.maxAge ?? 0) > 0,
shouldUseIndex: shouldUseIndex(meta),
success: result.success,
indexHit:
result.success && result.document.metadata.cacheState === "hit",
});
if (useIndex) {
meta.logger.debug("scrapeURL index metrics", {
module: "scrapeURL/index-metrics",
timeTaken: Date.now() - startTime,
changeTrackingEnabled: !!hasFormatOfType(
meta.options.formats,
"changeTracking",
),
summaryEnabled: !!hasFormatOfType(meta.options.formats, "summary"),
jsonEnabled: !!hasFormatOfType(meta.options.formats, "json"),
screenshotEnabled: !!hasFormatOfType(
meta.options.formats,
"screenshot",
),
imagesEnabled: !!hasFormatOfType(meta.options.formats, "images"),
brandingEnabled: !!hasFormatOfType(meta.options.formats, "branding"),
pdfMaxPages: getPDFMaxPages(meta.options.parsers),
maxAge: meta.options.maxAge,
headers: meta.options.headers
? Object.keys(meta.options.headers).length
: 0,
actions: meta.options.actions?.length ?? 0,
proxy: meta.options.proxy,
success: result.success,
indexHit:
result.success && result.document.metadata.cacheState === "hit",
});
}
setSpanAttributes(span, {
"scrape.success": true,
"scrape.duration_ms": Date.now() - startTime,
"scrape.index_hit":
result.success && result.document.metadata.cacheState === "hit",
});
return result;
} catch (error) {
// if (Object.values(meta.results).length > 0 && Object.values(meta.results).every(x => x.state === "error" && x.error instanceof FEPageLoadFailed)) {
// throw new FEPageLoadFailed();
// } else
meta.logger.debug("scrapeURL metrics", {
module: "scrapeURL/metrics",
timeTaken: Date.now() - startTime,
maxAgeValid: (meta.options.maxAge ?? 0) > 0,
shouldUseIndex: shouldUseIndex(meta),
success: false,
indexHit: false,
});
if (useIndex) {
meta.logger.debug("scrapeURL index metrics", {
module: "scrapeURL/index-metrics",
timeTaken: Date.now() - startTime,
changeTrackingEnabled: !!hasFormatOfType(
meta.options.formats,
"changeTracking",
),
summaryEnabled: !!hasFormatOfType(meta.options.formats, "summary"),
jsonEnabled: !!hasFormatOfType(meta.options.formats, "json"),
screenshotEnabled: !!hasFormatOfType(
meta.options.formats,
"screenshot",
),
imagesEnabled: !!hasFormatOfType(meta.options.formats, "images"),
brandingEnabled: !!hasFormatOfType(meta.options.formats, "branding"),
pdfMaxPages: getPDFMaxPages(meta.options.parsers),
maxAge: meta.options.maxAge,
headers: meta.options.headers
? Object.keys(meta.options.headers).length
: 0,
actions: meta.options.actions?.length ?? 0,
proxy: meta.options.proxy,
success: false,
indexHit: false,
});
}
// Set error attributes on span
let errorType = "unknown";
if (error instanceof NoEnginesLeftError) {
errorType = "NoEnginesLeftError";
meta.logger.warn("scrapeURL: All scraping engines failed!", { error });
} else if (error instanceof LLMRefusalError) {
errorType = "LLMRefusalError";
meta.logger.warn("scrapeURL: LLM refused to extract content", {
error,
});
} else if (
error instanceof Error &&
error.message.includes("Invalid schema for response_format")
) {
errorType = "LLMSchemaError";
// TODO: separate into custom error
meta.logger.warn("scrapeURL: LLM schema error", { error });
// TODO: results?
} else if (error instanceof SiteError) {
errorType = "SiteError";
meta.logger.warn("scrapeURL: Site failed to load in browser", {
error,
});
} else if (error instanceof SSLError) {
errorType = "SSLError";
meta.logger.warn("scrapeURL: SSL error", { error });
} else if (error instanceof ActionError) {
errorType = "ActionError";
meta.logger.warn("scrapeURL: Action(s) failed to complete", { error });
} else if (error instanceof UnsupportedFileError) {
errorType = "UnsupportedFileError";
meta.logger.warn("scrapeURL: Tried to scrape unsupported file", {
error,
});
} else if (error instanceof PDFInsufficientTimeError) {
errorType = "PDFInsufficientTimeError";
meta.logger.warn("scrapeURL: Insufficient time to process PDF", {
error,
});
} else if (error instanceof PDFOCRRequiredError) {
errorType = "PDFOCRRequiredError";
meta.logger.warn(
"scrapeURL: PDF requires OCR but fast mode was requested",
{
error,
},
);
} else if (error instanceof PDFPrefetchFailed) {
errorType = "PDFPrefetchFailed";
meta.logger.warn(
"scrapeURL: Failed to prefetch PDF that is protected by anti-bot",
{ error },
);
} else if (error instanceof DocumentPrefetchFailed) {
errorType = "DocumentPrefetchFailed";
meta.logger.warn(
"scrapeURL: Failed to prefetch document that is protected by anti-bot",
{ error },
);
} else if (error instanceof BrandingNotSupportedError) {
errorType = "BrandingNotSupportedError";
meta.logger.warn("scrapeURL: Branding not supported for this content", {
error,
});
} else if (error instanceof ProxySelectionError) {
errorType = "ProxySelectionError";
meta.logger.warn("scrapeURL: Proxy selection error", { error });
} else if (error instanceof DNSResolutionError) {
errorType = "DNSResolutionError";
meta.logger.warn("scrapeURL: DNS resolution error", { error });
} else if (error instanceof ScrapeRetryLimitError) {
errorType = "ScrapeRetryLimitError";
meta.logger.warn("scrapeURL: Retry limit reached", {
error,
retryStats: error.stats,
});
} else if (error instanceof AbortManagerThrownError) {
errorType = "AbortManagerThrownError";
throw error.inner;
} else {
captureExceptionWithZdrCheck(error, {
extra: {
zeroDataRetention: internalOptions.zeroDataRetention ?? false,
},
});
meta.logger.error("scrapeURL: Unexpected error happened", { error });
// TODO: results?
}
setSpanAttributes(span, {
"scrape.success": false,
"scrape.error": error instanceof Error ? error.message : String(error),
"scrape.error_type": errorType,
"scrape.duration_ms": Date.now() - startTime,
});
return {
success: false,
error,
};
}
});
}
|