yujunjun/firecrawl
1
0
Fork 0
mirror of https://github.com/mendableai/firecrawl.git synced 2025-11-01 18:42:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

compare format (FIR-1560) (#1405)

Browse Source
This commit is contained in:
Gergő Móricz 2025-04-02 19:52:43 +02:00 committed by GitHub
parent b3b63486f1
commit 24f5199359
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
24 changed files with 223 additions and 36 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
apps/api/requests.http
View File

@ -19,7 +19,7 @@ Authorization: Bearer {{$dotenv TEST_API_KEY}}
content-type: application/json
{
"url": "https://firecrawl.dev"
"url":"https://firecrawl.dev"
}
### Check Crawl Status

12
apps/api/src/__tests__/snips/scrape.test.ts
View File

@ -84,6 +84,18 @@ describe("Scrape tests", () => {
// expect(response.markdown).toMatch(/(\.g\.doubleclick\.net|amazon-adsystem\.com)\//);
// }, 30000);
// });
describe("Compare format", () => {
it.concurrent("works", async () => {
const response = await scrape({
url: "https://example.com",
formats: ["markdown", "compare"],
});
expect(response.compare).toBeDefined();
expect(response.compare?.previousScrapeAt).not.toBeNull();
});
});
describe("Location API (f-e dependant)", () => {
it.concurrent("works without specifying an explicit location", async () => {

1
apps/api/src/controllers/v0/crawl.ts
View File

@ -158,6 +158,7 @@ export async function crawlController(req: Request, res: Response) {
pageOptions,
undefined,
undefined,
team_id
);
internalOptions.disableSmartWaitCache = true; // NOTE: smart wait disabled for crawls to ensure contentful scrape, speed does not matter

1
apps/api/src/controllers/v0/crawlPreview.ts
View File

@ -99,6 +99,7 @@ export async function crawlPreviewController(req: Request, res: Response) {
pageOptions,
undefined,
undefined,
team_id
);
const sc: StoredCrawl = {

2
apps/api/src/controllers/v0/scrape.ts
View File

@ -66,6 +66,7 @@ export async function scrapeHelper(
extractorOptions,
timeout,
crawlerOptions,
team_id,
);
await addScrapeJob(
@ -297,6 +298,7 @@ export async function scrapeController(req: Request, res: Response) {
pageOptions,
extractorOptions,
timeout,
team_id,
);
logJob({

1
apps/api/src/controllers/v0/search.ts
View File

@ -72,6 +72,7 @@ export async function searchHelper(
undefined,
60000,
crawlerOptions,
team_id,
);
if (justSearch) {

2
apps/api/src/controllers/v1/batch-scrape.ts
View File

@ -82,7 +82,7 @@ export async function batchScrapeController(
: {
crawlerOptions: null,
scrapeOptions: req.body,
internalOptions: { disableSmartWaitCache: true }, // NOTE: smart wait disabled for batch scrapes to ensure contentful scrape, speed does not matter
internalOptions: { disableSmartWaitCache: true, teamId: req.auth.team_id }, // NOTE: smart wait disabled for batch scrapes to ensure contentful scrape, speed does not matter
team_id: req.auth.team_id,
createdAt: Date.now(),
plan: req.auth.plan,

2
apps/api/src/controllers/v1/crawl.ts
View File

@ -81,7 +81,7 @@ export async function crawlController(
originUrl: req.body.url,
crawlerOptions: toLegacyCrawlerOptions(crawlerOptions),
scrapeOptions,
internalOptions: { disableSmartWaitCache: true }, // NOTE: smart wait disabled for crawls to ensure contentful scrape, speed does not matter
internalOptions: { disableSmartWaitCache: true, teamId: req.auth.team_id }, // NOTE: smart wait disabled for crawls to ensure contentful scrape, speed does not matter
team_id: req.auth.team_id,
createdAt: Date.now(),
plan: req.auth.plan,

2
apps/api/src/controllers/v1/map.ts
View File

@ -85,7 +85,7 @@ export async function getMapResults({
scrapeOptions: undefined,
},
scrapeOptions: scrapeOptions.parse({}),
internalOptions: {},
internalOptions: { teamId },
team_id: teamId,
createdAt: Date.now(),
plan: plan,

2
apps/api/src/controllers/v1/scrape.ts
View File

@ -50,7 +50,7 @@ export async function scrapeController(
mode: "single_urls",
team_id: req.auth.team_id,
scrapeOptions: req.body,
internalOptions: {},
internalOptions: { teamId: req.auth.team_id },
plan: req.auth.plan!,
origin: req.body.origin,
is_scrape: true,

2
apps/api/src/controllers/v1/search.ts
View File

@ -83,7 +83,7 @@ async function scrapeSearchResult(
mode: "single_urls" as Mode,
team_id: options.teamId,
scrapeOptions: options.scrapeOptions,
internalOptions: {},
internalOptions: { teamId: options.teamId },
plan: options.plan || "free",
origin: options.origin,
is_scrape: true,

22
apps/api/src/controllers/v1/types.ts
View File

@ -20,7 +20,8 @@ export type Format =
| "links"
| "screenshot"
| "screenshot@fullPage"
| "extract";
| "extract"
| "compare";
export const url = z.preprocess(
(x) => {
@ -165,6 +166,7 @@ const baseScrapeOptions = z
"screenshot@fullPage",
"extract",
"json",
"compare",
])
.array()
.optional()
@ -172,6 +174,10 @@ const baseScrapeOptions = z
.refine(
(x) => !(x.includes("screenshot") && x.includes("screenshot@fullPage")),
"You may only specify either screenshot or screenshot@fullPage",
)
.refine(
(x) => !x.includes("compare") || x.includes("markdown"),
"The compare format requires the markdown format to be specified as well",
),
headers: z.record(z.string(), z.string()).optional(),
includeTags: z.string().array().optional(),
@ -546,6 +552,11 @@ export type Document = {
value: unknown
}[];
};
compare?: {
previousScrapeAt: string | null;
changeStatus: "new" | "same" | "changed" | "removed";
visibility: "visible" | "hidden";
}
metadata: {
title?: string;
description?: string;
@ -812,7 +823,7 @@ export function toLegacyCrawlerOptions(x: CrawlerOptions) {
};
}
export function fromLegacyCrawlerOptions(x: any): {
export function fromLegacyCrawlerOptions(x: any, teamId: string): {
crawlOptions: CrawlerOptions;
internalOptions: InternalOptions;
} {
@ -834,6 +845,7 @@ export function fromLegacyCrawlerOptions(x: any): {
}),
internalOptions: {
v0CrawlOnlyUrls: x.returnOnlyUrls,
teamId,
},
};
}
@ -847,6 +859,7 @@ export function fromLegacyScrapeOptions(
pageOptions: PageOptions,
extractorOptions: ExtractorOptions | undefined,
timeout: number | undefined,
teamId: string,
): { scrapeOptions: ScrapeOptions; internalOptions: InternalOptions } {
return {
scrapeOptions: scrapeOptions.parse({
@ -896,6 +909,7 @@ export function fromLegacyScrapeOptions(
internalOptions: {
atsv: pageOptions.atsv,
v0DisableJsDom: pageOptions.disableJsDom,
teamId,
},
// TODO: fallback, fetchPageContent, replaceAllPathsWithAbsolutePaths, includeLinks
};
@ -906,13 +920,15 @@ export function fromLegacyCombo(
extractorOptions: ExtractorOptions | undefined,
timeout: number | undefined,
crawlerOptions: any,
teamId: string,
): { scrapeOptions: ScrapeOptions; internalOptions: InternalOptions } {
const { scrapeOptions, internalOptions: i1 } = fromLegacyScrapeOptions(
pageOptions,
extractorOptions,
timeout,
teamId,
);
const { internalOptions: i2 } = fromLegacyCrawlerOptions(crawlerOptions);
const { internalOptions: i2 } = fromLegacyCrawlerOptions(crawlerOptions, teamId);
return { scrapeOptions, internalOptions: Object.assign(i1, i2) };
}

26
apps/api/src/lib/crawl-redis.ts
View File

@ -154,20 +154,20 @@ export async function finishCrawlKickoff(id: string) {
);
}
export async function finishCrawl(id: string) {
export async function finishCrawlPre(id: string) {
if (await isCrawlFinished(id)) {
_logger.debug("Marking crawl as finished.", {
_logger.debug("Marking crawl as pre-finished.", {
module: "crawl-redis",
method: "finishCrawl",
method: "finishCrawlPre",
crawlId: id,
});
const set = await redisConnection.setnx("crawl:" + id + ":finish", "yes");
await redisConnection.expire("crawl:" + id + ":finish", 24 * 60 * 60);
const set = await redisConnection.setnx("crawl:" + id + ":finished_pre", "yes");
await redisConnection.expire("crawl:" + id + ":finished_pre", 24 * 60 * 60);
return set === 1;
} else {
_logger.debug("Crawl can not be finished yet, not marking as finished.", {
_logger.debug("Crawl can not be pre-finished yet, not marking as finished.", {
module: "crawl-redis",
method: "finishCrawl",
method: "finishCrawlPre",
crawlId: id,
jobs_done: await redisConnection.scard("crawl:" + id + ":jobs_done"),
jobs: await redisConnection.scard("crawl:" + id + ":jobs"),
@ -177,6 +177,16 @@ export async function finishCrawl(id: string) {
}
}
export async function finishCrawl(id: string) {
_logger.debug("Marking crawl as finished.", {
module: "crawl-redis",
method: "finishCrawl",
crawlId: id,
});
await redisConnection.set("crawl:" + id + ":finish", "yes");
await redisConnection.expire("crawl:" + id + ":finish", 24 * 60 * 60);
}
export async function getCrawlJobs(id: string): Promise<string[]> {
return await redisConnection.smembers("crawl:" + id + ":jobs");
}
@ -250,7 +260,7 @@ export function generateURLPermutations(url: string | URL): URL[] {
return [urlWithHTML, urlWithPHP, urlWithSlash, urlWithBare];
});
return permutations;
return [...new Set(permutations.map(x => x.href))].map(x => new URL(x));
}
export async function lockURL(

1
apps/api/src/lib/extract/document-scraper.ts
View File

@ -44,6 +44,7 @@ export async function scrapeDocument(
scrapeOptions: scrapeOptions.parse({ ...internalScrapeOptions }),
internalOptions: {
useCache: true,
teamId: options.teamId,
},
plan: options.plan,
origin: options.origin,

4
apps/api/src/main/runWebScraper.ts
View File

@ -51,6 +51,7 @@ export async function startWebScraperPipeline({
priority: job.opts.priority,
is_scrape: job.data.is_scrape ?? false,
is_crawl: !!(job.data.crawl_id && job.data.crawlerOptions !== null),
urlInvisibleInCurrentCrawl: job.data.crawlerOptions?.urlInvisibleInCurrentCrawl ?? false,
});
}
@ -66,6 +67,7 @@ export async function runWebScraper({
priority,
is_scrape = false,
is_crawl = false,
urlInvisibleInCurrentCrawl = false,
}: RunWebScraperParams): Promise<ScrapeUrlResponse> {
const logger = _logger.child({
method: "runWebScraper",
@ -97,6 +99,8 @@ export async function runWebScraper({
response = await scrapeURL(bull_job_id, url, scrapeOptions, {
priority,
...internalOptions,
urlInvisibleInCurrentCrawl,
teamId: internalOptions?.teamId ?? team_id,
});
if (!response.success) {
if (response.error instanceof Error) {

1
apps/api/src/scraper/WebScraper/sitemap.ts
View File

@ -47,6 +47,7 @@ export async function getLinksFromSitemap(
],
v0DisableJsDom: true,
abort,
teamId: "sitemap",
},
);

5
apps/api/src/scraper/scrapeURL/index.ts
View File

@ -162,6 +162,8 @@ async function buildMetaObject(
}
export type InternalOptions = {
teamId: string;
priority?: number; // Passed along to fire-engine
forceEngine?: Engine | Engine[];
atsv?: boolean; // anti-bot solver, beta
@ -173,6 +175,7 @@ export type InternalOptions = {
isBackgroundIndex?: boolean;
fromCache?: boolean; // Indicates if the document was retrieved from cache
abort?: AbortSignal;
urlInvisibleInCurrentCrawl?: boolean;
};
export type EngineResultsTracker = {
@ -383,7 +386,7 @@ export async function scrapeURL(
id: string,
url: string,
options: ScrapeOptions,
internalOptions: InternalOptions = {},
internalOptions: InternalOptions,
): Promise<ScrapeUrlResponse> {
const meta = await buildMetaObject(id, url, options, internalOptions);
try {

32
apps/api/src/scraper/scrapeURL/scrapeURL.test.ts
View File

@ -31,7 +31,7 @@ describe("Standalone scrapeURL tests", () => {
"test:scrape-basic",
"https://www.roastmywebsite.ai/",
scrapeOptions.parse({}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -78,7 +78,7 @@ describe("Standalone scrapeURL tests", () => {
scrapeOptions.parse({
formats: ["markdown", "html"],
}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -102,7 +102,7 @@ describe("Standalone scrapeURL tests", () => {
scrapeOptions.parse({
onlyMainContent: false,
}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -125,7 +125,7 @@ describe("Standalone scrapeURL tests", () => {
onlyMainContent: false,
excludeTags: [".nav", "#footer", "strong"],
}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -145,7 +145,7 @@ describe("Standalone scrapeURL tests", () => {
"test:scrape-400",
"https://httpstat.us/400",
scrapeOptions.parse({}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -163,7 +163,7 @@ describe("Standalone scrapeURL tests", () => {
"test:scrape-401",
"https://httpstat.us/401",
scrapeOptions.parse({}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -181,7 +181,7 @@ describe("Standalone scrapeURL tests", () => {
"test:scrape-403",
"https://httpstat.us/403",
scrapeOptions.parse({}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -199,7 +199,7 @@ describe("Standalone scrapeURL tests", () => {
"test:scrape-404",
"https://httpstat.us/404",
scrapeOptions.parse({}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -217,7 +217,7 @@ describe("Standalone scrapeURL tests", () => {
"test:scrape-405",
"https://httpstat.us/405",
scrapeOptions.parse({}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -235,7 +235,7 @@ describe("Standalone scrapeURL tests", () => {
"test:scrape-500",
"https://httpstat.us/500",
scrapeOptions.parse({}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -253,7 +253,7 @@ describe("Standalone scrapeURL tests", () => {
"test:scrape-redirect",
"https://scrapethissite.com/",
scrapeOptions.parse({}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -285,7 +285,7 @@ describe("Standalone scrapeURL tests", () => {
scrapeOptions.parse({
formats: ["screenshot"],
}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -313,7 +313,7 @@ describe("Standalone scrapeURL tests", () => {
scrapeOptions.parse({
formats: ["screenshot@fullPage"],
}),
{ forceEngine },
{ forceEngine, teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -341,6 +341,7 @@ describe("Standalone scrapeURL tests", () => {
"test:scrape-pdf",
"https://arxiv.org/pdf/astro-ph/9301001.pdf",
scrapeOptions.parse({}),
{ teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -359,6 +360,7 @@ describe("Standalone scrapeURL tests", () => {
"test:scrape-docx",
"https://nvca.org/wp-content/uploads/2019/06/NVCA-Model-Document-Stock-Purchase-Agreement.docx",
scrapeOptions.parse({}),
{ teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -395,6 +397,7 @@ describe("Standalone scrapeURL tests", () => {
},
},
}),
{ teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -430,6 +433,7 @@ describe("Standalone scrapeURL tests", () => {
},
},
}),
{ teamId: "test" },
);
// expect(out.logs.length).toBeGreaterThan(0);
@ -451,7 +455,7 @@ describe("Standalone scrapeURL tests", () => {
async (i) => {
const url = "https://www.scrapethissite.com/?i=" + i;
const id = "test:concurrent:" + url;
const out = await scrapeURL(id, url, scrapeOptions.parse({}));
const out = await scrapeURL(id, url, scrapeOptions.parse({}), { teamId: "test" });
const replacer = (key: string, value: any) => {
if (value instanceof Error) {

42
apps/api/src/scraper/scrapeURL/transformers/diff.ts Normal file
View File

@ -0,0 +1,42 @@
import { supabase_service } from "../../../services/supabase";
import { Document } from "../../../controllers/v1/types";
import { Meta } from "../index";
export async function deriveDiff(meta: Meta, document: Document): Promise<Document> {
if (meta.options.formats.includes("compare")) {
const res = await supabase_service
.rpc("diff_get_last_scrape_1", {
i_team_id: meta.internalOptions.teamId,
i_url: document.metadata.sourceURL ?? meta.url,
});
const data: {
o_docs: Document[],
o_date_added: string,
} | undefined | null = (res.data ?? [])[0] as any;
if (data && data.o_docs.length > 0) {
const previousMarkdown = data.o_docs[0].markdown!;
const currentMarkdown = document.markdown!;
const transformer = (x: string) => [...x.replace(/\s+/g, "").replace(/\[iframe\]\(.+?\)/g, "")].sort().join("");
document.compare = {
previousScrapeAt: data.o_date_added,
changeStatus: document.metadata.statusCode === 404 ? "removed" : transformer(previousMarkdown) === transformer(currentMarkdown) ? "same" : "changed",
visibility: meta.internalOptions.urlInvisibleInCurrentCrawl ? "hidden" : "visible",
}
} else if (!res.error) {
document.compare = {
previousScrapeAt: null,
changeStatus: document.metadata.statusCode === 404 ? "removed" : "new",
visibility: meta.internalOptions.urlInvisibleInCurrentCrawl ? "hidden" : "visible",
}
} else {
meta.logger.error("Error fetching previous scrape", { error: res.error });
document.warning = "Comparing failed, please try again later." + (document.warning ? ` ${document.warning}` : "");
}
}
return document;
}

14
apps/api/src/scraper/scrapeURL/transformers/index.ts
View File

@ -8,7 +8,7 @@ import { performLLMExtract } from "./llmExtract";
import { uploadScreenshot } from "./uploadScreenshot";
import { removeBase64Images } from "./removeBase64Images";
import { saveToCache } from "./cache";
import { deriveDiff } from "./diff";
export type Transformer = (
meta: Meta,
document: Document,
@ -148,6 +148,17 @@ export function coerceFieldsToFormats(
);
}
if (!formats.has("compare") && document.compare !== undefined) {
meta.logger.warn(
"Removed compare from Document because it wasn't in formats -- this is extremely wasteful and indicates a bug.",
);
delete document.compare;
} else if (formats.has("compare") && document.compare === undefined) {
meta.logger.warn(
"Request had format compare, but there was no compare field in the result.",
);
}
if (meta.options.actions === undefined || meta.options.actions.length === 0) {
delete document.actions;
}
@ -164,6 +175,7 @@ export const transformerStack: Transformer[] = [
deriveMetadataFromRawHTML,
uploadScreenshot,
performLLMExtract,
deriveDiff,
coerceFieldsToFormats,
removeBase64Images,
];

73
apps/api/src/services/queue-worker.ts
View File

@ -28,6 +28,7 @@ import {
addCrawlJobs,
crawlToCrawler,
finishCrawl,
finishCrawlPre,
finishCrawlKickoff,
generateURLPermutations,
getCrawl,
@ -100,7 +101,77 @@ const gotJobInterval = Number(process.env.CONNECTION_MONITOR_INTERVAL) || 20;
const runningJobs: Set<string> = new Set();
async function finishCrawlIfNeeded(job: Job & { id: string }, sc: StoredCrawl) {
if (await finishCrawl(job.data.crawl_id)) {
if (await finishCrawlPre(job.data.crawl_id)) {
if (job.data.crawlerOptions && !await redisConnection.exists("crawl:" + job.data.crawl_id + ":invisible_urls")) {
await redisConnection.set("crawl:" + job.data.crawl_id + ":invisible_urls", "done", "EX", 60 * 60 * 24);
const sc = (await getCrawl(job.data.crawl_id))!;
const visitedUrls = new Set(await redisConnection.smembers(
"crawl:" + job.data.crawl_id + ":visited_unique",
));
const lastUrls: string[] = ((await supabase_service.rpc("diff_get_last_crawl_urls", {
i_team_id: job.data.team_id,
i_url: sc.originUrl!,
})).data ?? []).map(x => x.url);
const lastUrlsSet = new Set(lastUrls);
const univistedUrls = Array.from(lastUrlsSet).filter(x => !visitedUrls.has(x));
const addableJobCount = sc.crawlerOptions.limit === undefined ? Infinity : (sc.crawlerOptions.limit - await getDoneJobsOrderedLength(job.data.crawl_id));
console.log(sc.originUrl!, univistedUrls, visitedUrls, lastUrls, addableJobCount);
if (univistedUrls.length !== 0 && addableJobCount > 0) {
const jobs = univistedUrls.slice(0, addableJobCount).map((url) => {
const uuid = uuidv4();
return {
name: uuid,
data: {
url,
mode: "single_urls" as const,
team_id: job.data.team_id,
plan: job.data.plan!,
crawlerOptions: {
...job.data.crawlerOptions,
urlInvisibleInCurrentCrawl: true,
},
scrapeOptions: job.data.scrapeOptions,
internalOptions: sc.internalOptions,
origin: job.data.origin,
crawl_id: job.data.crawl_id,
sitemapped: true,
webhook: job.data.webhook,
v1: job.data.v1,
},
opts: {
jobId: uuid,
priority: 20,
},
};
});
const lockedIds = await lockURLsIndividually(
job.data.crawl_id,
sc,
jobs.map((x) => ({ id: x.opts.jobId, url: x.data.url })),
);
const lockedJobs = jobs.filter((x) =>
lockedIds.find((y) => y.id === x.opts.jobId),
);
await addCrawlJobs(
job.data.crawl_id,
lockedJobs.map((x) => x.opts.jobId),
);
await addScrapeJobs(lockedJobs);
return;
}
}
await finishCrawl(job.data.crawl_id);
(async () => {
const originUrl = sc.originUrl
? normalizeUrlOnlyHostname(sc.originUrl)

1
apps/api/src/types.ts
View File

@ -59,6 +59,7 @@ export interface RunWebScraperParams {
priority?: number;
is_scrape?: boolean;
is_crawl?: boolean;
urlInvisibleInCurrentCrawl?: boolean;
}
export type RunWebScraperResult =

2
apps/js-sdk/firecrawl/package.json
View File

@ -1,6 +1,6 @@
{
"name": "@mendable/firecrawl-js",
"version": "1.21.0",
"version": "1.21.1",
"description": "JavaScript SDK for Firecrawl API",
"main": "dist/index.js",
"types": "dist/index.d.ts",

7
apps/js-sdk/firecrawl/src/index.ts
View File

@ -69,6 +69,11 @@ export interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult
screenshot?: string;
metadata?: FirecrawlDocumentMetadata;
actions: ActionsSchema;
compare?: {
previousScrapeAt: string | null;
changeStatus: "new" | "same" | "changed" | "removed";
visibility: "visible" | "hidden";
};
// v1 search only
title?: string;
description?: string;
@ -79,7 +84,7 @@ export interface FirecrawlDocument<T = any, ActionsSchema extends (ActionsResult
* Defines the options and configurations available for scraping web content.
*/
export interface CrawlScrapeOptions {
formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json")[];
formats?: ("markdown" | "html" | "rawHtml" | "content" | "links" | "screenshot" | "screenshot@fullPage" | "extract" | "json" | "compare")[];
headers?: Record<string, string>;
includeTags?: string[];
excludeTags?: string[];