nested includeHtml inside pageOptions

apps/api/src/__tests__/e2e_withAuth/index.test.ts

@@ -88,7 +88,7 @@ describe("E2E Tests for API Routes", () => {
         .post("/v0/scrape")
         .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
         .set("Content-Type", "application/json")
-        .send({ url: "https://firecrawl.dev", includeHtml: true });
+        .send({ url: "https://firecrawl.dev", pageOptions: { includeHtml: true }});
       expect(response.statusCode).toBe(200);
       expect(response.body).toHaveProperty("data");
       expect(response.body.data).toHaveProperty("content");
@@ -270,12 +270,12 @@ describe("E2E Tests for API Routes", () => {
       );
     }, 60000); // 60 seconds
 
-    it("should return a successful response for a valid crawl job with toMarkdown set to false option", async () => {
+    it("should return a successful response for a valid crawl job with includeHtml set to true option", async () => {
       const crawlResponse = await request(TEST_URL)
         .post("/v0/crawl")
         .set("Authorization", `Bearer ${process.env.TEST_API_KEY}`)
         .set("Content-Type", "application/json")
-        .send({ url: "https://firecrawl.dev", includeHtml: true });
+        .send({ url: "https://firecrawl.dev", pageOptions: { includeHtml: true } });
       expect(crawlResponse.statusCode).toBe(200);
 
       const response = await request(TEST_URL)

apps/api/src/controllers/crawl.ts

@@ -35,8 +35,7 @@ export async function crawlController(req: Request, res: Response) {
     
     const mode = req.body.mode ?? "crawl";
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false };
-    const includeHtml = req.body.includeHtml || false;
 
     if (mode === "single_urls" && !url.includes(",")) {
       try {
@@ -48,7 +47,6 @@ export async function crawlController(req: Request, res: Response) {
             returnOnlyUrls: true,
           },
           pageOptions: pageOptions,
-          includeHtml: includeHtml,
         });
 
         const docs = await a.getDocuments(false, (progress) => {
@@ -75,7 +73,6 @@ export async function crawlController(req: Request, res: Response) {
       team_id: team_id,
       pageOptions: pageOptions,
       origin: req.body.origin ?? "api",
-      includeHtml: includeHtml,
     });
 
     res.json({ jobId: job.id });

apps/api/src/controllers/crawlPreview.ts

@@ -26,8 +26,7 @@ export async function crawlPreviewController(req: Request, res: Response) {
 
     const mode = req.body.mode ?? "crawl";
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false };
-    const includeHtml = req.body.includeHtml ?? false;
 
     const job = await addWebScraperJob({
       url: url,
@@ -36,7 +35,6 @@ export async function crawlPreviewController(req: Request, res: Response) {
       team_id: "preview",
       pageOptions: pageOptions,
       origin: "website-preview",
-      includeHtml: includeHtml,
     });
 
     res.json({ jobId: job.id });

apps/api/src/controllers/scrape.ts

@@ -15,7 +15,6 @@ export async function scrapeHelper(
   crawlerOptions: any,
   pageOptions: PageOptions,
   extractorOptions: ExtractorOptions,
-  includeHtml: boolean = false
 ): Promise<{
   success: boolean;
   error?: string;
@@ -41,7 +40,6 @@ export async function scrapeHelper(
     },
     pageOptions: pageOptions,
     extractorOptions: extractorOptions,
-    includeHtml: includeHtml
   });
 
   const docs = await a.getDocuments(false);
@@ -93,12 +91,11 @@ export async function scrapeController(req: Request, res: Response) {
       return res.status(status).json({ error });
     }
     const crawlerOptions = req.body.crawlerOptions ?? {};
-    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false };
+    const pageOptions = req.body.pageOptions ?? { onlyMainContent: false, includeHtml: false };
     const extractorOptions = req.body.extractorOptions ?? {
       mode: "markdown"
     }
     const origin = req.body.origin ?? "api";
-    const includeHtml = req.body.includeHtml ?? false;
 
     try {
       const { success: creditsCheckSuccess, message: creditsCheckMessage } =
@@ -117,7 +114,6 @@ export async function scrapeController(req: Request, res: Response) {
       crawlerOptions,
       pageOptions,
       extractorOptions,
-      includeHtml
     );
     const endTime = new Date().getTime();
     const timeTakenInSeconds = (endTime - startTime) / 1000;
@@ -137,7 +133,6 @@ export async function scrapeController(req: Request, res: Response) {
       origin: origin, 
       extractor_options: extractorOptions,
       num_tokens: numTokens,
-      includeHtml: includeHtml
     });
     return res.status(result.returnCode).json(result);
   } catch (error) {

apps/api/src/controllers/search.ts

@@ -14,7 +14,6 @@ export async function searchHelper(
   crawlerOptions: any,
   pageOptions: PageOptions,
   searchOptions: SearchOptions,
-  includeHtml: boolean = false
 ): Promise<{
   success: boolean;
   error?: string;
@@ -60,7 +59,6 @@ export async function searchHelper(
   await a.setOptions({
     mode: "single_urls",
     urls: res.map((r) => r.url).slice(0, searchOptions.limit ?? 7),
-    includeHtml,
     crawlerOptions: {
       ...crawlerOptions,
     },
@@ -68,6 +66,7 @@ export async function searchHelper(
       ...pageOptions,
       onlyMainContent: pageOptions?.onlyMainContent ?? true,
       fetchPageContent: pageOptions?.fetchPageContent ?? true,
+      includeHtml: pageOptions?.includeHtml ?? false,
       fallback: false,
     },
   });
@@ -119,6 +118,7 @@ export async function searchController(req: Request, res: Response) {
     }
     const crawlerOptions = req.body.crawlerOptions ?? {};
     const pageOptions = req.body.pageOptions ?? {
+      includeHtml: false,
       onlyMainContent: true,
       fetchPageContent: true,
       fallback: false,
@@ -126,7 +126,6 @@ export async function searchController(req: Request, res: Response) {
     const origin = req.body.origin ?? "api";
 
     const searchOptions = req.body.searchOptions ?? { limit: 7 };
-    const includeHtml = req.body.includeHtml ?? false;
 
     try {
       const { success: creditsCheckSuccess, message: creditsCheckMessage } =
@@ -145,7 +144,6 @@ export async function searchController(req: Request, res: Response) {
       crawlerOptions,
       pageOptions,
       searchOptions,
-      includeHtml
     );
     const endTime = new Date().getTime();
     const timeTakenInSeconds = (endTime - startTime) / 1000;
@@ -161,7 +159,6 @@ export async function searchController(req: Request, res: Response) {
       crawlerOptions: crawlerOptions,
       pageOptions: pageOptions,
       origin: origin,
-      includeHtml,
     });
     return res.status(result.returnCode).json(result);
   } catch (error) {

apps/api/src/lib/entities.ts

@@ -12,8 +12,9 @@ export interface Progress {
 
 export type PageOptions = {
   onlyMainContent?: boolean;
+  includeHtml?: boolean;
   fallback?: boolean;
-  fetchPageContent?: boolean;  
+  fetchPageContent?: boolean;
 };
 
 export type ExtractorOptions = {
@@ -46,7 +47,6 @@ export type WebScraperOptions = {
   pageOptions?: PageOptions;
   extractorOptions?: ExtractorOptions;
   concurrentRequests?: number;
-  includeHtml?: boolean;
 };
 
 export interface DocumentUrl {

apps/api/src/main/runWebScraper.ts

@@ -26,8 +26,7 @@ export async function startWebScraperPipeline({
     onError: (error) => {
       job.moveToFailed(error);
     },
-    team_id: job.data.team_id,
+    team_id: job.data.team_id
-    includeHtml: job.data.includeHtml,
   })) as { success: boolean; message: string; docs: Document[] };
 }
 export async function runWebScraper({
@@ -39,7 +38,6 @@ export async function runWebScraper({
   onSuccess,
   onError,
   team_id,
-  includeHtml = false,
 }: {
   url: string;
   mode: "crawl" | "single_urls" | "sitemap";
@@ -49,7 +47,6 @@ export async function runWebScraper({
   onSuccess: (result: any) => void;
   onError: (error: any) => void;
   team_id: string;
-  includeHtml?: boolean;
 }): Promise<{
   success: boolean;
   message: string;
@@ -62,16 +59,14 @@ export async function runWebScraper({
         mode: mode,
         urls: [url],
         crawlerOptions: crawlerOptions,
-        pageOptions: pageOptions,
+        pageOptions: pageOptions
-        includeHtml: includeHtml,
       });
     } else {
       await provider.setOptions({
         mode: mode,
         urls: url.split(","),
         crawlerOptions: crawlerOptions,
-        pageOptions: pageOptions,
+        pageOptions: pageOptions
-        includeHtml: includeHtml,
       });
     }
     const docs = (await provider.getDocuments(false, (progress: Progress) => {

apps/api/src/scraper/WebScraper/crawler.ts

@@ -19,7 +19,6 @@ export class WebCrawler {
   private robotsTxtUrl: string;
   private robots: any;
   private generateImgAltText: boolean;
-  private includeHtml: boolean;
 
   constructor({
     initialUrl,
@@ -28,7 +27,6 @@ export class WebCrawler {
     maxCrawledLinks,
     limit = 10000,
     generateImgAltText = false,
-    includeHtml = false,
   }: {
     initialUrl: string;
     includes?: string[];
@@ -36,7 +34,6 @@ export class WebCrawler {
     maxCrawledLinks?: number;
     limit?: number;
     generateImgAltText?: boolean;
-    includeHtml?: boolean;
   }) {
     this.initialUrl = initialUrl;
     this.baseUrl = new URL(initialUrl).origin;
@@ -48,7 +45,6 @@ export class WebCrawler {
     // Deprecated, use limit instead
     this.maxCrawledLinks = maxCrawledLinks ?? limit;
     this.generateImgAltText = generateImgAltText ?? false;
-    this.includeHtml = includeHtml ?? false;
   }
 
 

apps/api/src/scraper/WebScraper/index.ts

@@ -24,7 +24,6 @@ export class WebScraperDataProvider {
   private extractorOptions?: ExtractorOptions;
   private replaceAllPathsWithAbsolutePaths?: boolean = false;
   private generateImgAltTextModel: "gpt-4-turbo" | "claude-3-opus" = "gpt-4-turbo";
-  private includeHtml: boolean = false;
 
   authorize(): void {
     throw new Error("Method not implemented.");
@@ -46,7 +45,7 @@ export class WebScraperDataProvider {
       const batchUrls = urls.slice(i, i + this.concurrentRequests);
       await Promise.all(
         batchUrls.map(async (url, index) => {
-          const result = await scrapSingleUrl(url, this.pageOptions, this.includeHtml);
+          const result = await scrapSingleUrl(url, this.pageOptions);
           processedUrls++;
           if (inProgress) {
             inProgress({
@@ -109,7 +108,6 @@ export class WebScraperDataProvider {
       maxCrawledLinks: this.maxCrawledLinks,
       limit: this.limit,
       generateImgAltText: this.generateImgAltText,
-      includeHtml: this.includeHtml,
     });
     let links = await crawler.start(inProgress, 5, this.limit);
     if (this.returnOnlyUrls) {
@@ -144,7 +142,7 @@ export class WebScraperDataProvider {
     });
     return links.map(url => ({
       content: "",
-      html: this.includeHtml ? "" : undefined,
+      html: this.pageOptions?.includeHtml ? "" : undefined,
       markdown: "",
       metadata: { sourceURL: url },
     }));
@@ -326,10 +324,9 @@ export class WebScraperDataProvider {
     this.limit = options.crawlerOptions?.limit ?? 10000;
     this.generateImgAltText =
       options.crawlerOptions?.generateImgAltText ?? false;
-    this.pageOptions = options.pageOptions ?? {onlyMainContent: false };
+    this.pageOptions = options.pageOptions ?? { onlyMainContent: false, includeHtml: false };
     this.extractorOptions = options.extractorOptions ?? {mode: "markdown"}
     this.replaceAllPathsWithAbsolutePaths = options.crawlerOptions?.replaceAllPathsWithAbsolutePaths ?? false;
-    this.includeHtml = options?.includeHtml ?? false;
     //! @nicolas, for some reason this was being injected and breakign everything. Don't have time to find source of the issue so adding this check
     this.excludes = this.excludes.filter((item) => item !== "");
 

apps/api/src/scraper/WebScraper/single_url.ts

@@ -103,8 +103,7 @@ export async function scrapWithPlaywright(url: string): Promise<string> {
 
 export async function scrapSingleUrl(
   urlToScrap: string,
-  pageOptions: PageOptions = { onlyMainContent: true },
+  pageOptions: PageOptions = { onlyMainContent: true, includeHtml: false },
-  includeHtml: boolean = false
 ): Promise<Document> {
   urlToScrap = urlToScrap.trim();
 
@@ -193,7 +192,7 @@ export async function scrapSingleUrl(
         url: urlToScrap,
         content: text,
         markdown: text,
-        html: includeHtml ? html : undefined,
+        html: pageOptions.includeHtml ? html : undefined,
         metadata: { ...metadata, sourceURL: urlToScrap },
       } as Document;
     }
@@ -217,7 +216,7 @@ export async function scrapSingleUrl(
     return {
       content: text,
       markdown: text,
-      html: includeHtml ? html : undefined,
+      html: pageOptions.includeHtml ? html : undefined,
       metadata: { ...metadata, sourceURL: urlToScrap },
     } as Document;
   } catch (error) {

apps/api/src/types.ts

@@ -25,7 +25,6 @@ export interface WebScraperOptions {
   pageOptions: any;
   team_id: string;
   origin?: string;
-  includeHtml?: boolean;
 }
 
 export interface FirecrawlJob {
@@ -42,7 +41,6 @@ export interface FirecrawlJob {
   origin: string;
   extractor_options?: ExtractorOptions,
   num_tokens?: number,
-  includeHtml?: boolean;
 }
 
 export enum RateLimiterMode {