Skip to content

Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

Update index.ts

Nicolasc1d613778068
diff --git a/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts b/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts
index f0c3c4076..f16662e10 100644
--- a/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts
+++ b/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts
@@ -305,7 +305,12 @@ export async function scrapePDF(
statusCode: response.status,
html: result?.html ?? "",
markdown: result?.markdown ?? "",
- pdfMetadata,
+ pdfMetadata: {
+ // Rust parser gets the metadata incorrectly, so we overwrite the page count here with the effective page count
+ // TODO: fix this later
+ numPages: effectivePageCount,
+ title: pdfMetadata.title,
+ },
proxyUsed: "basic",
};