Skip to content

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

fix(api): pass maxPages to Rust PDF extractor to limit content extraction

firecrawl-spring[bot]ba6e755b6acf
diff --git a/apps/api/native/src/pdf.rs b/apps/api/native/src/pdf.rs
index 14a680185..412821b00 100644
--- a/apps/api/native/src/pdf.rs
+++ b/apps/api/native/src/pdf.rs
@@ -40,9 +40,15 @@ fn to_napi_result(result: pdf_inspector::PdfProcessResult) -> PdfProcessResult {
}
/// Process a PDF file: detect type, extract text + markdown if text-based.
+/// When `max_pages` is provided, only the first N pages are extracted.
#[napi]
-pub fn process_pdf(path: String) -> Result<PdfProcessResult> {
- let result = rust_process_pdf(&path, PdfOptions::new()).map_err(|e| {
+pub fn process_pdf(path: String, max_pages: Option<u32>) -> Result<PdfProcessResult> {
+ let opts = match max_pages {
+ Some(n) if n > 0 => PdfOptions::new().pages(1..=n),
+ _ => PdfOptions::new(),
+ };
+
+ let result = rust_process_pdf(&path, opts).map_err(|e| {
Error::new(
Status::GenericFailure,
format!("Failed to process PDF: {e}"),
diff --git a/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts b/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts
index f98a021e0..caf1d8170 100644
--- a/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts
+++ b/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts
@@ -190,7 +190,7 @@ export async function scrapePDF(meta: Meta): Promise<EngineScrapeResult> {
// Rust extraction enabled (fast / auto modes).
try {
const startedAt = Date.now();
- const pdfResult = processPdf(tempFilePath);
+ const pdfResult = processPdf(tempFilePath, maxPages ?? undefined);
const durationMs = Date.now() - startedAt;
logger.info("processPdf completed", {