Skip to content

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

fix(scraper): return contentType from PDF and document engines (#3202)

firecrawl-spring[bot]5902897cdc66
diff --git a/apps/api/src/scraper/scrapeURL/engines/document/index.ts b/apps/api/src/scraper/scrapeURL/engines/document/index.ts
index 993635601..51582e813 100644
--- a/apps/api/src/scraper/scrapeURL/engines/document/index.ts
+++ b/apps/api/src/scraper/scrapeURL/engines/document/index.ts
@@ -149,6 +149,7 @@ export async function scrapeDocument(meta: Meta): Promise<EngineScrapeResult> {
url: response.url,
statusCode: response.status,
html,
+ contentType: response.headers.get("content-type") ?? undefined,
proxyUsed,
};
} finally {
diff --git a/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts b/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts
index d34a4e7b4..a974f3f9b 100644
--- a/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts
+++ b/apps/api/src/scraper/scrapeURL/engines/pdf/index.ts
@@ -63,6 +63,7 @@ export async function scrapePDF(meta: Meta): Promise<EngineScrapeResult> {
html: content,
markdown: content,
+ contentType: "application/pdf",
proxyUsed: meta.pdfPrefetch.proxyUsed,
};
} else {
@@ -97,6 +98,7 @@ export async function scrapePDF(meta: Meta): Promise<EngineScrapeResult> {
html: content,
markdown: content,
+ contentType: "application/pdf",
proxyUsed: "basic",
};
}
@@ -452,6 +454,7 @@ export async function scrapePDF(meta: Meta): Promise<EngineScrapeResult> {
title: metadataTitle,
},
+ contentType: "application/pdf",
proxyUsed: "basic",
};
} finally {