Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
TypeScript aiai-agentsai-crawlerai-scrapingai-searchcrawlerdata-extractionhtml-to-markdownllmmarkdownscraperscrapingweb-crawlerweb-dataweb-data-extractionweb-scraperweb-scrapingweb-searchwebscraping
fix(branding): improve error messages for PDFs and documents (#2776)
Abimael Martelle374660cd308
diff --git a/apps/api/src/scraper/scrapeURL/engines/index.ts b/apps/api/src/scraper/scrapeURL/engines/index.tsindex e9197ec47..7a897cc1b 100644--- a/apps/api/src/scraper/scrapeURL/engines/index.ts+++ b/apps/api/src/scraper/scrapeURL/engines/index.ts@@ -609,9 +609,16 @@ export async function buildFallbackList(meta: Meta): Promise<f => !f.unsupportedFeatures.has("branding"),);if (!hasCDPEngine) {- throw new Error(- "Branding extraction requires Chrome CDP (fire-engine). ",- );+ if (meta.featureFlags.has("pdf")) {+ throw new Error(+ "Branding extraction is only supported for HTML web pages. PDFs are not supported.",+ );+ } else if (meta.featureFlags.has("document")) {+ throw new Error(+ "Branding extraction is only supported for HTML web pages. Documents (docx, xlsx, etc.) are not supported.",+ );+ }+ throw new Error("Branding extraction requires Chrome CDP (fire-engine).");}}