From c22c87ab0a9f3a0ade34e8957ca23c13a99c11d3 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Gerg=C5=91=20M=C3=B3ricz?= Date: Wed, 5 Mar 2025 18:48:05 +0100 Subject: [PATCH] fix(crawler): check for more strings --- apps/api/src/scraper/WebScraper/crawler.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/apps/api/src/scraper/WebScraper/crawler.ts b/apps/api/src/scraper/WebScraper/crawler.ts index 5e91b46e..126520e2 100644 --- a/apps/api/src/scraper/WebScraper/crawler.ts +++ b/apps/api/src/scraper/WebScraper/crawler.ts @@ -179,7 +179,7 @@ export class WebCrawler { const isAllowed = this.ignoreRobotsTxt ? true - : (this.robots.isAllowed(link, "FireCrawlAgent") ?? true); + : ((this.robots.isAllowed(link, "FireCrawlAgent") || this.robots.isAllowed(link, "FirecrawlAgent")) ?? true); // Check if the link is disallowed by robots.txt if (!isAllowed) { this.logger.debug(`Link disallowed by robots.txt: ${link}`, { @@ -453,7 +453,7 @@ export class WebCrawler { return ignoreRobotsTxt ? true : this.robots - ? (this.robots.isAllowed(url, "FireCrawlAgent") ?? true) + ? ((this.robots.isAllowed(url, "FireCrawlAgent") || this.robots.isAllowed(url, "FirecrawlAgent")) ?? true) : true; }