From fbabc779f59c3889424f42e9d75a844807da475a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Gerg=C5=91=20M=C3=B3ricz?= <mo.geryy@gmail.com>
Date: Tue, 12 Nov 2024 18:20:53 +0100
Subject: [PATCH] fix(crawler): relative URL handling on non-start pages (#893)

* fix(crawler): relative URL handling on non-start pages

* fix(crawl): further fixing
---
 apps/api/src/lib/crawl-redis.ts            | 4 ++--
 apps/api/src/scraper/WebScraper/crawler.ts | 2 +-
 apps/api/src/services/queue-worker.ts      | 4 ++--
 3 files changed, 5 insertions(+), 5 deletions(-)

diff --git a/apps/api/src/lib/crawl-redis.ts b/apps/api/src/lib/crawl-redis.ts
index b5936ad6..bd79a86d 100644
--- a/apps/api/src/lib/crawl-redis.ts
+++ b/apps/api/src/lib/crawl-redis.ts
@@ -166,10 +166,10 @@ export async function lockURLs(id: string, sc: StoredCrawl, urls: string[]): Pro
     return res;
 }
 
-export function crawlToCrawler(id: string, sc: StoredCrawl): WebCrawler {
+export function crawlToCrawler(id: string, sc: StoredCrawl, initialUrl?: string): WebCrawler {
     const crawler = new WebCrawler({
         jobId: id,
-        initialUrl: sc.originUrl!,
+        initialUrl: initialUrl ?? sc.originUrl!,
         includes: sc.crawlerOptions?.includes ?? [],
         excludes: sc.crawlerOptions?.excludes ?? [],
         maxCrawledLinks: sc.crawlerOptions?.maxCrawledLinks ?? 1000,
diff --git a/apps/api/src/scraper/WebScraper/crawler.ts b/apps/api/src/scraper/WebScraper/crawler.ts
index 9e3f7cd2..e5a25f37 100644
--- a/apps/api/src/scraper/WebScraper/crawler.ts
+++ b/apps/api/src/scraper/WebScraper/crawler.ts
@@ -171,7 +171,7 @@ export class WebCrawler {
     let fullUrl = href;
     if (!href.startsWith("http")) {
       try {
-        fullUrl = new URL(href, this.baseUrl).toString();
+        fullUrl = new URL(href, url).toString();
       } catch (_) {
         return null;
       }
diff --git a/apps/api/src/services/queue-worker.ts b/apps/api/src/services/queue-worker.ts
index 428e7e01..5a0b28db 100644
--- a/apps/api/src/services/queue-worker.ts
+++ b/apps/api/src/services/queue-worker.ts
@@ -352,10 +352,10 @@ async function processJob(job: Job & { id: string }, token: string) {
 
       if (!job.data.sitemapped && job.data.crawlerOptions !== null) {
         if (!sc.cancelled) {
-          const crawler = crawlToCrawler(job.data.crawl_id, sc);
+          const crawler = crawlToCrawler(job.data.crawl_id, sc, doc.metadata?.url ?? doc.metadata?.sourceURL ?? undefined);
 
           const links = crawler.filterLinks(
-            crawler.extractLinksFromHTML(rawHtml ?? "", sc.originUrl as string),
+            crawler.extractLinksFromHTML(rawHtml ?? "", doc.metadata?.url ?? doc.metadata?.sourceURL ?? sc.originUrl as string),
             Infinity,
             sc.crawlerOptions?.maxDepth ?? 10
           );