AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-19 19:09:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(crawler): bad urls from sitemap

Browse Source
This commit is contained in:
Gergő Móricz 2025-01-17 17:07:44 +01:00
parent 237d0dc197
commit 5992c57158
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
apps/api/src/scraper/WebScraper/crawler.ts
View File

@ -228,7 +228,7 @@ export class WebCrawler {
); );
leftOfLimit -= filteredLinks.length; leftOfLimit -= filteredLinks.length;
let uniqueURLs: string[] = []; let uniqueURLs: string[] = [];
for (const url of urls) { for (const url of filteredLinks) {
if ( if (
await redisConnection.sadd( await redisConnection.sadd(
"sitemap:" + this.jobId + ":links", "sitemap:" + this.jobId + ":links",