AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-10 04:08:58 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update crawler.ts

Browse Source
This commit is contained in:
Nicolas 2024-06-24 16:52:01 -03:00 committed by GitHub
parent 08c1fa799b
commit 90b7fff366
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
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

@ -418,7 +418,7 @@ export class WebCrawler {
const normalizedUrl = normalizeUrl(url); const normalizedUrl = normalizeUrl(url);
const normalizedSitemapLinks = sitemapLinks.map(link => normalizeUrl(link)); const normalizedSitemapLinks = sitemapLinks.map(link => normalizeUrl(link));
// has to be greater than 0 to avoid adding the initial URL to the sitemap links, and preventing crawler to crawl
if (!normalizedSitemapLinks.includes(normalizedUrl) && sitemapLinks.length > 0) { if (!normalizedSitemapLinks.includes(normalizedUrl) && sitemapLinks.length > 0) {
sitemapLinks.push(url); sitemapLinks.push(url);
} }