mirror of
https://github.com/mendableai/firecrawl.git
synced 2024-11-16 11:42:24 +08:00
Update apps/api/src/scraper/WebScraper/crawler.ts
no need for regex Co-authored-by: Gergő Móricz <mo.geryy@gmail.com>
This commit is contained in:
parent
a684bd3c5d
commit
5e728c1a4d
|
@ -64,15 +64,7 @@ export class WebCrawler {
|
|||
private filterLinks(sitemapLinks: string[], limit: number, maxDepth: number): string[] {
|
||||
return sitemapLinks
|
||||
.filter((link) => {
|
||||
|
||||
// if link is not a complete url, add the base url
|
||||
link = link.trim();
|
||||
const isCompleteUrl = new RegExp('^(?:[a-z+]+:)?//', 'i');
|
||||
if (!isCompleteUrl.test(link)){
|
||||
link = this.baseUrl + link;
|
||||
}
|
||||
|
||||
const url = new URL(link);
|
||||
const url = new URL(link.trim(), this.baseUrl);
|
||||
const path = url.pathname;
|
||||
|
||||
const depth = getURLDepth(url.toString());
|
||||
|
|
Loading…
Reference in New Issue
Block a user