AI/firecrawl
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/mendableai/firecrawl synced 2025-08-14 16:15:57 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix(WebScraper/sitemap): await urlsHandler to fix race condition

Browse Source
This commit is contained in:
Gergő Móricz 2024-12-30 16:09:14 +01:00
parent 8ae34a0d31
commit 71a8f7452c
2 changed files with 6 additions and 2 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

@ -506,7 +506,7 @@ export class WebCrawler {
// Get all links from the main domain's sitemap
sitemapCount += await getLinksFromSitemap(
{ sitemapUrl: mainDomainSitemapUrl, urlsHandler(urls) {
urlsHandler(urls.filter(link => {
return urlsHandler(urls.filter(link => {
try {
const linkUrl = new URL(link);
return linkUrl.hostname.endsWith(hostname);

6
apps/api/src/scraper/WebScraper/sitemap.ts
View File

@ -103,7 +103,11 @@ export async function getLinksFromSitemap(
)
.map((url) => url.loc[0]);
count += validUrls.length;
urlsHandler(validUrls);
const h = urlsHandler(validUrls);
if (h instanceof Promise) {
await h;
}
}
return count;