Austin/firecrawl
1
0
Fork 0
mirror of https://github.com/mendableai/firecrawl.git synced 2024-11-16 11:42:24 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

fix(crawl): initialURL setting is unnecessary
Some checks are pending
Deploy Images to GHCR / push-app-image (push) Waiting to run
Details

Browse Source
This commit is contained in:
Gergő Móricz 2024-11-12 23:35:07 +01:00
parent 93ac20f930
commit 5ce4aaf0ec
2 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
apps/api/src/lib/crawl-redis.ts
View File

@ -166,10 +166,10 @@ export async function lockURLs(id: string, sc: StoredCrawl, urls: string[]): Pro
return res; return res;
} }
export function crawlToCrawler(id: string, sc: StoredCrawl, initialUrl?: string): WebCrawler { export function crawlToCrawler(id: string, sc: StoredCrawl): WebCrawler {
const crawler = new WebCrawler({ const crawler = new WebCrawler({
jobId: id, jobId: id,
initialUrl: initialUrl ?? sc.originUrl!, initialUrl: sc.originUrl!,
includes: sc.crawlerOptions?.includes ?? [], includes: sc.crawlerOptions?.includes ?? [],
excludes: sc.crawlerOptions?.excludes ?? [], excludes: sc.crawlerOptions?.excludes ?? [],
maxCrawledLinks: sc.crawlerOptions?.maxCrawledLinks ?? 1000, maxCrawledLinks: sc.crawlerOptions?.maxCrawledLinks ?? 1000,

2
apps/api/src/services/queue-worker.ts
View File

@ -352,7 +352,7 @@ async function processJob(job: Job & { id: string }, token: string) {
if (!job.data.sitemapped && job.data.crawlerOptions !== null) { if (!job.data.sitemapped && job.data.crawlerOptions !== null) {
if (!sc.cancelled) { if (!sc.cancelled) {
const crawler = crawlToCrawler(job.data.crawl_id, sc, doc.metadata?.url ?? doc.metadata?.sourceURL ?? undefined); const crawler = crawlToCrawler(job.data.crawl_id, sc);
const links = crawler.filterLinks( const links = crawler.filterLinks(
crawler.extractLinksFromHTML(rawHtml ?? "", doc.metadata?.url ?? doc.metadata?.sourceURL ?? sc.originUrl as string), crawler.extractLinksFromHTML(rawHtml ?? "", doc.metadata?.url ?? doc.metadata?.sourceURL ?? sc.originUrl as string),