all: ignore HTML page from external domain

Any HTML link that is from domain other than the scanned domain should
net get parsed.
It only check if the link is valid or not.

1 files changed, 4 insertions, 0 deletions

diff --git a/worker.go b/worker.go
index ac25bf4..700c9a5 100644
--- a/worker.go
+++ b/worker.go
@@ -137,6 +137,10 @@ func (wrk *worker) scan(linkq linkQueue) {
 	if linkq.kind == atom.Img {
 		return
 	}
+	if !strings.HasPrefix(linkq.url, wrk.baseUrl.String()) {
+		// Do not parse the page from external domain.
+		return
+	}
 	err = wrk.parseHTML(linkq.url, httpResp.Body)
 	if err != nil {
 		wrk.errq <- fmt.Errorf(`%s %s: %w`, logp, linkq.url, err)