brokenlinks: skip parsing non-HTML page

If the response Content-type return other than "text/html", skip parsing
the content and return immediately.

1 files changed, 11 insertions, 7 deletions

diff --git a/brokenlinks/worker.go b/brokenlinks/worker.go
index 09c8b12..3e089fc 100644
--- a/brokenlinks/worker.go
+++ b/brokenlinks/worker.go
@@ -266,14 +266,18 @@ func (wrk *worker) scan(linkq jarink.Link) (resultq map[string]jarink.Link) {
 		return resultq
 	}
 
-	// After we check the code for [html.Parse] there are no cases where
-	// it will return an error.
-	// The only possible error is when reading from body (io.Reader), and
-	// that is also almost impossible.
-	//
-	// [html.Parse]: https://go.googlesource.com/net/+/refs/tags/v0.40.0/html/parse.go#2347
+	contentType := httpResp.Header.Get(`Content-Type`)
+	if !strings.HasPrefix(contentType, `text/html`) {
+		return resultq
+	}
+
 	var doc *html.Node
-	doc, _ = html.Parse(httpResp.Body)
+	doc, err = html.Parse(httpResp.Body)
+	if err != nil {
+		linkq.ErrScan = err
+		resultq[linkq.Url] = linkq
+		return resultq
+	}
 
 	var parentUrl *url.URL