cap number of favicons to 50 per host

2026-05-20 00:53:24 -04:00 · 2026-05-20 00:53:24 -04:00 · 03e343a136
commit 03e343a136
parent cd896427eb
1 changed files with 1 additions and 1 deletions
--- a/pipeline/02_warc_parse/parser.go
+++ b/pipeline/02_warc_parse/parser.go
@ -47,7 +47,7 @@ func ParseHTML(body []byte, protocol, hostname string) ParseResult {
 				continue
 			}

-			if tagName == "link" && hasAttr {
+			if tagName == "link" && hasAttr && len(result.Icons) < 50 {
 				icon := parseLinkTag(tokenizer, protocol, hostname)
 				if icon != nil {
 					result.Icons = append(result.Icons, *icon)