feat(duckduckgo): detect anti-bot challenge and surface ErrBlocked
CI / build (push) Successful in 1m0s
CI / test (push) Successful in 1m8s
CI / vet (push) Successful in 1m12s

DuckDuckGo intermittently serves a CAPTCHA modal ("Unfortunately, bots
use DuckDuckGo too...") instead of search results. The result selector
matches zero elements on that page, so callers used to get
([]Result{}, nil) — silent empty results that look like "no matches."

Detect the challenge via the BEM class .anomaly-modal__title and return
a typed ErrBlocked so callers can distinguish blocked from no-results
and react (retry, fallback to another engine, surface to user).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
2026-04-27 23:25:28 +00:00
parent c3be14095a
commit 841f1ec2bf
3 changed files with 40 additions and 0 deletions
+21
View File
@@ -2,6 +2,7 @@ package duckduckgo
import (
"context"
"errors"
"testing"
"gitea.stevedudenhoeffer.com/steve/go-extractor"
@@ -106,6 +107,26 @@ func TestExtractResults_NoLinks(t *testing.T) {
}
}
func TestExtractResults_Blocked(t *testing.T) {
doc := &extractortest.MockDocument{
MockNode: extractortest.MockNode{
Children: map[string]extractor.Nodes{
".anomaly-modal__title": {
&extractortest.MockNode{TextValue: "Unfortunately, bots use DuckDuckGo too."},
},
},
},
}
results, err := extractResults(doc)
if !errors.Is(err, ErrBlocked) {
t.Fatalf("expected ErrBlocked, got %v", err)
}
if results != nil {
t.Errorf("expected nil results when blocked, got %v", results)
}
}
func TestSearch_UsesMockBrowser(t *testing.T) {
doc := &extractortest.MockDocument{
URLValue: "https://duckduckgo.com/?q=test",