package duckduckgo import ( "bytes" "errors" "os" "strings" "testing" "github.com/karust/openserp/core" ) func TestParseDDGHTML(t *testing.T) { t.Parallel() data, err := os.ReadFile("testdata/search_results.html") if err != nil { t.Fatalf("read fixture: %v", err) } results, err := ParseHTML(bytes.NewReader(data)) if err != nil { t.Fatalf("ParseHTML() error = %v", err) } rank := 0 for i, r := range results { if r.Ad { continue } rank++ if r.Rank != rank { t.Fatalf("rank sequence broken at index %d: got %d, want %d", i, r.Rank, rank) } if r.URL == "" { t.Fatalf("result %d: empty URL", i) } if r.Title == "" { t.Fatalf("result %d: empty Title", i) } if !strings.HasPrefix(r.URL, "http") { t.Fatalf("result %d: URL not absolute: %s", i, r.URL) } } if rank == 0 { t.Fatal("expected at least one organic result") } } func TestParseDDGHTMLEmpty(t *testing.T) { t.Parallel() results, err := ParseHTML(bytes.NewReader([]byte(""))) if err != nil { t.Fatalf("ParseHTML() error = %v", err) } if len(results) != 0 { t.Fatalf("expected zero results for empty HTML, got %d", len(results)) } } func TestParseDDGHTMLCaptcha(t *testing.T) { t.Parallel() html := `
` results, err := ParseHTML(bytes.NewReader([]byte(html))) if !errors.Is(err, core.ErrCaptcha) { t.Fatalf("expected ErrCaptcha, got results=%d err=%v", len(results), err) } } func TestParseDDGHTMLNoResults(t *testing.T) { t.Parallel() html := `