feat(14-02): add WaybackMachine + CommonCrawl recon sources

- WaybackMachineSource queries CDX API for historical snapshots
- CommonCrawlSource queries CC Index API for matching pages
- Both credentialless, rate-limited at 1 req/5s, RespectsRobots=true
- RegisterAll extended to 42 sources (40 Phase 10-13 + 2 Phase 14)
- Full httptest-based test coverage for both sources

pkg/recon/sources/wayback_test.go

@@ -0,0 +1,168 @@
+package sources
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"net/http"
+	"net/http/httptest"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/salvacybersec/keyhunter/pkg/recon"
+)
+
+func waybackStubHandler(t *testing.T, calls *int32) http.HandlerFunc {
+	t.Helper()
+	return func(w http.ResponseWriter, r *http.Request) {
+		atomic.AddInt32(calls, 1)
+		if r.URL.Path != "/cdx/search/cdx" {
+			t.Errorf("unexpected path: %s", r.URL.Path)
+		}
+		if r.URL.Query().Get("query") == "" {
+			t.Errorf("missing query param")
+		}
+		w.Header().Set("Content-Type", "text/plain")
+		// Two CDX records per query: "timestamp original-url"
+		fmt.Fprintln(w, "20230101120000 https://example.com/config.js")
+		fmt.Fprintln(w, "20230615080000 https://example.com/env.json")
+	}
+}
+
+func TestWayback_SweepEmitsFindings(t *testing.T) {
+	reg := syntheticRegistry()
+	lim := recon.NewLimiterRegistry()
+	_ = lim.For("wayback", 1000, 100)
+
+	var calls int32
+	srv := httptest.NewServer(waybackStubHandler(t, &calls))
+	defer srv.Close()
+
+	src := &WaybackMachineSource{
+		BaseURL:  srv.URL,
+		Registry: reg,
+		Limiters: lim,
+		Client:   NewClient(),
+	}
+
+	out := make(chan recon.Finding, 32)
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	done := make(chan error, 1)
+	go func() { done <- src.Sweep(ctx, "", out); close(out) }()
+
+	var findings []recon.Finding
+	for f := range out {
+		findings = append(findings, f)
+	}
+	if err := <-done; err != nil {
+		t.Fatalf("Sweep error: %v", err)
+	}
+
+	// 2 keywords * 2 results = 4 findings
+	if len(findings) != 4 {
+		t.Fatalf("expected 4 findings, got %d", len(findings))
+	}
+	for _, f := range findings {
+		if f.SourceType != "recon:wayback" {
+			t.Errorf("SourceType=%q want recon:wayback", f.SourceType)
+		}
+	}
+	if got := atomic.LoadInt32(&calls); got != 2 {
+		t.Errorf("expected 2 server calls, got %d", got)
+	}
+}
+
+func TestWayback_SnapshotURL(t *testing.T) {
+	reg := syntheticRegistry()
+	lim := recon.NewLimiterRegistry()
+	_ = lim.For("wayback", 1000, 100)
+
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		w.Header().Set("Content-Type", "text/plain")
+		fmt.Fprintln(w, "20240101000000 https://target.com/page")
+	}))
+	defer srv.Close()
+
+	src := &WaybackMachineSource{
+		BaseURL:  srv.URL,
+		Registry: reg,
+		Limiters: lim,
+		Client:   NewClient(),
+	}
+
+	out := make(chan recon.Finding, 32)
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	done := make(chan error, 1)
+	go func() { done <- src.Sweep(ctx, "", out); close(out) }()
+
+	var findings []recon.Finding
+	for f := range out {
+		findings = append(findings, f)
+	}
+	if err := <-done; err != nil {
+		t.Fatalf("Sweep error: %v", err)
+	}
+
+	// Each finding should have a proper Wayback snapshot URL
+	for _, f := range findings {
+		want := srv.URL + "/web/20240101000000/https://target.com/page"
+		if f.Source != want {
+			t.Errorf("Source=%q want %q", f.Source, want)
+		}
+	}
+}
+
+func TestWayback_EnabledAlwaysTrue(t *testing.T) {
+	s := &WaybackMachineSource{}
+	if !s.Enabled(recon.Config{}) {
+		t.Fatal("expected Enabled=true")
+	}
+}
+
+func TestWayback_NameAndRate(t *testing.T) {
+	s := &WaybackMachineSource{}
+	if s.Name() != "wayback" {
+		t.Errorf("unexpected name: %s", s.Name())
+	}
+	if s.Burst() != 1 {
+		t.Errorf("burst: %d", s.Burst())
+	}
+	if !s.RespectsRobots() {
+		t.Error("expected RespectsRobots=true")
+	}
+}
+
+func TestWayback_CtxCancelled(t *testing.T) {
+	reg := syntheticRegistry()
+	lim := recon.NewLimiterRegistry()
+	_ = lim.For("wayback", 1000, 100)
+
+	src := &WaybackMachineSource{
+		BaseURL:  "http://127.0.0.1:1",
+		Registry: reg,
+		Limiters: lim,
+		Client:   NewClient(),
+	}
+
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	out := make(chan recon.Finding, 1)
+	err := src.Sweep(ctx, "", out)
+	if !errors.Is(err, context.Canceled) {
+		t.Fatalf("expected context.Canceled, got %v", err)
+	}
+}
+
+func TestWayback_NilRegistryNoError(t *testing.T) {
+	src := &WaybackMachineSource{Client: NewClient()}
+	out := make(chan recon.Finding, 1)
+	if err := src.Sweep(context.Background(), "", out); err != nil {
+		t.Fatalf("expected nil, got %v", err)
+	}
+}