feat(11-02): add PastebinSource and GistPasteSource for paste site scanning

- PastebinSource: two-phase search+raw-fetch with keyword matching - GistPasteSource: scrapes gist.github.com public search (no auth) - Both implement recon.ReconSource with httptest-based tests
2026-04-06 11:53:00 +03:00
parent 3aadeb2d1c
commit 3c500b5473
4 changed files with 547 additions and 0 deletions
--- a/pkg/recon/sources/pastebin_test.go
+++ b/pkg/recon/sources/pastebin_test.go
@@ -0,0 +1,120 @@
+package sources
+
+import (
+	"context"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+	"time"
+
+	"github.com/salvacybersec/keyhunter/pkg/providers"
+	"github.com/salvacybersec/keyhunter/pkg/recon"
+)
+
+func pastebinTestRegistry() *providers.Registry {
+	return providers.NewRegistryFromProviders([]providers.Provider{
+		{Name: "openai", Keywords: []string{"sk-proj-"}},
+	})
+}
+
+const pastebinSearchHTML = `<!doctype html>
+<html><body>
+  <a href="/Ab12Cd34">paste one</a>
+  <a href="/Ef56Gh78">paste two</a>
+  <a href="/about">nope</a>
+  <a href="/toolong123">nine chars nope</a>
+</body></html>`
+
+const pastebinRawContent1 = `some text with sk-proj-AAAA1234 leaked here`
+const pastebinRawContent2 = `nothing interesting in this paste`
+
+func TestPastebin_Sweep_ExtractsFindings(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		switch {
+		case r.URL.Path == "/search":
+			w.Header().Set("Content-Type", "text/html")
+			_, _ = w.Write([]byte(pastebinSearchHTML))
+		case r.URL.Path == "/raw/Ab12Cd34":
+			_, _ = w.Write([]byte(pastebinRawContent1))
+		case r.URL.Path == "/raw/Ef56Gh78":
+			_, _ = w.Write([]byte(pastebinRawContent2))
+		default:
+			http.NotFound(w, r)
+		}
+	}))
+	defer srv.Close()
+
+	src := &PastebinSource{
+		BaseURL:  srv.URL,
+		Registry: pastebinTestRegistry(),
+		Limiters: recon.NewLimiterRegistry(),
+		Client:   NewClient(),
+	}
+
+	out := make(chan recon.Finding, 16)
+	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
+	defer cancel()
+
+	if err := src.Sweep(ctx, "", out); err != nil {
+		t.Fatalf("Sweep err: %v", err)
+	}
+	close(out)
+
+	var findings []recon.Finding
+	for f := range out {
+		findings = append(findings, f)
+	}
+	// Only paste one has "sk-proj-", paste two doesn't match.
+	if len(findings) != 1 {
+		t.Fatalf("expected 1 finding, got %d", len(findings))
+	}
+	f := findings[0]
+	if f.SourceType != "recon:pastebin" {
+		t.Errorf("SourceType=%s, want recon:pastebin", f.SourceType)
+	}
+	if f.ProviderName != "openai" {
+		t.Errorf("ProviderName=%s, want openai", f.ProviderName)
+	}
+	wantSource := srv.URL + "/Ab12Cd34"
+	if f.Source != wantSource {
+		t.Errorf("Source=%s, want %s", f.Source, wantSource)
+	}
+}
+
+func TestPastebin_NameAndRate(t *testing.T) {
+	s := &PastebinSource{}
+	if s.Name() != "pastebin" {
+		t.Errorf("Name=%s", s.Name())
+	}
+	if s.Burst() != 1 {
+		t.Errorf("Burst=%d", s.Burst())
+	}
+	if !s.RespectsRobots() {
+		t.Error("expected RespectsRobots=true")
+	}
+	if !s.Enabled(recon.Config{}) {
+		t.Error("expected Enabled=true")
+	}
+}
+
+func TestPastebin_Sweep_CtxCancelled(t *testing.T) {
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		time.Sleep(500 * time.Millisecond)
+		_, _ = w.Write([]byte(pastebinSearchHTML))
+	}))
+	defer srv.Close()
+
+	src := &PastebinSource{
+		BaseURL:  srv.URL,
+		Registry: pastebinTestRegistry(),
+		Limiters: recon.NewLimiterRegistry(),
+		Client:   NewClient(),
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	out := make(chan recon.Finding, 4)
+	if err := src.Sweep(ctx, "", out); err == nil {
+		t.Fatal("expected ctx error")
+	}
+}