62a347f476
- ReplitSource scrapes /search HTML extracting /@user/repl anchors - CodeSandboxSource scrapes /search HTML extracting /s/slug anchors - Both use golang.org/x/net/html parser, 10 req/min rate, RespectsRobots=true - 10 httptest-backed tests covering extraction, ctx cancel, rate/name assertions
110 lines
2.7 KiB
Go
110 lines
2.7 KiB
Go
package sources
|
|
|
|
import (
|
|
"context"
|
|
"net/http"
|
|
"net/http/httptest"
|
|
"testing"
|
|
"time"
|
|
|
|
"github.com/salvacybersec/keyhunter/pkg/providers"
|
|
"github.com/salvacybersec/keyhunter/pkg/recon"
|
|
)
|
|
|
|
func codesandboxTestRegistry() *providers.Registry {
|
|
return providers.NewRegistryFromProviders([]providers.Provider{
|
|
{Name: "anthropic", Keywords: []string{"sk-ant-"}},
|
|
})
|
|
}
|
|
|
|
const codesandboxFixtureHTML = `<!doctype html>
|
|
<html><body>
|
|
<a href="/s/abc123-def">one</a>
|
|
<a href="/s/XYZ-789">two</a>
|
|
<a href="/docs">skip</a>
|
|
<a href="/s/abc/extra/path">skip deeper</a>
|
|
</body></html>`
|
|
|
|
func newCodeSandboxTestSource(srvURL string) *CodeSandboxSource {
|
|
return &CodeSandboxSource{
|
|
BaseURL: srvURL,
|
|
Registry: codesandboxTestRegistry(),
|
|
Limiters: recon.NewLimiterRegistry(),
|
|
Client: NewClient(),
|
|
}
|
|
}
|
|
|
|
func TestCodeSandbox_Sweep_ExtractsFindings(t *testing.T) {
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
if r.URL.Path != "/search" {
|
|
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/html")
|
|
_, _ = w.Write([]byte(codesandboxFixtureHTML))
|
|
}))
|
|
defer srv.Close()
|
|
|
|
src := newCodeSandboxTestSource(srv.URL)
|
|
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)
|
|
}
|
|
if len(findings) != 2 {
|
|
t.Fatalf("expected 2 findings, got %d", len(findings))
|
|
}
|
|
for _, f := range findings {
|
|
if f.SourceType != "recon:codesandbox" {
|
|
t.Errorf("unexpected SourceType: %s", f.SourceType)
|
|
}
|
|
}
|
|
}
|
|
|
|
func TestCodeSandbox_RespectsRobots(t *testing.T) {
|
|
s := &CodeSandboxSource{}
|
|
if !s.RespectsRobots() {
|
|
t.Fatal("expected RespectsRobots=true")
|
|
}
|
|
}
|
|
|
|
func TestCodeSandbox_EnabledAlwaysTrue(t *testing.T) {
|
|
s := &CodeSandboxSource{}
|
|
if !s.Enabled(recon.Config{}) {
|
|
t.Fatal("expected Enabled=true")
|
|
}
|
|
}
|
|
|
|
func TestCodeSandbox_Sweep_CtxCancelled(t *testing.T) {
|
|
srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
|
|
time.Sleep(500 * time.Millisecond)
|
|
}))
|
|
defer srv.Close()
|
|
|
|
src := newCodeSandboxTestSource(srv.URL)
|
|
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")
|
|
}
|
|
}
|
|
|
|
func TestCodeSandbox_NameAndRate(t *testing.T) {
|
|
s := &CodeSandboxSource{}
|
|
if s.Name() != "codesandbox" {
|
|
t.Fatalf("unexpected name: %s", s.Name())
|
|
}
|
|
}
|