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
96 lines
2.6 KiB
Go
96 lines
2.6 KiB
Go
package sources
|
|
|
|
import (
|
|
"context"
|
|
"fmt"
|
|
"net/http"
|
|
"net/url"
|
|
"regexp"
|
|
"time"
|
|
|
|
"golang.org/x/time/rate"
|
|
|
|
"github.com/salvacybersec/keyhunter/pkg/providers"
|
|
"github.com/salvacybersec/keyhunter/pkg/recon"
|
|
)
|
|
|
|
// CodeSandboxSource scrapes codesandbox.io search results for references to
|
|
// provider keywords. Mirrors ReplitSource: robots-respecting, 10 req/min,
|
|
// no credentials required.
|
|
type CodeSandboxSource struct {
|
|
BaseURL string
|
|
Registry *providers.Registry
|
|
Limiters *recon.LimiterRegistry
|
|
Client *Client
|
|
}
|
|
|
|
// codeSandboxLinkRE matches /s/<slug> sandbox result links.
|
|
var codeSandboxLinkRE = regexp.MustCompile(`^/s/[a-zA-Z0-9-]+$`)
|
|
|
|
// Compile-time assertion that CodeSandboxSource satisfies recon.ReconSource.
|
|
var _ recon.ReconSource = (*CodeSandboxSource)(nil)
|
|
|
|
func (s *CodeSandboxSource) Name() string { return "codesandbox" }
|
|
func (s *CodeSandboxSource) RateLimit() rate.Limit { return rate.Every(6 * time.Second) }
|
|
func (s *CodeSandboxSource) Burst() int { return 1 }
|
|
func (s *CodeSandboxSource) RespectsRobots() bool { return true }
|
|
func (s *CodeSandboxSource) Enabled(_ recon.Config) bool { return true }
|
|
|
|
// Sweep runs a CodeSandbox search per provider keyword and emits one Finding
|
|
// per matched result anchor.
|
|
func (s *CodeSandboxSource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
|
|
base := s.BaseURL
|
|
if base == "" {
|
|
base = "https://codesandbox.io"
|
|
}
|
|
client := s.Client
|
|
if client == nil {
|
|
client = NewClient()
|
|
}
|
|
|
|
queries := BuildQueries(s.Registry, "codesandbox")
|
|
if len(queries) == 0 {
|
|
return nil
|
|
}
|
|
|
|
for _, q := range queries {
|
|
if err := ctx.Err(); err != nil {
|
|
return err
|
|
}
|
|
|
|
if s.Limiters != nil {
|
|
if err := s.Limiters.Wait(ctx, s.Name(), s.RateLimit(), s.Burst(), false); err != nil {
|
|
return err
|
|
}
|
|
}
|
|
|
|
searchURL := fmt.Sprintf("%s/search?query=%s&type=sandboxes", base, url.QueryEscape(q))
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodGet, searchURL, nil)
|
|
if err != nil {
|
|
return fmt.Errorf("codesandbox: build req: %w", err)
|
|
}
|
|
resp, err := client.Do(ctx, req)
|
|
if err != nil {
|
|
return fmt.Errorf("codesandbox: fetch: %w", err)
|
|
}
|
|
links, err := extractAnchorHrefs(resp.Body, codeSandboxLinkRE)
|
|
_ = resp.Body.Close()
|
|
if err != nil {
|
|
return fmt.Errorf("codesandbox: parse html: %w", err)
|
|
}
|
|
|
|
for _, href := range links {
|
|
if err := ctx.Err(); err != nil {
|
|
return err
|
|
}
|
|
out <- recon.Finding{
|
|
Source: base + href,
|
|
SourceType: "recon:codesandbox",
|
|
Confidence: "low",
|
|
DetectedAt: time.Now(),
|
|
}
|
|
}
|
|
}
|
|
return nil
|
|
}
|