feat(11-01): add DuckDuckGoSource, YandexSource, and BraveSource
- DuckDuckGoSource scrapes HTML search (no API key, always enabled, RespectsRobots=true) - YandexSource uses Yandex XML Search API (user+key required, XML response parsing) - BraveSource uses Brave Search API (X-Subscription-Token header, JSON response) - All three follow established error handling: 401 aborts, transient continues, ctx cancellation returns
This commit is contained in:
153
pkg/recon/sources/brave.go
Normal file
153
pkg/recon/sources/brave.go
Normal file
@@ -0,0 +1,153 @@
|
||||
package sources
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"golang.org/x/time/rate"
|
||||
|
||||
"github.com/salvacybersec/keyhunter/pkg/providers"
|
||||
"github.com/salvacybersec/keyhunter/pkg/recon"
|
||||
)
|
||||
|
||||
// BraveSource implements recon.ReconSource against the Brave Search API.
|
||||
// It requires an API key (X-Subscription-Token) to be enabled.
|
||||
type BraveSource struct {
|
||||
APIKey string
|
||||
BaseURL string
|
||||
Registry *providers.Registry
|
||||
Limiters *recon.LimiterRegistry
|
||||
client *Client
|
||||
}
|
||||
|
||||
// Compile-time assertion.
|
||||
var _ recon.ReconSource = (*BraveSource)(nil)
|
||||
|
||||
// NewBraveSource constructs a BraveSource with the shared retry client.
|
||||
func NewBraveSource(apiKey string, reg *providers.Registry, lim *recon.LimiterRegistry) *BraveSource {
|
||||
return &BraveSource{
|
||||
APIKey: apiKey,
|
||||
BaseURL: "https://api.search.brave.com",
|
||||
Registry: reg,
|
||||
Limiters: lim,
|
||||
client: NewClient(),
|
||||
}
|
||||
}
|
||||
|
||||
func (s *BraveSource) Name() string { return "brave" }
|
||||
func (s *BraveSource) RateLimit() rate.Limit { return rate.Every(1 * time.Second) }
|
||||
func (s *BraveSource) Burst() int { return 1 }
|
||||
func (s *BraveSource) RespectsRobots() bool { return false }
|
||||
|
||||
// Enabled returns true only when APIKey is configured.
|
||||
func (s *BraveSource) Enabled(_ recon.Config) bool { return s.APIKey != "" }
|
||||
|
||||
// Sweep issues one Brave Search request per provider keyword and emits a
|
||||
// Finding for every web result.
|
||||
func (s *BraveSource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
|
||||
if s.APIKey == "" {
|
||||
return nil
|
||||
}
|
||||
base := s.BaseURL
|
||||
if base == "" {
|
||||
base = "https://api.search.brave.com"
|
||||
}
|
||||
|
||||
queries := BuildQueries(s.Registry, "brave")
|
||||
kwIndex := braveKeywordIndex(s.Registry)
|
||||
|
||||
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
|
||||
}
|
||||
}
|
||||
|
||||
endpoint := fmt.Sprintf("%s/res/v1/web/search?q=%s&count=20", base, url.QueryEscape(q))
|
||||
req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
|
||||
if err != nil {
|
||||
return fmt.Errorf("brave: build request: %w", err)
|
||||
}
|
||||
req.Header.Set("X-Subscription-Token", s.APIKey)
|
||||
req.Header.Set("Accept", "application/json")
|
||||
req.Header.Set("User-Agent", "keyhunter-recon")
|
||||
|
||||
resp, err := s.client.Do(ctx, req)
|
||||
if err != nil {
|
||||
if errors.Is(err, ErrUnauthorized) {
|
||||
return err
|
||||
}
|
||||
if errors.Is(err, context.Canceled) || errors.Is(err, context.DeadlineExceeded) {
|
||||
return err
|
||||
}
|
||||
continue
|
||||
}
|
||||
|
||||
var parsed braveSearchResponse
|
||||
decErr := json.NewDecoder(resp.Body).Decode(&parsed)
|
||||
_ = resp.Body.Close()
|
||||
if decErr != nil {
|
||||
continue
|
||||
}
|
||||
|
||||
provName := kwIndex[strings.ToLower(extractGoogleKeyword(q))]
|
||||
for _, it := range parsed.Web.Results {
|
||||
f := recon.Finding{
|
||||
ProviderName: provName,
|
||||
Confidence: "low",
|
||||
Source: it.URL,
|
||||
SourceType: "recon:brave",
|
||||
DetectedAt: time.Now(),
|
||||
}
|
||||
select {
|
||||
case out <- f:
|
||||
case <-ctx.Done():
|
||||
return ctx.Err()
|
||||
}
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
type braveSearchResponse struct {
|
||||
Web braveWebResults `json:"web"`
|
||||
}
|
||||
|
||||
type braveWebResults struct {
|
||||
Results []braveWebItem `json:"results"`
|
||||
}
|
||||
|
||||
type braveWebItem struct {
|
||||
URL string `json:"url"`
|
||||
Title string `json:"title"`
|
||||
Description string `json:"description"`
|
||||
}
|
||||
|
||||
// braveKeywordIndex maps lowercased keywords to provider names.
|
||||
func braveKeywordIndex(reg *providers.Registry) map[string]string {
|
||||
m := make(map[string]string)
|
||||
if reg == nil {
|
||||
return m
|
||||
}
|
||||
for _, p := range reg.List() {
|
||||
for _, k := range p.Keywords {
|
||||
kl := strings.ToLower(strings.TrimSpace(k))
|
||||
if kl == "" {
|
||||
continue
|
||||
}
|
||||
if _, exists := m[kl]; !exists {
|
||||
m[kl] = p.Name
|
||||
}
|
||||
}
|
||||
}
|
||||
return m
|
||||
}
|
||||
Reference in New Issue
Block a user