770705302c
- 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
117 lines
3.1 KiB
Go
117 lines
3.1 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"
|
|
)
|
|
|
|
// DuckDuckGoSource implements recon.ReconSource by scraping DuckDuckGo's HTML
|
|
// search endpoint. No API key is required -- this source is always enabled.
|
|
//
|
|
// It operates conservatively (2s per request) and declares RespectsRobots=true.
|
|
type DuckDuckGoSource struct {
|
|
BaseURL string
|
|
Registry *providers.Registry
|
|
Limiters *recon.LimiterRegistry
|
|
client *Client
|
|
}
|
|
|
|
// Compile-time assertion.
|
|
var _ recon.ReconSource = (*DuckDuckGoSource)(nil)
|
|
|
|
// ddgResultRE matches DuckDuckGo HTML result links. The HTML search page uses
|
|
// <a class="result__a" href="..."> anchors for organic results.
|
|
var ddgResultRE = regexp.MustCompile(`^https?://`)
|
|
|
|
// NewDuckDuckGoSource constructs a DuckDuckGoSource with the shared retry client.
|
|
func NewDuckDuckGoSource(reg *providers.Registry, lim *recon.LimiterRegistry) *DuckDuckGoSource {
|
|
return &DuckDuckGoSource{
|
|
BaseURL: "https://html.duckduckgo.com",
|
|
Registry: reg,
|
|
Limiters: lim,
|
|
client: NewClient(),
|
|
}
|
|
}
|
|
|
|
func (s *DuckDuckGoSource) Name() string { return "duckduckgo" }
|
|
func (s *DuckDuckGoSource) RateLimit() rate.Limit { return rate.Every(2 * time.Second) }
|
|
func (s *DuckDuckGoSource) Burst() int { return 1 }
|
|
func (s *DuckDuckGoSource) RespectsRobots() bool { return true }
|
|
|
|
// Enabled always returns true -- DuckDuckGo HTML scraping requires no credentials.
|
|
func (s *DuckDuckGoSource) Enabled(_ recon.Config) bool { return true }
|
|
|
|
// Sweep iterates provider keywords, scrapes DuckDuckGo HTML search, and emits
|
|
// a Finding per result link.
|
|
func (s *DuckDuckGoSource) Sweep(ctx context.Context, _ string, out chan<- recon.Finding) error {
|
|
base := s.BaseURL
|
|
if base == "" {
|
|
base = "https://html.duckduckgo.com"
|
|
}
|
|
client := s.client
|
|
if client == nil {
|
|
client = NewClient()
|
|
}
|
|
|
|
queries := BuildQueries(s.Registry, "duckduckgo")
|
|
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/html/?q=%s", base, url.QueryEscape(q))
|
|
req, err := http.NewRequestWithContext(ctx, http.MethodGet, searchURL, nil)
|
|
if err != nil {
|
|
return fmt.Errorf("duckduckgo: build req: %w", err)
|
|
}
|
|
req.Header.Set("User-Agent", "keyhunter-recon")
|
|
|
|
resp, err := client.Do(ctx, req)
|
|
if err != nil {
|
|
// Transient failures: continue to next query.
|
|
continue
|
|
}
|
|
links, parseErr := extractAnchorHrefs(resp.Body, ddgResultRE)
|
|
_ = resp.Body.Close()
|
|
if parseErr != nil {
|
|
continue
|
|
}
|
|
|
|
for _, href := range links {
|
|
if err := ctx.Err(); err != nil {
|
|
return err
|
|
}
|
|
f := recon.Finding{
|
|
Source: href,
|
|
SourceType: "recon:duckduckgo",
|
|
Confidence: "low",
|
|
DetectedAt: time.Now(),
|
|
}
|
|
select {
|
|
case out <- f:
|
|
case <-ctx.Done():
|
|
return ctx.Err()
|
|
}
|
|
}
|
|
}
|
|
return nil
|
|
}
|