trufflehog/pkg/detectors/adzuna/adzuna.go
Dustin Decker 14e44db2be
Move detectors.IsKnownFalsePositive from the detectors and into the engine (#2643)
* Remove detectors.IsKnownFalsePositive from detectors

* Centralize false positive removal in engine

* Don't apply fp filtering on custom regex to preserve previous behavior.

* fix empty branch

* update excludes

* update filtering

* Add result flag option and exclude some detectors
2024-04-22 15:18:04 -07:00

109 lines
2.9 KiB
Go

package adzuna
import (
"context"
"fmt"
regexp "github.com/wasilibs/go-re2"
"net/http"
"strings"
"github.com/trufflesecurity/trufflehog/v3/pkg/common"
"github.com/trufflesecurity/trufflehog/v3/pkg/detectors"
"github.com/trufflesecurity/trufflehog/v3/pkg/pb/detectorspb"
)
type Scanner struct {
client *http.Client
}
const adzunaURL = "https://api.adzuna.com"
var (
// Ensure the Scanner satisfies the interface at compile time.
_ detectors.Detector = (*Scanner)(nil)
defaultClient = common.SaneHttpClient()
// Make sure that your group is surrounded in boundary characters such as below to reduce false positives.
keyPat = regexp.MustCompile(detectors.PrefixRegex([]string{"adzuna"}) + `\b([a-z0-9]{32})\b`)
idPat = regexp.MustCompile(detectors.PrefixRegex([]string{"adzuna"}) + `\b([a-z0-9]{8})\b`)
)
// Keywords are used for efficiently pre-filtering chunks.
// Use identifiers in the secret preferably, or the provider name.
func (s Scanner) Keywords() []string {
return []string{"adzuna"}
}
func (s Scanner) getClient() *http.Client {
if s.client != nil {
return s.client
}
return defaultClient
}
// FromData will find and optionally verify Adzuna secrets in a given set of bytes.
func (s Scanner) FromData(ctx context.Context, verify bool, data []byte) (results []detectors.Result, err error) {
dataStr := string(data)
matches := keyPat.FindAllStringSubmatch(dataStr, -1)
idMatches := idPat.FindAllStringSubmatch(dataStr, -1)
for _, match := range matches {
if len(match) != 2 {
continue
}
resMatch := strings.TrimSpace(match[1])
for _, idMatch := range idMatches {
if len(idMatch) != 2 {
continue
}
resIdMatch := strings.TrimSpace(idMatch[1])
s1 := detectors.Result{
DetectorType: detectorspb.DetectorType_Adzuna,
Raw: []byte(resMatch),
RawV2: []byte(resMatch + resIdMatch),
}
if verify {
client := s.getClient()
isVerified, verificationErr := verifyAdzuna(ctx, client, resMatch, resIdMatch)
s1.Verified = isVerified
s1.SetVerificationError(verificationErr, resMatch)
}
results = append(results, s1)
}
}
return results, nil
}
func verifyAdzuna(ctx context.Context, client *http.Client, resMatch, resIdMatch string) (bool, error) {
// https://developer.adzuna.com/activedocs#!/adzuna/search
req, err := http.NewRequestWithContext(ctx, http.MethodGet, adzunaURL+fmt.Sprintf("/v1/api/jobs/us/search/1?app_id=%s&app_key=%s", resIdMatch, resMatch), nil)
if err != nil {
return false, err
}
res, err := client.Do(req)
if err != nil {
return false, err
}
defer res.Body.Close()
// https://developer.adzuna.com/overview
switch res.StatusCode {
case http.StatusOK:
return true, nil
case http.StatusUnauthorized:
return false, nil
default:
return false, fmt.Errorf("unexpected HTTP response status %d", res.StatusCode)
}
}
func (s Scanner) Type() detectorspb.DetectorType {
return detectorspb.DetectorType_Adzuna
}