add phash calculation for screenshot

This commit is contained in:
Doğan Can Bakır 2023-09-18 08:27:21 +00:00
parent 3a6838354d
commit e5d8036ec0
3 changed files with 37 additions and 0 deletions

2
go.mod
View File

@ -71,6 +71,7 @@ require (
github.com/cloudflare/cfssl v1.6.4 // indirect
github.com/cloudflare/circl v1.3.3 // indirect
github.com/cnf/structhash v0.0.0-20201127153200-e1b16c1ebc08 // indirect
github.com/corona10/goimagehash v1.1.0 // indirect
github.com/davecgh/go-spew v1.1.1 // indirect
github.com/dimchansky/utfbom v1.1.1 // indirect
github.com/dlclark/regexp2 v1.8.1 // indirect
@ -99,6 +100,7 @@ require (
github.com/modern-go/reflect2 v1.0.2 // indirect
github.com/muesli/reflow v0.3.0 // indirect
github.com/muesli/termenv v0.15.1 // indirect
github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 // indirect
github.com/nwaples/rardecode v1.1.3 // indirect
github.com/olekukonko/tablewriter v0.0.5 // indirect
github.com/pierrec/lz4 v2.6.1+incompatible // indirect

9
go.sum
View File

@ -41,6 +41,8 @@ github.com/cloudflare/circl v1.3.3 h1:fE/Qz0QdIGqeWfnwq0RE0R7MI51s0M2E4Ga9kq5AEM
github.com/cloudflare/circl v1.3.3/go.mod h1:5XYMA4rFBvNIrhs50XuiBJ15vF2pZn4nnUKZrLbUZFA=
github.com/cnf/structhash v0.0.0-20201127153200-e1b16c1ebc08 h1:ox2F0PSMlrAAiAdknSRMDrAr8mfxPCfSZolH+/qQnyQ=
github.com/cnf/structhash v0.0.0-20201127153200-e1b16c1ebc08/go.mod h1:pCxVEbcm3AMg7ejXyorUXi6HQCzOIBf7zEDVPtw0/U4=
github.com/corona10/goimagehash v1.1.0 h1:teNMX/1e+Wn/AYSbLHX8mj+mF9r60R1kBeqE9MkoYwI=
github.com/corona10/goimagehash v1.1.0/go.mod h1:VkvE0mLn84L4aF8vCb6mafVajEb6QYMHl2ZJLn0mOGI=
github.com/corpix/uarand v0.2.0 h1:U98xXwud/AVuCpkpgfPF7J5TQgr7R5tqT8VZP5KWbzE=
github.com/corpix/uarand v0.2.0/go.mod h1:/3Z1QIqWkDIhf6XWn/08/uMHoQ8JUoTIKc2iPchBOmM=
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@ -57,6 +59,7 @@ github.com/dsnet/golib v0.0.0-20171103203638-1ea166775780/go.mod h1:Lj+Z9rebOhdf
github.com/fatih/color v1.15.0 h1:kOqh6YHBtK8aywxGerMG2Eq3H6Qgoqeo13Bk2Mv/nBs=
github.com/fatih/color v1.15.0/go.mod h1:0h5ZqXfHYED7Bhv2ZJamyIOUej9KtShiJESRwBDUSsw=
github.com/frankban/quicktest v1.11.3 h1:8sXhOn0uLys67V8EsXLc6eszDs8VXWxL3iRvebPhedY=
github.com/frankban/quicktest v1.11.3/go.mod h1:wRf/ReqHper53s+kmmSZizM8NamnL3IM0I9ntUbOk+k=
github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo=
github.com/fsnotify/fsnotify v1.5.4 h1:jRbGcIw6P2Meqdwuo0H1p6JVLbL5DHKAKlYndzMwVZI=
github.com/gaukas/godicttls v0.0.4 h1:NlRaXb3J6hAnTmWdsEKb9bcSBD6BvcIjdGdeb0zfXbk=
@ -126,6 +129,7 @@ github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
github.com/logrusorgru/aurora v2.0.3+incompatible h1:tOpm7WcpBTn4fjmVfgpQq0EfczGlG91VSDkswnjF5A8=
github.com/logrusorgru/aurora v2.0.3+incompatible/go.mod h1:7rIyQOR62GCctdiQpZ/zOJlFyk6y+94wXzv6RNZgaR4=
github.com/lucasb-eyer/go-colorful v1.2.0 h1:1nnpGOrhyZZuNyfu1QjKiUICQ74+3FNCN69Aj6K7nkY=
@ -167,6 +171,8 @@ github.com/muesli/reflow v0.3.0/go.mod h1:pbwTDkVPibjO2kyvBQRBxTWEEGDGq0FlB1BIKt
github.com/muesli/termenv v0.13.0/go.mod h1:sP1+uffeLaEYpyOTb8pLCUctGcGLnoFjSn4YJK5e2bc=
github.com/muesli/termenv v0.15.1 h1:UzuTb/+hhlBugQz28rpzey4ZuKcZ03MeKsoG7IJZIxs=
github.com/muesli/termenv v0.15.1/go.mod h1:HeAQPTzpfs016yGtA4g00CsdYnVLJvxsS4ANqrZs2sQ=
github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646 h1:zYyBkD/k9seD2A7fsi6Oo2LfFZAehjjQMERAvZLEDnQ=
github.com/nfnt/resize v0.0.0-20180221191011-83c6a9932646/go.mod h1:jpp1/29i3P1S/RLdc7JQKbRpFeM1dOBd8T9ki5s+AY8=
github.com/nwaples/rardecode v1.1.3 h1:cWCaZwfM5H7nAD6PyEdcVnczzV8i/JtotnyW/dD9lEc=
github.com/nwaples/rardecode v1.1.3/go.mod h1:5DzqNKiOdpKKBH87u8VlvAnPZMXcGRhxWkRpHbbfGS0=
github.com/nxadm/tail v1.4.8 h1:nPr65rt6Y5JFSKQO7qToXr7pePgD6Gwiw05lkbyAQTE=
@ -347,6 +353,7 @@ github.com/zmap/zcrypto v0.0.0-20230422215203-9a665e1e9968/go.mod h1:xIuOvYCZX21
github.com/zmap/zlint/v3 v3.0.0/go.mod h1:paGwFySdHIBEMJ61YjoqT4h7Ge+fdYG4sUQhnTb1lJ8=
go.etcd.io/bbolt v1.3.7 h1:j+zJOnnEjF/kyHlDDgGnVL/AIqIJPq8UoB2GSNfkUfQ=
go.etcd.io/bbolt v1.3.7/go.mod h1:N9Mkw9X8x5fupy0IKsmuqVtoGDyxsaDlbk4Rd05IAQw=
go.uber.org/atomic v1.9.0/go.mod h1:fEN4uk6kAWBTFdckzkM89CLk9XfWZrxpCo0nPH17wJc=
go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
@ -468,6 +475,7 @@ google.golang.org/protobuf v1.31.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqw
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
gopkg.in/djherbis/times.v1 v1.3.0 h1:uxMS4iMtH6Pwsxog094W0FYldiNnfY/xba00vq6C2+o=
gopkg.in/djherbis/times.v1 v1.3.0/go.mod h1:AQlg6unIsrsCEdQYhTzERy542dz6SFdQFZFv6mUY0P8=
gopkg.in/fsnotify.v1 v1.4.7/go.mod h1:Tz8NjZHkW78fSQdbUxIjBTcgA1z1m8ZHf0WmKUhAMys=
@ -477,6 +485,7 @@ gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 h1:uRGJdciOHaEIrze2W8Q3AKkep
gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=
gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

View File

@ -8,6 +8,7 @@ import (
"encoding/json"
"fmt"
"html/template"
"image"
"io"
"net"
"net/http"
@ -25,6 +26,7 @@ import (
"golang.org/x/exp/maps"
"github.com/PuerkitoBio/goquery"
"github.com/corona10/goimagehash"
asnmap "github.com/projectdiscovery/asnmap/libs"
"github.com/projectdiscovery/fastdialer/fastdialer"
"github.com/projectdiscovery/httpx/common/customextract"
@ -1877,6 +1879,7 @@ retry:
screenshotBytes []byte
headlessBody string
)
var pHash uint64
if scanopts.Screenshot {
var err error
screenshotBytes, headlessBody, err = r.browser.ScreenshotWithBody(fullURL, r.hp.Options.Timeout)
@ -1890,6 +1893,12 @@ retry:
if err != nil {
gologger.Error().Msgf("Could not write screenshot at path '%s', to disk: %s", screenshotPath, err)
}
pHash, err = calculatePerceptionHash(screenshotBytes)
if err != nil {
gologger.Warning().Msgf("%v: %s", err, fullURL)
}
}
if scanopts.NoScreenshotBytes {
screenshotBytes = []byte{}
@ -1952,11 +1961,28 @@ retry:
HeadlessBody: headlessBody,
KnowledgeBase: map[string]interface{}{
"PageType": r.errorPageClassifier.Classify(respData),
"pHash": pHash,
},
}
return result
}
func calculatePerceptionHash(screenshotBytes []byte) (uint64, error) {
reader := bytes.NewReader(screenshotBytes)
img, _, err := image.Decode(reader)
if err != nil {
return 0, errors.Wrap(err, "failed to decode screenshot")
}
pHash, err := goimagehash.PerceptionHash(img)
if err != nil {
return 0, errors.Wrap(err, "failed to calculate perceptual hash")
}
return pHash.GetHash(), nil
}
func (r *Runner) handleFaviconHash(hp *httpx.HTTPX, req *retryablehttp.Request, currentResp *httpx.Response) (string, string, error) {
// Check if current URI is ending with .ico => use current body without additional requests
if path.Ext(req.URL.Path) == ".ico" {