mirror of
https://github.com/OpenStaticFish/MicroServices.git
synced 2026-10-13 06:35:12 +00:00
Add site analyzer service
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
# OpenStaticFish MicroServices
|
||||
|
||||
Basic local Kubernetes development setup using Nix, Kind, Tilt, Docker, and a small Go hello-world service.
|
||||
Basic local Kubernetes development setup using Nix, Kind, Tilt, Docker, and small Go microservices.
|
||||
|
||||
## Requirements
|
||||
|
||||
@@ -37,10 +37,16 @@ Open the Tilt UI:
|
||||
http://localhost:10350
|
||||
```
|
||||
|
||||
Test the hello-world service:
|
||||
Test the scraper service:
|
||||
|
||||
```bash
|
||||
curl http://localhost:8080
|
||||
curl http://localhost:8080/health
|
||||
```
|
||||
|
||||
Analyze a site once Tilt is running:
|
||||
|
||||
```bash
|
||||
scripts/analyze-site adaptive.co.uk
|
||||
```
|
||||
|
||||
Stop Tilt resources:
|
||||
@@ -154,10 +160,10 @@ kubectl get pods
|
||||
List running pods.
|
||||
|
||||
```bash
|
||||
kubectl logs -f deployment/hello-world-deployment
|
||||
kubectl logs -f deployment/site-analyzer-deployment
|
||||
```
|
||||
|
||||
Stream logs from the hello-world deployment.
|
||||
Stream logs from the site analyzer deployment.
|
||||
|
||||
```bash
|
||||
kubectl get svc
|
||||
@@ -174,10 +180,52 @@ docker ps
|
||||
List running containers, including Kind node containers.
|
||||
|
||||
```bash
|
||||
docker build -t hello-world ./services/hello-world
|
||||
docker build -t site-analyzer ./services/site-analyzer
|
||||
```
|
||||
|
||||
Build the hello-world image manually outside Tilt.
|
||||
Build the site analyzer image manually outside Tilt.
|
||||
|
||||
## Site Analyzer
|
||||
|
||||
The `site-analyzer` service accepts a URL and returns JSON describing visible site infrastructure and technology signals.
|
||||
|
||||
Endpoint:
|
||||
|
||||
```text
|
||||
POST http://localhost:8090/analyze
|
||||
```
|
||||
|
||||
Request:
|
||||
|
||||
```json
|
||||
{
|
||||
"url": "https://example.com"
|
||||
}
|
||||
```
|
||||
|
||||
Wrapper script:
|
||||
|
||||
```bash
|
||||
scripts/analyze-site https://example.com
|
||||
```
|
||||
|
||||
Override the endpoint if needed:
|
||||
|
||||
```bash
|
||||
scripts/analyze-site --endpoint http://localhost:8090/analyze example.com
|
||||
```
|
||||
|
||||
The response includes:
|
||||
|
||||
- `hosting.provider`: the visible edge/provider inferred from DNS, reverse DNS, and HTTP headers
|
||||
- `hosting.cdn`: CDN detected from headers, for example Cloudflare, Fastly, CloudFront, or Akamai
|
||||
- `hosting.origin_provider`: best-effort origin/platform inference, for example Pantheon when `pantheonsite.io` hints are exposed
|
||||
- `hosting.origin_evidence`: specific signals used for origin inference
|
||||
- `dns`: nameservers and common DNS records
|
||||
- `technologies`: CMS/framework/server signals such as Drupal, WordPress, React, Next.js, or Cloudflare
|
||||
- `security`: TLS/HSTS/security-header information
|
||||
|
||||
CDNs can hide the real origin. If a site is proxied through Cloudflare, the public DNS and IPs usually identify Cloudflare rather than the origin host. Origin detection is therefore best-effort and depends on leaked signals such as CSP entries, headers, HTML references, or provider-specific domains.
|
||||
|
||||
## Layout
|
||||
|
||||
@@ -186,11 +234,17 @@ Build the hello-world image manually outside Tilt.
|
||||
├── flake.nix
|
||||
├── Tiltfile
|
||||
├── k8s/
|
||||
│ └── hello-world.yaml
|
||||
│ ├── scraper.yaml
|
||||
│ └── site-analyzer.yaml
|
||||
├── scripts/
|
||||
│ ├── analyze-site
|
||||
│ └── setup-kind
|
||||
└── services/
|
||||
└── hello-world/
|
||||
├── scraper/
|
||||
│ ├── Dockerfile
|
||||
│ ├── go.mod
|
||||
│ └── main.go
|
||||
└── site-analyzer/
|
||||
├── Dockerfile
|
||||
├── go.mod
|
||||
└── main.go
|
||||
|
||||
@@ -22,8 +22,10 @@ allow_k8s_contexts('kind-openstaticfish')
|
||||
# --- Scraper Service ---
|
||||
# Builds the Docker image and deploys the manifest with live reload
|
||||
docker_build('scraper', './services/scraper')
|
||||
docker_build('site-analyzer', './services/site-analyzer')
|
||||
|
||||
k8s_yaml('./k8s/scraper.yaml')
|
||||
k8s_yaml('./k8s/site-analyzer.yaml')
|
||||
|
||||
local_resource(
|
||||
'webshare-secret',
|
||||
@@ -39,6 +41,12 @@ k8s_resource(
|
||||
labels=['scraper'],
|
||||
)
|
||||
|
||||
k8s_resource(
|
||||
workload='site-analyzer-deployment',
|
||||
port_forwards='8090:8090',
|
||||
labels=['site-analyzer'],
|
||||
)
|
||||
|
||||
# --- Local Resources ---
|
||||
# Run a simple health check as a local resource
|
||||
local_resource(
|
||||
@@ -47,3 +55,10 @@ local_resource(
|
||||
resource_deps=['scraper-deployment'],
|
||||
labels=['utility'],
|
||||
)
|
||||
|
||||
local_resource(
|
||||
'site-analyzer-health-check',
|
||||
cmd='curl -sf http://localhost:8090/health || echo "Site analyzer not ready"',
|
||||
resource_deps=['site-analyzer-deployment'],
|
||||
labels=['utility'],
|
||||
)
|
||||
|
||||
@@ -0,0 +1,60 @@
|
||||
# --- Site Analyzer Kubernetes Manifests ---
|
||||
# Managed by Tilt - run `tilt up` to deploy
|
||||
# Tear down with: `tilt down`
|
||||
|
||||
apiVersion: apps/v1
|
||||
kind: Deployment
|
||||
metadata:
|
||||
name: site-analyzer-deployment
|
||||
labels:
|
||||
app: site-analyzer
|
||||
spec:
|
||||
replicas: 1
|
||||
selector:
|
||||
matchLabels:
|
||||
app: site-analyzer
|
||||
template:
|
||||
metadata:
|
||||
labels:
|
||||
app: site-analyzer
|
||||
spec:
|
||||
containers:
|
||||
- name: site-analyzer
|
||||
image: site-analyzer
|
||||
ports:
|
||||
- containerPort: 8090
|
||||
env:
|
||||
- name: PORT
|
||||
value: "8090"
|
||||
resources:
|
||||
requests:
|
||||
memory: "64Mi"
|
||||
cpu: "100m"
|
||||
limits:
|
||||
memory: "256Mi"
|
||||
cpu: "500m"
|
||||
livenessProbe:
|
||||
httpGet:
|
||||
path: /health
|
||||
port: 8090
|
||||
initialDelaySeconds: 2
|
||||
periodSeconds: 10
|
||||
readinessProbe:
|
||||
httpGet:
|
||||
path: /health
|
||||
port: 8090
|
||||
initialDelaySeconds: 2
|
||||
periodSeconds: 5
|
||||
---
|
||||
apiVersion: v1
|
||||
kind: Service
|
||||
metadata:
|
||||
name: site-analyzer-service
|
||||
spec:
|
||||
selector:
|
||||
app: site-analyzer
|
||||
ports:
|
||||
- protocol: TCP
|
||||
port: 8090
|
||||
targetPort: 8090
|
||||
type: ClusterIP
|
||||
Executable
+66
@@ -0,0 +1,66 @@
|
||||
#!/usr/bin/env bash
|
||||
set -euo pipefail
|
||||
|
||||
endpoint="${SITE_ANALYZER_ENDPOINT:-http://localhost:8090/analyze}"
|
||||
|
||||
usage() {
|
||||
cat <<'USAGE'
|
||||
Usage:
|
||||
scripts/analyze-site [--endpoint URL] <site-url>
|
||||
|
||||
Examples:
|
||||
scripts/analyze-site https://example.com
|
||||
scripts/analyze-site --endpoint http://localhost:8090/analyze example.com
|
||||
SITE_ANALYZER_ENDPOINT=http://localhost:8090/analyze scripts/analyze-site example.com
|
||||
USAGE
|
||||
}
|
||||
|
||||
while [ "$#" -gt 0 ]; do
|
||||
case "$1" in
|
||||
-h|--help)
|
||||
usage
|
||||
exit 0
|
||||
;;
|
||||
--endpoint)
|
||||
if [ "$#" -lt 2 ]; then
|
||||
echo "Missing value for --endpoint" >&2
|
||||
usage >&2
|
||||
exit 1
|
||||
fi
|
||||
endpoint="$2"
|
||||
shift 2
|
||||
;;
|
||||
--endpoint=*)
|
||||
endpoint="${1#--endpoint=}"
|
||||
shift
|
||||
;;
|
||||
--*)
|
||||
echo "Unknown option: $1" >&2
|
||||
usage >&2
|
||||
exit 1
|
||||
;;
|
||||
*)
|
||||
break
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
if [ "$#" -ne 1 ]; then
|
||||
usage >&2
|
||||
exit 1
|
||||
fi
|
||||
|
||||
site_url="$1"
|
||||
payload=$(jq -cn --arg url "$site_url" '{url: $url}' 2>/dev/null || printf '{"url":"%s"}' "$site_url")
|
||||
|
||||
response=$(curl -fsS \
|
||||
-H 'Content-Type: application/json' \
|
||||
-X POST \
|
||||
--data "$payload" \
|
||||
"$endpoint")
|
||||
|
||||
if command -v jq >/dev/null 2>&1; then
|
||||
jq . <<<"$response"
|
||||
else
|
||||
printf '%s\n' "$response"
|
||||
fi
|
||||
@@ -0,0 +1,15 @@
|
||||
# --- Site Analyzer Service Dockerfile ---
|
||||
# Multi-stage build for minimal image size
|
||||
|
||||
FROM golang:1.26-alpine AS builder
|
||||
WORKDIR /app
|
||||
COPY go.mod go.sum ./
|
||||
RUN go mod download
|
||||
COPY . .
|
||||
RUN CGO_ENABLED=0 go build -o /site-analyzer .
|
||||
|
||||
FROM alpine:3.19
|
||||
RUN apk --no-cache add ca-certificates
|
||||
COPY --from=builder /site-analyzer /site-analyzer
|
||||
EXPOSE 8090
|
||||
ENTRYPOINT ["/site-analyzer"]
|
||||
@@ -0,0 +1,10 @@
|
||||
module github.com/openstaticfish/microservices/site-analyzer
|
||||
|
||||
go 1.26
|
||||
|
||||
require github.com/PuerkitoBio/goquery v1.9.2
|
||||
|
||||
require (
|
||||
github.com/andybalholm/cascadia v1.3.2 // indirect
|
||||
golang.org/x/net v0.25.0 // indirect
|
||||
)
|
||||
@@ -0,0 +1,40 @@
|
||||
github.com/PuerkitoBio/goquery v1.9.2 h1:4/wZksC3KgkQw7SQgkKotmKljk0M6V8TUvA8Wb4yPeE=
|
||||
github.com/PuerkitoBio/goquery v1.9.2/go.mod h1:GHPCaP0ODyyxqcNoFGYlAprUFH81NuRPd0GX3Zu2Mvk=
|
||||
github.com/andybalholm/cascadia v1.3.2 h1:3Xi6Dw5lHF15JtdcmAHD3i1+T8plmv7BQ/nsViSLyss=
|
||||
github.com/andybalholm/cascadia v1.3.2/go.mod h1:7gtRlve5FxPPgIgX36uWBX58OdBsSS6lUvCFb+h7KvU=
|
||||
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
|
||||
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
|
||||
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
|
||||
golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
|
||||
golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
|
||||
golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
|
||||
golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
|
||||
golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
|
||||
golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
|
||||
golang.org/x/net v0.9.0/go.mod h1:d48xBJpPfHeWQsugry2m+kC02ZBRGRgulfHnEXEuWns=
|
||||
golang.org/x/net v0.25.0 h1:d/OCCoBEUq33pjydKrGQhw7IlUPI2Oylr+8qLx49kac=
|
||||
golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
|
||||
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
||||
golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
||||
golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
|
||||
golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
|
||||
golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
|
||||
golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/sys v0.7.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
|
||||
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
|
||||
golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
|
||||
golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
|
||||
golang.org/x/term v0.7.0/go.mod h1:P32HKFT3hSsZrRxla30E9HqToFYAQPCMs/zFMBUFqPY=
|
||||
golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
|
||||
golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
|
||||
golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
|
||||
golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
|
||||
golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
|
||||
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
|
||||
golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
|
||||
golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
|
||||
golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
|
||||
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
|
||||
@@ -0,0 +1,563 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"io"
|
||||
"log"
|
||||
"net"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"os"
|
||||
"sort"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/PuerkitoBio/goquery"
|
||||
)
|
||||
|
||||
type AnalyzeRequest struct {
|
||||
URL string `json:"url"`
|
||||
}
|
||||
|
||||
type AnalyzeResponse struct {
|
||||
URL string `json:"url"`
|
||||
FinalURL string `json:"final_url,omitempty"`
|
||||
Domain string `json:"domain"`
|
||||
AnalyzedAt time.Time `json:"analyzed_at"`
|
||||
Hosting HostingInfo `json:"hosting"`
|
||||
DNS DNSInfo `json:"dns"`
|
||||
Technologies TechnologyInfo `json:"technologies"`
|
||||
Security SecurityInfo `json:"security"`
|
||||
HTTP HTTPInfo `json:"http"`
|
||||
Warnings []string `json:"warnings,omitempty"`
|
||||
}
|
||||
|
||||
type HostingInfo struct {
|
||||
Provider string `json:"provider,omitempty"`
|
||||
CDN string `json:"cdn,omitempty"`
|
||||
OriginProvider string `json:"origin_provider,omitempty"`
|
||||
OriginEvidence []string `json:"origin_evidence,omitempty"`
|
||||
IPAddresses []string `json:"ip_addresses,omitempty"`
|
||||
ReverseDNS []string `json:"reverse_dns,omitempty"`
|
||||
}
|
||||
|
||||
type DNSInfo struct {
|
||||
Provider string `json:"provider,omitempty"`
|
||||
Nameservers []string `json:"nameservers,omitempty"`
|
||||
Records map[string][]string `json:"records,omitempty"`
|
||||
}
|
||||
|
||||
type TechnologyInfo struct {
|
||||
CMS string `json:"cms,omitempty"`
|
||||
Framework string `json:"framework,omitempty"`
|
||||
Server string `json:"server,omitempty"`
|
||||
ProgrammingLanguage string `json:"programming_language,omitempty"`
|
||||
Detected []string `json:"detected,omitempty"`
|
||||
}
|
||||
|
||||
type SecurityInfo struct {
|
||||
SSL bool `json:"ssl"`
|
||||
HSTS bool `json:"hsts"`
|
||||
Headers map[string]string `json:"headers,omitempty"`
|
||||
}
|
||||
|
||||
type HTTPInfo struct {
|
||||
StatusCode int `json:"status_code,omitempty"`
|
||||
Headers map[string]string `json:"headers,omitempty"`
|
||||
}
|
||||
|
||||
type ErrorResponse struct {
|
||||
Error string `json:"error"`
|
||||
Details string `json:"details,omitempty"`
|
||||
}
|
||||
|
||||
type fetchedSite struct {
|
||||
FinalURL string
|
||||
StatusCode int
|
||||
Header http.Header
|
||||
Body []byte
|
||||
TLS bool
|
||||
}
|
||||
|
||||
func main() {
|
||||
port := os.Getenv("PORT")
|
||||
if port == "" {
|
||||
port = "8090"
|
||||
}
|
||||
|
||||
http.HandleFunc("/analyze", handleAnalyze)
|
||||
http.HandleFunc("/health", handleHealth)
|
||||
|
||||
log.Printf("site-analyzer listening on :%s", port)
|
||||
log.Fatal(http.ListenAndServe(":"+port, nil))
|
||||
}
|
||||
|
||||
func handleHealth(w http.ResponseWriter, r *http.Request) {
|
||||
w.WriteHeader(http.StatusOK)
|
||||
fmt.Fprint(w, "ok")
|
||||
}
|
||||
|
||||
func handleAnalyze(w http.ResponseWriter, r *http.Request) {
|
||||
if r.Method != http.MethodPost {
|
||||
respondWithError(w, http.StatusMethodNotAllowed, "Method not allowed", "Only POST requests are supported")
|
||||
return
|
||||
}
|
||||
|
||||
var req AnalyzeRequest
|
||||
if err := json.NewDecoder(r.Body).Decode(&req); err != nil {
|
||||
respondWithError(w, http.StatusBadRequest, "Invalid JSON", err.Error())
|
||||
return
|
||||
}
|
||||
if strings.TrimSpace(req.URL) == "" {
|
||||
respondWithError(w, http.StatusBadRequest, "Missing URL", "url field is required")
|
||||
return
|
||||
}
|
||||
|
||||
result, err := analyzeSite(req.URL)
|
||||
if err != nil {
|
||||
respondWithError(w, http.StatusInternalServerError, "Analysis failed", err.Error())
|
||||
return
|
||||
}
|
||||
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
json.NewEncoder(w).Encode(result)
|
||||
}
|
||||
|
||||
func analyzeSite(rawURL string) (*AnalyzeResponse, error) {
|
||||
normalizedURL := normalizeURL(rawURL)
|
||||
parsed, err := url.Parse(normalizedURL)
|
||||
if err != nil || parsed.Hostname() == "" {
|
||||
return nil, fmt.Errorf("invalid url")
|
||||
}
|
||||
|
||||
domain := strings.ToLower(parsed.Hostname())
|
||||
response := &AnalyzeResponse{
|
||||
URL: normalizedURL,
|
||||
Domain: domain,
|
||||
AnalyzedAt: time.Now().UTC(),
|
||||
DNS: DNSInfo{
|
||||
Records: make(map[string][]string),
|
||||
},
|
||||
Security: SecurityInfo{
|
||||
Headers: make(map[string]string),
|
||||
},
|
||||
HTTP: HTTPInfo{
|
||||
Headers: make(map[string]string),
|
||||
},
|
||||
}
|
||||
|
||||
var warnings []string
|
||||
if err := analyzeDNS(domain, &response.DNS, &response.Hosting); err != nil {
|
||||
warnings = append(warnings, "dns lookup failed: "+err.Error())
|
||||
}
|
||||
|
||||
fetched, err := fetchSite(normalizedURL)
|
||||
if err != nil {
|
||||
warnings = append(warnings, "http fetch failed: "+err.Error())
|
||||
} else {
|
||||
response.FinalURL = fetched.FinalURL
|
||||
response.HTTP.StatusCode = fetched.StatusCode
|
||||
response.HTTP.Headers = selectedHeaders(fetched.Header, []string{"server", "x-powered-by", "via", "x-generator", "x-vercel-id", "cf-ray", "x-drupal-cache"})
|
||||
response.Security = analyzeSecurity(fetched)
|
||||
response.Technologies = detectTechnologies(fetched)
|
||||
if provider := detectHostingFromHeaders(fetched.Header); provider != "" {
|
||||
response.Hosting.Provider = provider
|
||||
}
|
||||
response.Hosting.CDN = detectCDN(fetched.Header)
|
||||
response.Hosting.OriginProvider, response.Hosting.OriginEvidence = detectOriginProvider(fetched)
|
||||
}
|
||||
|
||||
if response.Hosting.Provider == "" {
|
||||
response.Hosting.Provider = detectHostingFromDNS(response.Hosting.ReverseDNS, response.DNS.Nameservers)
|
||||
}
|
||||
response.Warnings = warnings
|
||||
return response, nil
|
||||
}
|
||||
|
||||
func analyzeDNS(domain string, dnsInfo *DNSInfo, hosting *HostingInfo) error {
|
||||
var firstErr error
|
||||
|
||||
if ips, err := net.LookupHost(domain); err == nil {
|
||||
hosting.IPAddresses = sortedUnique(ips)
|
||||
dnsInfo.Records["A"] = filterIPs(ips, false)
|
||||
dnsInfo.Records["AAAA"] = filterIPs(ips, true)
|
||||
for _, ip := range ips {
|
||||
names, err := net.LookupAddr(ip)
|
||||
if err == nil {
|
||||
hosting.ReverseDNS = append(hosting.ReverseDNS, names...)
|
||||
}
|
||||
}
|
||||
hosting.ReverseDNS = sortedUnique(hosting.ReverseDNS)
|
||||
} else {
|
||||
firstErr = err
|
||||
}
|
||||
|
||||
if nsRecords, err := net.LookupNS(domain); err == nil {
|
||||
for _, ns := range nsRecords {
|
||||
dnsInfo.Nameservers = append(dnsInfo.Nameservers, strings.TrimSuffix(strings.ToLower(ns.Host), "."))
|
||||
}
|
||||
dnsInfo.Nameservers = sortedUnique(dnsInfo.Nameservers)
|
||||
dnsInfo.Provider = detectDNSProvider(dnsInfo.Nameservers)
|
||||
} else if firstErr == nil {
|
||||
firstErr = err
|
||||
}
|
||||
|
||||
if mxRecords, err := net.LookupMX(domain); err == nil {
|
||||
for _, mx := range mxRecords {
|
||||
dnsInfo.Records["MX"] = append(dnsInfo.Records["MX"], strings.TrimSuffix(strings.ToLower(mx.Host), "."))
|
||||
}
|
||||
dnsInfo.Records["MX"] = sortedUnique(dnsInfo.Records["MX"])
|
||||
}
|
||||
|
||||
for recordType, values := range dnsInfo.Records {
|
||||
if len(values) == 0 {
|
||||
delete(dnsInfo.Records, recordType)
|
||||
}
|
||||
}
|
||||
|
||||
return firstErr
|
||||
}
|
||||
|
||||
func fetchSite(targetURL string) (*fetchedSite, error) {
|
||||
client := &http.Client{Timeout: 20 * time.Second}
|
||||
req, err := http.NewRequest(http.MethodGet, targetURL, nil)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
req.Header.Set("User-Agent", "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0 Safari/537.36")
|
||||
req.Header.Set("Accept", "text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8")
|
||||
|
||||
resp, err := client.Do(req)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
body, err := io.ReadAll(io.LimitReader(resp.Body, 2*1024*1024))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return &fetchedSite{
|
||||
FinalURL: resp.Request.URL.String(),
|
||||
StatusCode: resp.StatusCode,
|
||||
Header: resp.Header,
|
||||
Body: body,
|
||||
TLS: resp.TLS != nil,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func analyzeSecurity(site *fetchedSite) SecurityInfo {
|
||||
securityHeaders := []string{"strict-transport-security", "content-security-policy", "x-frame-options", "x-content-type-options", "referrer-policy", "permissions-policy"}
|
||||
return SecurityInfo{
|
||||
SSL: site.TLS,
|
||||
HSTS: site.Header.Get("Strict-Transport-Security") != "",
|
||||
Headers: selectedHeaders(site.Header, securityHeaders),
|
||||
}
|
||||
}
|
||||
|
||||
func detectTechnologies(site *fetchedSite) TechnologyInfo {
|
||||
detected := map[string]bool{}
|
||||
tech := TechnologyInfo{}
|
||||
lowerHTML := strings.ToLower(string(site.Body))
|
||||
|
||||
if server := site.Header.Get("Server"); server != "" {
|
||||
tech.Server = server
|
||||
detected[server] = true
|
||||
}
|
||||
if poweredBy := site.Header.Get("X-Powered-By"); poweredBy != "" {
|
||||
detected[poweredBy] = true
|
||||
tech.ProgrammingLanguage = detectLanguageFromPoweredBy(poweredBy)
|
||||
}
|
||||
|
||||
if strings.Contains(lowerHTML, "wp-content/") || strings.Contains(lowerHTML, "wp-includes/") || strings.Contains(lowerHTML, "/wp-json/") {
|
||||
tech.CMS = "WordPress"
|
||||
detected["WordPress"] = true
|
||||
}
|
||||
if strings.Contains(lowerHTML, "drupal-settings-json") || strings.Contains(lowerHTML, "/sites/default/") || site.Header.Get("X-Drupal-Cache") != "" {
|
||||
tech.CMS = "Drupal"
|
||||
detected["Drupal"] = true
|
||||
}
|
||||
if strings.Contains(lowerHTML, "content=\"joomla!") || strings.Contains(lowerHTML, "/media/system/js/") {
|
||||
tech.CMS = "Joomla"
|
||||
detected["Joomla"] = true
|
||||
}
|
||||
if strings.Contains(lowerHTML, "/cdn/shop/") || strings.Contains(lowerHTML, "shopify.theme") {
|
||||
tech.CMS = "Shopify"
|
||||
detected["Shopify"] = true
|
||||
}
|
||||
|
||||
if strings.Contains(lowerHTML, "__next_data__") || strings.Contains(lowerHTML, "/_next/static/") || site.Header.Get("X-Nextjs-Cache") != "" {
|
||||
tech.Framework = "Next.js"
|
||||
detected["Next.js"] = true
|
||||
detected["React"] = true
|
||||
} else if strings.Contains(lowerHTML, "data-reactroot") || strings.Contains(lowerHTML, "react-dom") || strings.Contains(lowerHTML, "react.production.min.js") {
|
||||
tech.Framework = "React"
|
||||
detected["React"] = true
|
||||
} else if strings.Contains(lowerHTML, "__nuxt") || strings.Contains(lowerHTML, "/_nuxt/") {
|
||||
tech.Framework = "Nuxt"
|
||||
detected["Nuxt"] = true
|
||||
detected["Vue"] = true
|
||||
} else if strings.Contains(lowerHTML, "vue.js") || strings.Contains(lowerHTML, "data-v-") {
|
||||
tech.Framework = "Vue"
|
||||
detected["Vue"] = true
|
||||
} else if strings.Contains(lowerHTML, "ng-version") || strings.Contains(lowerHTML, "angular.js") {
|
||||
tech.Framework = "Angular"
|
||||
detected["Angular"] = true
|
||||
} else if strings.Contains(lowerHTML, "svelte") || strings.Contains(lowerHTML, "/_app/immutable/") {
|
||||
tech.Framework = "SvelteKit"
|
||||
detected["SvelteKit"] = true
|
||||
}
|
||||
|
||||
doc, err := goquery.NewDocumentFromReader(strings.NewReader(string(site.Body)))
|
||||
if err == nil {
|
||||
doc.Find("meta[name='generator']").Each(func(_ int, s *goquery.Selection) {
|
||||
content := strings.TrimSpace(s.AttrOr("content", ""))
|
||||
if content != "" {
|
||||
detected[content] = true
|
||||
if tech.CMS == "" {
|
||||
tech.CMS = detectCMSFromGenerator(content)
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
for _, header := range []string{"CF-Ray", "X-Vercel-ID", "X-GitHub-Request-Id", "Fly-Request-Id"} {
|
||||
if site.Header.Get(header) != "" {
|
||||
detected[detectTechnologyFromHeader(header)] = true
|
||||
}
|
||||
}
|
||||
|
||||
tech.Detected = mapKeys(detected)
|
||||
return tech
|
||||
}
|
||||
|
||||
func detectDNSProvider(nameservers []string) string {
|
||||
return firstPatternMatch(nameservers, map[string]string{
|
||||
"cloudflare.com": "Cloudflare",
|
||||
"awsdns": "Amazon Route 53",
|
||||
"domaincontrol.com": "GoDaddy",
|
||||
"googledomains.com": "Google Domains",
|
||||
"google.com": "Google Cloud DNS",
|
||||
"dnsimple.com": "DNSimple",
|
||||
"digitalocean.com": "DigitalOcean",
|
||||
"dnsmadeeasy.com": "DNS Made Easy",
|
||||
"namecheap.com": "Namecheap",
|
||||
"registrar-servers.com": "Namecheap",
|
||||
"nsone.net": "NS1",
|
||||
"azure-dns": "Azure DNS",
|
||||
"linode.com": "Linode",
|
||||
"he.net": "Hurricane Electric",
|
||||
})
|
||||
}
|
||||
|
||||
func detectHostingFromHeaders(header http.Header) string {
|
||||
switch {
|
||||
case header.Get("CF-Ray") != "":
|
||||
return "Cloudflare"
|
||||
case header.Get("X-Vercel-ID") != "":
|
||||
return "Vercel"
|
||||
case header.Get("X-GitHub-Request-Id") != "":
|
||||
return "GitHub Pages"
|
||||
case header.Get("Fly-Request-Id") != "":
|
||||
return "Fly.io"
|
||||
case strings.Contains(strings.ToLower(header.Get("Server")), "netlify"):
|
||||
return "Netlify"
|
||||
default:
|
||||
return ""
|
||||
}
|
||||
}
|
||||
|
||||
func detectCDN(header http.Header) string {
|
||||
switch {
|
||||
case header.Get("CF-Ray") != "" || strings.EqualFold(header.Get("Server"), "cloudflare"):
|
||||
return "Cloudflare"
|
||||
case header.Get("X-Served-By") != "" && strings.Contains(strings.ToLower(header.Get("Via")), "varnish"):
|
||||
return "Fastly"
|
||||
case header.Get("X-Cache") != "" && strings.Contains(strings.ToLower(header.Get("Via")), "cloudfront"):
|
||||
return "Amazon CloudFront"
|
||||
case header.Get("X-Akamai-Transformed") != "":
|
||||
return "Akamai"
|
||||
default:
|
||||
return ""
|
||||
}
|
||||
}
|
||||
|
||||
func detectOriginProvider(site *fetchedSite) (string, []string) {
|
||||
lowerHTML := strings.ToLower(string(site.Body))
|
||||
lowerCSP := strings.ToLower(site.Header.Get("Content-Security-Policy"))
|
||||
lowerHeaders := strings.ToLower(flattenHeaders(site.Header))
|
||||
|
||||
if strings.Contains(lowerHTML, "pantheonsite.io") || strings.Contains(lowerCSP, "pantheonsite.io") || strings.Contains(lowerHeaders, "pantheon") {
|
||||
var evidence []string
|
||||
if strings.Contains(lowerHTML, "pantheonsite.io") {
|
||||
evidence = append(evidence, "html references pantheonsite.io")
|
||||
}
|
||||
if strings.Contains(lowerCSP, "pantheonsite.io") {
|
||||
evidence = append(evidence, "content-security-policy allows pantheonsite.io")
|
||||
}
|
||||
if strings.Contains(lowerHeaders, "pantheon") {
|
||||
evidence = append(evidence, "response headers mention pantheon")
|
||||
}
|
||||
if strings.Contains(strings.ToLower(site.Header.Get("Via")), "varnish") {
|
||||
evidence = append(evidence, "via header includes varnish")
|
||||
}
|
||||
return "Pantheon", evidence
|
||||
}
|
||||
|
||||
return "", nil
|
||||
}
|
||||
|
||||
func detectHostingFromDNS(reverseDNS []string, nameservers []string) string {
|
||||
provider := firstPatternMatch(reverseDNS, map[string]string{
|
||||
"amazonaws.com": "AWS",
|
||||
"googleusercontent.com": "Google Cloud",
|
||||
"azure.com": "Azure",
|
||||
"cloudapp.net": "Azure",
|
||||
"digitalocean.com": "DigitalOcean",
|
||||
"linode.com": "Linode",
|
||||
"ovh.net": "OVHcloud",
|
||||
"hetzner": "Hetzner",
|
||||
"github.io": "GitHub Pages",
|
||||
"netlify": "Netlify",
|
||||
"vercel": "Vercel",
|
||||
})
|
||||
if provider != "" {
|
||||
return provider
|
||||
}
|
||||
return firstPatternMatch(nameservers, map[string]string{"cloudflare.com": "Cloudflare"})
|
||||
}
|
||||
|
||||
func detectLanguageFromPoweredBy(value string) string {
|
||||
lower := strings.ToLower(value)
|
||||
switch {
|
||||
case strings.Contains(lower, "php"):
|
||||
return "PHP"
|
||||
case strings.Contains(lower, "express"):
|
||||
return "Node.js"
|
||||
case strings.Contains(lower, "next.js"):
|
||||
return "Node.js"
|
||||
case strings.Contains(lower, "asp.net"):
|
||||
return ".NET"
|
||||
default:
|
||||
return ""
|
||||
}
|
||||
}
|
||||
|
||||
func detectCMSFromGenerator(value string) string {
|
||||
lower := strings.ToLower(value)
|
||||
switch {
|
||||
case strings.Contains(lower, "wordpress"):
|
||||
return "WordPress"
|
||||
case strings.Contains(lower, "drupal"):
|
||||
return "Drupal"
|
||||
case strings.Contains(lower, "joomla"):
|
||||
return "Joomla"
|
||||
case strings.Contains(lower, "shopify"):
|
||||
return "Shopify"
|
||||
default:
|
||||
return ""
|
||||
}
|
||||
}
|
||||
|
||||
func detectTechnologyFromHeader(header string) string {
|
||||
switch header {
|
||||
case "CF-Ray":
|
||||
return "Cloudflare"
|
||||
case "X-Vercel-ID":
|
||||
return "Vercel"
|
||||
case "X-GitHub-Request-Id":
|
||||
return "GitHub Pages"
|
||||
case "Fly-Request-Id":
|
||||
return "Fly.io"
|
||||
default:
|
||||
return header
|
||||
}
|
||||
}
|
||||
|
||||
func firstPatternMatch(values []string, patterns map[string]string) string {
|
||||
for _, value := range values {
|
||||
lower := strings.ToLower(value)
|
||||
for pattern, provider := range patterns {
|
||||
if strings.Contains(lower, pattern) {
|
||||
return provider
|
||||
}
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func selectedHeaders(header http.Header, names []string) map[string]string {
|
||||
selected := make(map[string]string)
|
||||
for _, name := range names {
|
||||
if value := header.Get(name); value != "" {
|
||||
selected[strings.ToLower(name)] = value
|
||||
}
|
||||
}
|
||||
return selected
|
||||
}
|
||||
|
||||
func flattenHeaders(header http.Header) string {
|
||||
var values []string
|
||||
for name, headerValues := range header {
|
||||
values = append(values, name)
|
||||
values = append(values, headerValues...)
|
||||
}
|
||||
return strings.Join(values, " ")
|
||||
}
|
||||
|
||||
func filterIPs(values []string, wantIPv6 bool) []string {
|
||||
var ips []string
|
||||
for _, value := range values {
|
||||
ip := net.ParseIP(value)
|
||||
if ip == nil {
|
||||
continue
|
||||
}
|
||||
isIPv6 := ip.To4() == nil
|
||||
if isIPv6 == wantIPv6 {
|
||||
ips = append(ips, value)
|
||||
}
|
||||
}
|
||||
return sortedUnique(ips)
|
||||
}
|
||||
|
||||
func normalizeURL(rawURL string) string {
|
||||
rawURL = strings.TrimSpace(rawURL)
|
||||
if strings.HasPrefix(rawURL, "http://") || strings.HasPrefix(rawURL, "https://") {
|
||||
return rawURL
|
||||
}
|
||||
return "https://" + rawURL
|
||||
}
|
||||
|
||||
func sortedUnique(values []string) []string {
|
||||
seen := make(map[string]bool)
|
||||
var result []string
|
||||
for _, value := range values {
|
||||
value = strings.TrimSpace(value)
|
||||
if value == "" || seen[value] {
|
||||
continue
|
||||
}
|
||||
seen[value] = true
|
||||
result = append(result, value)
|
||||
}
|
||||
sort.Strings(result)
|
||||
return result
|
||||
}
|
||||
|
||||
func mapKeys(values map[string]bool) []string {
|
||||
keys := make([]string, 0, len(values))
|
||||
for value := range values {
|
||||
if value != "" {
|
||||
keys = append(keys, value)
|
||||
}
|
||||
}
|
||||
sort.Strings(keys)
|
||||
return keys
|
||||
}
|
||||
|
||||
func respondWithError(w http.ResponseWriter, status int, err string, details string) {
|
||||
w.Header().Set("Content-Type", "application/json")
|
||||
w.WriteHeader(status)
|
||||
json.NewEncoder(w).Encode(ErrorResponse{Error: err, Details: details})
|
||||
}
|
||||
Reference in New Issue
Block a user