Merge pull request #1066 from projectdiscovery/dev

v1.1.1

.github/dependabot.yml

@@ -20,26 +20,26 @@ updates:
     allow:
       - dependency-name: "github.com/projectdiscovery/*"
 
-#  # Maintain dependencies for GitHub Actions
-#  - package-ecosystem: "github-actions"
-#    directory: "/"
-#    schedule:
-#      interval: "weekly"
-#    target-branch: "dev"
-#    commit-message:
-#      prefix: "chore"
-#      include: "scope"
-#    labels:
-#      - "Type: Maintenance"
-#
-#  # Maintain dependencies for docker
-#  - package-ecosystem: "docker"
-#    directory: "/"
-#    schedule:
-#      interval: "weekly"
-#    target-branch: "dev"
-#    commit-message:
-#      prefix: "chore"
-#      include: "scope"
-#    labels:
-#      - "Type: Maintenance"
+  # Maintain dependencies for GitHub Actions
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    target-branch: "dev"
+    commit-message:
+      prefix: "chore"
+      include: "scope"
+    labels:
+      - "Type: Maintenance"
+
+  # Maintain dependencies for docker
+  - package-ecosystem: "docker"
+    directory: "/"
+    schedule:
+      interval: "weekly"
+    target-branch: "dev"
+    commit-message:
+      prefix: "chore"
+      include: "scope"
+    labels:
+      - "Type: Maintenance"

.goreleaser/windows.yml

@@ -15,6 +15,8 @@ builds:
     goos:
       - windows
     goarch:
+      - 386
+      - arm64
       - amd64
 
 archives:

Dockerfile

@@ -1,13 +1,12 @@
-FROM golang:1.20.6-alpine AS builder
+FROM golang:1.21-alpine AS build-env
 RUN apk add --no-cache git gcc musl-dev
 WORKDIR /app
 COPY . /app
 RUN go mod download
 RUN go build ./cmd/katana
 
 FROM alpine:3.18.5
-RUN apk -U upgrade --no-cache \
-    && apk add --no-cache bind-tools ca-certificates chromium
+RUN apk add --no-cache bind-tools ca-certificates chromium
 COPY --from=builder /app/katana /usr/local/bin/
 
 ENTRYPOINT ["katana"]

README.md

@@ -30,7 +30,6 @@
 
  - Fast And fully configurable web crawling
  - **Standard** and **Headless** mode
- - **Active** and **Passive** mode
  - **JavaScript** parsing / crawling
  - Customizable **automatic form filling**
  - **Scope control** - Preconfigured field / Regex 
@@ -44,7 +43,7 @@
 katana requires **Go 1.18** to install successfully. To install, just run the below command or download pre-compiled binary from [release page](https://github.com/projectdiscovery/katana/releases).
 
 ```console
-go install github.com/projectdiscovery/katana/cmd/katana@latest
+CGO_ENABLED=1 go install github.com/projectdiscovery/katana/cmd/katana@latest
 ```
 
 **More options to install / run katana-**
@@ -157,10 +156,6 @@ HEADLESS:
    -cwu, -chrome-ws-url string       use chrome browser instance launched elsewhere with the debugger listening at this URL
    -xhr, -xhr-extraction             extract xhr request url,method in jsonl output
 
-PASSIVE:
-   -ps, -passive                   enable passive sources to discover target endpoints
-   -pss, -passive-source string[]  passive source to use for url discovery (waybackarchive,commoncrawl,alienvault)
-
 SCOPE:
    -cs, -crawl-scope string[]       in scope url regex to be followed by crawler
    -cos, -crawl-out-scope string[]  out of scope url regex to be excluded by crawler
@@ -193,6 +188,7 @@ OUTPUT:
    -o, -output string                file to write output to
    -sr, -store-response              store http requests/responses
    -srd, -store-response-dir string  store http requests/responses to custom directory
+   -sfd, -store-field-dir string     store per-host field to custom directory
    -or, -omit-raw                    omit raw requests/responses from jsonl output
    -ob, -omit-body                   omit response body from jsonl output
    -j, -jsonl                        write output in jsonl format
@@ -688,7 +684,7 @@ katana -u https://tesla.com -f email,phone
 *`-store-field`*
 ---
 
-To compliment `field` option which is useful to filter output at run time, there is `-sf, -store-fields` option which works exactly like field option except instead of filtering, it stores all the information on the disk under `katana_field` directory sorted by target url.
+To compliment `field` option which is useful to filter output at run time, there is `-sf, -store-fields` option which works exactly like field option except instead of filtering, it stores all the information on the disk under `katana_field` directory sorted by target url. Use `-sfd` or `-store-field-dir` to store data in a different location.
 
 ```
 katana -u https://tesla.com -sf key,fqdn,qurl -silent

cmd/katana/main.go

@@ -17,6 +17,7 @@ import (
 	"github.com/projectdiscovery/katana/pkg/types"
 	errorutil "github.com/projectdiscovery/utils/errors"
 	fileutil "github.com/projectdiscovery/utils/file"
+	folderutil "github.com/projectdiscovery/utils/folder"
 	"github.com/rs/xid"
 )
 
@@ -68,7 +69,14 @@ func main() {
 		gologger.Fatal().Msgf("could not execute crawling: %s", err)
 	}
 
-	// on successful execution remove the resume file in case it exists
+	// on successful execution:
+
+	// deduplicate the lines in each file in the store-field-dir
+	//use options.StoreFieldDir once https://github.com/projectdiscovery/katana/pull/877 is merged
+	storeFieldDir := "katana_field"
+	_ = folderutil.DedupeLinesInFiles(storeFieldDir)
+
+	// remove the resume file in case it exists
 	if fileutil.FileExists(resumeFilename) {
 		os.Remove(resumeFilename)
 	}
@@ -126,10 +134,6 @@ pipelines offering both headless and non-headless crawling.`)
 		flagSet.StringVarP(&options.ChromeWSUrl, "chrome-ws-url", "cwu", "", "use chrome browser instance launched elsewhere with the debugger listening at this URL"),
 		flagSet.BoolVarP(&options.XhrExtraction, "xhr-extraction", "xhr", false, "extract xhr request url,method in jsonl output"),
 	)
-	flagSet.CreateGroup("passive", "Passive",
-		flagSet.BoolVarP(&options.Passive, "passive", "ps", false, "enable passive sources to discover target endpoints"),
-		flagSet.StringSliceVarP(&options.PassiveSource, "passive-source", "pss", nil, "passive source to use for url discovery (waybackarchive,commoncrawl,alienvault)", goflags.NormalizedStringSliceOptions),
-	)
 
 	flagSet.CreateGroup("scope", "Scope",
 		flagSet.StringSliceVarP(&options.Scope, "crawl-scope", "cs", nil, "in scope url regex to be followed by crawler", goflags.FileCommaSeparatedStringSliceOptions),
@@ -168,6 +172,8 @@ pipelines offering both headless and non-headless crawling.`)
 		flagSet.StringVarP(&options.OutputFile, "output", "o", "", "file to write output to"),
 		flagSet.BoolVarP(&options.StoreResponse, "store-response", "sr", false, "store http requests/responses"),
 		flagSet.StringVarP(&options.StoreResponseDir, "store-response-dir", "srd", "", "store http requests/responses to custom directory"),
+		flagSet.BoolVarP(&options.NoClobber, "no-clobber", "ncb", false, "do not overwrite output file"),
+		flagSet.StringVarP(&options.StoreFieldDir, "store-field-dir", "sfd", "", "store per-host field to custom directory"),
 		flagSet.BoolVarP(&options.OmitRaw, "omit-raw", "or", false, "omit raw requests/responses from jsonl output"),
 		flagSet.BoolVarP(&options.OmitBody, "omit-body", "ob", false, "omit response body from jsonl output"),
 		flagSet.BoolVarP(&options.JSON, "jsonl", "j", false, "write output in jsonl format"),

go.mod

@@ -11,23 +11,21 @@ require (
 	github.com/lukasbob/srcset v0.0.0-20190730101422-86b742e617f3
 	github.com/mitchellh/mapstructure v1.5.0
 	github.com/pkg/errors v0.9.1
-	github.com/projectdiscovery/dsl v0.0.48
-	github.com/projectdiscovery/fastdialer v0.0.64
-	github.com/projectdiscovery/goflags v0.1.45
-	github.com/projectdiscovery/gologger v1.1.12
-	github.com/projectdiscovery/hmap v0.0.41
-	github.com/projectdiscovery/mapcidr v1.1.16
-	github.com/projectdiscovery/ratelimit v0.0.33
-	github.com/projectdiscovery/retryablehttp-go v1.0.53
-	github.com/projectdiscovery/useragent v0.0.41
-	github.com/projectdiscovery/utils v0.0.85
-	github.com/projectdiscovery/wappalyzergo v0.0.115
+	github.com/projectdiscovery/dsl v0.2.5
+	github.com/projectdiscovery/fastdialer v0.2.9
+	github.com/projectdiscovery/goflags v0.1.64
+	github.com/projectdiscovery/gologger v1.1.27
+	github.com/projectdiscovery/hmap v0.0.63
+	github.com/projectdiscovery/mapcidr v1.1.34
+	github.com/projectdiscovery/ratelimit v0.0.60
+	github.com/projectdiscovery/retryablehttp-go v1.0.82
+	github.com/projectdiscovery/utils v0.2.15
+	github.com/projectdiscovery/wappalyzergo v0.1.24
 	github.com/remeh/sizedwaitgroup v1.0.0
 	github.com/rs/xid v1.5.0
-	github.com/shirou/gopsutil/v3 v3.23.7
 	github.com/stretchr/testify v1.9.0
 	go.uber.org/multierr v1.11.0
-	golang.org/x/net v0.21.0
+	golang.org/x/net v0.29.0
 	gopkg.in/yaml.v3 v3.0.1
 )
 
@@ -37,46 +35,49 @@ require (
 	github.com/Masterminds/semver/v3 v3.2.1 // indirect
 	github.com/Mzack9999/gcache v0.0.0-20230410081825-519e28eab057 // indirect
 	github.com/VividCortex/ewma v1.2.0 // indirect
-	github.com/alecthomas/chroma v0.10.0 // indirect
+	github.com/alecthomas/chroma/v2 v2.14.0 // indirect
 	github.com/andybalholm/brotli v1.0.6 // indirect
 	github.com/aymanbagabas/go-osc52/v2 v2.0.1 // indirect
-	github.com/charmbracelet/glamour v0.6.0 // indirect
+	github.com/bits-and-blooms/bitset v1.13.0 // indirect
+	github.com/charmbracelet/glamour v0.8.0 // indirect
+	github.com/charmbracelet/lipgloss v0.13.0 // indirect
+	github.com/charmbracelet/x/ansi v0.3.2 // indirect
 	github.com/cheggaaa/pb/v3 v3.1.4 // indirect
 	github.com/cloudflare/circl v1.3.7 // indirect
 	github.com/ditashi/jsbeautifier-go v0.0.0-20141206144643-2520a8026a9c // indirect
-	github.com/dlclark/regexp2 v1.8.1 // indirect
+	github.com/dlclark/regexp2 v1.11.4 // indirect
 	github.com/docker/go-units v0.5.0 // indirect
 	github.com/fatih/color v1.15.0 // indirect
-	github.com/gaukas/godicttls v0.0.4 // indirect
+	github.com/gaissmai/bart v0.9.5 // indirect
 	github.com/golang/protobuf v1.5.3 // indirect
 	github.com/google/go-github/v30 v30.1.0 // indirect
 	github.com/google/go-querystring v1.1.0 // indirect
+	github.com/google/shlex v0.0.0-20191202100458-e7afc7fbc510 // indirect
+	github.com/google/uuid v1.3.1 // indirect
 	github.com/hashicorp/go-version v1.6.0 // indirect
 	github.com/hdm/jarm-go v0.0.7 // indirect
 	github.com/kataras/jwt v0.1.8 // indirect
-	github.com/klauspost/compress v1.16.7 // indirect
+	github.com/klauspost/compress v1.17.4 // indirect
 	github.com/klauspost/pgzip v1.2.5 // indirect
 	github.com/kr/pretty v0.3.1 // indirect
 	github.com/lucasb-eyer/go-colorful v1.2.0 // indirect
 	github.com/mattn/go-colorable v0.1.13 // indirect
-	github.com/mattn/go-isatty v0.0.19 // indirect
-	github.com/mattn/go-runewidth v0.0.14 // indirect
+	github.com/mattn/go-isatty v0.0.20 // indirect
+	github.com/mattn/go-runewidth v0.0.16 // indirect
 	github.com/mholt/archiver/v3 v3.5.1 // indirect
 	github.com/minio/selfupdate v0.6.1-0.20230907112617-f11e74f84ca7 // indirect
 	github.com/muesli/reflow v0.3.0 // indirect
-	github.com/muesli/termenv v0.15.1 // indirect
-	github.com/olekukonko/tablewriter v0.0.5 // indirect
+	github.com/muesli/termenv v0.15.3-0.20240618155329-98d742f6907a // indirect
 	github.com/pierrec/lz4/v4 v4.1.2 // indirect
-	github.com/projectdiscovery/asnmap v1.1.0 // indirect
+	github.com/projectdiscovery/asnmap v1.1.1 // indirect
 	github.com/projectdiscovery/blackrock v0.0.1 // indirect
 	github.com/projectdiscovery/gostruct v0.0.2 // indirect
 	github.com/projectdiscovery/machineid v0.0.0-20240226150047-2e2c51e35983 // indirect
-	github.com/projectdiscovery/stringsutil v0.0.2 // indirect
-	github.com/quic-go/quic-go v0.37.7 // indirect
-	github.com/refraction-networking/utls v1.5.4 // indirect
-	github.com/rivo/uniseg v0.4.4 // indirect
+	github.com/refraction-networking/utls v1.6.7 // indirect
+	github.com/rivo/uniseg v0.4.7 // indirect
 	github.com/rogpeppe/go-internal v1.12.0 // indirect
 	github.com/sashabaranov/go-openai v1.14.2 // indirect
+	github.com/shirou/gopsutil/v3 v3.23.7 // indirect
 	github.com/shoenig/go-m1cpu v0.1.6 // indirect
 	github.com/smacker/go-tree-sitter v0.0.0-20230720070738-0d0a9f78d8f8 // indirect
 	github.com/spaolacci/murmur3 v1.1.0 // indirect
@@ -90,10 +91,13 @@ require (
 	github.com/tidwall/tinyqueue v0.1.1 // indirect
 	github.com/ysmood/fetchup v0.2.3 // indirect
 	github.com/ysmood/got v0.34.1 // indirect
-	github.com/yuin/goldmark v1.5.4 // indirect
-	github.com/yuin/goldmark-emoji v1.0.1 // indirect
+	github.com/yuin/goldmark v1.7.4 // indirect
+	github.com/yuin/goldmark-emoji v1.0.3 // indirect
+	github.com/zcalusic/sysinfo v1.0.2 // indirect
 	golang.org/x/oauth2 v0.11.0 // indirect
-	golang.org/x/term v0.17.0 // indirect
+	golang.org/x/sync v0.8.0 // indirect
+	golang.org/x/term v0.24.0 // indirect
+	golang.org/x/time v0.5.0 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
 	google.golang.org/protobuf v1.33.0 // indirect
 )
@@ -110,38 +114,37 @@ require (
 	github.com/dsnet/compress v0.0.2-0.20210315054119-f66993602bf5 // indirect
 	github.com/go-ole/go-ole v1.2.6 // indirect
 	github.com/golang/snappy v0.0.4 // indirect
-	github.com/gorilla/css v1.0.0 // indirect
+	github.com/gorilla/css v1.0.1 // indirect
 	github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0 // indirect
-	github.com/microcosm-cc/bluemonday v1.0.25 // indirect
+	github.com/microcosm-cc/bluemonday v1.0.27 // indirect
 	github.com/miekg/dns v1.1.56 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
 	github.com/nwaples/rardecode v1.1.3 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c // indirect
-	github.com/projectdiscovery/networkpolicy v0.0.8
-	github.com/projectdiscovery/retryabledns v1.0.58 // indirect
+	github.com/projectdiscovery/networkpolicy v0.0.9
+	github.com/projectdiscovery/retryabledns v1.0.81 // indirect
 	github.com/saintfish/chardet v0.0.0-20230101081208-5e3ef4b5456d // indirect
 	github.com/syndtr/goleveldb v1.0.0 // indirect
 	github.com/tklauser/go-sysconf v0.3.12 // indirect
 	github.com/tklauser/numcpus v0.6.1 // indirect
 	github.com/ulikunitz/xz v0.5.11 // indirect
 	github.com/weppos/publicsuffix-go v0.30.1-0.20230422193905-8fecedd899db // indirect
 	github.com/xi2/xz v0.0.0-20171230120015-48954b6210f8 // indirect
-	github.com/yl2chen/cidranger v1.0.2 // indirect
 	github.com/ysmood/goob v0.4.0 // indirect
 	github.com/ysmood/gson v0.7.3 // indirect
 	github.com/ysmood/leakless v0.8.0 // indirect
 	github.com/yusufpapurcu/wmi v1.2.4 // indirect
 	github.com/zmap/rc2 v0.0.0-20190804163417-abaa70531248 // indirect
 	github.com/zmap/zcrypto v0.0.0-20230422215203-9a665e1e9968 // indirect
 	go.etcd.io/bbolt v1.3.7 // indirect
-	golang.org/x/crypto v0.19.0 // indirect
-	golang.org/x/exp v0.0.0-20230905200255-921286631fa9
-	golang.org/x/mod v0.12.0 // indirect
-	golang.org/x/sys v0.17.0 // indirect
-	golang.org/x/text v0.14.0 // indirect
-	golang.org/x/tools v0.13.0 // indirect
+	golang.org/x/crypto v0.27.0 // indirect
+	golang.org/x/exp v0.0.0-20230905200255-921286631fa9 // indirect
+	golang.org/x/mod v0.17.0 // indirect
+	golang.org/x/sys v0.25.0 // indirect
+	golang.org/x/text v0.18.0 // indirect
+	golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d // indirect
 	gopkg.in/djherbis/times.v1 v1.3.0 // indirect
 	gopkg.in/yaml.v2 v2.4.0
 )