katana v1.0.0

.github/workflows/build-test.yml

@@ -5,15 +5,17 @@ on:
   pull_request:
     branches:
       - dev
-
+    paths:
+      - '**.go'
+      - '**.mod'
 jobs:
   build:
     name: Test Builds
     runs-on: ${{ matrix.os }}
     strategy:
       matrix:
-        os: [ubuntu-latest, windows-latest, macOS-12]
-        go-version: [1.18.x, 1.19.x]
+        os: [ubuntu-latest-16-cores, windows-latest-8-cores, macOS-12]
+        go-version: [1.19.x, 1.20.x]
     steps:
       - name: Set up Go
         uses: actions/setup-go@v3

.github/workflows/codeql-analysis.yml

@@ -5,11 +5,14 @@ on:
   pull_request:
     branches:
       - dev
+    paths:
+      - '**.go'
+      - '**.mod'
 
 jobs:
   analyze:
     name: Analyze
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-latest-16-cores
     permissions:
       actions: read
       contents: read

.github/workflows/dockerhub-push.yml

@@ -9,7 +9,7 @@ on:
 
 jobs:
   docker:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-latest-16-cores
     steps:
       - name: Checkout
         uses: actions/checkout@v3
@@ -32,7 +32,7 @@ jobs:
           password: ${{ secrets.DOCKER_TOKEN }}
 
       - name: Build and push
-        uses: docker/build-push-action@v3
+        uses: docker/build-push-action@v4
         with:
           context: .
           platforms: linux/amd64,linux/arm64

.github/workflows/lint-test.yml

@@ -5,21 +5,26 @@ on:
   pull_request:
     branches:
       - dev
-
+    paths:
+      - '**.go'
+      - '**.mod'
 jobs:
   lint:
     name: Lint Test
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-latest-16-cores
     steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
       - name: Set up Go
         uses: actions/setup-go@v3
         with:
-          go-version: 1.18
-      - name: Checkout code
-        uses: actions/checkout@v3
+          go-version: 1.19
+          cache: true
+
       - name: Run golangci-lint
-        uses: golangci/golangci-lint-action@v3.3.1
+        uses: golangci/golangci-lint-action@v3.4.0
         with:
           version: latest
           args: --timeout 5m
-          working-directory: .
+          working-directory: .

.github/workflows/release-binary.yml

@@ -8,7 +8,7 @@ on:
 
 jobs:
   release:
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-latest-16-cores
     steps:
       - name: "Check out code"
         uses: actions/checkout@v3
@@ -18,7 +18,8 @@ jobs:
       - name: "Set up Go"
         uses: actions/setup-go@v3
         with: 
-          go-version: 1.18
+          go-version: 1.19
+          cache: true
 
       - name: "Create release on GitHub"
         uses: goreleaser/goreleaser-action@v4

.github/workflows/security-crawl-maze-score.yaml

@@ -6,12 +6,12 @@ on:
 jobs:
   build:
     name: Run Scoring
-    runs-on: ubuntu-latest
+    runs-on: ubuntu-latest-16-cores
     steps:
       - name: Set up Go
         uses: actions/setup-go@v3
         with:
-          go-version: 1.18
+          go-version: 1.19
 
       - name: Check out code
         uses: actions/checkout@v3

Dockerfile

@@ -1,11 +1,11 @@
-FROM golang:1.19.4-alpine AS builder
+FROM golang:1.20.2-alpine AS builder
 RUN apk add --no-cache git
 WORKDIR /app
 COPY . /app
 RUN go mod download
 RUN go build ./cmd/katana
 
-FROM alpine:3.17.0
+FROM alpine:3.17.2
 RUN apk -U upgrade --no-cache \
     && apk add --no-cache bind-tools ca-certificates chromium
 COPY --from=builder /app/katana /usr/local/bin/

README.md

@@ -109,36 +109,43 @@ This will display help for the tool. Here are all the switches it supports.
 Usage:
   ./katana [flags]
 
+Katana is a fast crawler focused on execution in automation
+pipelines offering both headless and non-headless crawling.
+
 Flags:
 INPUT:
    -u, -list string[]  target url / list to crawl
 
 CONFIGURATION:
-   -d, -depth int                maximum depth to crawl (default 2)
+   -r, -resolvers string[]       list of custom resolver (file or comma separated)
+   -d, -depth int                maximum depth to crawl (default 3)
    -jc, -js-crawl                enable endpoint parsing / crawling in javascript file
    -ct, -crawl-duration int      maximum duration to crawl the target for
    -kf, -known-files string      enable crawling of known files (all,robotstxt,sitemapxml)
-   -mrs, -max-response-size int  maximum response size to read (default 2097152)
+   -mrs, -max-response-size int  maximum response size to read (default 9223372036854775807)
    -timeout int                  time to wait for request in seconds (default 10)
-   -aff, -automatic-form-fill    enable optional automatic form filling (experimental)
+   -aff, -automatic-form-fill    enable automatic form filling (experimental)
    -retry int                    number of times to retry the request (default 1)
    -proxy string                 http/socks5 proxy to use
    -H, -headers string[]         custom header/cookie to include in request
    -config string                path to the katana configuration file
    -fc, -form-config string      path to custom form configuration file
+   -flc, -field-config string    path to custom field configuration file
+   -s, -strategy string          Visit strategy (depth-first, breadth-first) (default "depth-first")
 
 DEBUG:
    -health-check, -hc        run diagnostic check up
    -elog, -error-log string  file to write sent requests error log
 
 HEADLESS:
-   -hl, -headless                   enable headless hybrid crawling (experimental)
-   -sc, -system-chrome              use local installed chrome browser instead of katana installed
-   -sb, -show-browser               show the browser on the screen with headless mode
-   -ho, -headless-options string[]  start headless chrome with additional options
-   -nos, -no-sandbox                start headless chrome in --no-sandbox mode
-   -scp, -system-chrome-path string use specified chrome binary path for headless crawling
-   -noi, -no-incognito              start headless chrome without incognito mode
+   -hl, -headless                    enable headless hybrid crawling (experimental)
+   -sc, -system-chrome               use local installed chrome browser instead of katana installed
+   -sb, -show-browser                show the browser on the screen with headless mode
+   -ho, -headless-options string[]   start headless chrome with additional options
+   -nos, -no-sandbox                 start headless chrome in --no-sandbox mode
+   -cdd, -chrome-data-dir string     path to store chrome browser data
+   -scp, -system-chrome-path string  use specified chrome browser for headless crawling
+   -noi, -no-incognito               start headless chrome without incognito mode
 
 SCOPE:
    -cs, -crawl-scope string[]       in scope url regex to be followed by crawler
@@ -148,8 +155,10 @@ SCOPE:
    -do, -display-out-scope          display external endpoint from scoped crawling
 
 FILTER:
-   -f, -field string                field to display in output (url,path,fqdn,rdn,rurl,qurl,qpath,file,key,value,kv,dir,udir)
-   -sf, -store-field string         field to store in per-host output (url,path,fqdn,rdn,rurl,qurl,qpath,file,key,value,kv,dir,udir)
+   -mr, -match-regex string[]       regex or list of regex to match on output url (cli, file)
+   -fr, -filter-regex string[]      regex or list of regex to filter on output url (cli, file)
+   -f, -field string                field to display in output (url,path,fqdn,rdn,rurl,qurl,qpath,file,ufile,key,value,kv,dir,udir)
+   -sf, -store-field string         field to store in per-host output (url,path,fqdn,rdn,rurl,qurl,qpath,file,ufile,key,value,kv,dir,udir)
    -em, -extension-match string[]   match output for given extension (eg, -em php,html,js)
    -ef, -extension-filter string[]  filter output for given extension (eg, -ef png,css)
 
@@ -160,13 +169,19 @@ RATE-LIMIT:
    -rl, -rate-limit int          maximum requests to send per second (default 150)
    -rlm, -rate-limit-minute int  maximum number of requests to send per minute
 
+UPDATE:
+   -up, -update                 update katana to latest version
+   -duc, -disable-update-check  disable automatic katana update check
+
 OUTPUT:
-   -o, -output string  file to write output to
-   -j, -json           write output in JSONL(ines) format
-   -nc, -no-color      disable output content coloring (ANSI escape codes)
-   -silent             display output only
-   -v, -verbose        display verbose output
-   -version            display project version
+   -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
+   -j, -json                         write output in JSONL(ines) format
+   -nc, -no-color                    disable output content coloring (ANSI escape codes)
+   -silent                           display output only
+   -v, -verbose                      display verbose output
+   -version                          display project version
 ```
 
 ## Running Katana
@@ -485,6 +500,8 @@ CONFIGURATION:
    -H, -headers string[]         custom header/cookie to include in request
    -config string                path to the katana configuration file
    -fc, -form-config string      path to custom form configuration file
+   -flc, -field-config string    path to custom field configuration file
+   -s, -strategy string          Visit strategy (depth-first, breadth-first) (default "depth-first")
 ```
 
 ## Filters
@@ -627,6 +644,21 @@ Here are additional filter options -
 ```
 
 
+*`-match-regex`*
+---
+The `-match-regex` or `-mr` flag allows you to filter output URLs using regular expressions. When using this flag, only URLs that match the specified regular expression will be printed in the output.
+
+```
+katana -u https://tesla.com -mr 'https://shop\.tesla\.com/*' -silent
+```
+*`-filter-regex`*
+---
+The `-filter-regex` or `-fr` flag allows you to filter output URLs using regular expressions. When using this flag, it will skip the URLs that are match the specified regular expression.
+
+```
+katana -u https://tesla.com -fr 'https://www\.tesla\.com/*' -silent
+```
+
 ## Rate Limit
 
 It's easy to get blocked / banned while crawling if not following target websites limits, katana comes with multiple option to tune the crawl to go as fast / slow we want.

cmd/integration-test/library.go

@@ -1,8 +1,11 @@
 package main
 
 import (
+	"math"
+
 	"github.com/projectdiscovery/katana/pkg/engine/standard"
 	"github.com/projectdiscovery/katana/pkg/types"
+	"github.com/projectdiscovery/katana/pkg/utils/queue"
 )
 
 var libraryTestcases = map[string]TestCase{
@@ -17,9 +20,10 @@ func (h *goIntegrationTest) Execute() error {
 	options := &types.Options{
 		MaxDepth:     1,
 		FieldScope:   "rdn",
-		BodyReadSize: 2 * 1024 * 1024,
+		BodyReadSize: math.MaxInt,
 		RateLimit:    150,
 		Verbose:      debug,
+		Strategy:     queue.DepthFirst.String(),
 	}
 	crawlerOptions, err := types.NewCrawlerOptions(options)
 	if err != nil {