update README

.github/workflows/release-binaries.yaml

@@ -22,7 +22,7 @@ jobs:
       -
         name: Set version
         run: |
-          echo -n $(git describe --tags --abbrev=0) > cmd/VERSION
+          echo -n $(git describe --tags --abbrev=0) > handlers/VERSION
       -
         name: Set up Go
         uses: actions/setup-go@v3

.github/workflows/release-docker.yaml

@@ -42,7 +42,7 @@ jobs:
       - name: Set version
         id: version
         run: |
-          echo ${GITHUB_REF#refs/tags/v} > cmd/VERSION
+          echo ${GITHUB_REF#refs/tags/v} > handlers/VERSION
 
       # Install the cosign tool except on PR
       # https://github.com/sigstore/cosign-installer

README.md

@@ -12,24 +12,30 @@ Freedom of information is an essential pillar of democracy and informed decision
 
 Certain sites may display missing images or encounter formatting issues. This can be attributed to the site's reliance on JavaScript or CSS for image and resource loading, which presents a limitation when accessed through this proxy. If you prefer a full experience, please concider buying a subscription for the site.
 
+> **Disclaimer:** This project is intended for educational purposes only. The author does not endorse or encourage any unethical or illegal activity. Use this tool at your own risk.
+
 ### Features
 - [x] Bypass Paywalls
 - [x] Remove CORS headers from responses, assets, and images ...
+- [x] Apply domain based ruleset/code to modify response
 - [x] Keep site browsable
 - [x] API
-- [x] Show RAW HTML
-- [x] Docker container
+- [x] Fetch RAW HTML
+- [x] Custom User Agent
+- [x] Custom X-Forwarded-For IP
+- [x] [Docker container](https://github.com/kubero-dev/ladder/pkgs/container/ladder)
 - [x] Linux binary
 - [x] Mac OS binary
 - [x] Windows binary (untested)
-- [x] Remove most of the ads (unexpected side effect)
+- [x] Removes most of the ads (unexpected side effect)
 - [x] Basic Auth
 - [x] Disable logs
-- [x] Custom User Agent
-- [x] Custom X-Forwarded-For IP
+- [x] No Tracking
 
 ## Installation
 
+> **Warning:** If your instance will be publicly accessible, make sure to enable Basic Auth. This will prevent unauthorized users from using your proxy. If you do not enable Basic Auth, anyone can use your proxy to browse nasty/illegal stuff. And you will be responsible for it.
+
 ### Binary
 1) Download binary [here](https://github.com/kubero-dev/ladder/releases/latest)
 2) Unpack and run the binary `./ladder`
@@ -54,15 +60,15 @@ docker-compose up -d
 3) Press Enter
 
 Or direct by appending the URL to the end of the proxy URL:
-http://localhost:8080/https://www.google.com
+http://localhost:8080/https://www.example.com
 
 ### API
 ```bash
-curl -X GET "http://localhost:8080/api/https://www.google.com"
+curl -X GET "http://localhost:8080/api/https://www.example.com"
 ```
 
 ### RAW
-http://localhost:8080/raw/https://www.google.com
+http://localhost:8080/raw/https://www.example.com
 
 ## Configuration
 
@@ -77,3 +83,10 @@ http://localhost:8080/raw/https://www.google.com
 | `USERPASS` | Enables Basic Auth, format `admin:123456` | `` |
 | `LOG_URLS` | Log fetched URL's | `true` |
 | `DISABLE_FORM` | Disables URL Form Frontpage | `false` |
+| `RULES_URL` | URL to a ruleset file | `https://raw.githubusercontent.com/kubero-dev/ladder/main/ruleset.yaml` |
+
+### Ruleset
+
+It is possible to apply custom rules to modify the response. This can be used to remove unwanted or modify elements from the page. The ruleset is a YAML file that contains a list of rules for each domain and is loaded on startup
+
+See in [ruleset.yaml](ruleset.yaml) for an example.

go.mod

@@ -5,6 +5,12 @@ go 1.21.1
 require github.com/gofiber/fiber/v2 v2.50.0
 
 require (
+	github.com/andybalholm/cascadia v1.3.1 // indirect
+	golang.org/x/net v0.8.0 // indirect
+)
+
+require (
+	github.com/PuerkitoBio/goquery v1.8.1
 	github.com/andybalholm/brotli v1.0.6 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/google/uuid v1.4.0 // indirect

go.sum

@@ -1,5 +1,9 @@
+github.com/PuerkitoBio/goquery v1.8.1 h1:uQxhNlArOIdbrH1tr0UXwdVFgDcZDrZVdcpygAcwmWM=
+github.com/PuerkitoBio/goquery v1.8.1/go.mod h1:Q8ICL1kNUJ2sXGoAhPGUdYDJvgQgHzJsnnd3H7Ho5jQ=
 github.com/andybalholm/brotli v1.0.6 h1:Yf9fFpf49Zrxb9NlQaluyE92/+X7UVHlhMNJN2sxfOI=
 github.com/andybalholm/brotli v1.0.6/go.mod h1:fO7iG3H7G2nSZ7m0zPUDn85XEX2GTukHGRSepvi9Eig=
+github.com/andybalholm/cascadia v1.3.1 h1:nhxRkql1kdYCc8Snf7D5/D3spOX+dBgjA6u8x004T2c=
+github.com/andybalholm/cascadia v1.3.1/go.mod h1:R4bJ1UQfqADjvDa4P6HZHLh/3OxWWEqc0Sk8XGwHqvA=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -35,10 +39,42 @@ github.com/valyala/fasthttp v1.50.0 h1:H7fweIlBm0rXLs2q0XbalvJ6r0CUPFWK3/bB4N13e
 github.com/valyala/fasthttp v1.50.0/go.mod h1:k2zXd82h/7UZc3VOdJ2WaUqt1uZ/XpXAfE9i+HBC3lA=
 github.com/valyala/tcplisten v1.0.0 h1:rBHj/Xf+E1tRGZyWIWwJDiRY0zc1Js+CV5DqwacVSA8=
 github.com/valyala/tcplisten v1.0.0/go.mod h1:T0xQ8SeCZGxckz9qRXTfG43PvQ/mcWh7FwZEA7Ioqkc=
+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/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 v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/net v0.7.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
+golang.org/x/net v0.8.0 h1:Zrh2ngAOFYneWTAIAPethzeaQLuHwhuBkuV6ZiRnUaQ=
+golang.org/x/net v0.8.0/go.mod h1:QVkue5JL9kW//ek3r6jTKnTFis1tRmNAW2P1shuFdJc=
+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/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 v0.0.0-20210423082822-04245dca01da/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 v0.0.0-20220811171246-fbc7d0a398ab/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.13.0 h1:Af8nKPmuFypiUBjVoU9V20FiaFXOcuZI21p0ycVYYGE=
 golang.org/x/sys v0.13.0/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/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 v0.3.6/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/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/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 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=

handlers/proxy.go

@@ -10,11 +10,14 @@ import (
 	"regexp"
 	"strings"
 
+	"github.com/PuerkitoBio/goquery"
 	"github.com/gofiber/fiber/v2"
+	"gopkg.in/yaml.v3"
 )
 
 var UserAgent = getenv("USER_AGENT", "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)")
 var ForwardedFor = getenv("X_FORWARDED_FOR", "66.249.66.1")
+var rulesSet = loadRules()
 
 func ProxySite(c *fiber.Ctx) error {
 	// Get the url from the URL
@@ -95,6 +98,9 @@ func rewriteHtml(bodyB []byte, u *url.URL) string {
 	body = strings.ReplaceAll(body, "url(/", "url(/https://"+u.Host+"/")
 	body = strings.ReplaceAll(body, "href=\"https://"+u.Host, "href=\"/https://"+u.Host+"/")
 
+	if os.Getenv("RULES_URL") != "" {
+		body = applyRules(u.Host, u.Path, body)
+	}
 	return body
 }
 
@@ -105,3 +111,84 @@ func getenv(key, fallback string) string {
 	}
 	return value
 }
+
+func loadRules() RuleSet {
+	rulesUrl := os.Getenv("RULES_URL")
+	if rulesUrl == "" {
+		RulesList := RuleSet{}
+		return RulesList
+	}
+	log.Println("Loading rules")
+
+	resp, err := http.Get(rulesUrl)
+	if err != nil {
+		log.Println("ERROR:", err)
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode >= 400 {
+		log.Println("ERROR:", resp.StatusCode, rulesUrl)
+	}
+
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		log.Println("ERROR:", err)
+	}
+
+	var ruleSet RuleSet
+	yaml.Unmarshal(body, &ruleSet)
+	if err != nil {
+		log.Println("ERROR:", err)
+	}
+
+	log.Println("Loaded rules for", len(ruleSet), "Domains")
+	return ruleSet
+}
+
+func applyRules(domain string, path string, body string) string {
+	if len(rulesSet) == 0 {
+		return body
+	}
+
+	for _, rule := range rulesSet {
+		if rule.Domain != domain {
+			continue
+		}
+		if rule.Path != "" && rule.Path != path {
+			continue
+		}
+		for _, regexRule := range rule.RegexRules {
+			re := regexp.MustCompile(regexRule.Match)
+			body = re.ReplaceAllString(body, regexRule.Replace)
+		}
+		for _, injection := range rule.Injections {
+			doc, err := goquery.NewDocumentFromReader(strings.NewReader(body))
+			if err != nil {
+				log.Fatal(err)
+			}
+			doc.Find(injection.Position).AppendHtml(injection.Code)
+			body, err = doc.Html()
+			if err != nil {
+				log.Fatal(err)
+			}
+		}
+	}
+
+	return body
+}
+
+type Rule struct {
+	Match   string `yaml:"match"`
+	Replace string `yaml:"replace"`
+}
+
+type RuleSet []struct {
+	Domain      string `yaml:"domain"`
+	Path        string `yaml:"path,omitempty"`
+	GoogleCache bool   `yaml:"googleCache,omitempty"`
+	RegexRules  []Rule `yaml:"regexRules"`
+	Injections  []struct {
+		Position string `yaml:"position"`
+		Code     string `yaml:"code"`
+	} `yaml:"injections"`
+}

ruleset.yaml

@@ -0,0 +1,25 @@
+- domain: www.example.com
+  regexRules:
+    - match: <script\s+([^>]*\s+)?src="(/)([^"]*)"
+      replace: <script $1 script="/https://www.example.com/$3"
+  injections:
+    - position: head # Position where to inject the code
+      code: | 
+        <script>
+          window.localStorage.clear();
+          console.log("test");
+          alert("Hello!");
+        </script>
+- domain: www.anotherdomain.com # Domain where the rule applies
+  path: /article                # Path where the rule applies
+  googleCache: false            # Search also in Google Cache
+  regexRules:                   # Regex rules to apply
+    - match: <script\s+([^>]*\s+)?src="(/)([^"]*)"
+      replace: <script $1 script="/https://www.example.com/$3"
+  injections:
+    - position: .left-content article .post-title # Position where to inject the code into DOM
+      code: | 
+        <script>
+          window.localStorage.clear();
+          console.log("test");
+        </script>