WIP: Add rules argument

README.md

@@ -3,8 +3,6 @@
 </p>
 
 <h1 align="center">Ladder</h1>
-<div><img alt="License" src="https://img.shields.io/github/license/kubero-dev/ladder"> <img alt="go.mod Go version " src="https://img.shields.io/github/go-mod/go-version/kubero-dev/ladder"> <img alt="GitHub tag (with filter)" src="https://img.shields.io/github/v/tag/kubero-dev/ladder"> <img alt="GitHub (Pre-)Release Date" src="https://img.shields.io/github/release-date-pre/kubero-dev/ladder"> <img alt="GitHub Downloads all releases" src="https://img.shields.io/github/downloads/kubero-dev/ladder/total"> <img alt="GitHub Build Status (with event)" src="https://img.shields.io/github/actions/workflow/status/kubero-dev/ladder/release-binaries.yaml"></div>
-
 
 *Ladder is a web proxy to help bypass paywalls.* This is a selfhosted version of [1ft.io](https://1ft.io) and [12ft.io](https://12ft.io). It is inspired by [13ft](https://github.com/wasi-master/13ft).
 
@@ -27,7 +25,7 @@ Freedom of information is an essential pillar of democracy and informed decision
 - [x] Linux binary
 - [x] Mac OS binary
 - [x] Windows binary (untested)
-- [x] Removes most of the ads (unexpected side effect ¯\\\_(ツ)_/¯ )
+- [x] Removes most of the ads (unexpected side effect ¯\_(ツ)_/¯ )
 - [x] Basic Auth
 - [x] Disable logs
 - [x] No Tracking
@@ -38,7 +36,7 @@ Freedom of information is an essential pillar of democracy and informed decision
 - [ ] Fetch from Google Cache if not available
 
 ### Limitations
-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 consider buying a subscription for the site.
+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.
 
 Some sites do not expose their content to search engines, which means that the proxy cannot access the content. A future version will try to fetch the content from Google Cache.
 
@@ -62,9 +60,6 @@ curl https://raw.githubusercontent.com/kubero-dev/ladder/main/docker-compose.yam
 docker-compose up -d
 ```
 
-### Helm
-See [README.md](/helm-chart/README.md) in helm-chart sub-directory for more information.
-
 ## Usage
 
 ### Browser
@@ -75,11 +70,6 @@ See [README.md](/helm-chart/README.md) in helm-chart sub-directory for more info
 Or direct by appending the URL to the end of the proxy URL:
 http://localhost:8080/https://www.example.com
 
-Or create a bookmark with the following URL:
-```javascript
-javascript:window.location.href="http://localhost:8080/"+location.href
-```
-
 ### API
 ```bash
 curl -X GET "http://localhost:8080/api/https://www.example.com"
@@ -106,7 +96,7 @@ http://localhost:8080/ruleset
 | `LOG_URLS` | Log fetched URL's | `true` |
 | `DISABLE_FORM` | Disables URL Form Frontpage | `false` |
 | `FORM_PATH` | Path to custom Form HTML | `` |
-| `RULESET` | URL to a ruleset file | `https://raw.githubusercontent.com/kubero-dev/ladder/main/ruleset.yaml` or `/path/to/my/rules.yaml` |
+| `RULESET` | URL to a ruleset file | `https://raw.githubusercontent.com/kubero-dev/ladder/main/ruleset.yaml` or `/path/to/my/rules.yaml` or `default` |
 | `EXPOSE_RULESET` | Make your Ruleset available to other ladders | `true` |
 | `ALLOWED_DOMAINS` | Comma separated list of allowed domains. Empty = no limitations | `` |
 | `ALLOWED_DOMAINS_RULESET` | Allow Domains from Ruleset. false = no limitations | `false` |
@@ -121,15 +111,12 @@ See in [ruleset.yaml](ruleset.yaml) for an example.
 
 ```yaml
 - domain: www.example.com
-  domains:                     # Additional domains to apply the rule
-    - www.example.com
-    - www.beispiel.de
   regexRules:
     - match: <script\s+([^>]*\s+)?src="(/)([^"]*)"
       replace: <script $1 script="/https://www.example.com/$3"
   injections:
     - position: head # Position where to inject the code
-      append: |      # possible keys: append, prepend, replace
+      append: | 
         <script>
           window.localStorage.clear();
           console.log("test");

cmd/main.go

@@ -7,6 +7,7 @@ import (
 	"ladder/handlers"
 	"log"
 	"os"
+	"strconv"
 	"strings"
 
 	"github.com/akamensky/argparse"
@@ -22,28 +23,34 @@ func main() {
 
 	parser := argparse.NewParser("ladder", "Every Wall needs a Ladder")
 
-	portEnv := os.Getenv("PORT")
+	p := os.Getenv("PORT")
 	if os.Getenv("PORT") == "" {
-		portEnv = "8080"
+		p = "8080"
 	}
 	port := parser.String("p", "port", &argparse.Options{
 		Required: false,
-		Default:  portEnv,
+		Default:  p,
 		Help:     "Port the webserver will listen on"})
 
+	pf, _ := strconv.ParseBool(os.Getenv("PREFORK"))
 	prefork := parser.Flag("P", "prefork", &argparse.Options{
 		Required: false,
+		Default:  pf,
 		Help:     "This will spawn multiple processes listening"})
 
+	r := os.Getenv("RULESET")
+	ruleset := parser.String("r", "ruleset", &argparse.Options{
+		Required: false,
+		Default:  r,
+		Help:     "Path or URL to your ruleset"})
+
+	handlers.LoadRules(*ruleset)
+
 	err := parser.Parse(os.Args)
 	if err != nil {
 		fmt.Print(parser.Usage(err))
 	}
 
-	if os.Getenv("PREFORK") == "true" {
-		*prefork = true
-	}
-
 	app := fiber.New(
 		fiber.Config{
 			Prefork: *prefork,

docker-compose.yaml

@@ -3,17 +3,12 @@ services:
   ladder:
     image: ghcr.io/kubero-dev/ladder:latest
     container_name: ladder
-    #build: .
+    build: .
     #restart: always
     #command: sh -c ./ladder
     environment:
       - PORT=8080
-      - RULESET=/app/ruleset.yaml
+      #- PREFORK=true
-      #- ALLOWED_DOMAINS_RULESET=false
-      #- EXPOSE_RULESET=true
-      #- PREFORK=false
-      #- DISABLE_FORM=fase
-      #- FORM_PATH=/app/form.html
       #- X_FORWARDED_FOR=66.249.66.1
       #- USER_AGENT=Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)
       #- USERPASS=foo:bar
@@ -21,6 +16,11 @@ services:
       #- GODEBUG=netdns=go
     ports:
       - "8080:8080"
-    volumes:
+    deploy:
-      - ./ruleset.yaml:/app/ruleset.yaml
+      resources:
-      - ./handlers/form.html:/app/form.html
+        limits:
+          cpus: "0.50"
+          memory: 512M
+        reservations:
+          cpus: "0.25"
+          memory: 128M

handlers/api.go

@@ -27,8 +27,7 @@ func Api(c *fiber.Ctx) error {
 		Version: version,
 		Body:    body,
 	}
-
+	response.Request.Headers = make([]interface{}, 0)
-	response.Request.Headers = make([]any, 0, len(req.Header))
 	for k, v := range req.Header {
 		response.Request.Headers = append(response.Request.Headers, map[string]string{
 			"key":   k,
@@ -36,7 +35,7 @@ func Api(c *fiber.Ctx) error {
 		})
 	}
 
-	response.Response.Headers = make([]any, 0, len(resp.Header))
+	response.Response.Headers = make([]interface{}, 0)
 	for k, v := range resp.Header {
 		response.Response.Headers = append(response.Response.Headers, map[string]string{
 			"key":   k,

handlers/proxy.go

@@ -17,8 +17,11 @@ import (
 
 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()
+var rulesSet RuleSet
+
+// var rulesSet = loadRules()
 var allowedDomains = strings.Split(os.Getenv("ALLOWED_DOMAINS"), ",")
+var Aaaa = "aaaa"
 
 func ProxySite(c *fiber.Ctx) error {
 	// Get the url from the URL
@@ -56,7 +59,7 @@ func fetchSite(urlpath string, queries map[string]string) (string, *http.Request
 		return "", nil, nil, fmt.Errorf("domain not allowed. %s not in %s", u.Host, allowedDomains)
 	}
 
-	if os.Getenv("LOG_URLS	") == "true" {
+	if os.Getenv("DEBUG	") == "true" {
 		log.Println(u.String() + urlQuery)
 	}
 
@@ -117,13 +120,18 @@ func getenv(key, fallback string) string {
 	return value
 }
 
-func loadRules() RuleSet {
+func LoadRules(rulesUrl string) RuleSet {
-	rulesUrl := os.Getenv("RULESET")
+	//rulesUrl := os.Getenv("RULESET")
 	if rulesUrl == "" {
 		RulesList := RuleSet{}
 		return RulesList
 	}
-	log.Println("Loading rules")
+
+	if rulesUrl == "default" {
+		rulesUrl = "https://raw.githubusercontent.com/kubero-dev/ladder/main/ruleset.yaml"
+	}
+
+	log.Println("Loading rules: " + rulesUrl)
 
 	var ruleSet RuleSet
 	if strings.HasPrefix(rulesUrl, "http") {
@@ -155,17 +163,14 @@ func loadRules() RuleSet {
 		yaml.Unmarshal(yamlFile, &ruleSet)
 	}
 
-	domains := []string{}
 	for _, rule := range ruleSet {
-
+		//log.Println("Loaded rules for", rule.Domain)
-		domains = append(domains, rule.Domain)
-		domains = append(domains, rule.Domains...)
 		if os.Getenv("ALLOWED_DOMAINS_RULESET") == "true" {
-			allowedDomains = append(allowedDomains, domains...)
+			allowedDomains = append(allowedDomains, rule.Domain)
 		}
 	}
 
-	log.Println("Loaded ", len(ruleSet), " rules for", len(domains), "Domains")
+	log.Println("Loaded rules for", len(ruleSet), "Domains")
 	return ruleSet
 }
 
@@ -175,10 +180,7 @@ func applyRules(domain string, path string, body string) string {
 	}
 
 	for _, rule := range rulesSet {
-		domains := rule.Domains
+		if rule.Domain != domain {
-		domains = append(domains, rule.Domain)
-		for _, ruleDomain := range domains {
-			if ruleDomain != domain {
 			continue
 		}
 		if len(rule.Paths) > 0 && !StringInSlice(path, rule.Paths) {
@@ -208,7 +210,6 @@ func applyRules(domain string, path string, body string) string {
 			}
 		}
 	}
-	}
 
 	return body
 }
@@ -220,7 +221,6 @@ type Rule struct {
 
 type RuleSet []struct {
 	Domain      string   `yaml:"domain"`
-	Domains     []string `yaml:"domains,omitempty"`
 	Paths       []string `yaml:"paths,omitempty"`
 	GoogleCache bool     `yaml:"googleCache,omitempty"`
 	RegexRules  []Rule   `yaml:"regexRules"`

helm-chart/Chart.yaml

@@ -1,6 +0,0 @@
-apiVersion: v2
-name: ladder
-description: A helm chart to deploy kubero-dev/ladder 
-type: application
-version: "1.0"
-appVersion: "v0.0.11"

helm-chart/README.md

@@ -1,27 +0,0 @@
-# Helm Chart for deployment of Ladder
-This folder contains a basic helm chart deployment for the ladder app.  
-
-# Deployment pre-reqs
-## Values
-Edit the values to your own preferences, with the only minimum requirement being `ingress.HOST` (line 19) being updated to your intended domain name.  
-
-Other variables in `values.yaml` can be updated as to your preferences, with details on each variable being listed in the main [README.md](/README.md) in the root of this repo.  
-
-## Defaults in K8s
-No ingress default has been specified. 
-You can set this manually by adding an annotation to the ingress.yaml - if needed.  
-For example, to use Traefik - 
-```yaml
-metadata:
-  name: ladder-ingress
-  annotations:
-    kubernetes.io/ingress.class: traefik
-```
-
-## Helm Install
-`helm install <name> <location> -n <namespace-name> --create-namespace`  
-`helm install ladder .\ladder\ -n ladder --create-namespace`  
-
-## Helm Upgrade
-`helm upgrade <name> <location> -n <namespace-name>`  
-`helm upgrade ladder .\ladder\ -n ladder`  

helm-chart/templates/deployment.yaml

@@ -1,55 +0,0 @@
----
-apiVersion: apps/v1
-kind: Deployment
-metadata:
-  labels:
-    app: ladder
-  name: ladder
-spec:
-  replicas: 1
-  selector:
-    matchLabels:
-      app: ladder
-  template:
-    metadata:
-      labels:
-        app: ladder
-    spec:
-      containers:
-      - image: "{{ .Values.image.RELEASE }}"
-        imagePullPolicy: Always
-        name: ladder
-        resources:
-          limits:
-            cpu: 250m
-            memory: 128Mi
-          requests:
-            cpu: 250m
-            memory: 128Mi
-        env:
-          - name: PORT
-            value: "{{ .Values.env.PORT }}"
-          - name: PREFORK
-            value: "{{ .Values.env.PREFORK }}"
-          - name: USER_AGENT
-            value: "{{ .Values.env.USER_AGENT }}"
-          - name: X_FORWARDED_FOR
-            value: "{{ .Values.env.X_FORWARDED_FOR }}"
-          - name: USERPASS
-            value: "{{ .Values.env.USERPASS }}"
-          - name: LOG_URLS
-            value: "{{ .Values.env.LOG_URLS }}"
-          - name: DISABLE_FORM
-            value: "{{ .Values.env.DISABLE_FORM }}"
-          - name: FORM_PATH
-            value: "{{ .Values.env.FORM_PATH }}"
-          - name: RULESET
-            value: "{{ .Values.env.RULESET }}"
-          - name: EXPOSE_RULESET
-            value: "{{ .Values.env.EXPOSE_RULESET }}"
-          - name: ALLOWED_DOMAINS
-            value: "{{ .Values.env.ALLOWED_DOMAINS }}"
-          - name: ALLOWED_DOMAINS_RULESET
-            value: "{{ .Values.env.ALLOWED_DOMAINS_RULESET }}"
-      restartPolicy: Always
-      terminationGracePeriodSeconds: 30

helm-chart/templates/ingress.yaml

@@ -1,17 +0,0 @@
----
-apiVersion: networking.k8s.io/v1
-kind: Ingress
-metadata:
-  name: ladder-ingress
-spec:
-  rules:
-  - host: "{{ .Values.ingress.HOST }}"
-    http:
-      paths:
-      - path: /
-        pathType: Prefix
-        backend:
-          service:
-            name: ladder-service
-            port:
-              number: {{ .Values.ingress.PORT }}

helm-chart/templates/service.yaml

@@ -1,14 +0,0 @@
----
-kind: Service
-apiVersion: v1
-metadata:
-  name: ladder-service
-spec:
-  type: ClusterIP
-  selector:
-    app: ladder
-  ports:
-  - name: http
-    port: {{ .Values.ingress.PORT }}
-    protocol: TCP
-    targetPort: {{ .Values.env.PORT }}

helm-chart/values.yaml

@@ -1,20 +0,0 @@
-image:
-  RELEASE: ghcr.io/kubero-dev/ladder:v0.0.11
-  
-env:
-  PORT: 8080
-  PREFORK: "false"
-  USER_AGENT: "Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)"
-  X_FORWARDED_FOR:
-  USERPASS: ""
-  LOG_URLS: "true"
-  DISABLE_FORM: "false"
-  FORM_PATH: ""
-  RULESET: "https://raw.githubusercontent.com/kubero-dev/ladder/main/ruleset.yaml"
-  EXPOSE_RULESET: "true"
-  ALLOWED_DOMAINS: ""
-  ALLOWED_DOMAINS_RULESET: "false"
-
-ingress:
-  HOST: "ladder.domain.com"
-  PORT: 80

ruleset.yaml

@@ -1,6 +1,4 @@
 - domain: www.example.com
-  domains: 
-  - www.beispiel.com
   regexRules:
     - match: <script\s+([^>]*\s+)?src="(/)([^"]*)"
       replace: <script $1 script="/https://www.example.com/$3"
@@ -55,92 +53,3 @@
             removeDOMElement(paywall)
           });
         </script>
-- domains: 
-  - www.architecturaldigest.com
-  - www.bonappetit.com
-  - www.cntraveler.com
-  - www.epicurious.com
-  - www.gq.com
-  - www.newyorker.com
-  - www.vanityfair.com
-  - www.vogue.com
-  - www.wired.com
-  injections:
-    - position: head
-      append: |
-        <script>
-          document.addEventListener("DOMContentLoaded", () => {
-            const banners = document.querySelectorAll('.paywall-bar, div[class^="MessageBannerWrapper-"');
-            banners.forEach(el => { el.remove(); });
-          });
-        </script>
-- domains: 
-  - www.nytimes.com
-  - www.time.com
-  injections:
-    - position: head
-      append: |
-        <script>
-          window.localStorage.clear();
-          document.addEventListener("DOMContentLoaded", () => {
-            const banners = document.querySelectorAll('div[data-testid="inline-message"], div[id^="ad-"], div[id^="leaderboard-"], div.expanded-dock, div.pz-ad-box, div[id="top-wrapper"], div[id="bottom-wrapper"]');
-            banners.forEach(el => { el.remove(); });
-          });
-        </script>
-- domains: 
-  - www.thestar.com
-  - www.niagarafallsreview.ca
-  - www.stcatharinesstandard.ca
-  - www.thepeterboroughexaminer.com
-  - www.therecord.com
-  - www.thespec.com
-  - www.wellandtribune.ca
-  injections:
-    - position: head
-      append: |
-        <script>
-          window.localStorage.clear();
-          document.addEventListener("DOMContentLoaded", () => {
-            const paywall = document.querySelectorAll('div.subscriber-offers');
-            paywall.forEach(el => { el.remove(); });
-            const subscriber_only = document.querySelectorAll('div.subscriber-only');
-            for (const elem of subscriber_only) {
-              if (elem.classList.contains('encrypted-content') && dompurify_loaded) {
-                const parser = new DOMParser();
-                const doc = parser.parseFromString('<div>' + DOMPurify.sanitize(unscramble(elem.innerText)) + '</div>', 'text/html');
-                const content_new = doc.querySelector('div');
-                elem.parentNode.replaceChild(content_new, elem);
-              }
-              elem.removeAttribute('style');
-              elem.removeAttribute('class');
-            }
-            const banners = document.querySelectorAll('div.subscription-required, div.redacted-overlay, div.subscriber-hide, div.tnt-ads-container');
-            banners.forEach(el => { el.remove(); });
-            const ads = document.querySelectorAll('div.tnt-ads-container, div[class*="adLabelWrapper"]');
-            ads.forEach(el => { el.remove(); });
-            const recommendations = document.querySelectorAll('div[id^="tncms-region-article"]');
-            recommendations.forEach(el => { el.remove(); });
-          });
-        </script>
-- domain: www.usatoday.com
-  injections:
-    - position: head
-      append: |
-        <script>
-          document.addEventListener("DOMContentLoaded", () => {
-            const banners = document.querySelectorAll('div.roadblock-container, .gnt_nb, [aria-label="advertisement"], div[id="main-frame-error"]');
-            banners.forEach(el => { el.remove(); });
-          });
-        </script>
-- domain: www.washingtonpost.com
-  injections:
-    - position: head
-      append: |
-        <script>
-          document.addEventListener("DOMContentLoaded", () => {
-            let paywall = document.querySelectorAll('div[data-qa$="-ad"], div[id="leaderboard-wrapper"], div[data-qa="subscribe-promo"]');
-            paywall.forEach(el => { el.remove(); });
-            const images = document.querySelectorAll('img');
-            images.forEach(image => { image.parentElement.style.filter = ''; });
-          });
-        </script>