fix default port, set to 8080

Feature/multiple domains

README.md

@@ -121,12 +121,15 @@ 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: | 
+      append: |      # possible keys: append, prepend, replace
         <script>
           window.localStorage.clear();
           console.log("test");

cmd/main.go

@@ -22,9 +22,13 @@ func main() {
 
 	parser := argparse.NewParser("ladder", "Every Wall needs a Ladder")
 
+	portEnv := os.Getenv("PORT")
+	if os.Getenv("PORT") == "" {
+		portEnv = "8080"
+	}
 	port := parser.String("p", "port", &argparse.Options{
 		Required: false,
-		Default:  os.Getenv("PORT"),
+		Default:  portEnv,
 		Help:     "Port the webserver will listen on"})
 
 	prefork := parser.Flag("P", "prefork", &argparse.Options{

docker-compose.yaml

@@ -3,13 +3,17 @@ 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
@@ -19,11 +23,4 @@ services:
       - "8080:8080"
     volumes:
       - ./ruleset.yaml:/app/ruleset.yaml
-    deploy:
-      resources:
-        limits:
-          cpus: "0.50"
-          memory: 512M
-        reservations:
-          cpus: "0.25"
-          memory: 128M
+      - ./handlers/form.html:/app/form.html

handlers/proxy.go

@@ -155,14 +155,17 @@ 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, rule.Domain)
+			allowedDomains = append(allowedDomains, domains...)
 		}
 	}
 
-	log.Println("Loaded rules for", len(ruleSet), "Domains")
+	log.Println("Loaded ", len(ruleSet), " rules for", len(domains), "Domains")
 	return ruleSet
 }
 
@@ -172,33 +175,37 @@ func applyRules(domain string, path string, body string) string {
 	}
 
 	for _, rule := range rulesSet {
-		if rule.Domain != domain {
-			continue
-		}
-		if len(rule.Paths) > 0 && !StringInSlice(path, rule.Paths) {
-			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)
+		domains := rule.Domains
+		domains = append(domains, rule.Domain)
+		for _, ruleDomain := range domains {
+			if ruleDomain != domain {
+				continue
 			}
-			if injection.Replace != "" {
-				doc.Find(injection.Position).ReplaceWithHtml(injection.Replace)
+			if len(rule.Paths) > 0 && !StringInSlice(path, rule.Paths) {
+				continue
 			}
-			if injection.Append != "" {
-				doc.Find(injection.Position).AppendHtml(injection.Append)
+			for _, regexRule := range rule.RegexRules {
+				re := regexp.MustCompile(regexRule.Match)
+				body = re.ReplaceAllString(body, regexRule.Replace)
 			}
-			if injection.Prepend != "" {
-				doc.Find(injection.Position).PrependHtml(injection.Prepend)
-			}
-			body, err = doc.Html()
-			if err != nil {
-				log.Fatal(err)
+			for _, injection := range rule.Injections {
+				doc, err := goquery.NewDocumentFromReader(strings.NewReader(body))
+				if err != nil {
+					log.Fatal(err)
+				}
+				if injection.Replace != "" {
+					doc.Find(injection.Position).ReplaceWithHtml(injection.Replace)
+				}
+				if injection.Append != "" {
+					doc.Find(injection.Position).AppendHtml(injection.Append)
+				}
+				if injection.Prepend != "" {
+					doc.Find(injection.Position).PrependHtml(injection.Prepend)
+				}
+				body, err = doc.Html()
+				if err != nil {
+					log.Fatal(err)
+				}
 			}
 		}
 	}
@@ -213,6 +220,7 @@ 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"`

ruleset.yaml

@@ -1,4 +1,6 @@
 - domain: www.example.com
+  domains: 
+  - www.beispiel.com
   regexRules:
     - match: <script\s+([^>]*\s+)?src="(/)([^"]*)"
       replace: <script $1 script="/https://www.example.com/$3"
@@ -53,3 +55,92 @@
             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>