begin migrating old v1 rulesets to v2 rulesets

.air.toml

@@ -12,7 +12,7 @@ tmp_dir = "tmp"
   exclude_regex = ["_test.go"]
   exclude_unchanged = false
   follow_symlink = false
-  full_bin = "./tmp/main --ruleset ./ruleset_v2.yaml"
+  full_bin = "./tmp/main --ruleset ./rulesets_v2"
   include_dir = []
   include_ext = ["go", "tpl", "tmpl", "yaml", "html", "js"]
   include_file = []

proxychain/ruleset/ruleset.go

@@ -35,18 +35,15 @@ func (rs *Ruleset) UnmarshalYAML(unmarshal func(interface{}) error) error {
 	}
 	yamlRuleset := &AuxRuleset{}
 
-	if err := unmarshal(&yamlRuleset); err != nil {
+	// First, try to unmarshal as AuxRuleset
-		// if there is no top-level rule key, we'll try to unmarshal as if it is just a bare rule
+	err := unmarshal(yamlRuleset)
-		recovered := false
+	if err != nil {
-		yamlRule := &Rule{}
+		// If that fails, try to unmarshal directly into a slice of Rules
-		if err := unmarshal(&yamlRule); err != nil {
+		var directRules []Rule
-			yamlRuleset.Rules = append(yamlRuleset.Rules, *yamlRule)
+		if err := unmarshal(&directRules); err != nil {
-			recovered = true
-		}
-
-		if !recovered {
 			return err
 		}
+		yamlRuleset.Rules = directRules
 	}
 
 	rs._rulemap = make(map[string]*Rule)
@@ -224,6 +221,7 @@ func (rs *Ruleset) loadRulesFromLocalDir(path string) error {
 		if !isYAML {
 			return nil
 		}
+		fmt.Printf("loadRulesFromLocalDir :: loading rule: %s\n", path)
 
 		tmpRs := Ruleset{_rulemap: make(map[string]*Rule)}
 		err = tmpRs.loadRulesFromLocalFile(path)
@@ -268,6 +266,7 @@ func (rs *Ruleset) loadRulesFromLocalFile(path string) error {
 		e := fmt.Errorf("failed to read rules from local file: '%s'", path)
 		return errors.Join(e, err)
 	}
+	fmt.Printf("loadRulesFromLocalFile :: %s\n", path)
 
 	isJSON := strings.HasSuffix(path, ".json")
 	if isJSON {

rulesets_v2/BE_Belgium/demorgen-be.yaml

@@ -0,0 +1,23 @@
+- domains:
+  - demorgen.be
+
+  requestmodifiers:
+    - name: MasqueradeAsGoogleBot
+
+    - name: SpoofReferrer
+      params: ["https://news.google.com"]
+
+    - name: SetOutgoingCookie
+      params: ["isBot", "true"]
+
+    - name: SetOutgoingCookie
+      params: ["authId", "1"]
+
+  responsemodifiers:
+    - name: BypassContentSecurityPolicy
+    - name: InjectScriptAfterDOMContentLoaded
+      params:
+        - | 
+            let paywall = document.querySelectorAll('script[src*="advertising-cdn.dpgmedia.cloud"], div[data-temptation-position="ARTICLE_BOTTOM"]');
+            paywall.forEach(el => { el.remove(); });
+            document.querySelector('div[data-advert-placeholder-collapses]').remove();

rulesets_v2/BE_Belgium/dpg-media.yaml

@@ -0,0 +1,44 @@
+- domains:
+  - myprivacy.dpgmedia.be
+  - myprivacy.dpgmedia.nl
+
+  requestmodifiers:
+    - name: SpoofReferrer
+      params: ["https://news.google.com"]
+
+    - name: SetOutgoingCookie
+      params: ["isBot", "true"]
+
+    - name: SetOutgoingCookie
+      params: ["authId", "1"]
+
+    - name: SpoofXForwardedFor
+      params: ["none"]
+
+
+- domains:
+  - demorgen.be
+
+  requestmodifiers:
+    - name: MasqueradeAsGoogleBot
+
+    - name: SpoofReferrer
+      params: ["https://news.google.com"]
+
+    - name: SetOutgoingCookie
+      params: ["isBot", "true"]
+
+    - name: SetOutgoingCookie
+      params: ["authId", "1"]
+
+    - name: SpoofXForwardedFor
+      params: ["none"]
+
+  responsemodifiers:
+    - name: BypassContentSecurityPolicy
+    - name: InjectScriptAfterDOMContentLoaded
+      params:
+        - | 
+            let paywall = document.querySelectorAll('script[src*="advertising-cdn.dpgmedia.cloud"], div[data-temptation-position="ARTICLE_BOTTOM"]');
+            paywall.forEach(el => { el.remove(); });
+            document.querySelector('div[data-advert-placeholder-collapses]').remove();

rulesets_v2/CA_Canada/_multi-metroland-media-group.yaml

@@ -0,0 +1,34 @@
+rules:
+  - domains: 
+    - thestar.com
+    - niagarafallsreview.ca
+    - stcatharinesstandard.ca
+    - thepeterboroughexaminer.com
+    - therecord.com
+    - thespec.com
+    - wellandtribune.ca
+    responsemodifications:
+      - name: DeleteLocalStorageData
+      - name: DeleteSessionStorageData
+      - name: InjectScriptAfterDOMContentLoaded
+        params:
+          - |
+              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(); });