aeorank 2.2.0 → 2.3.0

package/dist/cli.js

@@ -207,18 +207,21 @@ async function prefetchSiteData(domain) {
   if (homepage) homepage.category = "homepage";
   return { domain, protocol, homepage, llmsTxt, robotsTxt, faqPage, sitemapXml, rssFeed, aiTxt, redirectedTo: null, parkedReason: null, blogSample };
 }
+function stripScripts(html) {
+  return html.replace(/<script(?![^>]*type\s*=\s*["']application\/ld\+json["'])[^>]*>[\s\S]*?<\/script>/gi, "").replace(/<style[\s\S]*?<\/style>/gi, "");
+}
 function getCombinedHtml(data) {
-  const parts = [data.homepage?.text || ""];
+  const parts = [stripScripts(data.homepage?.text || "")];
   if (data.blogSample) {
     for (const page of data.blogSample) {
-      parts.push(page.text);
+      parts.push(stripScripts(page.text));
     }
   }
   return parts.join("\n");
 }
 function getBlogHtml(data) {
   if (!data.blogSample || data.blogSample.length === 0) return "";
-  return data.blogSample.map((p) => p.text).join("\n");
+  return data.blogSample.map((p) => stripScripts(p.text)).join("\n");
 }
 function checkLlmsTxt(data) {
   const findings = [];
@@ -1416,14 +1419,17 @@ function checkQueryAnswerAlignment(data) {
   }
   let answered = 0;
   for (const qHeading of questionHeadings) {
-    const escapedHeading = qHeading.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
-    const pattern = new RegExp(escapedHeading + "[\\s\\S]{0,200}?<\\/h[23]>([\\s\\S]{0,1500}?)(?=<h[1-6]|$)", "i");
-    const match = pattern.exec(combinedHtml);
-    if (match) {
-      const afterContent = match[1].replace(/<[^>]*>/g, " ").replace(/\s+/g, " ").trim();
-      if (afterContent.length >= 20) {
-        answered++;
+    try {
+      const escapedHeading = qHeading.replace(/[.*+?^${}()|[\]\\]/g, "\\$&");
+      const pattern = new RegExp(escapedHeading + "[\\s\\S]{0,200}?<\\/h[23]>([\\s\\S]{0,1500}?)(?=<h[1-6]|$)", "i");
+      const match = pattern.exec(combinedHtml);
+      if (match) {
+        const afterContent = match[1].replace(/<[^>]*>/g, " ").replace(/\s+/g, " ").trim();
+        if (afterContent.length >= 20) {
+          answered++;
+        }
       }
+    } catch {
     }
   }
   const rate = Math.round(answered / questionHeadings.length * 100);
@@ -1902,27 +1908,32 @@ function checkTopicCoherence(data) {
   const bigramFocusRatio = blogPages.length > 0 ? dominantBigramCount / blogPages.length : 0;
   let score = 0;
   const bestFocusRatio = Math.max(focusRatio, bigramFocusRatio);
+  const dominantPageCount = Math.max(dominantTermCount, dominantBigramCount);
+  const hasStrongAbsolutePresence = dominantPageCount >= 10;
   if (bestFocusRatio >= 0.8) {
     score += 7;
   } else if (bestFocusRatio >= 0.6) {
     score += 6;
-  } else if (bestFocusRatio >= 0.45) {
+  } else if (bestFocusRatio >= 0.45 || hasStrongAbsolutePresence && bestFocusRatio >= 0.3) {
     score += 5;
-  } else if (bestFocusRatio >= 0.3) {
-    score += 3;
+  } else if (bestFocusRatio >= 0.3 || hasStrongAbsolutePresence && bestFocusRatio >= 0.2) {
+    score += 4;
   } else if (bestFocusRatio >= 0.15) {
     score += 2;
   } else {
     score += 1;
   }
-  const clusterPenaltyReduced = focusRatio >= 0.7;
-  if (topicClusterCount <= 3) {
+  const clusterPenaltyReduced = focusRatio >= 0.7 || hasStrongAbsolutePresence;
+  const scaledLow = Math.max(3, Math.floor(blogPages.length / 10));
+  const scaledMid = Math.max(6, Math.floor(blogPages.length / 5));
+  const scaledHigh = Math.max(10, Math.floor(blogPages.length / 3));
+  if (topicClusterCount <= scaledLow) {
     score += 3;
     findings.push({ severity: "info", detail: `${topicClusterCount} topic cluster(s) - tightly focused content` });
-  } else if (topicClusterCount <= 6) {
+  } else if (topicClusterCount <= scaledMid) {
     score += clusterPenaltyReduced ? 2 : 1;
     findings.push({ severity: "info", detail: `${topicClusterCount} topic clusters${clusterPenaltyReduced ? " within a focused niche" : " - moderately focused"}` });
-  } else if (topicClusterCount <= 10) {
+  } else if (topicClusterCount <= scaledHigh) {
     score += clusterPenaltyReduced ? 1 : 0;
     if (!clusterPenaltyReduced) {
       findings.push({ severity: "low", detail: `${topicClusterCount} topic clusters - scattered content`, fix: "Reduce the number of distinct topics. Focus blog content on 2-3 core expertise areas." });