@rmdes/indiekit-endpoint-microsub 1.0.33 → 1.0.35

package/lib/feeds/normalizer.js

@@ -7,6 +7,28 @@ import crypto from "node:crypto";
 
 import sanitizeHtml from "sanitize-html";
 
+/**
+ * Extract image URLs from HTML content.
+ * Used as a fallback when no explicit photo/enclosure is provided.
+ * @param {string} html - HTML content (already sanitized)
+ * @returns {string[]} Array of image URLs
+ */
+function extractImagesFromHtml(html) {
+  if (!html) {
+    return [];
+  }
+  const urls = [];
+  const imgRegex = /<img[^>]+src=["']([^"']+)["'][^>]*>/gi;
+  let match;
+  while ((match = imgRegex.exec(html)) !== null) {
+    const src = match[1];
+    if (src && !urls.includes(src)) {
+      urls.push(src);
+    }
+  }
+  return urls;
+}
+
 /**
  * Parse a date string with fallback for non-standard formats
  * @param {string|Date} dateInput - Date string or Date object
@@ -150,7 +172,9 @@ export function normalizeItem(item, feedUrl, feedType) {
     type: "entry",
     uid,
     url,
-    name: item.title || undefined,
+    name: item.title
+      ? sanitizeHtml(item.title, { allowedTags: [] }).trim()
+      : undefined,
     published: toISOStringSafe(item.pubdate),
     updated: toISOStringSafe(item.date),
     _source: {
@@ -230,6 +254,14 @@ export function normalizeItem(item, feedUrl, feedType) {
     }
   }
 
+  // Extract images from HTML content as fallback
+  if (!normalized.photo && normalized.content?.html) {
+    const extracted = extractImagesFromHtml(normalized.content.html);
+    if (extracted.length > 0) {
+      normalized.photo = extracted;
+    }
+  }
+
   return normalized;
 }
 
@@ -241,7 +273,9 @@ export function normalizeItem(item, feedUrl, feedType) {
  */
 export function normalizeFeedMeta(meta, feedUrl) {
   const normalized = {
-    name: meta.title || feedUrl,
+    name: meta.title
+      ? sanitizeHtml(meta.title, { allowedTags: [] }).trim()
+      : feedUrl,
   };
 
   if (meta.description) {
@@ -303,7 +337,9 @@ export function normalizeJsonFeedItem(item, feedUrl) {
     type: "entry",
     uid,
     url,
-    name: item.title || undefined,
+    name: item.title
+      ? sanitizeHtml(item.title, { allowedTags: [] }).trim()
+      : undefined,
     published: item.date_published
       ? new Date(item.date_published).toISOString()
       : undefined,
@@ -389,6 +425,14 @@ export function normalizeJsonFeedItem(item, feedUrl) {
     normalized["bookmark-of"] = [item.external_url];
   }
 
+  // Extract images from HTML content as fallback
+  if (!normalized.photo && normalized.content?.html) {
+    const extracted = extractImagesFromHtml(normalized.content.html);
+    if (extracted.length > 0) {
+      normalized.photo = extracted;
+    }
+  }
+
   return normalized;
 }
 
@@ -400,7 +444,9 @@ export function normalizeJsonFeedItem(item, feedUrl) {
  */
 export function normalizeJsonFeedMeta(feed, feedUrl) {
   const normalized = {
-    name: feed.title || feedUrl,
+    name: feed.title
+      ? sanitizeHtml(feed.title, { allowedTags: [] }).trim()
+      : feedUrl,
   };
 
   if (feed.description) {
@@ -560,6 +606,14 @@ export function normalizeHfeedItem(entry, feedUrl) {
     normalized.syndication = properties.syndication;
   }
 
+  // Extract images from HTML content as fallback
+  if (!normalized.photo && normalized.content?.html) {
+    const extracted = extractImagesFromHtml(normalized.content.html);
+    if (extracted.length > 0) {
+      normalized.photo = extracted;
+    }
+  }
+
   return normalized;
 }
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@rmdes/indiekit-endpoint-microsub",
-  "version": "1.0.33",
+  "version": "1.0.35",
   "description": "Microsub endpoint for Indiekit. Enables subscribing to feeds and reading content using the Microsub protocol.",
   "keywords": [
     "indiekit",