Merge pull request #106 from extractus/7.0.3

v7.0.3

package.json

@@ -37,8 +37,8 @@
   "devDependencies": {
     "eslint": "^8.47.0",
     "https-proxy-agent": "^7.0.1",
-    "jest": "^29.6.2",
-    "nock": "^13.3.2"
+    "jest": "^29.6.3",
+    "nock": "^13.3.3"
   },
   "keywords": [
     "extractor",

src/main.test.js

@@ -212,6 +212,23 @@ describe('test extract() standard feed', () => {
     })
     expect(validateProps(result.entries[0])).toBe(true)
   })
+
+  test('extract rss feed from medium.com (content:encoded)', async () => {
+    const url = 'https://medium.com/feed/@ameliakusiak'
+    const xml = readFileSync('test-data/medium-feed.xml', 'utf8')
+    const { baseUrl, path } = parseUrl(url)
+    nock(baseUrl).get(path).reply(200, xml, {
+      'Content-Type': 'application/xml',
+    })
+    const result = await extract(url)
+    feedAttrs.forEach((k) => {
+      expect(hasProperty(result, k)).toBe(true)
+    })
+    entryAttrs.forEach((k) => {
+      expect(hasProperty(result.entries[0], k)).toBe(true)
+    })
+    expect(validateProps(result.entries[0])).toBe(true)
+  })
 })
 
 describe('test extract() with `useISODateFormat` option', () => {

src/utils/parseRssFeed.js

@@ -27,15 +27,17 @@ const transform = (item, options) => {
     link = '',
     pubDate = '',
     description = '',
+    'content:encoded': content = '',
   } = item
 
   const published = useISODateFormat ? toISODateString(pubDate) : pubDate
+  const htmlContent = getText(content || description)
   const entry = {
     id: getEntryId(guid, link, pubDate),
     title: getText(title),
     link: getPureUrl(link, guid, baseUrl),
     published,
-    description: buildDescription(description, descriptionMaxLen),
+    description: buildDescription(htmlContent || description, descriptionMaxLen),
   }
 
   const extraFields = getExtraEntryFields(item)