Update podcast rss feed parser to use psc chapters on episodes

server/models/Feed.js

@@ -607,6 +607,7 @@ class Feed extends Model {
       custom_namespaces: {
         itunes: 'http://www.itunes.com/dtds/podcast-1.0.dtd',
         podcast: 'https://podcastindex.org/namespace/1.0',
+        psc: 'http://podlove.org/simple-chapters',
         googleplay: 'http://www.google.com/schemas/play-podcasts/1.0'
       },
       custom_elements: customElements

server/models/FeedEpisode.js

@@ -325,6 +325,24 @@ class FeedEpisode extends Model {
       customElements.push({ 'itunes:summary': { _cdata: this.description } })
     }
 
+    customElements.push({
+      'psc:chapters': [
+        {
+          _attr: {
+            version: '1.2'
+          },
+          'psc:chapter': [
+            {
+              _attr: {
+                title: 'Test',
+                start: '00:00:00'
+              }
+            }
+          ]
+        }
+      ]
+    })
+
     return {
       title: this.title,
       description: this.description || '',

server/models/PodcastEpisode.js

@@ -80,9 +80,13 @@ class PodcastEpisode extends Model {
     if (rssPodcastEpisode.guid) {
       podcastEpisode.extraData.guid = rssPodcastEpisode.guid
     }
+
     if (audioFile.chapters?.length) {
       podcastEpisode.chapters = audioFile.chapters.map((ch) => ({ ...ch }))
+    } else if (rssPodcastEpisode.chapters?.length) {
+      podcastEpisode.chapters = rssPodcastEpisode.chapters.map((ch) => ({ ...ch }))
     }
+
     return this.create(podcastEpisode)
   }
 

server/utils/index.js

@@ -243,3 +243,29 @@ module.exports.isValidASIN = (str) => {
   if (!str || typeof str !== 'string') return false
   return /^[A-Z0-9]{10}$/.test(str)
 }
+
+/**
+ * Convert timestamp to seconds
+ * @example "01:00:00" => 3600
+ * @example "01:00" => 60
+ * @example "01" => 1
+ *
+ * @param {string} timestamp
+ * @returns {number}
+ */
+module.exports.timestampToSeconds = (timestamp) => {
+  if (typeof timestamp !== 'string') {
+    return null
+  }
+  const parts = timestamp.split(':').map(Number)
+  if (parts.some(isNaN)) {
+    return null
+  } else if (parts.length === 1) {
+    return parts[0]
+  } else if (parts.length === 2) {
+    return parts[0] * 60 + parts[1]
+  } else if (parts.length === 3) {
+    return parts[0] * 3600 + parts[1] * 60 + parts[2]
+  }
+  return null
+}

server/utils/podcastUtils.js

@@ -1,9 +1,17 @@
 const axios = require('axios')
 const ssrfFilter = require('ssrf-req-filter')
 const Logger = require('../Logger')
-const { xmlToJSON, levenshteinDistance } = require('./index')
+const { xmlToJSON, levenshteinDistance, timestampToSeconds } = require('./index')
 const htmlSanitizer = require('../utils/htmlSanitizer')
 
+/**
+ * @typedef RssPodcastChapter
+ * @property {number} id
+ * @property {string} title
+ * @property {number} start
+ * @property {number} end
+ */
+
 /**
  * @typedef RssPodcastEpisode
  * @property {string} title
@@ -22,6 +30,7 @@ const htmlSanitizer = require('../utils/htmlSanitizer')
  * @property {string} guid
  * @property {string} chaptersUrl
  * @property {string} chaptersType
+ * @property {RssPodcastChapter[]} chapters
  */
 
 /**
@@ -205,12 +214,53 @@ function extractEpisodeData(item) {
     const cleanKey = key.split(':').pop()
     episode[cleanKey] = extractFirstArrayItemString(item, key)
   })
+
+  // Extract psc:chapters if duration is set
+  let episodeDuration = !isNaN(episode.duration) ? timestampToSeconds(episode.duration) : null
+  if (item['psc:chapters']?.[0]?.['psc:chapter']?.length && episodeDuration) {
+    // Example chapter:
+    // {"id":0,"start":0,"end":43.004286,"title":"chapter 1"}
+
+    const cleanedChapters = item['psc:chapters'][0]['psc:chapter'].map((chapter, index) => {
+      if (!chapter['$']?.title || !chapter['$']?.start || typeof chapter['$']?.start !== 'string' || typeof chapter['$']?.title !== 'string') {
+        return null
+      }
+
+      const start = timestampToSeconds(chapter['$'].start)
+      if (start === null) {
+        return null
+      }
+
+      return {
+        id: index,
+        title: chapter['$'].title,
+        start
+      }
+    })
+
+    if (cleanedChapters.some((chapter) => !chapter)) {
+      Logger.warn(`[podcastUtils] Invalid chapter data for ${episode.enclosure.url}`)
+    } else {
+      episode.chapters = cleanedChapters.map((chapter, index) => {
+        const nextChapter = cleanedChapters[index + 1]
+        const end = nextChapter ? nextChapter.start : episodeDuration
+        return {
+          id: chapter.id,
+          title: chapter.title,
+          start: chapter.start,
+          end
+        }
+      })
+    }
+  }
+
   return episode
 }
 
 function cleanEpisodeData(data) {
   const pubJsDate = data.pubDate ? new Date(data.pubDate) : null
   const publishedAt = pubJsDate && !isNaN(pubJsDate) ? pubJsDate.valueOf() : null
+
   return {
     title: data.title,
     subtitle: data.subtitle || '',
@@ -227,7 +277,8 @@ function cleanEpisodeData(data) {
     enclosure: data.enclosure,
     guid: data.guid || null,
     chaptersUrl: data.chaptersUrl || null,
-    chaptersType: data.chaptersType || null
+    chaptersType: data.chaptersType || null,
+    chapters: data.chapters || []
   }
 }