Mirrors/audiobookshelf
Mirrors/audiobookshelf
1
0
Fork 0
mirror of https://github.com/advplyr/audiobookshelf.git synced 2025-01-22 00:07:52 +01:00
Code Issues Packages Projects Releases Wiki Activity

Update podcast RSS parser to handle HTML not wrapped in CDATA #3778

Browse Source
This commit is contained in:
advplyr 2025-01-10 15:42:52 -06:00
parent 7001adb4dd
commit 0f20ed101e
1 changed files with 27 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
server/utils/podcastUtils.js
View File

@ -52,6 +52,29 @@ function extractFirstArrayItem(json, key) {
return json[key][0] return json[key][0]
} }
function extractStringOrStringify(json) {
try {
if (typeof json[Object.keys(json)[0]]?.[0] === 'string') {
return json[Object.keys(json)[0]][0]
}
// Handles case where html was included without being wrapped in CDATA
return JSON.stringify(value)
} catch {
return ''
}
}
function extractFirstArrayItemString(json, key) {
const item = extractFirstArrayItem(json, key)
if (!item) return ''
if (typeof item === 'object') {
if (item?.['_'] && typeof item['_'] === 'string') return item['_']
return extractStringOrStringify(item)
}
return typeof item === 'string' ? item : ''
}
function extractImage(channel) { function extractImage(channel) {
if (!channel.image || !channel.image.url || !channel.image.url.length) { if (!channel.image || !channel.image.url || !channel.image.url.length) {
if (!channel['itunes:image'] || !channel['itunes:image'].length || !channel['itunes:image'][0]['$']) { if (!channel['itunes:image'] || !channel['itunes:image'].length || !channel['itunes:image'][0]['$']) {
@ -101,7 +124,7 @@ function extractPodcastMetadata(channel) {
} }
if (channel['description']) { if (channel['description']) {
const rawDescription = extractFirstArrayItem(channel, 'description') || '' const rawDescription = extractFirstArrayItemString(channel, 'description')
metadata.description = htmlSanitizer.sanitize(rawDescription.trim()) metadata.description = htmlSanitizer.sanitize(rawDescription.trim())
metadata.descriptionPlain = htmlSanitizer.stripAllTags(rawDescription.trim()) metadata.descriptionPlain = htmlSanitizer.stripAllTags(rawDescription.trim())
} }
@ -145,7 +168,8 @@ function extractEpisodeData(item) {
// Supposed to be the plaintext description but not always followed // Supposed to be the plaintext description but not always followed
if (item['description']) { if (item['description']) {
const rawDescription = extractFirstArrayItem(item, 'description') || '' const rawDescription = extractFirstArrayItemString(item, 'description')
if (!episode.description) episode.description = htmlSanitizer.sanitize(rawDescription.trim()) if (!episode.description) episode.description = htmlSanitizer.sanitize(rawDescription.trim())
episode.descriptionPlain = htmlSanitizer.stripAllTags(rawDescription.trim()) episode.descriptionPlain = htmlSanitizer.stripAllTags(rawDescription.trim())
} }
@ -175,9 +199,7 @@ function extractEpisodeData(item) {
const arrayFields = ['title', 'itunes:episodeType', 'itunes:season', 'itunes:episode', 'itunes:author', 'itunes:duration', 'itunes:explicit', 'itunes:subtitle'] const arrayFields = ['title', 'itunes:episodeType', 'itunes:season', 'itunes:episode', 'itunes:author', 'itunes:duration', 'itunes:explicit', 'itunes:subtitle']
arrayFields.forEach((key) => { arrayFields.forEach((key) => {
const cleanKey = key.split(':').pop() const cleanKey = key.split(':').pop()
let value = extractFirstArrayItem(item, key) episode[cleanKey] = extractFirstArrayItemString(item, key)
if (value?.['_']) value = value['_']
episode[cleanKey] = value
}) })
return episode return episode
} }