VeritableValor/invidious
1
0
Fork 0
mirror of https://github.com/iv-org/invidious.git synced 2026-07-07 06:06:48 -05:00
Code Issues Packages Projects Releases Wiki Activity

fix parsing for podcasts

Browse Source 
For some reason, Podcasts contains an empty JSON Object that we have to
skip, therefore we just iterate metadataRows until finding metadataParts
since metadataRows will not always contain a single Object.
This commit is contained in:
Fijxu 2026-05-22 22:16:05 -04:00
parent f684437754
commit dc7a7e4e33
1 changed files with 50 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

65
src/invidious/yt_backend/extractors.cr
View File

@ -682,9 +682,11 @@ private module Parsers
author_thumbnail: nil,
badges: VideoBadges::None,
})
elsif content_type == "LOCKUP_CONTENT_TYPE_PODCAST"
# TODO
else # If it's a podcast, it's content_type would be "LOCKUP_CONTENT_TYPE_PODCAST"
# If it's a playlist, it's content_type would be "LOCKUP_CONTENT_TYPE_PLAYLIST"
# If it's a podcast, it's content_type would be "LOCKUP_CONTENT_TYPE_PODCAST"
# Playlist and Podcasts structures are quite similar, so we can use the same logic
# we use to parse Playlists data, for Podcasts.
else
thumbnail_view_model = item_contents.dig(
"contentImage", "collectionThumbnailViewModel",
"primaryThumbnail", "thumbnailViewModel"
@ -694,16 +696,36 @@ private module Parsers
playlist_id = item_contents["contentId"].as_s
# This complicated sequences tries to extract the following data structure:
# "overlays": [{
# "thumbnailOverlayBadgeViewModel": {
# "thumbnailBadges": [{
# "thumbnailBadgeViewModel": {
# "text": "430 episodes",
# "badgeStyle": "THUMBNAIL_OVERLAY_BADGE_STYLE_DEFAULT"
# }
# }]
# }
# }]
#
# "overlays": [
# {
# "thumbnailOverlayBadgeViewModel": {
# "thumbnailBadges": [
# {
# "thumbnailBadgeViewModel": {
# "icon": {
# "sources": [
# {
# "clientResource": {
# "imageName": "BROADCAST"
# }
# }
# ]
# },
# "text": "5 episodes",
# "badgeStyle": "THUMBNAIL_OVERLAY_BADGE_STYLE_DEFAULT",
# "backgroundColor": {
# "lightTheme": 991526,
# "darkTheme": 991526
# }
# }
# }
# ],
# "position": "THUMBNAIL_OVERLAY_BADGE_POSITION_BOTTOM_END"
# }
# },
# ... <-- There is another item bellow the Object we use to extract episodes/videos
# ]
#
# NOTE: this simplistic `.to_i` conversion might not work on larger
# playlists and hasn't been tested.
@ -718,9 +740,22 @@ private module Parsers
metadata = item_contents.dig("metadata", "lockupMetadataViewModel")
title = metadata.dig("title", "content").as_s
metadata_parts = metadata.dig("metadata", "contentMetadataViewModel", "metadataRows", 0, "metadataParts", 0)
# metadataParts is not always in the first place of the metadataRows array, therefore,
# we search for it iterating the array. We have only seen metadataRows with at least
# 2 items inside it.
#
# It looks like this:
# "metadataRows": [
# {}, <-- empty Object
# {
# "metadataParts": [ ... ] <-- metadataParts with the information we are searching for.
# }
# ]
metadata_parts = metadata.dig("metadata", "contentMetadataViewModel", "metadataRows")
.as_a.find { |row| row["metadataParts"]? }
.try &.dig("metadataParts", 0)
if author_info = metadata_parts["text"]?
if author_info = metadata_parts.try &.["text"]?
author = author_info["content"].as_s
author_id = author_info.dig?("commandRuns", 0, "onTap", "innertubeCommand", "browseEndpoint", "browseId")
.try &.as_s || author_fallback.id