rays/ipodderx-rs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Do not auto-download enclosures that are not audio or video

Browse Source 
Blog feeds put each article's header image in an <enclosure>, so a text
feed read as a podcast full of episodes: 149 images, 74 MB across 11
feeds. media_types defaults to audio and video, with a per-feed override.

Such enclosures stay listed and stay downloadable by hand; the row names
what it is rather than saying "skipped". An unknown type is allowed, since
the real type is only known after downloading, and a torrent is allowed as
a container judged once unpacked.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01AdXho5tTkjFLeUXKbEjKBh
This commit is contained in:
Ray Slakinski
2026-09-10 17:13:59 +00:00
parent 8b21d19365
commit a83f62ccd3
7 changed files with 131 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
src/main.rs
View File

@@ -412,6 +412,7 @@ pub async fn add_one(
url: url.to_owned(),
folder: folder.clone(),
group: None,
media_types: None,
schedule: None,
keywords: keywords.clone(),
allow_explicit: false,
@@ -494,6 +495,7 @@ async fn import(ctx: &Ctx, config_path: &std::path::Path, file: &std::path::Path
url,
folder: None,
group: None,
media_types: None,
schedule: None,
keywords: vec![],
allow_explicit: false,
@@ -711,6 +713,7 @@ pub fn subscriptions(ctx: &Ctx) -> Result<Vec<Sub>> {
url: m.url.clone(),
folder: Some(format!("{base}/{title}")),
group: Some(m.group_id.clone()),
media_types: parent.and_then(|p| p.media_types.clone()),
schedule: parent.and_then(|p| p.schedule.clone()),
keywords: parent.map(|p| p.keywords.clone()).unwrap_or_default(),
allow_explicit: parent.is_some_and(|p| p.allow_explicit),
@@ -837,7 +840,7 @@ async fn scan_one(
}
// Filters run once, at discovery, and are recorded in `state`. The download
// queue below is then just "everything still pending".
if let Some(reason) = reject(feed_cfg, entry, &enc.url) {
if let Some(reason) = reject(&ctx.cfg(), feed_cfg, entry, enc) {
ctx.db.mark_enclosure(&enc.url, "skipped", Some(reason))?;
}
}
@@ -991,10 +994,25 @@ async fn sync_opml(
}
/// Why this enclosure should not be downloaded, if it should not be.
fn reject(feed_cfg: &config::Feed, entry: &feed::Entry, url: &str) -> Option<&'static str> {
fn reject(
cfg: &config::Config,
feed_cfg: &config::Feed,
entry: &feed::Entry,
enc: &feed::Enclosure,
) -> Option<&'static str> {
let url = enc.url.as_str();
if !feed_cfg.auto_download {
return Some("auto_download is off");
}
// Blog feeds put the article's header image in an <enclosure>; without this a text
// feed reads as a podcast full of episodes and fills the disk with artwork.
let wanted = feed_cfg
.media_types
.as_deref()
.unwrap_or(&cfg.general.media_types);
if !config::wanted_media(enc.mime.as_deref(), wanted) {
return Some("not a wanted media type");
}
if entry.explicit && !feed_cfg.allow_explicit {
return Some("explicit");
}