Github/lowfi
1
0
Fork 0
mirror of https://github.com/talwat/lowfi synced 2025-08-17 23:22:19 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: ignore two tracks with lyrics

Browse Source
This commit is contained in:
talwat 2025-08-08 23:03:38 +02:00
parent c3b14f3589
commit 4efd8e9e34
2 changed files with 19 additions and 22 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
data/chillhop-new.txt
View File

@ -930,8 +930,6 @@ https://stream.chillhop.com/mp3/
21658!Puesta De Sol 21658!Puesta De Sol
21657!Cueva 21657!Cueva
21656!Ámbar 21656!Ámbar
21773!Esfera
21655!Dando Vueltas
21654!Leña 21654!Leña
21653!Libélula 21653!Libélula
21652!Pie in the Sky 21652!Pie in the Sky

37
src/scrapers/chillhop.rs
View File

@ -61,9 +61,6 @@ struct Release {
enum ReleaseError { enum ReleaseError {
#[error("invalid release: {0}")] #[error("invalid release: {0}")]
Invalid(#[from] eyre::Error), Invalid(#[from] eyre::Error),
#[error("release explicitly ignored")]
Ignored,
} }
impl Release { impl Release {
@ -76,15 +73,6 @@ impl Release {
let content = get(&client, &path).await?; let content = get(&client, &path).await?;
let html = Html::parse_document(&content); let html = Html::parse_document(&content);
let author = html.select(&RELEASE_AUTHOR).next();
if let Some(author) = author {
if author.inner_html() == "Kenji" {
// No lyrics!
return Err(ReleaseError::Ignored);
}
}
let textarea = html let textarea = html
.select(&RELEASE_TEXTAREA) .select(&RELEASE_TEXTAREA)
.next() .next()
@ -179,7 +167,17 @@ async fn scan_page(
pub async fn scrape() -> eyre::Result<()> { pub async fn scrape() -> eyre::Result<()> {
const PAGE_COUNT: usize = 40; const PAGE_COUNT: usize = 40;
const USER_AGENT: &str = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36"; const USER_AGENT: &str = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/138.0.0.0 Safari/537.36";
const TRACK_COUNT: u64 = 1650; const TRACK_COUNT: u64 = 1625;
const IGNORED_TRACKS: [u32; 3] = [
74707, // 404
21655, // Lyrics
21773, // Lyrics
];
const IGNORED_ARTISTS: [&str; 1] = [
"Kenji", // Lyrics
];
fs::create_dir_all("./cache/chillhop").await.unwrap(); fs::create_dir_all("./cache/chillhop").await.unwrap();
let client = Client::builder().user_agent(USER_AGENT).build().unwrap(); let client = Client::builder().user_agent(USER_AGENT).build().unwrap();
@ -200,12 +198,13 @@ pub async fn scrape() -> eyre::Result<()> {
let mut results: Vec<Result<Release, ReleaseError>> = futures.collect().await; let mut results: Vec<Result<Release, ReleaseError>> = futures.collect().await;
bar.finish_and_clear(); bar.finish_and_clear();
// I mean, is it... optimal? Absolutely not. Does it work? Yes.
eprintln!("sorting..."); eprintln!("sorting...");
results.sort_by_key(|x| if let Ok(x) = x { x.index } else { 0 }); results.sort_by_key(|x| if let Ok(x) = x { x.index } else { 0 });
results.reverse(); results.reverse();
eprintln!("printing..."); eprintln!("printing...");
let mut printed = Vec::with_capacity(TRACK_COUNT as usize); let mut printed = Vec::with_capacity(TRACK_COUNT as usize); // Lazy way to get rid of dupes.
for result in results { for result in results {
let release = match result { let release = match result {
Ok(release) => release, Ok(release) => release,
@ -216,7 +215,11 @@ pub async fn scrape() -> eyre::Result<()> {
}; };
for mut track in release.tracks { for mut track in release.tracks {
if track.file_id == 74707 { if IGNORED_TRACKS.contains(&track.file_id) {
continue;
}
if IGNORED_ARTISTS.contains(&track.artists.as_ref()) {
continue; continue;
} }
@ -233,10 +236,6 @@ pub async fn scrape() -> eyre::Result<()> {
eprintln!("-- ERROR REPORT --"); eprintln!("-- ERROR REPORT --");
for error in errors { for error in errors {
if matches!(error, ReleaseError::Ignored) {
continue;
}
eprintln!("{error}"); eprintln!("{error}");
} }