fabi/Mangalord
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: close Chromium tabs on crawler fetch error paths

Browse Source 
new_page() opened a tab that was only closed on the happy path; a `?` on
wait_for_nav / content() leaked it (chromiumoxide doesn't close on drop),
so errored fetches accumulated tabs in the shared browser. Add a generic,
unit-tested `close_after(close, body)` helper and wrap the three fetch
sites (chapter content, session probe, source navigate) so the tab is
closed on every exit path — including navigate's content()-read branch,
which previously leaked.

Bump to 0.124.5.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-07-07 21:04:50 +02:00
parent b7d8faadf7
commit 46134c8760
7 changed files with 136 additions and 53 deletions
Download Patch File Download Diff File Expand all files Collapse all files

50
backend/src/crawler/source/target.rs
View File

@@ -20,7 +20,7 @@ use super::{
use crate::crawler::detect::{
has_logo_sentinel, is_broken_page_body, retry_on_transient_with_hook, PageError,
};
use crate::crawler::nav::{wait_for_nav, wait_for_selector, NavError, SELECTOR_TIMEOUT};
use crate::crawler::nav::{close_after, wait_for_nav, wait_for_selector, NavError, SELECTOR_TIMEOUT};
use crate::crawler::safety::ensure_public_target;
/// `sources.id` value for this Source impl. Exposed as a const so the
@@ -258,26 +258,34 @@ async fn navigate(
.new_page(url)
.await
.map_err(|e| PageError::Other(anyhow::Error::from(e)))?;
match wait_for_nav(&page).await {
Ok(()) => {}
Err(NavError::Timeout(_)) => {
page.close().await.ok();
return Err(PageError::transient("nav timeout"));
}
Err(NavError::Cdp(e)) => {
page.close().await.ok();
return Err(PageError::Other(anyhow::Error::from(e)));
}
}
// Best-effort wait for the page-type marker. We deliberately
// discard a timeout here — see fn-level doc.
let _ = wait_for_selector(&page, marker, SELECTOR_TIMEOUT).await;
let html = page
.content()
.await
.map_err(|e| PageError::Other(anyhow::Error::from(e)))?;
page.close().await.ok();
classify_navigate_html(html)
// Close the tab on every exit path — the previous code closed on the two
// nav-error branches but leaked it on a content() read error.
let closer = page.clone();
close_after(
async move {
closer.close().await.ok();
},
async {
match wait_for_nav(&page).await {
Ok(()) => {}
Err(NavError::Timeout(_)) => {
return Err(PageError::transient("nav timeout"));
}
Err(NavError::Cdp(e)) => {
return Err(PageError::Other(anyhow::Error::from(e)));
}
}
// Best-effort wait for the page-type marker. We deliberately
// discard a timeout here — see fn-level doc.
let _ = wait_for_selector(&page, marker, SELECTOR_TIMEOUT).await;
let html = page
.content()
.await
.map_err(|e| PageError::Other(anyhow::Error::from(e)))?;
classify_navigate_html(html)
},
)
.await
}
/// Classify a fetched body. The broken-page template is universal across