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

feat(crawler): recircuit TOR on transient pages and unauthenticated probes

Browse Source 
- target.rs swaps retry_on_transient → retry_on_transient_with_hook,
  signaling NEWNYM via ctx.tor between attempts when configured.
- session.rs gains verify_session_with_recircuit; the bare
  verify_session is now a one-line wrapper passing tor=None,
  unauth_max_recircuit=0. The inner run_session_probe_loop is
  pure-over-IO and unit-tested with closure-based fakes.
- content.rs extracts fetch_chapter_html_once + the closure-driven
  fetch_chapter_html_with_recircuit, used by sync_chapter_content to
  retry on Transient or Unauthenticated up to a recircuit_budget.
  Budget = 0 (no TOR) preserves original behavior bit-for-bit.
- app.rs and bin/crawler.rs construct the controller before on_launch
  and pass it into verify_session_with_recircuit, so a transient
  hiccup at startup no longer requires PHPSESSID rotation.

Recircuit budget defaults to CRAWLER_TOR_RECIRCUIT_MAX_ATTEMPTS (3).
Errors from NEWNYM are logged and swallowed — failing to recircuit
should not take down the crawl.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-05-31 18:52:28 +02:00
parent 8557e432a2
commit 8c6378b877
5 changed files with 699 additions and 114 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
backend/src/app.rs
View File

@@ -123,6 +123,18 @@ async fn spawn_crawler_daemon(
}
let rate = Arc::new(rate);
let tor = crate::crawler::tor::TorController::from_parts(
cfg.tor_control_url.as_deref(),
cfg.tor_control_password.as_deref(),
cfg.tor_control_cookie_path.as_deref(),
)
.context("build TorController from CRAWLER_TOR_CONTROL_* env")?
.map(Arc::new);
if let Some(t) = &tor {
tracing::info!(?t, "TOR control configured; transient pages will trigger NEWNYM");
}
let tor_recircuit_max = cfg.tor_recircuit_max_attempts;
// Browser manager. on_launch re-injects PHPSESSID on every fresh
// chromium spawn so an idle teardown followed by re-launch stays
// authenticated without operator action.
@@ -135,17 +147,24 @@ async fn spawn_crawler_daemon(
let sid = sid.clone();
let domain = domain.clone();
let start_url = start_url.clone();
let tor_for_launch = tor.as_ref().map(Arc::clone);
let on_launch: browser_manager::OnLaunch = Arc::new(move |browser| {
let sid = sid.clone();
let domain = domain.clone();
let start_url = start_url.clone();
let tor_for_launch = tor_for_launch.as_ref().map(Arc::clone);
Box::pin(async move {
session::inject_phpsessid(&browser, &sid, &domain)
.await
.context("on_launch: inject_phpsessid")?;
session::verify_session(&browser, &start_url)
.await
.context("on_launch: verify_session")?;
session::verify_session_with_recircuit(
&browser,
&start_url,
tor_for_launch.as_deref(),
tor_recircuit_max,
)
.await
.context("on_launch: verify_session")?;
Ok(())
})
});
@@ -157,17 +176,6 @@ async fn spawn_crawler_daemon(
let session_expired = Arc::new(AtomicBool::new(false));
let tor = crate::crawler::tor::TorController::from_parts(
cfg.tor_control_url.as_deref(),
cfg.tor_control_password.as_deref(),
cfg.tor_control_cookie_path.as_deref(),
)
.context("build TorController from CRAWLER_TOR_CONTROL_* env")?
.map(Arc::new);
if let Some(t) = &tor {
tracing::info!(?t, "TOR control configured; transient pages will trigger NEWNYM");
}
let metadata_pass: Option<Arc<dyn MetadataPass>> = cfg.start_url.as_ref().map(|url| {
let m: Arc<dyn MetadataPass> = Arc::new(RealMetadataPass {
browser_manager: Arc::clone(&browser_manager),