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

feat(crawler): plumb TorController through FetchContext and pipelines

Browse Source 
Adds CRAWLER_TOR_CONTROL_URL / _PASSWORD / _COOKIE_PATH /
_RECIRCUIT_MAX_ATTEMPTS to CrawlerConfig and to bin/crawler.rs's
env reads. Constructs an Option<Arc<TorController>> at daemon /
CLI startup and threads it through FetchContext,
pipeline::run_metadata_pass, and content::sync_chapter_content as
Option<&TorController>.

Pure scaffolding — the controller isn't used yet; behavior is
unchanged. Next commit wires the retry hooks and session-probe
recircuit.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
MechaCat02
2026-05-31 18:43:15 +02:00
parent d6d84dedcb
commit 8557e432a2
6 changed files with 82 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
backend/src/config.rs
View File

@@ -97,6 +97,20 @@ pub struct CrawlerConfig {
pub cookie_domain: Option<String>,
pub user_agent: Option<String>,
pub proxy: Option<String>,
/// `tcp://host:port`, `host:port`, or bare `host` (default port
/// 9051). When `None`, TOR-recircuit-on-transient is disabled and
/// the crawler behaves identically to pre-TOR releases.
pub tor_control_url: Option<String>,
/// HashedControlPassword auth. Used only when
/// `tor_control_cookie_path` is `None`.
pub tor_control_password: Option<String>,
/// Cookie-file auth path (e.g.
/// `/var/lib/tor/control_auth_cookie`). Takes precedence over
/// password when both are set.
pub tor_control_cookie_path: Option<PathBuf>,
/// Maximum NEWNYM-and-retry cycles per recircuit-eligible failure.
/// Defaults to 3.
pub tor_recircuit_max_attempts: u32,
pub browser: LaunchOptions,
/// Hosts the crawler is allowed to download images / covers from.
/// Always seeded with the host of `start_url` and (when set) the
@@ -124,6 +138,10 @@ impl Default for CrawlerConfig {
cookie_domain: None,
user_agent: None,
proxy: None,
tor_control_url: None,
tor_control_password: None,
tor_control_cookie_path: None,
tor_recircuit_max_attempts: 3,
browser: LaunchOptions::headless(),
download_allowlist: DownloadAllowlist::new(),
max_image_bytes: DEFAULT_MAX_IMAGE_BYTES,
@@ -234,6 +252,18 @@ impl CrawlerConfig {
proxy: std::env::var("CRAWLER_PROXY")
.ok()
.filter(|s| !s.trim().is_empty()),
tor_control_url: std::env::var("CRAWLER_TOR_CONTROL_URL")
.ok()
.filter(|s| !s.trim().is_empty()),
tor_control_password: std::env::var("CRAWLER_TOR_CONTROL_PASSWORD")
.ok()
.filter(|s| !s.trim().is_empty()),
tor_control_cookie_path: std::env::var("CRAWLER_TOR_CONTROL_COOKIE_PATH")
.ok()
.filter(|s| !s.trim().is_empty())
.map(PathBuf::from),
tor_recircuit_max_attempts: env_u64("CRAWLER_TOR_RECIRCUIT_MAX_ATTEMPTS", 3)
.max(1) as u32,
browser: LaunchOptions::from_env(),
download_allowlist,
max_image_bytes: env_usize("CRAWLER_MAX_IMAGE_BYTES", DEFAULT_MAX_IMAGE_BYTES),