9ff49166a5
Until now, when the target site returned its 403 "we're sorry, the request file are not found" response on a page that actually exists, selectors matched nothing and the crawler treated the page as "legitimately empty". Pagination walks silently dropped whole pages worth of mangas, fetch_manga skipped individual entries, and the startup session probe blamed PHPSESSID for what was a site hiccup. This branch adds a single detection layer that the whole pipeline routes through: - `crawler::detect`: PageError::Transient typed signal, plus two primitives (`is_broken_page_body` matches the universal 403 body; `has_logo_sentinel` asserts #logo, the site-wide header element) and a `retry_on_transient` helper that retries a closure on Transient with a small attempt budget. - `navigate()` screens every fetched body for the broken-page signature before handing it to a selector. - Parsers (`parse_manga_list_from`, `parse_manga_detail`, `parse_chapter_pages`) check their structural sentinels (#logo for full-layout pages; a#pic_container for the reader, which doesn't render #logo) and return Result<_, PageError>. Empty Vec is now reserved for genuinely empty pages. - `discover()` retries each pagination page up to 3× (2s apart) before failing the whole Discover job — at which point the existing job system's retry/backoff takes over for longer outages. - `verify_session` is three-state: broken-page → retry probe; #logo present but #avatar_menu absent → genuine logout (the only state that should blame PHPSESSID); both present → ok. Test coverage added at the helper level: 13 unit tests for the detection module (body signature, logo sentinel, PageError, retry helper), parser-level tests for both transient and legitimately-empty inputs, and 6 unit tests for the session probe classifier. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
58 lines
1.6 KiB
TOML
58 lines
1.6 KiB
TOML
[package]
|
|
name = "mangalord"
|
|
version = "0.30.0"
|
|
edition = "2021"
|
|
default-run = "mangalord"
|
|
|
|
[lib]
|
|
path = "src/lib.rs"
|
|
|
|
[[bin]]
|
|
name = "mangalord"
|
|
path = "src/main.rs"
|
|
|
|
[[bin]]
|
|
name = "crawler"
|
|
path = "src/bin/crawler.rs"
|
|
|
|
[dependencies]
|
|
axum = { version = "0.7", features = ["macros", "multipart"] }
|
|
tokio = { version = "1", features = ["full"] }
|
|
sqlx = { version = "0.8", features = ["runtime-tokio", "postgres", "uuid", "chrono", "macros", "migrate"] }
|
|
serde = { version = "1", features = ["derive"] }
|
|
serde_json = "1"
|
|
uuid = { version = "1", features = ["v4", "serde"] }
|
|
chrono = { version = "0.4", features = ["serde"] }
|
|
chrono-tz = "0.9"
|
|
tracing = "0.1"
|
|
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
|
|
tower = { version = "0.5", features = ["util"] }
|
|
tower-http = { version = "0.6", features = ["trace", "cors"] }
|
|
thiserror = "1"
|
|
anyhow = "1"
|
|
async-trait = "0.1"
|
|
dotenvy = "0.15"
|
|
argon2 = "0.5"
|
|
rand = "0.8"
|
|
sha2 = "0.10"
|
|
subtle = "2"
|
|
base64 = "0.22"
|
|
axum-extra = { version = "0.9", features = ["cookie", "typed-header"] }
|
|
time = "0.3"
|
|
infer = "0.16"
|
|
tokio-util = { version = "0.7", features = ["io"] }
|
|
futures-core = "0.3"
|
|
futures-util = "0.3"
|
|
bytes = "1"
|
|
chromiumoxide = { version = "0.7", features = ["tokio-runtime", "_fetcher-rusttls-tokio"], default-features = false }
|
|
scraper = "0.20"
|
|
reqwest = { version = "0.12", default-features = false, features = ["rustls-tls", "socks", "cookies"] }
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3"
|
|
tower = { version = "0.5", features = ["util"] }
|
|
http-body-util = "0.1"
|
|
mime = "0.3"
|
|
futures-util = "0.3"
|
|
tokio = { version = "1", features = ["test-util"] }
|