c33f30972e
Four crawler defences in one PR (all four threats the review flagged in §3 of REVIEW.md): - New crawler::safety module with is_safe_url + accumulate_capped + fetch_bytes_capped. Rejects non-http(s) schemes, RFC1918 / loopback / link-local / CGNAT / ULA / IPv6-link-local hosts, and any host not on the operator's allowlist (defaults to CRAWLER_START_URL host + CRAWLER_CDN_HOST + CRAWLER_DOWNLOAD_ALLOWLIST extras). - Streaming size cap (CRAWLER_MAX_IMAGE_BYTES, default 32 MiB) so a 10 GiB \"image\" can't fill memory before disk. - looks_like_image() reject path: non-image bytes fail the chapter or cover instead of being stored as .bin and served as application/octet-stream. - session::classify_chapter_probe: three-way classifier replaces the binary #avatar_menu check at content.rs:115. A transient hiccup (broken-page body, or logged-in-but-no-reader) now retries with backoff instead of falsely freezing every worker on session_expired. 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 = "0.34.1"
|
|
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", "stream"] }
|
|
|
|
[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"] }
|