mirror of
https://github.com/0xMassi/webclaw.git
synced 2026-07-13 05:42:11 +02:00
02302e7a1d
Extraction ~22% faster on the corpus benchmark with byte-identical output: - hoist recompiled CSS selectors in the markdown noise path - single-pass shared og() meta parsing across vertical extractors - output-safe QuickJS gating (skip the JS VM when no candidate data) + reuse the already-parsed document instead of re-parsing - wreq connect_timeout + connection-pool tuning; dedup the retry loop Reliability + correctness: - char-boundary-safe truncation of LLM error bodies (shared helper) - HTTP connect/read timeouts on all LLM provider clients - isolate pdf-extract behind catch_unwind + spawn_blocking - OSS server: crawl inherits the shared fetch profile; ProviderChain built once in AppState; request TimeoutLayer API / safety / docs: - #[non_exhaustive] on public enums + result structs (+ builders) - #![forbid(unsafe_code)] on pure crates, deny on llm - //! crate docs + doctests; scrub bypass/vendor/target specifics from public crate docs and comments Tooling: [profile.release] lto/codegen-units/strip, MSRV pin, deny.toml + cargo-deny CI, macOS test matrix. CLI main.rs split into focused modules.
34 lines
898 B
TOML
34 lines
898 B
TOML
[package]
|
|
name = "webclaw-fetch"
|
|
description = "HTTP client with browser TLS fingerprint impersonation via wreq"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
rust-version.workspace = true
|
|
license.workspace = true
|
|
|
|
[lints]
|
|
workspace = true
|
|
|
|
[dependencies]
|
|
webclaw-core = { workspace = true }
|
|
webclaw-pdf = { path = "../webclaw-pdf" }
|
|
serde = { workspace = true }
|
|
thiserror = { workspace = true }
|
|
tracing = { workspace = true }
|
|
tokio = { workspace = true }
|
|
async-trait = "0.1"
|
|
wreq = { version = "6.0.0-rc.28", features = ["cookies", "gzip", "brotli", "zstd", "deflate"] }
|
|
wreq-util = "3.0.0-rc.10"
|
|
http = "1"
|
|
bytes = "1"
|
|
url = "2"
|
|
rand = "0.8"
|
|
quick-xml = { version = "0.37", features = ["serde"] }
|
|
regex = "1"
|
|
reqwest = { version = "0.12", default-features = false, features = ["json", "rustls-tls"] }
|
|
serde_json.workspace = true
|
|
calamine = "0.34"
|
|
zip = "2"
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3"
|