mirror of
https://github.com/0xMassi/webclaw.git
synced 2026-06-17 23:55:13 +02:00
179efbcf87
Rescued from the stale perf/audit-fixes branch and ported cleanly onto current main (fetch + CLI only — the original commit never touched the server/MCP map surfaces). `--map` used to return only what a site advertises in sitemap.xml, which is nothing for sites with no sitemap (e.g. Hacker News) or a thin one. Now discovery is layered: - webclaw-fetch::discover_urls() / MapOptions — sitemaps first (authoritative, carries lastmod/priority/changefreq); when the sitemap is thin (< min_sitemap_urls) and the fallback is enabled, run a bounded same-origin crawl and harvest links from every fetched page plus the unfetched frontier, deduped against the sitemap set. - sitemap.rs: gzip (.xml.gz) support via a new decode_sitemap_body() + FetchClient::fetch_raw() (raw bytes, no lossy UTF-8); deeper index recursion (3->5); 4 more fallback paths. - CLI: --map-pages / --no-map-crawl / --map-limit; crawler logs now go to stderr so `--map -f json` stays machine-parseable. One new dependency: flate2 (already resolved in the lockfile transitively). Includes the commit's unit tests (map dedup/origin, gzip decode). Original work by the prior author on perf/audit-fixes; this re-applies only the map slice onto main. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
38 lines
1.3 KiB
TOML
38 lines
1.3 KiB
TOML
[package]
|
|
name = "webclaw-fetch"
|
|
description = "HTTP client with browser TLS fingerprint impersonation via wreq"
|
|
version.workspace = true
|
|
edition.workspace = true
|
|
license.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"
|
|
# Pinned to exact pre-release versions: wreq/wreq-util are release candidates
|
|
# with no semver stability between rc.N builds. An exact pin keeps `cargo build`,
|
|
# `cargo install` (which ignores Cargo.lock), and the release workflow all on the
|
|
# version that compiles.
|
|
wreq = { version = "=6.0.0-rc.29", features = ["cookies", "gzip", "brotli", "zstd", "deflate", "stream"] }
|
|
wreq-util = "=3.0.0-rc.12"
|
|
http = "1"
|
|
bytes = "1"
|
|
# Stream adapter for `wreq::Response::bytes_stream()` (wreq 6.0.0-rc.29 dropped
|
|
# `Response::chunk()`); used to buffer bodies under the running size ceiling.
|
|
futures-util = "0.3"
|
|
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"
|
|
flate2 = "1"
|
|
|
|
[dev-dependencies]
|
|
tempfile = "3"
|