[package]
edition = "2021"
name = "docrawl"
version = "0.1.5"
build = false
exclude = [
".git*",
".github",
"target",
"out",
"out_*",
"*.log",
]
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Docs-focused crawler library and CLI: crawl documentation sites, extract main content, convert to Markdown, mirror paths, and save with frontmatter."
homepage = "https://github.com/neur0map/docrawl"
documentation = "https://docs.rs/docrawl"
readme = "README.md"
keywords = [
"crawler",
"docs",
"markdown",
"scraping",
"http",
]
categories = [
"command-line-utilities",
"web-programming::http-client",
"parsing",
"text-processing",
]
license = "MIT"
repository = "https://github.com/neur0map/docrawl"
[lib]
name = "docrawl"
path = "src/lib.rs"
[[bin]]
name = "docrawl"
path = "src/bin/docrawl/main.rs"
[[example]]
name = "benchmark"
path = "examples/benchmark.rs"
[[example]]
name = "comparison_benchmark"
path = "examples/comparison_benchmark.rs"
[[example]]
name = "programmatic"
path = "examples/programmatic.rs"
[dependencies.async-trait]
version = "0.1"
[dependencies.bytes]
version = "1"
[dependencies.chrono]
version = "0.4"
features = ["serde"]
[dependencies.clap]
version = "4"
features = ["derive"]
[dependencies.fast_html2md]
version = "0.0.48"
[dependencies.futures]
version = "0.3.31"
[dependencies.governor]
version = "0.6"
[dependencies.indicatif]
version = "0.18"
[dependencies.lol_html]
version = "2.6"
[dependencies.pathdiff]
version = "0.2"
[dependencies.regex]
version = "1"
[dependencies.reqwest]
version = "0.12"
features = [
"json",
"gzip",
"brotli",
"deflate",
"cookies",
"stream",
]
[dependencies.reqwest-middleware]
version = "0.4"
[dependencies.reqwest-retry]
version = "0.7"
[dependencies.robotstxt]
version = "0.3"
[dependencies.scraper]
version = "0.24"
[dependencies.serde]
version = "1"
features = ["derive"]
[dependencies.serde_json]
version = "1"
[dependencies.sitemap]
version = "0.4"
[dependencies.sled]
version = "0.34"
[dependencies.tokio]
version = "1"
features = ["full"]
[dependencies.tracing]
version = "0.1"
[dependencies.tracing-subscriber]
version = "0.3"
[dependencies.url]
version = "2.5"
[dependencies.uuid]
version = "1"
features = ["v4"]
[dependencies.xxhash-rust]
version = "0.8"
features = ["xxh3"]