[package]
edition = "2021"
rust-version = "1.88"
name = "rust_scrapling"
version = "0.4.1"
authors = ["Liohtml"]
build = false
exclude = [
"docs/",
"scripts/",
".github/",
".claude/",
]
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Modern web scraping: spiders, CSS selectors, robots.txt/AutoThrottle politeness, and LLM/RAG-ready Markdown extraction - a Rust port of Scrapling"
homepage = "https://github.com/Liohtml/RUSTScrapling"
documentation = "https://docs.rs/rust_scrapling"
readme = "README.md"
keywords = [
"scraping",
"web-scraping",
"crawler",
"rag",
"llm",
]
categories = [
"web-programming",
"parser-implementations",
"command-line-utilities",
]
license = "MIT OR Apache-2.0"
repository = "https://github.com/Liohtml/RUSTScrapling"
[lib]
name = "rust_scrapling"
path = "src/lib.rs"
[[bin]]
name = "rust_scrapling"
path = "src/main.rs"
[[example]]
name = "benchmark"
path = "examples/benchmark.rs"
[[test]]
name = "core_attributes_handler"
path = "tests/core_attributes_handler.rs"
[[test]]
name = "core_storage"
path = "tests/core_storage.rs"
[[test]]
name = "core_text_handler"
path = "tests/core_text_handler.rs"
[[test]]
name = "engine_crawl"
path = "tests/engine_crawl.rs"
[[test]]
name = "fetchers_client"
path = "tests/fetchers_client.rs"
[[test]]
name = "fetchers_config"
path = "tests/fetchers_config.rs"
[[test]]
name = "integration_test"
path = "tests/integration_test.rs"
[[test]]
name = "parser_adaptive"
path = "tests/parser_adaptive.rs"
[[test]]
name = "parser_selector"
path = "tests/parser_selector.rs"
[[test]]
name = "parser_selector_generation"
path = "tests/parser_selector_generation.rs"
[[test]]
name = "spiders_links"
path = "tests/spiders_links.rs"
[[test]]
name = "spiders_request"
path = "tests/spiders_request.rs"
[[test]]
name = "spiders_result"
path = "tests/spiders_result.rs"
[[test]]
name = "spiders_scheduler"
path = "tests/spiders_scheduler.rs"
[[test]]
name = "spiders_session"
path = "tests/spiders_session.rs"
[[test]]
name = "spiders_shopify"
path = "tests/spiders_shopify.rs"
[[test]]
name = "spiders_templates"
path = "tests/spiders_templates.rs"
[dependencies.async-trait]
version = "0.1"
[dependencies.clap]
version = "4"
features = ["derive"]
[dependencies.cssparser]
version = "0.37"
[dependencies.ego-tree]
version = "0.11"
[dependencies.encoding_rs]
version = "0.8"
[dependencies.env_logger]
version = "0.11"
[dependencies.flate2]
version = "1"
[dependencies.indexmap]
version = "2"
features = ["serde"]
[dependencies.log]
version = "0.4"
[dependencies.percent-encoding]
version = "2"
[dependencies.regex]
version = "1"
[dependencies.reqwest]
version = "0.12"
features = [
"json",
"cookies",
"gzip",
"brotli",
"deflate",
"rustls-tls",
]
[dependencies.rusqlite]
version = "0.40"
features = ["bundled"]
[dependencies.scraper]
version = "0.27"
[dependencies.serde]
version = "1"
features = ["derive"]
[dependencies.serde_json]
version = "1"
features = ["preserve_order"]
[dependencies.sha2]
version = "0.11"
[dependencies.tempfile]
version = "3"
[dependencies.thiserror]
version = "2"
[dependencies.tokio]
version = "1"
features = [
"rt-multi-thread",
"macros",
"time",
"sync",
"fs",
]
[dependencies.url]
version = "2"
[dev-dependencies.proptest]
version = "1"
[dev-dependencies.tokio]
version = "1"
features = [
"net",
"io-util",
]