[package]
edition = "2024"
name = "web2llm"
version = "0.1.1"
build = false
autolib = false
autobins = false
autoexamples = false
autotests = false
autobenches = false
description = "Fetch web pages and convert to clean Markdown for LLM pipelines"
homepage = "https://github.com/Quippy22/web2llm"
readme = "README.md"
keywords = [
"web",
"scraping",
"markdown",
"llm",
"rag",
]
categories = [
"web-programming",
"text-processing",
]
license = "MIT"
repository = "https://github.com/Quippy22/web2llm"
[lib]
name = "web2llm"
path = "src/lib.rs"
[[example]]
name = "basic"
path = "examples/basic.rs"
[[example]]
name = "batch"
path = "examples/batch.rs"
[[test]]
name = "batch"
path = "tests/batch.rs"
[[test]]
name = "content_scoring"
path = "tests/content_scoring.rs"
[[test]]
name = "pipeline"
path = "tests/pipeline.rs"
[[bench]]
name = "extraction"
path = "benches/extraction.rs"
harness = false
[dependencies.chrono]
version = "0.4.44"
[dependencies.futures]
version = "0.3.32"
[dependencies.governor]
version = "0.10.4"
[dependencies.htmd]
version = "0.5.0"
[dependencies.reqwest]
version = "0.13"
features = ["native-tls"]
[dependencies.scraper]
version = "0.25.0"
[dependencies.texting_robots]
version = "0.2.2"
[dependencies.thiserror]
version = "2.0.18"
[dependencies.tokio]
version = "1.50.0"
features = ["full"]
[dependencies.url]
version = "2.5.8"
[dev-dependencies.criterion]
version = "0.8.2"
features = [
"html_reports",
"async_tokio",
]
[dev-dependencies.tempfile]
version = "3.10"
[dev-dependencies.wiremock]
version = "0.6.5"