类库
› webclaw
0xMassi/webclaw
Webclaw是一个基于Rust的高性能本地优先网页内容提取工具,专为LLM设计。它支持CLI、REST API和MCP服务器,能将网页快速转换为干净的Markdown或JSON格式,适用于AI代理和RAG管道,解决传统爬虫输出杂乱或受限的问题。
标签
技术栈
crates/webclaw-cli rust
异步运行时
Tokio
查看全部依赖 (10)
依赖
clap
dotenvy
rand
0.8
serde_json
tracing
tracing-subscriber
webclaw-core
webclaw-fetch
webclaw-llm
webclaw-pdf
crates/webclaw-core rust
异步运行时
Tokio
查看全部依赖 (6)
依赖
ego-tree
0.10
scraper
0.22
serde
serde_json
thiserror
tracing
crates/webclaw-fetch rust
异步运行时
Tokio
查看全部依赖 (7)
依赖
async-trait
0.1
serde
thiserror
tracing
webclaw-core
webclaw-pdf
开发依赖
tempfile
3
crates/webclaw-mcp rust
查看全部依赖 (4)
依赖
webclaw-core
webclaw-fetch
webclaw-llm
webclaw-pdf
crates/webclaw-pdf rust
查看全部依赖 (3)
依赖
pdf-extract
0.7
thiserror
tracing
crates/webclaw-server rust
查看全部依赖 (4)
依赖
webclaw-core
webclaw-fetch
webclaw-llm
webclaw-pdf
截图