dsh-webfetch
纯文本 agent 的网页阅读工具。五个只读工具：web_fetch（把任意 URL 渲染成干净的 Markdown 或纯文本）、web_links（清单页内链接）、web_feed（RSS 2.0 / Atom 条目解析）、web_headers（不下正文即取 HTTP 状态、响应头与重定向链，HEAD 失败自动回退 GET）、web_table（把 HTML 表格抽成结构化行，含表头识别与 colspan/rowspan 网格展开）。传输层为 Node fetch 加一套零依赖 HTTP 代理实现（CONNECT 隧道、绝对 URI 请求、NO_PROXY 的后缀/通配/IPv4 CIDR 匹配、Proxy-Authorization）。零运行时依赖。
Web reading tools for text-only agents. Five read-only tools: web_fetch (any URL rendered as clean Markdown or plain text), web_links (inventory of a page's links), web_feed (RSS 2.0 / Atom entries), web_headers (HTTP status, response headers and redirect chain without downloading the body, HEAD with automatic GET fallback), and web_table (HTML tables extracted as structured rows with header detection and colspan/rowspan grid expansion). Transport is Node fetch plus a zero-dependency HTTP proxy implementation (CONNECT tunnelling, absolute-URI requests, NO_PROXY with suffix/wildcard/IPv4-CIDR matching, Proxy-Authorization). Zero runtime dependencies.
怎么安装
dsh plugin add github:TYEclipse/dsh-webfetch 简介
dsh-webfetch 为 DeepSeek Harness 智能体装上「阅读器」：给定 URL，抓取网页并提取干净的 Markdown / 纯文本正文，附带链接清单、RSS/Atom 订阅源解析与网页表格结构化提取。零运行时依赖，只读，不发送任何凭证。 English | 中文简介 A web page reader plugin for DeepSeek Harness (dsh). dsh agents can search, but until now they could not *read the page behind a URL*. dsh-webfetch closes that gap with five read-only tools and **zero runtime dependencies** (Node built-ins + global fetch only). Tools web_fetch Fetch a web page and extract its readable content. | Parameter | Type | Default | Description | | ------------- | -------------------- | ---------- | ----------------------------…
推荐参考
信息
- 协议
- MIT
- 语言
- TypeScript
- GitHub 星标
- 2
- 月下载
- –
- 最近更新
- 2026-09-16
- 创建于
- 2026-08-13
基础安全检查
- 检查结果
- curated 收录但无 npm 包/安装命令
- 收录来源
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- 主题标签
- deepseek-harness, dsh-plugin, feed-reader, html-table, http-headers, proxy, redirects, rss, table-extraction, web-scraping