dsh-scrape-webpage
网页抓取与分析插件:抓取网页正文并给出统计与关键词分析,支持内容图片下载与识图分析器扩展接口。
7 results
网页抓取与分析插件:抓取网页正文并给出统计与关键词分析,支持内容图片下载与识图分析器扩展接口。
Web page reader for DeepSeek Harness (dsh): fetch any URL and extract clean markdown or plain text, inventory links, read RSS/Atom feeds, and inspect HTTP headers without the body — zero runtime dependencies
Keyless web-search provider for DeepSeek Harness (dsh): DuckDuckGo + Startpage scrapers and Perplexity's anonymous ask endpoint behind a consensus fan-out. No API keys, no signup, no quota owner.
DeepSeek Harness plugin: intercept a page's real data APIs (XHR/fetch JSON) and return structured fields — comments, rankings, prices, tables — with token-efficient field extraction. Requires playwright.
HTML 解析:从 HTML 提取标题/meta/标题层级/链接/表格/纯文本等结构化数据
Firecrawl web providers for DeepSeek Harness: search the web and scrape pages to clean markdown through ctx.web
浏览今日头条文章的实战经验打包成 DSH 插件:webfetch 工具(三级策略:直连 → Edge 常驻无头浏览器 CDP → dump-dom 兜底,自动识别头条反爬质询页)+ toutiao-reader 技能(URL 形态、质询处理、常驻浏览器管理、沙箱与代理经验)。