Decodo/dsh-web-fetch ↗★ 0

@decodo/dsh-web-fetch

使用Decodo API作为网页抓取工具的底层驱动 适合需要让AI抓取和分析复杂网页内容的用户,需自备Decodo账号及Token。

包名
@decodo/dsh-web-fetch
兼容性
待验证
Harness 依赖范围
>=0.1.2-rc.1 <0.3.0
版本
1.0.1
许可证
MIT
最近更新
2026年10月1日

安装

$npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Decodo/dsh-web-fetch

Configuration

Override in your profile's cordis.patch.yml. A patch replaces the row's whole config, so restate every field you want to keep.

- id: web-fetch-decodo
  config:
    tokenEnv: SCRAPER_API_TOKEN   # env var holding the Web Scraping API Basic Auth token
    output: markdown              # markdown (default) or html
    maxFetchesPerSession: 200     # fetch limit per dsh process; 0 disables
    maxContentChars: 200000       # body cap; longer bodies are cut and flagged truncated
    requestTimeoutMs: 60000       # request timeout, keep at or below the tool's fetchTimeoutMs
FieldDefaultMeaning
tokenEnvSCRAPER_API_TOKENEnv var holding the Web Scraping API Basic Auth token; sent as Basic Auth
outputmarkdownmarkdown for Decodo's Markdown, html for the raw page
maxFetchesPerSession200Requests allowed per dsh process; 0 disables the cap
maxContentChars200000Body cap; longer bodies are cut and flagged truncated
requestTimeoutMs60000Request timeout

With output: markdown, the plugin requests Markdown from Decodo. When conversion succeeds, the plugin passes the result to the model unchanged. If the page is too large or empty, or if conversion fails, Decodo returns raw HTML with a note. DeepSeek Harness then converts the HTML. With output: html, Decodo always returns raw HTML for DeepSeek Harness to convert.