dsh-webfetch
Web page reader for DeepSeek Harness (dsh): fetch any URL and extract clean markdown or plain text, inventory links, read RSS/Atom feeds, inspect HTTP headers without the body, and extract HTML tables as structured rows — zero runtime dependencies 适合网页内容抓取与信息提取任务,提供干净的文本和结构化数据。
설치
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:TYEclipse/dsh-webfetchConfiguration
All settings are optional (defaults shown):
plugins:
dsh-webfetch:
timeoutMs: 10000 # per-request timeout (1000–60000)
maxBytes: 1500000 # response size cap in bytes (10000–5000000)
maxChars: 50000 # extracted content cap in chars (1000–200000)
maxRedirects: 3 # redirect hops to follow (0–10)
userAgent: "dsh-webfetch/0.3 (DeepSeek Harness plugin)"