Summary
Reader and Search in one small package.
It wraps Jina's Reader and Search endpoints — clean text out of a URL, screenshots, dates and concurrent reads — in a single server. The repository is archived, so the successor its author names is worth looking at before you install this one.
What it is
A lightweight client for Jina.AI's Reader and Search APIs, covering page extraction, screenshots, publication-date detection, and web, ArXiv and image search. The repository is archived and its author points to webskim as the successor.
What you get
- A URL's content extracted as clean text, with filtering and extraction options
- A screenshot of a webpage captured
- A page's publication date detected from the page itself
- Several URLs read concurrently in one call
- Web search with advanced filtering, ArXiv paper search and image search, plus a concurrent multi-search
- A server status and system information call
Requirements
Node with npm install and npm run build, plus a Jina API key in JINA_API_KEY — free keys are issued at jina.ai/api. Jina bills the reads and searches on its own terms.
Setup effort
Build from source — clone the repository and build it, then point your client at the binary