shidianguji-fetcher

To convert Shidianguji literature into Markdown, this skill automates the extraction of full books or specific chapters from provided URLs and merges them into structured Markdown files. It bypasses the platform's unstable internal search by directly fetching the web pages.

Yes, you can batch download ancient texts and search them locally. The skill builds a local corpus of historical and philosophical Chinese classics, enabling offline keyword searches across your downloaded Markdown collection for research workflows.

Yes, you need a Node.js runtime to scrape Shidianguji books. The skill relies on Node.js with the undici package for network requests and linkedom for HTML parsing to automate the web scraping and data archiving process.

Automated web scraping handles unstable Shidianguji search functionality by directly navigating to specific book or chapter URLs. It uses undici for network requests and linkedom for HTML parsing to extract content, bypassing the need for the platform's internal search.

The best way to archive ancient Chinese classics for offline analysis is using automated retrieval tools that convert web content into structured Markdown. This skill downloads full texts and enables local context keyword searching without relying on the source website.

When extracting classical texts, limitations of using linkedom for HTML parsing include dependency on the Shidianguji website's current HTML structure. If the platform changes its web page layout or blocks automated requests, the web scraping and Markdown conversion process may fail.