
Cnki Parse Results
Pulls structured paper metadata from CNKI search results pages into a clean format you can actually work with. It extracts titles, authors, journals, publication dates, citation counts, and download stats by running JavaScript against CNKI's DOM, which apparently uses stable jQuery selectors. Falls back to parsing the accessibility tree if the DOM structure changes. Handles the typical CNKI quirks like captcha detection and those "网络首发" (online first) labels. Useful when you're doing literature reviews or building datasets from Chinese academic sources and don't want to manually copy paste from CNKI's interface. The selector table in the source is genuinely helpful if you ever need to modify the extraction logic.
- skills.sh installs
- 403
- GitHub stars
- 1.1K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add cookjohn/cnki-skills --skill cnki-parse-results --agent claude-codeInstalls into .claude/skills of the current project.
Files
CNKI Parse Search Results
Extract structured paper data from the current CNKI search results page.
Prerequisites
The current Chrome page must be a CNKI search results page (URL contains kns.cnki.net and page shows "条结果").
Steps
1. Verify we are on a results page
Use mcp__chrome-devtools__take_snapshot. Verify the page contains "条结果". If not, inform the user that no search results page is currently open.
Check for captcha ("拖动下方拼图完成验证") - if found, notify user to solve it manually.
2. Extract results via JavaScript
Use mcp__chrome-devtools__evaluate_script with this function:
Sponsors
Details
- Repository
- github.com/cookjohn/cnki-skills
- First seen
- Jun 3, 2026