
Cnki Advanced Search
This automates CNKI's old-style advanced search interface with proper field filters and source category checkboxes (SCI, EI, CSSCI, 北大核心), which the newer interface lacks. It handles the full form logic: subject/title/keyword fields, multi-row boolean queries, author and journal filters, date ranges, and source type selection. The implementation is a single async script that fills the form, submits, waits for results, and returns the count and URL. Use this when you need precise filtered searches beyond basic keywords. It includes captcha detection and verified selectors for all form elements. Works with the companion parse and navigation skills for complete result extraction.
- skills.sh installs
- 760
- GitHub stars
- 1.1K
- last updated
- Aug 21, 2026
Install
$ npx -y skills add cookjohn/cnki-skills --skill cnki-advanced-search --agent claude-codeInstalls into .claude/skills of the current project.
Files
CNKI Advanced Search (高级检索)
Perform a filtered search on CNKI using the old-style advanced search interface (only interface with source category checkboxes).
Arguments
$ARGUMENTS describes the search criteria in natural language. Parse it to identify:
- Subject keywords (主题) — default field
- Title keywords (篇名)
- Keywords (关键词)
- Author name (作者) — separate field
#au_1_value1 - Journal/source (文献来源) — separate field
#magazine_value1 - Date range (时间范围) —
#startYear/#endYear - Source category (来源类别:SCI, EI, 北大核心, CSSCI, CSCD)
Steps
1. Navigate
Use mcp__chrome-devtools__navigate_page → https://kns.cnki.net/kns/AdvSearch?classid=7NS01R8M
2. Search + get results (single async evaluate_script)
Replace placeholder values with actual search criteria:
Sponsors
Details
- Repository
- github.com/cookjohn/cnki-skills
- First seen
- Jun 3, 2026