skills.rest
wentorai
wentoraiCOMMUNITY
Explore all skills by this author →
GitHub

cnki-parse-results

Extract structured paper metadata from CNKI search results pages via browser JavaScript.

850|114|Updated Mar 9, 2026
Search Tags:#literature review#academic search#Browser Automation#parse#cnki#bibliographic data#Web scraping
One-click install
npx skills add https://github.com/wentorai/Research-Claw --skill cnki-parse-results
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: cnki-parse-results
Source: https://github.com/wentorai/Research-Claw/tree/main/skills/cnki-parse-results
Command: npx skills add https://github.com/wentorai/Research-Claw --skill cnki-parse-results

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Manually copying paper titles, authors, journals, and citation counts from CNKI search results is slow and error-prone. This Skill automates the extraction of structured bibliographic data from an open CNKI results page using browser automation.

Core Features & Use Cases

  • Structured Extraction: Parses each result row into title, URL, authors, journal, date, database type, citations, downloads, and online-first status.
  • Captcha & Page Validation: Verifies the current page is a CNKI results page and alerts the user when a captcha requires manual solving.
  • Fallback Parsing: Falls back to accessibility-tree snapshot parsing when the DOM structure changes and JavaScript selectors return empty.
  • Use Case: After running a CNKI literature search, ask the agent to extract all 20 results on the page into a numbered list with citation counts for building a literature review.

Quick Start

Parse the current CNKI search results page and list all papers with their authors, journals, and citation counts.

Frequently Asked Questions about cnki-parse-results

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I extract paper data from CNKI search results?▼

Open the CNKI search results page in the managed Chrome browser, then run this Skill. It executes JavaScript against the .result-table-list DOM to extract titles, authors, journals, dates, citations, and downloads into a structured numbered list.

What data fields can be parsed from a CNKI results page?▼

The extraction returns title, URL, export ID, authors, journal, publication date, database type, citation count, download count, and online-first status for each paper, plus total result count and page info.

Does CNKI scraping work when a captcha appears?▼

No, automated extraction pauses when CNKI shows the sliding puzzle captcha. The Skill detects the captcha text and notifies you to solve it manually in the browser before continuing.

Why does CNKI parsing return empty results?▼

Empty results usually mean the DOM structure changed or the page is not a results page. The Skill falls back to snapshot-based parsing of the accessibility tree, looking for title, author, and journal link patterns.

Can I use this without the RC browser tool?▼

No, the Skill depends on the RC browser tool's managed Chrome instance on CDP port 18800. It uses browser actions like evaluate and snapshot, so a standalone script or other browser profile will not work.

Related Skills

Explore More Education & Research Skills→
cookjohncookjohn
19

pm-search

Search PubMed via NCBI E-utilities and return structured PMIDs and metadata.

Community
Intermediate
echo-iceecho-ice

reference-manager

Verify references in mathematical contest papers and generate BibTeX entries.

Community
Advanced
Victory-HugoVictory-Hugo
1

citation-management

Convert bibliographic identifiers into structured BibTeX entries.

Community
Advanced
Luqman-Ud-DinLuqman-Ud-Din

qa-test-export

Detect broken export and download controls on data-driven web pages.

Community
Advanced