skills.rest
ptreezh
ptreezhCOMMUNITY
Explore all skills by this author →
GitHub

pubscholar-auto-search

Automate PubScholar searches with adaptive query expansion and JSON/CSV metadata export.

24|7|Updated Nov 15, 2025
Search Tags:#web-automation#metadata-extraction#literature-search#keyword-expansion#pubscholar#chinese-academia
One-click install
npx skills add https://github.com/ptreezh/sscisubagent-skills --skill pubscholar-auto-search
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: pubscholar-auto-search
Source: https://github.com/ptreezh/sscisubagent-skills/tree/main/skills/pubscholar-auto-search
Command: npx skills add https://github.com/ptreezh/sscisubagent-skills --skill pubscholar-auto-search

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires playwright, beautifulsoup4, lxml, pandas, openpyl, requests, aiohttp, python-dotenv, csv, json, re, asyncio, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill removes the manual effort of searching PubScholar for Chinese academic resources by automating query submission, adaptive keyword expansion when results are insufficient, and structured metadata extraction.

Core Features & Use Cases

  • PubScholar web search automation: Runs browser-based searches on https://pubscholar.cn for Chinese papers, literature, patents, and related documents.
  • Two-stage retrieval with result-threshold expansion: Performs a precise search first, then automatically expands keywords when the number of results is below a configurable minimum.
  • Structured metadata extraction & export: Collects paper fields such as title, authors, journal, year, abstract, keywords, and source URL, and supports exporting to JSON/CSV.

What problem does it solve? (example scenario)

You need 20+ Chinese literature entries for a topic like “数字鸿沟 教育”; run this Skill so it searches precisely, expands synonyms/English translations when results are low, and returns deduplicated structured records ready for analysis or citation formatting.

Quick Start

Tell the AI to search PubScholar for Chinese papers about digital divide in education and return structured results with automatic expansion until at least 5 results are found.

Frequently Asked Questions about pubscholar-auto-search

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

FAQPage Schema
How do I automate PubScholar searches for Chinese academic literature?▼

Automate PubScholar searches by using Playwright-driven browser automation to submit queries, extract structured metadata like title and authors, and export deduplicated records to JSON or CSV.

What is adaptive keyword expansion for retrieving Chinese papers?▼

Adaptive keyword expansion is a two-stage retrieval mechanism that performs a precise search first, then automatically expands synonyms and English translations when initial PubScholar results fall below a configured minimum threshold.

How do I extract structured metadata from Chinese academic resources?▼

Extract structured metadata from Chinese academic resources by scraping PubScholar search results to collect fields like title, authors, journal, year, abstract, keywords, and source URL, then deduplicate records by URL.

Can I batch search multiple Chinese paper topics and export results to CSV?▼

Yes, you can perform batch topic searches on PubScholar and export the extracted literature metadata, including patents and conference papers, directly to structured CSV or JSON files for analysis.

Does PubScholar automation work for finding Chinese patents and conference papers?▼

Yes, PubScholar automation works for finding Chinese patents and conference papers by running browser-based web searches on pubscholar.cn to retrieve various academic documents with structured metadata extraction.

What are the limitations of using Playwright for PubScholar literature search?▼

Limitations of using Playwright for PubScholar literature search include the requirement of a browser automation environment and dependencies like beautifulsoup4 and lxml, which may face issues if the website's DOM structure changes unexpectedly.

Related Skills

Explore More Education & Research Skills→
bitwize-music-studiobitwize-music-studio
408

setup

Detect Python environments and configure venv dependencies for the Claude Music plugin.

Official
Intermediate
silvainfmsilvainfm
2

duckdb

Run SQL analytics directly on CSV, Parquet, and JSON files and Pandas or Polars DataFrames.

Community
Advanced
valalavvalalav

zolka_search

Search zolka.ru genealogical sections for surnames and retrieve matching snippets and links.

Community
Intermediate
u9401066u9401066

literature-search

Search PubMed and Zotero literature with keyword queries and MeSH expansion.

Community
Intermediate