baidu-scholar-search_skill

This skill retrieves Chinese and English literature from Baidu Scholar based on keywords, returning journals, conference papers, and dissertations.

Python

2.5k

GitHub Stars

3

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill openclaw/skills --skill baidu-scholar-search

_meta.json298 B
baidu_scholar_search.sh550 B
SKILL.md2.3 KB

Overview

This skill provides a lightweight interface to Baidu Academic (Baidu Scholar) for searching Chinese and English academic literature. It retrieves structured metadata such as title, abstract, keywords, paperId, and publication type for journals, conferences, and dissertations. The skill requires a BAIDU_API_KEY in the environment and supports optional abstract retrieval and pagination.

How this skill works

Given search keywords, the skill calls the Baidu Scholar Search API endpoint and returns a list of matching records with metadata fields like title, abstract (optional), keywords, and paperId. It accepts parameters for query terms (wd), page number, and a flag to enable abstracts, then issues a GET request with the API key in the Authorization header. The API response is parsed and delivered as structured search results for downstream consumption.

When to use it

Finding Chinese or bilingual academic literature on a topic quickly
Collecting metadata for literature reviews or citation discovery
Filtering by publication types such as journals, conference papers, and dissertations
Paging through large result sets to build a corpus or index

Best practices

Set BAIDU_API_KEY securely as an environment variable and avoid embedding keys in code
Start with short, focused keywords and broaden queries iteratively to improve recall
Enable abstracts only when you need summaries to reduce payload size and speed up requests
Respect rate limits and cache frequent queries to reduce API calls and cost
Validate and normalize returned metadata (authors, dates, titles) before storing in your database

Example use cases

Researcher searches for recent work on 'machine learning interpretability' across Chinese and English sources
Library curator harvests metadata to supplement an institutional bibliography
Student locates conference papers and dissertations on a specific method or region
Data engineer batches paged queries to assemble a local search index for offline analysis

FAQ

The required parameter is wd (search keywords). Optional parameters include pageNum (default 0) and enable_abstract (default false).

How do I authenticate requests?

Provide a valid API key via the BAIDU_API_KEY environment variable and include it as an Authorization: Bearer <API_KEY> header in requests.