Google Scholar Scraper

Papers & Citations — academic paper records with citation counts, authors, venues, DOIs and open-access links (source: OpenAlex, ~250M works including arXiv preprints).

📊 What you get

Clean JSON, one dataset row per paper (16 fields):

• title — Paper title
• abstract — Abstract (reconstructed)
• year / publicationDate — Publication year and date
• citationCount — Citations to date
• referenceCount — Works referenced
• authors / authorCount — Author list (first 10) and total
• venue — Journal or conference
• url / openAccessPdf — Landing page and free PDF when available
• doi / arxivId / paperId — Identifiers
• source — openalex.org

In Research Tracker mode each row also carries citationTier, citationsPerYear, recency, paperAge, hasOpenAccess, hasDOI, abstractLength, abstractDetail, and the run-level landscape report (citation stats, year/venue/author distributions, top papers, auto-insights) is written to the run's key-value store under OUTPUT — it is a summary, not a paper, so it is never placed in the dataset and never billed as a result.

Pricing: $0.040 per paper (Pay-Per-Event) — about 25 papers per $1. Runs that return no papers (empty search, missing query) deliver 0 rows and are not charged per result.

🤖 Use with AI agents

Point Claude, the OpenAI Agents SDK, an n8n flow or any MCP-aware client at it.

Sample agent prompt:

Run Google Scholar Scraper on my input and return the structured results.

Sample input:

{ "query": "large language models", "maxResults": 25, "outputMode": "tracker" }

Agentic payments (x402): Supports agentic payment via x402 — call this actor with USDC, no API key required.

🔗 Related tools — Academic research tools

PubMed Research

A NexGenData utility actor.