Pricing

from $2.00 / 1,000 results

Try for free

Go to Apify Store

Research Scraper

Try for free

One actor, 8 science databases: PubMed, arXiv, OpenAlex, Crossref, Europe PMC, DOAJ, Zenodo and OSF. Get plain-language summaries, open-access full text, translation to any language, citation counts, BibTeX/RIS and ISO-standardized output ready for RAG/LLM.

Pricing

from $2.00 / 1,000 results

Rating

0.0

(0)

Developer

Marlon Vasquez

Actor stats

Bookmarked

Total users

Monthly active users

a month ago

Last modified

Research Scraper — 8 Science Databases in One

Research paper scraper that searches PubMed, arXiv, OpenAlex, Crossref, Europe PMC, DOAJ, Zenodo and OSF in a single run, and returns structured scholarly data with summaries, full text, citations and translations.

Search scientific papers from 8 databases at once

Give it a topic and get papers from all sources, deduplicated, with citations. Perfect for literature reviews, meta-analyses, and building RAG/LLM datasets from scientific literature.

PubMed scraper + arXiv + OpenAlex + Crossref

Feature	This Actor	Typical scrapers
Sources	8 databases	only one
Citation counts + sort by citations	✅	❌
Deduplication across sources	✅	—
BibTeX / RIS export	✅	❌
Plain-language summary	✅	❌
Open-access full text (PMC)	✅	❌
Translation to ANY language	✅	❌
ISO standardization	✅	❌
Free tier (first 10 results free)	✅	❌

Translate papers into any language

Set targetLanguage to any ISO code (es, fr, de, pt, zh-CN, ja, ar, hi, ru, tr…) and the Actor translates the title, abstract and summary.

ISO-standardized output

Every article is normalized to open standards: ISO 639 (language), ISO 8601 (dates), ISSN (ISO 3297), ISO 4 (journal abbreviation), ISO 690 and APA citations, plus a standardization score (0-100).

RAG-ready output

Each item includes a clean markdown field and chunks (text split for retrieval), ready for LLM pipelines.

Input

Field	Type	Default	Description
`queries`	string[]	—	Search terms
`sources`	string[]	pubmed, arxiv, openalex, crossref, europepmc, doaj, zenodo, osf	Databases
`maxResults`	int	20	Total results
`targetLanguage`	string	`en`	Any language
`sortBy`	string	relevance	or `citations`
`freeTier`	int	10	First N results free

Pricing

Pay per event. The first 10 results of a run are free — only results beyond that are charged.

Use it from your stack (integration-ready)

MCP / AI agents — discoverable via the Apify MCP server (Claude, Cursor, etc.).
n8n / Make / Zapier — run it as a node/step and pass queries.
LangChain / LlamaIndex — load papers (markdown + chunks) as documents for RAG.
Google Sheets / Airbyte — push the dataset straight into your sheets or warehouse.
API — POST https://api.apify.com/v2/acts/vexmeavf~research-scraper/run-sync-get-dataset-items with your token.

Schedule recommendation

Run daily or weekly to monitor new publications on your topics (ideal with Apify Schedules).

FAQ

Is there a free API key needed? No. All 8 sources use free public APIs.

Can I get the full text of the papers? Yes, for open-access articles (fetched from PMC).

What is this good for? Literature reviews, research monitoring, and building datasets of scientific papers for AI models.

Can I export citations? Yes — ISO 690, APA, BibTeX and RIS are included per article.

Academic Research MCP | 6 Tools: OpenAlex, PubMed, arXiv

themineworks/academic-research-mcp

Scholarly search for AI agents: OpenAlex works, Crossref metadata, arXiv preprints, OpenCitations graphs and PubMed, behind one MCP endpoint. No result, no charge.

The Mine Works

OpenAlex Academic Research Scraper

gentle_cloud/openalex-research-scraper

Search and extract academic paper metadata from the OpenAlex API. Supports keyword search, author search, institution filter, and citation analysis. Free, no API key required. 250M+ scholarly works.

Monkey Coder

Deep Research MCP - Web Search for AI Agents

renzomacar/deep-research-mcp

Give your AI agent the web: multi-source search, clean-markdown page reading, and one-call deep research dossiers. No OpenAI/Perplexity key required — your agent does the synthesis. MCP server, pay-per-event.

Renzo Madueno

SpringerLink Scraper — Journals, Books & Conference Papers

trev0n/springerlink-scraper

Scrape SpringerLink journals, books and conference papers: abstracts, author keywords, full author lists with affiliations and ORCIDs, open-access status, PDF links and exact citation counts. Includes incremental monitoring that emits only new or updated papers.

Paweł

Mcp Research Server

fiery_dream/mcp-research-server

AI-powered research assistant with web search, academic search, and document Q&A capabilities. Can operate as an MCP server for AI clients or in direct query mode.

Cody Churchwell

Academic Research & Papers Scraper (OpenAlex)

rupom888/academic-research-scraper

Search 200M+ academic papers, researchers, and institutions via OpenAlex API. Completely free, no API key needed. Get paper titles, abstracts, DOIs, citations, authors, open access links, and concepts. Filter by year, paper type, open access, and field of study.

Syed Rupom

AI RAG Feeder V2

mickeywmoore/ai-rag-feeder-v2

Turn any website into AI-ready Markdown. Scrapes entire domains, removes ads/clutter, and formats text specifically for RAG pipelines and LLM training data.

Mickey Moore

LLM-Ready Web Scraper

devoted_helix/llm-web-scraper

Convert web pages to clean, LLM-friendly text. Perfect for RAG pipelines, AI chatbot training, and fine-tuning datasets. Removes ads,menus, and clutter automatically.

batuhan senavci

arXiv Research Trend Monitor

glowing_glove/arxiv-research-trend-monitor

Track arXiv research topics and extract recent papers, authors, categories, abstracts, and research trend signals for AI and market research.

Ushba Khan

PubMed Research Paper Intelligence

wakey7dev/pubmed-research-normalizer

Search PubMed for biomedical literature — titles, abstracts, authors, MeSH terms. 36M+ citations. Pharma research, healthcare, academic literature reviews.