pip install crossref-local

git clone https://github.com/ywatanabe1989/crossref-local
cd crossref-local && make install

# 1. Download CrossRef data (~100GB compressed)
aria2c "https://academictorrents.com/details/..."

# 2. Build SQLite database (~days)
pip install dois2sqlite
dois2sqlite build /path/to/crossref-data ./data/crossref.db

# 3. Build FTS5 index (~60 hours) & citations table (~days)
make fts-build-screen
make citations-build-screen

from crossref_local import search, get, count

# Full-text search (22ms for 541 matches across 167M records)
results = search("hippocampal sharp wave ripples")
for work in results:
    print(f"{work.title} ({work.year})")

# Get by DOI
work = get("10.1126/science.aax0758")
print(work.citation())

# Count matches
n = count("machine learning")  # 477,922 matches

from crossref_local import aio

async def main():
    counts = await aio.count_many(["CRISPR", "neural network", "climate"])
    results = await aio.search("machine learning")

crossref-local search "CRISPR genome editing" -n 5
crossref-local search-by-doi 10.1038/nature12373
crossref-local status  # Configuration and database stats

$ crossref-local search "RS-1 enhances CRISPR" -n 1 -a

Found 4 matches in 128.4ms

1. RS-1 enhances CRISPR/Cas9- and TALEN-mediated knock-in efficiency (2016)
   DOI: 10.1038/ncomms10548
   Journal: Nature Communications
   Abstract: Zinc-finger nuclease, transcription activator-like effector nuclease
   and CRISPR/Cas9 are becoming major tools for genome editing...

crossref-local relay --host 0.0.0.0 --port 31291

# Search works (FTS5)
curl "http://localhost:31291/works?q=CRISPR&limit=10"

# Get by DOI
curl "http://localhost:31291/works/10.1038/nature12373"

# Batch DOI lookup
curl -X POST "http://localhost:31291/works/batch" \
  -H "Content-Type: application/json" \
  -d '{"dois": ["10.1038/nature12373", "10.1126/science.aax0758"]}'

# Citation endpoints
curl "http://localhost:31291/citations/10.1038/nature12373/citing"
curl "http://localhost:31291/citations/10.1038/nature12373/cited"
curl "http://localhost:31291/citations/10.1038/nature12373/count"

# Collection endpoints
curl "http://localhost:31291/collections"
curl -X POST "http://localhost:31291/collections" \
  -H "Content-Type: application/json" \
  -d '{"name": "my_papers", "query": "CRISPR", "limit": 100}'
curl "http://localhost:31291/collections/my_papers/download?format=bibtex"

# Database info
curl "http://localhost:31291/info"

# On local machine (if server is remote)
ssh -L 31291:127.0.0.1:31291 your-server

# Python client
from crossref_local import configure_http
configure_http("http://localhost:31291")

# Or via CLI
crossref-local --http search "CRISPR"

crossref-local mcp start

{
  "mcpServers": {
    "crossref-local": {
      "command": "crossref-local",
      "args": ["mcp", "start"],
      "env": {
        "CROSSREF_LOCAL_DB": "/path/to/crossref.db"
      }
    }
  }
}

# On server: start persistent MCP server
crossref-local mcp start -t http --host 0.0.0.0 --port 8082

{
  "mcpServers": {
    "crossref-remote": {
      "url": "http://your-server:8082/mcp"
    }
  }
}

crossref-local mcp doctor        # Check dependencies and database
crossref-local mcp list-tools    # Show available MCP tools
crossref-local mcp installation  # Show client config examples

from crossref_local.impact_factor import ImpactFactorCalculator

with ImpactFactorCalculator() as calc:
    result = calc.calculate_impact_factor("Nature", target_year=2023)
    print(f"IF: {result['impact_factor']:.3f}")  # 54.067

from crossref_local import get_citing, get_cited, CitationNetwork

citing = get_citing("10.1038/nature12373")  # 1539 papers
cited = get_cited("10.1038/nature12373")

# Build visualization (like Connected Papers)
network = CitationNetwork("10.1038/nature12373", depth=2)
network.save_html("citation_network.html")  # requires: pip install crossref-local[viz]

import scitex

# Resolve DOIs and enrich bibliography
scitex.scholar.enrich_bibtex("references.bib")

# Check citation accuracy
scitex.scholar.check_citations("manuscript.tex")