fulltext-retrieval

name	fulltext-retrieval
description	Batch download open-access PDFs by DOI using legitimate OA APIs (Unpaywall, PMC, OpenAlex, Crossref). Optional PDF→Markdown conversion for token-efficient LLM analysis.
triggers	PDF download, fulltext retrieval, open access PDF, batch download papers, meta-analysis PDF, PDF to markdown, convert PDF
tools	Read, Write, Edit, Bash, Grep, Glob
model	inherit

Fulltext Retrieval Skill

Batch download open-access full-text PDFs from a DOI list using legitimate OA APIs only.

Pipeline

DOI list → Unpaywall → PMC (Europe PMC / OA FTP / web) → OpenAlex → Crossref → landing page

Each DOI goes through these sources in order until a valid PDF (≥10 KB, %PDF- header) is found.

Quick Start

# Prepare a DOI list (one per line)
cat > dois.txt << 'EOF'
10.1007/s00330-010-1783-x
10.1002/mp.12524
10.1148/radiol.13131265
EOF

# Run
python fetch_oa.py dois.txt --output pdfs/ --email [e-mail]

# Verbose mode for debugging
python fetch_oa.py dois.txt -o pdfs/ -e [e-mail] --verbose

Input Formats

Plain text — one DOI per line:

10.1007/s00330-010-1783-x
10.1002/mp.12524

TSV with header — must contain a DOI column, optional PMID column:

ID	Title	DOI	PMID	Year
1	Some paper	10.1007/s00330-010-1783-x	20628747	2010

When a PMID is available, the PMC lookup is more reliable (PMID → PMCID conversion).

PMC Download (JS-Challenge Resistant)

PMC web pages may block automated downloads with JavaScript proof-of-work challenges. This tool uses three fallback methods:

Method A: Europe PMC REST API (most reliable)

PMCID="PMC9733600"
curl -sLo output.pdf \
  "https://europepmc.org/backend/ptpmcrender.fcgi?accid=${PMCID}&blobtype=pdf"

Method B: PMC OA FTP Service

curl -s "https://www.ncbi.nlm.nih.gov/pmc/utils/oa/oa.fcgi?id=${PMCID}" | \
    grep -oE 'href="[^"]*\.pdf"' | head -1 | \
    sed 's/href="//;s/"//' | xargs curl -sLo output.pdf

DOI/PMID → PMCID Conversion

# Works with both DOI and PMID
curl -s "https://www.ncbi.nlm.nih.gov/pmc/utils/idconv/v1.0/?ids=${DOI}&format=json" | \
    python3 -c "import sys,json; print(json.load(sys.stdin)['records'][0].get('pmcid',''))"

Output

• PDFs saved as {DOI_safe}.pdf (slashes replaced with underscores)
• manual_needed.txt — DOIs that could not be retrieved via OA
• Summary with OA/PMC/fail/skip counts

Requirements

• Python 3.10+ (stdlib only, no pip dependencies)
• Contact email (required by Unpaywall Terms of Service)

API Policies

Source	Rate Limit	Notes
Unpaywall	100 req/sec	Email required
NCBI PMC	3 req/sec without API key	Add &api_key= for higher limits
OpenAlex	100k req/day	Polite pool with email in User-Agent
Crossref	50 req/sec with email	Plus service with mailto: in UA
Europe PMC	No documented limit	Be polite, ≤1 req/sec recommended

The script uses 0.3–0.5 second delays between requests.

PDF → Markdown Conversion (Optional)

After downloading PDFs, convert them to LLM-friendly Markdown for token-efficient repeated analysis. Uses pymupdf4llm — optimized for academic papers with two-column layout handling and table preservation.

Quick Start

# Install (one-time)
pip install pymupdf4llm

# Convert all PDFs in a directory
python pdf_to_md.py pdfs/

# Convert with verbose output
python pdf_to_md.py pdfs/ -v

# Custom output directory
python pdf_to_md.py pdfs/ -o markdown/

# First 10 pages only (useful for long supplements)
python pdf_to_md.py pdfs/ --pages 0-9

# Overwrite existing conversions
python pdf_to_md.py pdfs/ --force

Combined Workflow

# Step 1: Download PDFs
python fetch_oa.py dois.txt -o pdfs/ -e [e-mail]

# Step 2: Convert to Markdown (only successful downloads)
python pdf_to_md.py pdfs/ -v

After conversion, .md files sit alongside .pdf files. Claude Code can then use Read for full content or Grep for targeted extraction — significantly more token-efficient than re-reading PDFs.

When to Convert

Scenario	Recommendation
Screening/triage (read once)	Skip — read PDF directly
Data extraction from k≥5 studies	Convert — repeated reads save tokens
Meta-analysis full pipeline	Convert — papers referenced across multiple phases
Single paper deep review	Optional — marginal benefit

Academic Paper Defaults

• Images: Skipped (saves tokens; figures referenced by caption text)
• Tables: lines_strict strategy (preserves grid-line tables accurately)
• Layout: Two-column academic layout handled automatically
• Headers/footers: Removed by pymupdf4llm

Dependency Note

pdf_to_md.py requires pymupdf4llm (AGPL-3.0). This is an optional dependency — fetch_oa.py remains stdlib-only with zero external dependencies. The AGPL license applies to pymupdf4llm itself, not to this skill.

Limitations

• Only retrieves open-access articles. Paywalled articles require institutional access.
• Landing page scraping may fail on publisher-specific JavaScript-heavy pages.
• Some recent articles may not yet be indexed by OA sources.
• PDF→Markdown quality depends on the PDF's text layer. Scanned-only PDFs may produce poor output.

Anti-Hallucination

• Never fabricate file paths, URLs, DOIs, or package names. Verify existence before recommending.
• Never invent journal metadata, impact factors, or submission policies without verification at the journal's website.
• If a tool, package, or resource does not exist or you are unsure, say so explicitly rather than guessing.