Open Access Guide

import requests

def check_oa_status(doi: str) -> dict:
    """
    Check open access availability using the Unpaywall API.

    Args:
        doi: DOI of the paper (e.g., '10.1038/s41586-021-03819-2')
    Returns:
        OA status and best available link
    """
    email = "researcher@university.edu"  # Required by Unpaywall API
    url = f"https://api.unpaywall.org/v2/{doi}?email={email}"

    response = requests.get(url)
    if response.status_code != 200:
        return {'error': f'API returned status {response.status_code}'}

    data = response.json()

    # Find best OA location
    best_location = data.get('best_oa_location', {})

    return {
        'doi': doi,
        'title': data.get('title', ''),
        'is_oa': data.get('is_oa', False),
        'oa_status': data.get('oa_status', 'closed'),
        'journal_is_oa': data.get('journal_is_oa', False),
        'best_oa_url': best_location.get('url', None) if best_location else None,
        'version': best_location.get('version', None) if best_location else None,
        'license': best_location.get('license', None) if best_location else None,
        'all_locations': len(data.get('oa_locations', []))
    }

# Example
result = check_oa_status('10.1038/s41586-021-03819-2')
if result['is_oa']:
    print(f"OA available: {result['best_oa_url']}")
else:
    print("Not openly available -- check Green OA options below")

def batch_oa_lookup(dois: list[str]) -> list[dict]:
    """
    Check OA status for a batch of DOIs.
    Unpaywall supports up to 100,000 DOIs per day.
    """
    results = []
    for doi in dois:
        status = check_oa_status(doi)
        results.append(status)

    # Summary statistics
    total = len(results)
    oa_count = sum(1 for r in results if r.get('is_oa', False))
    print(f"OA availability: {oa_count}/{total} ({oa_count/total*100:.1f}%)")

    # Group by OA status
    by_status = {}
    for r in results:
        status = r.get('oa_status', 'unknown')
        by_status.setdefault(status, []).append(r)

    for status, papers in by_status.items():
        print(f"  {status}: {len(papers)} papers")

    return results

def check_sherpa_romeo(issn: str, api_key: str) -> dict:
    """
    Check journal self-archiving policy via SHERPA/RoMEO.

    Args:
        issn: Journal ISSN
        api_key: SHERPA/RoMEO API key
    """
    url = f"https://v2.sherpa.ac.uk/cgi/retrieve/by_id?item-type=publication&format=Json&api-key={api_key}&filter=[[%22issn%22,%22equals%22,%22{issn}%22]]"

    response = requests.get(url)
    data = response.json()

    if not data.get('items'):
        return {'error': 'Journal not found'}

    journal = data['items'][0]
    policies = journal.get('publisher_policy', [])

    results = {
        'journal': journal.get('title', [{}])[0].get('title', ''),
        'publisher': journal.get('publishers', [{}])[0].get('publisher', {}).get('name', ''),
        'policies': []
    }

    for policy in policies:
        for permitted in policy.get('permitted_oa', []):
            results['policies'].append({
                'version': permitted.get('article_version', ''),
                'location': permitted.get('location', {}).get('location', []),
                'conditions': permitted.get('conditions', []),
                'embargo': permitted.get('embargo', {}).get('amount', 0),
                'license': permitted.get('license', [])
            })

    return results