search_openalex2.py

#!/usr/bin/env python3
"""Final OpenAlex searches for NeKo-PIGNN literature gaps."""
import urllib.request
import urllib.parse
import json
import time

def search_openalex(query, per_page=20):
    url = f'https://api.openalex.org/works?filter=title_and_abstract.search:{urllib.parse.quote(query)}&sort=publication_date:desc&per_page={per_page}'
    req = urllib.request.Request(url, headers={'User-Agent': 'Mozilla/5.0 (research bot)'})
    with urllib.request.urlopen(req, timeout=30) as resp:
        return json.loads(resp.read().decode('utf-8'))

def extract_papers(data, min_year=2024):
    papers = []
    for r in data.get('results', []):
        year = r.get('publication_year', 0)
        if year < min_year:
            continue
        title = r.get('title', 'No title')
        date = r.get('publication_date', str(year))
        doi = r.get('doi', '')
        authors = []
        for a in r.get('authorships', []):
            author = a.get('author', {})
            if author:
                authors.append(author.get('display_name', '?'))
        loc = r.get('primary_location', {}) or {}
        source = loc.get('source', {}) or {}
        journal = source.get('display_name', '') or ''
        is_oa = r.get('open_access', {}).get('is_oa', False) if r.get('open_access') else False
        cited_by = r.get('cited_by_count', 0)
        papers.append({'title': title, 'date': date, 'year': year, 'doi': doi,
                       'authors': authors, 'journal': journal, 'is_oa': is_oa,
                       'cited_by': cited_by})
    return papers

def print_papers(papers, label):
    print(f"\n{'='*80}")
    print(f"📚 {label} ({len(papers)} papers)")
    print(f"{'='*80}")
    if not papers:
        print("  (no results)")
        return
    for i, p in enumerate(papers, 1):
        print(f"\n  [{i}] [{p['year']}-{p['date'][5:10] if p['date'] else '??'}] {p['title'][:140]}")
        print(f"      Journal: {p['journal'][:70]}")
        print(f"      Authors: {', '.join(p['authors'][:4])}{' et al.' if len(p['authors']) > 4 else ''}")
        print(f"      DOI: {p['doi'][:70]}")
        print(f"      Cited: {p['cited_by']}")

QUERIES = [
    # Wildfire detection with GOES/VIIRS + AI
    ("VIIRS+active+fire+deep+learning+detection+2025", "VIIRS Active Fire DL 2025+"),
    ("wildfire+detection+multi+spectral+satellite+deep+learning+transformer", "Multi-spectral DL Transformer Wildfire"),
    ("wildfire+propagation+physics+informed+neural+network+Rothermel", "PINN+Rothermel Wildfire Propagation"),
    ("wildfire+spread+graph+neural+network+spatiotemporal", "ST-GNN Wildfire Spread"),
    ("wildfire+recurrent+graph+network+prediction", "Recurrent GNN Wildfire"),
    ("wildfire+digital+twin+simulation+prediction+2025+2026", "Digital Twin Wildfire Simulation 2025-2026"),
    ("deep+koopman+operator+forecast+environmental+system", "Deep Koopman Environmental Forecasting"),
    ("koopman+autoencoder+environmental+monitoring", "Koopman Autoencoder Environmental"),
    ("wildfire+caatinga+burned+area+detection", "Caatinga Burned Area Detection"),
    ("cerrado+wildfire+deep+learning+detection+2025", "Cerrado Wildfire DL 2025+"),
    ("amazon+wildfire+deep+learning+detection+2025+2026", "Amazon Wildfire DL Detection 2025+"),
    ("wildfire+detection+unsupervised+anomaly+detection+GOES", "Unsupervised Anomaly Wildfire GOES"),
    ("physics+informed+wildfire+model+reduced+order+modeling", "Physics Informed Reduced Order Wildfire"),
    ("wildfire+prediction+ensemble+deep+learning+earth+observation", "Ensemble DL Earth Observation Wildfire"),
    ("wildfire+propagation+cellular+automata+neural+network", "Cellular Automata Neural Wildfire"),
    ("graph+neural+operator+wildfire+dynamics", "Graph Neural Operator Wildfire"),
    ("wildfire+large+language+model+monitoring+detection", "LLM Wildfire Monitoring"),
    ("wildfire+attention+mechanism+satellite+detection+2025", "Attention Mechanism Satellite Wildfire"),
    ("wildfire+spatiotemporal+neural+network+forecast+GOES", "ST Neural Net GOES Wildfire"),
    ("wildfire+transfer+learning+domain+adaptation+satellite", "Transfer Learning Domain Adapt Wildfire"),
]

for query, label in QUERIES:
    try:
        data = search_openalex(query, per_page=10)
        papers = extract_papers(data, min_year=2024)
        recent = [p for p in papers if p['year'] >= 2025]
        print_papers(recent if recent else papers[:5], label)
        time.sleep(0.4)
    except Exception as e:
        print(f"\n⚠️ Error for '{label}': {e}")