#!/usr/bin/env python3
"""
Search arXiv via its public Atom API. No API key required.

CLI usage:
    python3 search_arxiv.py "UAV magnetic compensation" --max 10

Importable:
    from search_arxiv import search_arxiv
"""
import sys
import json
import argparse
import urllib.request
import urllib.parse
import xml.etree.ElementTree as ET

ARXIV_API = "http://export.arxiv.org/api/query"
NS = {"atom": "http://www.w3.org/2005/Atom"}


def search_arxiv(query, max_results=10, timeout=20):
    params = {
        "search_query": f"all:{query}",
        "start": 0,
        "max_results": max_results,
        "sortBy": "relevance",
        "sortOrder": "descending",
    }
    url = f"{ARXIV_API}?{urllib.parse.urlencode(params)}"
    with urllib.request.urlopen(url, timeout=timeout) as resp:
        data = resp.read()
    root = ET.fromstring(data)
    results = []
    for entry in root.findall("atom:entry", NS):
        id_el = entry.find("atom:id", NS)
        title_el = entry.find("atom:title", NS)
        summary_el = entry.find("atom:summary", NS)
        published_el = entry.find("atom:published", NS)
        if id_el is None or title_el is None:
            continue
        arxiv_id_full = id_el.text.strip()
        arxiv_id = arxiv_id_full.rsplit("/", 1)[-1]
        title = " ".join(title_el.text.split())
        summary = " ".join(summary_el.text.split()) if summary_el is not None else ""
        authors = [
            a.find("atom:name", NS).text
            for a in entry.findall("atom:author", NS)
            if a.find("atom:name", NS) is not None
        ]
        published = published_el.text[:10] if published_el is not None else None
        pdf_url = None
        for link in entry.findall("atom:link", NS):
            if link.attrib.get("title") == "pdf":
                pdf_url = link.attrib.get("href")
        results.append({
            "source": "arxiv",
            "arxiv_id": arxiv_id,
            "title": title,
            "authors": authors,
            "year": published[:4] if published else None,
            "published": published,
            "abstract": summary,
            "pdf_url": pdf_url,
            "doi": None,
        })
    return results


if __name__ == "__main__":
    ap = argparse.ArgumentParser(description=__doc__)
    ap.add_argument("query")
    ap.add_argument("--max", type=int, default=10)
    args = ap.parse_args()
    try:
        out = search_arxiv(args.query, args.max)
        print(json.dumps(out, ensure_ascii=False, indent=2))
    except Exception as e:
        print(json.dumps({"error": str(e)}, ensure_ascii=False))
        sys.exit(1)