arxiv_retrieval_service.py

import arxiv
from typing import List, Dict, Any

class ArxivRetrievalService:
    def __init__(self):
        self.client = arxiv.Client(delay_seconds=3, num_retries=3)

    def fetch_metadata(self, query: str, max_results: int = 10) -> List[Dict[str, Any]]:
        search = arxiv.Search(
            query=query, 
            max_results=max_results, 
            sort_by=arxiv.SortCriterion.SubmittedDate
        )
        
        results = []
        for result in self.client.results(search):
            metadata = {
                "title": result.title,
                "authors": [author.name for author in result.authors],
                "published": result.published.isoformat(),
                "updated": result.updated.isoformat(),
                "pdf_url": result.pdf_url,
                "entry_id": result.entry_id,
                "summary": result.summary,
                "categories": result.categories,
                "primary_category": result.primary_category,
                "html_url": f"http://arxiv.org/abs/{result.entry_id.split('/')[-1]}"
            }
            results.append(metadata)
        
        return results

# Usage:
# arxiv_service = ArxivRetrievalService()
# metadata = arxiv_service.fetch_metadata("quantum computing", max_results=5)