papers.py

import os
import requests
import tempfile
from datetime import datetime, timezone, timedelta
import base64
from tqdm.auto import tqdm
import pymupdf

DAILY_PAPERS_API_URL = "https://huggingface.co/api/daily_papers"

class PaperManager:
    def fetch_papers(self, date=None):
        """
        Fetch papers from the API with optional date filtering.
        
        Args:
            date (str, optional): Date string in 'YYYY-MM-DD' format. Defaults to today's date.
        
        Returns:
            bool: True if papers were successfully fetched, False otherwise.
        """
        try:
            # Use today's date if none provided
            if date is None:
                date = datetime.now().strftime('%Y-%m-%d')
                
            # Construct the URL with the date parameter
            url = f"{DAILY_PAPERS_API_URL}?date={date}&limit=100"
                
            print(f"Fetching papers from: {url}")
            response = requests.get(url)
            response.raise_for_status()
            data = response.json()

            if not data:
                print("No data received from API.")
                return False

            self.raw_papers = data  # Store raw data
            print(f"Found {len(data)} papers for date {date}")
            return True

        except requests.RequestException as e:
            print(f"Error fetching papers: {e}")
            return False
        except Exception as e:
            print(f"Unexpected error: {e}")
            return False

    def get_top_content(self):
        """
        Get the most upvoted paper from today's submissions.
        
        Returns:
            dict: Dictionary mapping paper titles to their contents.
        """
        # Fetch papers from today
        if not self.fetch_papers():
            return {}
        
        # Sort by upvotes
        if self.raw_papers:
            sorted_papers = sorted(
                self.raw_papers,
                key=lambda x: x.get('paper', {}).get('upvotes', 0),
                reverse=True
            )
            
            # Take only the top paper
            self.papers = [sorted_papers[0]] if sorted_papers else []
        else:
            print("No papers found for today.")
            self.papers = []
        
        # Get content
        contents = {}
        print(f"Processing {len(self.papers)} papers:")
        for paper in tqdm(self.papers):
            paper_id = paper["paper"]['id']
            content = self.get_paper_text(paper_id)
            contents[paper["paper"]['title']] = {"id": paper_id, "content": content}
        
        return contents

    def get_paper_text(self, paper_id):
        url = f"https://arxiv.org/pdf/{paper_id}.pdf"
        response = requests.get(url)
        
        if response.status_code != 200:
            raise Exception(f"Failed to download PDF: {response.status_code}")
        
        with open("temp.pdf", "wb") as f:
            f.write(response.content)

        with pymupdf.open("temp.pdf") as doc:
            text = ""
            for page in doc:
                text += page.get_text()        
        return text


    # def get_top_content(self):
    #     self.fetch_papers()
    #     self.filter_top_papers()
    #     contents =  {}
    #     print(f"Processing {len(self.papers)} papers:")
    #     for paper in tqdm(self.papers):
    #         paper_id = paper["paper"]['id']
    #         contents[paper["paper"]['title']] = self.get_paper_text(paper_id)
    #     return contents

    
# Example usage
if __name__ == "__main__":
    paper_manager = PaperManager()
    top_papers = paper_manager.get_top_content()
    for title, content in top_papers.items():
        print(f"Title: {title}")
        print(f"Content: {content[:100]}...")  # Print first 100 characters of content