# import streamlit as st
# import requests
# import xmltodict

# # arXiv API base URL
# ARXIV_API_BASE = "http://export.arxiv.org/api/query"

# def fetch_papers(query, max_results=10):
#     """Fetch papers from the arXiv API."""
#     try:
#         # Build the API query URL
#         api_url = f"{ARXIV_API_BASE}?search_query=all:{query}&start=0&max_results={max_results}"

#         # Make the API request
#         response = requests.get(api_url, headers={'Accept': 'application/xml'})
#         response.raise_for_status()

#         # Parse the XML response
#         data = xmltodict.parse(response.text)
#         entries = data.get('feed', {}).get('entry', [])

#         if not isinstance(entries, list):  # Handle single result
#             entries = [entries]

#         # Extract relevant fields
#         papers = []
#         for entry in entries:
#             papers.append({
#                 'title': entry.get('title'),
#                 'summary': entry.get('summary'),
#                 'published': entry.get('published'),
#                 'authors': [author['name'] for author in entry.get('author', [])] if isinstance(entry.get('author'), list) else [entry.get('author', {}).get('name')],
#                 'link': entry.get('id')
#             })

#         return papers
#     except Exception as e:
#         st.error(f"Error fetching papers: {e}")
#         return []

# # Streamlit app UI
# st.title("arXiv Research Paper Search")
# st.subheader("Find academic papers on your topic of interest")

# # Input fields
# query = st.text_input("Enter a topic or keywords", placeholder="e.g., machine learning, quantum computing")
# max_results = st.slider("Number of results", min_value=1, max_value=50, value=10)

# if st.button("Search"):
#     if query.strip():
#         st.info(f"Searching for papers on: **{query}**")
#         papers = fetch_papers(query, max_results)
        
#         if papers:
#             st.success(f"Found {len(papers)} papers!")
#             for idx, paper in enumerate(papers, start=1):
#                 st.write(f"### {idx}. {paper['title']}")
#                 st.write(f"**Authors**: {', '.join(paper['authors'])}")
#                 st.write(f"**Published**: {paper['published']}")
#                 st.write(f"[Read More]({paper['link']})")
#                 st.write("---")
#         else:
#             st.warning("No papers found. Try a different query.")
#     else:
#         st.error("Please enter a topic or keywords to search.")

import streamlit as st
import requests
import xmltodict
from datetime import datetime

# arXiv API base URL
ARXIV_API_BASE = "http://export.arxiv.org/api/query"

def fetch_papers(query, max_results=10):
    """Fetch papers from the arXiv API."""
    try:
        # Build the API query URL
        api_url = f"{ARXIV_API_BASE}?search_query=all:{query}&start=0&max_results={max_results}"

        # Make the API request
        response = requests.get(api_url, headers={'Accept': 'application/xml'})
        response.raise_for_status()

        # Parse the XML response
        data = xmltodict.parse(response.text)
        entries = data.get('feed', {}).get('entry', [])

        if not isinstance(entries, list):  # Handle single result
            entries = [entries]

        # Extract relevant fields
        papers = []
        for entry in entries:
            papers.append({
                'title': entry.get('title'),
                'summary': entry.get('summary'),
                'published': entry.get('published'),
                'authors': [author['name'] for author in entry.get('author', [])] if isinstance(entry.get('author'), list) else [entry.get('author', {}).get('name')],
                'link': entry.get('id')
            })

        return papers
    except Exception as e:
        st.error(f"Error fetching papers: {e}")
        return []

def filter_papers_by_year(papers, start_year, end_year):
    """Filter papers by the publication year range."""
    filtered_papers = []
    for paper in papers:
        try:
            published_year = int(paper['published'][:4])  # Extract year from the published date
            if start_year <= published_year <= end_year:
                filtered_papers.append(paper)
        except ValueError:
            continue  # Skip if the year is not valid
    return filtered_papers

# Streamlit app UI
st.title("arXiv Research Paper Search")
st.subheader("Find academic papers on your topic of interest")

# Input fields
query = st.text_input("Enter a topic or keywords", placeholder="e.g., machine learning, quantum computing")
max_results = st.slider("Number of results", min_value=1, max_value=50, value=10)

# Year filter
col1, col2 = st.columns(2)
with col1:
    start_year = st.number_input("Start Year", min_value=1900, max_value=datetime.now().year, value=2000, step=1)
with col2:
    end_year = st.number_input("End Year", min_value=1900, max_value=datetime.now().year, value=datetime.now().year, step=1)

if st.button("Search"):
    if query.strip():
        st.info(f"Searching for papers on: **{query}**")
        papers = fetch_papers(query, max_results)
        
        # Filter papers by year
        papers_filtered = filter_papers_by_year(papers, start_year, end_year)
        
        if papers_filtered:
            st.success(f"Found {len(papers_filtered)} papers between {start_year} and {end_year}!")
            for idx, paper in enumerate(papers_filtered, start=1):
                st.write(f"### {idx}. {paper['title']}")
                st.write(f"**Authors**: {', '.join(paper['authors'])}")
                st.write(f"**Published**: {paper['published']}")
                st.write(f"[Read More]({paper['link']})")
                st.write("---")
        else:
            st.warning(f"No papers found between {start_year} and {end_year}. Try a different query or adjust the year range.")
    else:
        st.error("Please enter a topic or keywords to search.")