import requests
import os
import csv

# Define input and output paths
query_file_path = "/School/Stanford_University/Programs/Leadership_Education_for_Aspiring_Physicians/Research/Literature/Scholarly/Query/scholar_queries.csv"
output_dir = "/School/Stanford_University/Programs/Leadership_Education_for_Aspiring_Physicians/Research/Literature/Scholarly/Results"
os.makedirs(output_dir, exist_ok=True)

# Fetch results using CrossRef API
def get_crossref_results(query, num_results=1000):  # Back to 1000
    print(f"Fetching results for query: '{query}'")
    url = f"https://api.crossref.org/works"
    params = {"query": query, "rows": num_results}

    try:
        response = requests.get(url, params=params)
        response.raise_for_status()
        data = response.json()

        # Extract items from response
        results = data.get("message", {}).get("items", [])
        if not results:
            print("No results found.")
            return "No results found."

        # Sort results by citation count in descending order
        sorted_results = sorted(
            results,
            key=lambda x: int(x.get("is-referenced-by-count", 0)),
            reverse=True
        )
        # Select the top 50 most-cited results
        top_results = sorted_results[:50]

        # Format results
        formatted_results = ""
        for i, result in enumerate(top_results, start=1):
            title = result.get("title", ["No title available"])[0]
            link = result.get("URL", "No link available")
            citation_count = result.get("is-referenced-by-count", "0")
            formatted_results += f"{i}. {title}\n   Citations: {citation_count}\n   Link: {link}\n\n"

        return formatted_results

    except requests.exceptions.RequestException as e:
        print(f"Error: {e}")
        return "No results found or an error occurred."

# Process queries and write to file
with open(query_file_path, newline='', encoding='utf-8') as csvfile:
    reader = csv.reader(csvfile)
    for row in reader:
        if row:
            query = row[0]
            result_text = get_crossref_results(query)
            
            # Clean query string for filename
            safe_query = "".join(c if c.isalnum() or c in " _-" else "_" for c in query)
            output_file_path = os.path.join(output_dir, f"scholar_{safe_query}_result.txt")
            
            with open(output_file_path, "w", encoding="utf-8") as output_file:
                output_file.write(result_text)
            
            print(f"Results for query '{query}' saved to '{output_file_path}'")