import gradio as gr
import requests
from bs4 import BeautifulSoup
import re

def fetch_pdf_links_and_titles():
    try:
        url = "https://finance.naver.com/research/company_list.naver"
        response = requests.get(url)
        soup = BeautifulSoup(response.text, 'html.parser')

        seen_urls = set()
        links_html = "<div style='margin-top: 20px;'>"
        pdf_links = soup.find_all('a', href=re.compile("^https://ssl.pstatic.net/imgstock/upload/research/company/.*\.pdf$"))
        for link in pdf_links:
            title = link.text.strip()
            full_url = link['href']
            if full_url not in seen_urls:
                seen_urls.add(full_url)
                # HTML 문자열로 링크를 추가하며 타이틀과 URL을 포함
                links_html += f"<p><a href='{full_url}' download='{full_url.split('/')[-1]}'>{title}</a></p>"
        links_html += "</div>"
        return links_html if links_html else "No PDF links found."
    except Exception as e:
        return f"An error occurred: {str(e)}"

# Gradio 인터페이스
with gr.Blocks() as app:
    btn_fetch = gr.Button("PDF 링크 및 정보 조회")
    output_html = gr.HTML()
    btn_fetch.click(
        fn=fetch_pdf_links_and_titles,
        outputs=output_html
    )

app.launch()