app.py

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

def fetch_pdf_links():
    url = "https://finance.naver.com/research/company_list.naver"
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')
    
    # 모든 PDF 링크를 찾습니다.
    pdf_links = soup.find_all('a', href=re.compile("\.pdf$"))
    links = []
    for link in pdf_links:
        full_url = "https://finance.naver.com" + link['href']
        # 각 링크를 HTML 링크 형태로 저장
        links.append([f"<a href='{full_url}' target='_blank'>{full_url}</a>"])
    return links

# Gradio 인터페이스
with gr.Blocks() as app:
    btn_fetch = gr.Button("PDF 링크 조회")
    output_links = gr.Dataframe(headers=["PDF 링크"], interactive=False)
    btn_fetch.click(
        fn=fetch_pdf_links,
        outputs=output_links
    )

app.launch()