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

def extract_pdf_links(url):
    response = requests.get(url)
    soup = BeautifulSoup(response.text, 'html.parser')

    pdf_links = []
    for link in soup.find_all('a', href=True):
        if re.search(r'\.pdf', link['href']):
            pdf_links.append(link['href'])

    return pdf_links[:100]

def generate_html(pdf_links):
    html = ""
    for link in pdf_links:
        html += f'<a href="{link}" target="_blank" download>{link}</a><br/>'
    return html

def extract_and_download(url):
    pdf_links = extract_pdf_links(url)
    return generate_html(pdf_links)

title = "네이버 증권 리서치 링크- https://finance.naver.com/research/company_list.naver"

iface = gr.Interface(extract_and_download, 
                     inputs="text", 
                     outputs="html",
                     title=title)

iface.launch()