Update app.py

app.py

@@ -3,26 +3,27 @@ import requests
 from bs4 import BeautifulSoup
 import re
 
-def fetch_pdf_links():
+def fetch_pdf_links_and_titles():
     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$"))
-    links = []
+    # 모든 PDF 링크와 제목을 찾습니다.
+    pdf_links = soup.find_all('a', href=re.compile("^https://ssl.pstatic.net/imgstock/upload/research/company/.*\.pdf$"))
+    links_and_titles = []
     for link in pdf_links:
-        full_url = "https://finance.naver.com" + link['href']
+        title = link.text.strip()  # 링크 텍스트에서 제목 추출
+        full_url = link['href']
         # 다운로드 가능한 링크 형태로 저장
-        links.append([f"<a href='{full_url}' download='{full_url.split('/')[-1]}'>{full_url.split('/')[-1]}</a>"])
-    return links
+        links_and_titles.append([title, f"<a href='{full_url}' download='{full_url.split('/')[-1]}'>{full_url}</a>"])
+    return links_and_titles
 
 # 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 = gr.Button("PDF 링크 및 정보 조회")
+    output_links = gr.Dataframe(headers=["Title", "PDF 링크"], interactive=False)
     btn_fetch.click(
-        fn=fetch_pdf_links,
+        fn=fetch_pdf_links_and_titles,
         outputs=output_links
     )