Update app.py

app.py

@@ -5,13 +5,7 @@ import pandas as pd
 from transformers import *
 from tqdm import tqdm
 from tensorflow.python.client import device_lib
-
-from selenium import webdriver
-from selenium.webdriver.chrome.service import Service
-from selenium.webdriver.chrome.options import Options
-from selenium.webdriver.common.by import By
-from selenium.webdriver.support.ui import WebDriverWait
-from selenium.webdriver.support import expected_conditions as EC
+import requests
 from bs4 import BeautifulSoup
 import time
 
@@ -68,55 +62,41 @@ def movie_evaluation_predict(sentence):
     elif predict_answer == 1:
       st.write("(긍정 확률 : %.2f) 긍정적인 영화 평가입니다." % predict_value)
 
-def setup_driver():
-    chrome_options = Options()
-    chrome_options.add_argument("--headless")  # 백그라운드 실행
-    chrome_options.add_argument("--no-sandbox")
-    
-    driver = webdriver.Chrome(options=chrome_options)
-    return driver
-
 def scrape_content(url):
-    driver = setup_driver()
-    try:
-        driver.get(url)
-        # 페이지 로딩 대기
-        time.sleep(3)
-        
-        # 본문 추출
-        soup = BeautifulSoup(driver.page_source, 'html.parser')
-        content = soup.find('article')  # 본문 태그에 맞게 수정
-        
-        # 댓글 추출
-        comments = soup.find_all('span', class_='u_cbox_contents')  # 댓글 태그에 맞게 수정
-        
-        return {
-            'content': content.text if content else "본문을 찾을 수 없습니다.",
-            'comments': [comment.text for comment in comments]
-        }
-    finally:
-        driver.quit()
+    # 웹 페이지 요청
+    response = requests.get(url)
+    soup = BeautifulSoup(response.content, 'html.parser')
+    
+    # 본문 추출
+    article_body = soup.find_all('div', class_='newsct_article')
+    content = ' '.join([p.get_text() for p in article_body])
+    
+    # 댓글 추출 (예시)
+    comments = soup.find_all('span', class_='u_cbox_contents')
+    comment_list = [comment.get_text() for comment in comments]
+    
+    return content, comment_list
 
 
 def main():
     sentiment_model = create_sentiment_bert()
 
+    st.title("웹 컨텐츠 스크래퍼")
+    
+    # URL 입력 받기
     url = st.text_input("URL을 입력하세요")
     
-    if st.button("크롤링 시작"):
+    if st.button("스크랩 시작"):
         if url:
-            with st.spinner("크롤링 중..."):
-                result = scrape_content(url)
-                
-                st.subheader("본문")
-                st.write(result['content'])
-                
-                st.subheader("댓글")
-                for idx, comment in enumerate(result['comments'], 1):
-                    st.write(f"{idx}. {comment}")
-        else:
-            st.error("URL을 입력해주세요")
-
+            content, comments = scrape_content(url)
+            
+            # 결과 표시
+            st.subheader("본문 내용")
+            st.write(content)
+            
+            st.subheader("댓글")
+            for comment in comments:
+                st.write(comment)
     
     '''
     test = st.form('test')