create summarization of news url

newsurl

@@ -0,0 +1,38 @@
+import streamlit as st
+from transformers import BartForConditionalGeneration, PreTrainedTokenizerFast
+import requests
+from bs4 import BeautifulSoup
+
+# KoBART 모델 로딩
+model = BartForConditionalGeneration.from_pretrained("digit82/kobart-summarization")
+tokenizer = PreTrainedTokenizerFast.from_pretrained("digit82/kobart-summarization")
+
+# 뉴스 본문 추출 함수
+def get_article_text(naver_url):
+    headers = {"User-Agent": "Mozilla/5.0"}
+    response = requests.get(naver_url, headers=headers)
+    soup = BeautifulSoup(response.text, "html.parser")
+    article_body = soup.select_one("article") or soup.select_one("#dic_area")
+    return article_body.get_text(strip=True) if article_body else None
+
+# 뉴스 요약 함수
+def summarize_korean_news(text):
+    input_ids = tokenizer.encode(text, return_tensors="pt", max_length=1024, truncation=True)
+    summary_ids = model.generate(input_ids, max_length=128, min_length=30, num_beams=4, early_stopping=True)
+    return tokenizer.decode(summary_ids[0], skip_special_tokens=True)
+
+# Streamlit 앱 UI
+st.title("HL만도 뉴스 요약기")
+st.write("HL만도 관련 최신 뉴스를 요약해 드립니다!")
+
+# 사용자로부터 URL 입력 받기
+url = st.text_input("뉴스 URL을 입력하세요:")
+
+if url:
+    article = get_article_text(url)
+    if article:
+        summary = summarize_korean_news(article)
+        st.subheader("뉴스 요약")
+        st.write(summary)
+    else:
+        st.write("기사 본문을 가져올 수 없습니다.")