From a205c300c0fb2fe71329413eddbf815afc366c87 Mon Sep 17 00:00:00 2001
From: icurfer <icurfer@gmail.com>
Date: Tue, 1 Oct 2024 23:45:35 +0900
Subject: [PATCH] =?UTF-8?q?text=EC=B6=94=EC=B6=9C?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 translate_article.py | 30 ++++++++++++++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/translate_article.py b/translate_article.py
index e69de29..0d41d91 100644
--- a/translate_article.py
+++ b/translate_article.py
@@ -0,0 +1,30 @@
+import requests
+from bs4 import BeautifulSoup
+import get_url
+
+
+url = get_url.fetch_data_from_mariadb()['url']
+
+def getContents():
+    # HTTP GET 요청으로 페이지 가져오기
+    response = requests.get(url)
+
+    # 응답 상태 확인
+    if response.status_code == 200:
+        # HTML 파싱
+        soup = BeautifulSoup(response.text, 'html.parser')
+        
+        # HTML 태그를 제거 후 페이지의 모든 텍스트 가져오기 (전체 내용)
+        page_content = soup.get_text()
+
+        # 빈 줄을 제거하고 텍스트만 출력 (줄바꿈 문자를 기준으로 필터링)
+        lines = [line.strip() for line in page_content.splitlines() if line.strip()]
+        
+        # 결과 출력
+        contents = "\n".join(lines)
+        return contents
+    else:
+        print(f"Failed to fetch the URL. Status code: {response.status_code}")
+        
+tmp = getContents()
+print(tmp)
\ No newline at end of file