Update app.py

app.py

@@ -368,23 +368,60 @@ def clean_text(text):
 
 def get_article_content(url):
     """URL에서 기사 내용 스크래핑"""
-    if not url or 'github.com' in url or 'twitter.com' in url:
+    if not url:
+        return None
+        
+    # 스킵할 도메인 목록
+    skip_domains = ['github.com', 'twitter.com', 'linkedin.com', 'facebook.com']
+    if any(domain in url.lower() for domain in skip_domains):
         return None
         
     try:
-        headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36'}
-        response = requests.get(url, headers=headers, timeout=10)
+        headers = {
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36',
+            'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
+            'Accept-Language': 'en-US,en;q=0.5',
+            'Connection': 'keep-alive',
+        }
+        
+        # 타임아웃 증가 및 재시도 설정
+        session = requests.Session()
+        retries = requests.adapters.Retry(total=3, backoff_factor=1)
+        session.mount('https://', requests.adapters.HTTPAdapter(max_retries=retries))
+        
+        response = session.get(url, headers=headers, timeout=15)
+        response.raise_for_status()
+        
         soup = BeautifulSoup(response.text, 'html.parser')
         
         # 불필요한 요소 제거
-        for tag in soup(['script', 'style', 'nav', 'footer', 'header']):
+        for tag in soup(['script', 'style', 'nav', 'footer', 'header', 'aside', 'iframe']):
             tag.decompose()
             
-        paragraphs = soup.find_all('p')
-        text = ' '.join(p.get_text() for p in paragraphs)
+        # 본문 내용 추출
+        article_text = ""
+        
+        # article 태그 확인
+        article = soup.find('article')
+        if article:
+            paragraphs = article.find_all('p')
+        else:
+            # main 태그 확인
+            main = soup.find('main')
+            if main:
+                paragraphs = main.find_all('p')
+            else:
+                # body에서 직접 검색
+                paragraphs = soup.find_all('p')
+        
+        text = ' '.join(p.get_text().strip() for p in paragraphs if p.get_text().strip())
         text = clean_text(text)
         
+        if not text:
+            return None
+            
         return text[:4000]  # 텍스트 길이 제한
+        
     except Exception as e:
         print(f"Scraping error for {url}: {str(e)}")
         return None
@@ -592,23 +629,32 @@ def generate_report(title, info, progress=gr.Progress()):
         
         progress(0.5, desc="AI 모델 처리 중...")
         
-        response = hf_client.text_generation(
-            prompt,
-            max_new_tokens=4000,
-            temperature=0.3,
-            repetition_penalty=1.2
-        )
-        
-        progress(1.0, desc="완료!")
-        
-        if response:
-            return [
-                gr.update(value=response, visible=True),  # report_content
-                gr.update(value="접기", visible=True)     # show_report
-            ]
-        else:
+        try:
+            response = hf_client.text_generation(
+                prompt,
+                max_new_tokens=4000,
+                temperature=0.3,
+                repetition_penalty=1.2
+            )
+            
+            progress(0.8, desc="결과 처리 중...")
+            
+            if response:
+                formatted_response = f"""### AI 리포팅 결과\n\n{response}"""
+                return [
+                    gr.update(value=formatted_response, visible=True),
+                    gr.update(value="접기", visible=True)
+                ]
+            else:
+                return [
+                    gr.update(value="리포팅 생성에 실패했습니다.", visible=True),
+                    gr.update(value="접기", visible=True)
+                ]
+                
+        except Exception as e:
+            print(f"Model error: {str(e)}")
             return [
-                gr.update(value="리포팅 생성에 실패했습니다.", visible=True),
+                gr.update(value="AI 모델 처리 중 오류가 발생했습니다.", visible=True),
                 gr.update(value="접기", visible=True)
             ]
             
@@ -618,6 +664,8 @@ def generate_report(title, info, progress=gr.Progress()):
             gr.update(value="리포팅 생성 중 오류가 발생했습니다.", visible=True),
             gr.update(value="접기", visible=True)
         ]
+    finally:
+        progress(1.0, desc="완료!")
 
 def toggle_report(report_content, show_report):
     """리포트 표시/숨김 토글"""
@@ -627,42 +675,52 @@ def toggle_report(report_content, show_report):
     ]
 
 css = """
+/* 전역 스타일 */
 footer {visibility: hidden;}
+
+/* 레이아웃 컨테이너 */
 #status_area {
-    background: rgba(255, 255, 255, 0.9);  /* 약간 투명한 흰색 배경 */
+    background: rgba(255, 255, 255, 0.9);
     padding: 15px;
     border-bottom: 1px solid #ddd;
     margin-bottom: 20px;
-    box-shadow: 0 2px 5px rgba(0,0,0,0.1);  /* 부드러운 그림자 효과 */
+    box-shadow: 0 2px 5px rgba(0,0,0,0.1);
 }
+
 #results_area {
     padding: 10px;
     margin-top: 10px;
 }
-/* 탭 스타일 개선 */
+
+/* 탭 스타일 */
 .tabs {
     border-bottom: 2px solid #ddd !important;
     margin-bottom: 20px !important;
 }
+
 .tab-nav {
     border-bottom: none !important;
     margin-bottom: 0 !important;
 }
+
 .tab-nav button {
     font-weight: bold !important;
     padding: 10px 20px !important;
 }
+
 .tab-nav button.selected {
-    border-bottom: 2px solid #1f77b4 !important;  /* 선택된 탭 강조 */
+    border-bottom: 2px solid #1f77b4 !important;
     color: #1f77b4 !important;
 }
-/* 검색 상태 메시지 스타일 */
+
+/* 상태 메시지 */
 #status_area .markdown-text {
     font-size: 1.1em;
     color: #2c3e50;
     padding: 10px 0;
 }
-/* 검색 결과 컨테이너 스타일 */
+
+/* 기본 컨테이너 */
 .group {
     border: 1px solid #eee;
     padding: 15px;
@@ -670,23 +728,20 @@ footer {visibility: hidden;}
     border-radius: 5px;
     background: white;
 }
-/* 검색 버튼 스타일 */
+
+/* 버튼 스타일 */
 .primary-btn {
     background: #1f77b4 !important;
     border: none !important;
 }
-/* 검색어 입력창 스타일 */
+
+/* 입력 필드 */
 .textbox {
     border: 1px solid #ddd !important;
     border-radius: 4px !important;
 }
-.report-section {
-    margin-top: 15px;
-    padding: 15px;
-    border-top: 1px solid #eee;
-    background: #f9f9f9;
-}
 
+/* Hacker News 아티클 스타일 */
 .hn-article-group {
     height: auto !important;
     min-height: 250px;
@@ -695,33 +750,75 @@ footer {visibility: hidden;}
     border: 1px solid #eee;
     border-radius: 5px;
     background: white;
+    box-shadow: 0 1px 3px rgba(0,0,0,0.05);
 }
+
+/* 리포트 섹션 스타일 */
+.report-section {
+    margin-top: 15px;
+    padding: 15px;
+    border-top: 1px solid #eee;
+    background: #f9f9f9;
+    border-radius: 4px;
+}
+
 .report-content {
     margin-top: 15px;
     padding: 15px;
     border-top: 1px solid #eee;
     background: #f9f9f9;
+    border-radius: 4px;
+    font-size: 0.95em;
+    line-height: 1.6;
 }
 
-.progress-bar {
+/* 프로그레스 바 */
+.progress {
     position: fixed;
     top: 0;
     left: 0;
     width: 100%;
     height: 4px;
+    background: #f0f0f0;
+    z-index: 1000;
+}
+
+.progress-bar {
+    height: 100%;
     background: #1f77b4;
+    transition: width 0.3s ease;
+    position: fixed;
+    top: 0;
+    left: 0;
+    width: 100%;
     z-index: 1000;
 }
+
+/* 리포트 콘텐츠 토글 */
 .hn-article-group .report-content {
     display: none;
     margin-top: 15px;
     padding: 15px;
     border-top: 1px solid #eee;
     background: #f9f9f9;
+    transition: all 0.3s ease;
 }
+
 .hn-article-group .report-content.visible {
     display: block;
 }
+
+/* 반응형 디자인 */
+@media (max-width: 768px) {
+    .hn-article-group {
+        padding: 10px;
+        margin-bottom: 15px;
+    }
+    
+    .report-content {
+        padding: 10px;
+    }
+}
 """
 
 with gr.Blocks(theme="Nymbo/Nymbo_Theme", css=css, title="NewsAI 서비스") as iface: