Update app.py

app.py

@@ -87,20 +87,45 @@ def summarize_text(title, description, text):
 """
     return call_api(prompt, max_tokens=8000, temperature=0.35, top_p=0.95)
 
+def split_sentences(text):
+    sentences = re.split(r"(니다|에요|구나|해요|군요|겠어요|시오|해라|예요|아요|데요|대요|세요|어요|게요|구요|고요|나요|하죠)(?![\w])", text)
+    combined_sentences = []
+    current_sentence = ""
+    for i in range(0, len(sentences), 2):
+        if i + 1 < len(sentences):
+            sentence = sentences[i] + sentences[i + 1]
+        else:
+            sentence = sentences[i]
+        if len(current_sentence) + len(sentence) > 100:  # 100자를 초과할 경우
+            combined_sentences.append(current_sentence.strip())
+            current_sentence = sentence.strip()
+        else:
+            current_sentence += sentence
+        if sentence.endswith(('.', '?', '!')):
+            combined_sentences.append(current_sentence.strip())
+            current_sentence = ""
+    if current_sentence:
+        combined_sentences.append(current_sentence.strip())
+    return combined_sentences
+
+def display_script(title, script):
+    script_sentences = split_sentences(script)
+    formatted_script = "\n\n".join(script_sentences)
+    return f"# {title}\n\n{formatted_script}"
+
 def analyze(url, progress=gr.Progress()):
     try:
         progress(0, desc="스크립트 추출 중...")
         title, description, script = get_youtube_script(url)
         
         progress(0.25, desc="원문 스크립트 처리 중...")
-        script_sentences = split_sentences(script)
-        script_content = f"# {title}\n\n" + "\n".join(script_sentences)
+        script_content = display_script(title, script)
         
         # 원문 스크립트 먼저 출력하고 진행
         yield script_content, "요약 준비 중..."
         
         progress(0.5, desc="요약 생성 중...")
-        summary = summarize_text(title, description, "\n".join(script_sentences))
+        summary = summarize_text(title, description, script)
         
         progress(0.75, desc="요약 내용 정리 중...")
         summary_content = f"# {title}\n\n{summary}"
@@ -112,34 +137,6 @@ def analyze(url, progress=gr.Progress()):
         logging.exception(error_msg)
         yield error_msg, error_msg
 
-def split_sentences(text):
-    sentence_end = r'(니다|에요|구나|해요|군요|겠어요|시오|해라|예요|아요|데요|대요|세요|어요|게요|구요|고요|나요|하죠)(?![\w])'
-    segments = re.split(f'({sentence_end})', text)
-    
-    combined_sentences = []
-    current_sentence = ""
-    
-    for i in range(0, len(segments), 2):
-        segment = segments[i]
-        if i + 1 < len(segments):
-            segment += segments[i + 1]
-        
-        if len(current_sentence) + len(segment) > 100:
-            if current_sentence:
-                combined_sentences.append(current_sentence.strip())
-            current_sentence = segment.strip()
-        else:
-            current_sentence += (' ' if current_sentence else '') + segment.strip()
-        
-        if re.search(sentence_end, segment):
-            combined_sentences.append(current_sentence.strip())
-            current_sentence = ""
-    
-    if current_sentence:
-        combined_sentences.append(current_sentence.strip())
-    
-    return combined_sentences
-
 # Gradio 인터페이스
 with gr.Blocks() as demo:
     gr.Markdown("## YouTube 스크립트 추출 및 요약 도구")