Update app.py

app.py

@@ -1,34 +1,114 @@
 import gradio as gr
-import json
-import emoji
 import re
+import emoji
+import logging
+from typing import Tuple, Optional
+from functools import lru_cache
 from collections import Counter
 
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+def count_emojis(text: str) -> int:
+    """Подсчет количества эмодзи в тексте"""
+    return len([c for c in text if c in emoji.EMOJI_DATA])
+
+def extract_mentions(text: str) -> list:
+    """Извлечение упоминаний пользователей"""
+    return re.findall(r'@(\w+)', text)
+
+def is_spam(text: str) -> bool:
+    """Определение спам-комментариев"""
+    spam_indicators = ['🔥' * 3, '❤️' * 3, 'follow me', 'check my']
+    return any(indicator in text.lower() for indicator in spam_indicators)
+
+def extract_comment_data(comment_text: str) -> Tuple[Optional[str], Optional[str], int, int]:
+    """Извлекает данные из комментария"""
+    try:
+        # Extract username
+        username_match = re.search(r'Фото профиля\s+(.+?)\n', comment_text)
+        username = username_match.group(1).strip() if username_match else None
+        
+        if not username:
+            return None, None, 0, 0
+        
+        # Extract comment text
+        comment_lines = comment_text.split('\n')
+        comment = ""
+        time_pattern = r'\d+\s*(?:ч\.|нед\.)'
+        
+        # Identify where the comment text starts
+        for i, line in enumerate(comment_lines):
+            if re.search(time_pattern, line):
+                if i + 1 < len(comment_lines):
+                    comment = comment_lines[i + 1].strip()
+                break
+        
+        # Clean up comment text
+        comment = re.sub(r'\d+\s*(?:ч\.|нед\.)\s*$', '', comment)
+        comment = re.sub(r'"Нравится":\s*\d+\s*Ответить\s*$', '', comment)
+        
+        # Extract likes
+        likes_match = re.search(r'"Нравится":\s*(\d+)', comment_text)
+        likes = int(likes_match.group(1)) if likes_match else 0
+        
+        # Extract time
+        time_match = re.search(r'(\d+)\s*(?:ч\.|нед\.)', comment_text)
+        time = int(time_match.group(1)) if time_match else 0
+        
+        return username, comment.strip(), likes, time
+
+    except Exception as e:
+        logger.error(f"Error extracting data: {e}")
+        return None, None, 0, 0
+
+@lru_cache(maxsize=100)
 def analyze_post(content_type: str, link: str, post_likes: int, 
                 post_date: str, description: str, comment_count: int, 
                 all_comments: str) -> Tuple[str, str, str, str, str]:
+    """Анализирует пост и комментарии"""
     try:
-        comments_data = json.loads(all_comments)
+        if not all_comments or 'Фото профиля' not in all_comments:
+            return "Ошибка: неверный формат данных", "", "", "", "0"
 
+        blocks = re.split(r'(?=Фото профиля)', all_comments)
+        blocks = [b.strip() for b in blocks if b.strip()]
+        
+        comments_data = []
         total_emojis = 0
         mentions = []
         spam_count = 0
-        total_likes = 0
-
-        for comment in comments_data:
-            username = comment['username']
-            comment_text = comment['comment']
-            likes = comment.get('likes', 0) #Обработка отсутствия ключа likes
-            total_likes += likes
-
-            total_emojis += len([c for c in comment_text if c in emoji.EMOJI_DATA])
-            mentions.extend(re.findall(r'@(\w+)', comment_text))
+        
+        for block in blocks:
+            username, comment, likes, time = extract_comment_data(block)
+            if username and comment:
+                emoji_count = count_emojis(comment)
+                comment_mentions = extract_mentions(comment)
+                is_spam_comment = is_spam(comment)
+                
+                comments_data.append({
+                    'username': username,
+                    'comment': comment,
+                    'likes': likes,
+                    'time': time,
+                    'emoji_count': emoji_count,
+                    'mentions': comment_mentions,
+                    'is_spam': is_spam_comment
+                })
+                
+                total_emojis += emoji_count
+                mentions.extend(comment_mentions)
+                if is_spam_comment:
+                    spam_count += 1
 
+        # Подсчет статистики
         total_comments = len(comments_data)
-        unique_users = len(set(comment['username'] for comment in comments_data))
+        unique_users = len(set(item['username'] for item in comments_data))
+        total_likes = sum(item['likes'] for item in comments_data)
         avg_likes = total_likes / total_comments if total_comments > 0 else 0
 
-        commenter_counts = Counter(comment['username'] for comment in comments_data)
+        # Топ комментаторы
+        commenter_counts = Counter(item['username'] for item in comments_data)
         top_commenters = commenter_counts.most_common(5)
 
         analytics = f"""
@@ -46,40 +126,77 @@ def analyze_post(content_type: str, link: str, post_likes: int,
         {chr(10).join(f'• {user}: {count} комментария' for user, count in top_commenters if count > 1)}
         """
 
-        usernames = "\n".join(comment['username'] for comment in comments_data)
-        comments = "\n".join(comment['comment'] for comment in comments_data)
-        likes_chronology = "\n".join(str(comment.get('likes', 0)) for comment in comments_data)
-
-
-        return (analytics, usernames, comments, likes_chronology, str(total_likes))
+        return (
+            analytics,
+            "\n".join(item['username'] for item in comments_data),
+            "\n".join(item['comment'] for item in comments_data),
+            "\n".join(str(item['likes']) for item in comments_data),
+            str(total_likes)
+        )
 
-    except json.JSONDecodeError:
-        return "Ошибка: Неверный JSON-ввод", "", "", "", "0"
     except Exception as e:
-        return f"Произошла ошибка: {e}", "", "", "", "0"
+        logger.error(f"Analysis error: {e}")
+        return str(e), "", "", "", "0"
 
+# Создаем интерфейс Gradio
 iface = gr.Interface(
     fn=analyze_post,
     inputs=[
-        gr.Radio(choices=["Фото", "Видео"], label="Тип контента", value="Фото"),
-        gr.Textbox(label="Ссылка на пост", placeholder="Вставьте ссылку на пост"),
-        gr.Number(label="Лайки", value=0, minimum=0),
-        gr.Textbox(label="Дата поста", placeholder="YYYY-MM-DD"),
-        gr.Textbox(label="Описание", lines=3, placeholder="Описание поста"),
-        gr.Number(label="Количество комментариев", value=0, minimum=0),
-        gr.Textbox(label="Комментарии (JSON)", lines=10, 
-                   placeholder='Вставьте данные в формате JSON (см. пример)')
+        gr.Radio(
+            choices=["Photo", "Video"],
+            label="Content Type",
+            value="Photo"
+        ),
+        gr.Textbox(
+            label="Link to Post",
+            placeholder="Вставьте ссылку на пост"
+        ),
+        gr.Number(
+            label="Likes",
+            value=0,
+            minimum=0
+        ),
+        gr.Textbox(
+            label="Post Date",
+            placeholder="YYYY-MM-DD"
+        ),
+        gr.Textbox(
+            label="Description",
+            lines=3,
+            placeholder="Описание поста"
+        ),
+        gr.Number(
+            label="Comment Count",
+            value=0,
+            minimum=0
+        ),
+        gr.Textbox(
+            label="Comments",
+            lines=10,
+            placeholder="Вставьте комментарии"
+        )
     ],
     outputs=[
-        gr.Textbox(label="Анализ", lines=15),
-        gr.Textbox(label="Пользователи"),
-        gr.Textbox(label="Комментарии"),
-        gr.Textbox(label="Хронология лайков"),
-        gr.Textbox(label="Всего лайков")
+        gr.Textbox(label="Analytics Summary", lines=15),
+        gr.Textbox(label="Usernames"),
+        gr.Textbox(label="Comments"),
+        gr.Textbox(label="Likes Chronology"),
+        gr.Textbox(label="Total Likes on Comments")
     ],
-    title="Расширенный анализатор комментариев Instagram",
-    description="Анализатор комментариев Instagram с расширенной аналитикой.  Введите комментарии в формате JSON.",
+    title="Enhanced Instagram Comment Analyzer",
+    description="Анализатор комментариев Instagram с расширенной аналитикой",
     theme="default"
 )
 
-iface.launch(share=True, debug=True, show_error=True)
+if __name__ == "__main__":
+    try:
+        iface.launch(
+            share=True,  # Создает публичную ссылку
+            debug=True,  # Включает режим отладки
+            show_error=True  # Показывает подробности ошибок
+        )
+    except Exception as e:
+        logger.error(f"Error launching interface: {e}", exc_info=True)
+
+
+ошбика . ничего не работает