Update app.py

app.py

@@ -6,6 +6,9 @@ import emoji
 import logging
 from typing import Tuple, List, Optional
 import statistics
+import csv
+from textblob import TextBlob
+import numpy as np
 
 # Настройка логирования
 logging.basicConfig(level=logging.INFO)
@@ -25,9 +28,8 @@ def extract_mentions(text):
 
 def get_comment_words(text):
     """Получает список слов из комментария для анализа"""
-    # Очищаем текст от эмодзи и приводим к нижнему регистру
     words = re.findall(r'\w+', text.lower())
-    return [w for w in words if len(w) > 2]  # Исключаем короткие слова
+    return [w for w in words if len(w) > 2]
 
 def analyze_sentiment(text):
     """Расширенный анализ тональности по эмодзи и ключевым словам"""
@@ -42,23 +44,34 @@ def analyze_sentiment(text):
     positive_count = sum(1 for ind in positive_indicators if ind in text_lower)
     negative_count = sum(1 for ind in negative_indicators if ind in text_lower)
     
-    # Учитываем восклицательные знаки как усилители эмоций
     exclamation_count = text.count('!')
     positive_count += exclamation_count * 0.5 if positive_count > negative_count else 0
     negative_count += exclamation_count * 0.5 if negative_count > positive_count else 0
     
-    if positive_count > negative_count:
+    # Добавляем анализ через TextBlob для более точной оценки
+    blob = TextBlob(text)
+    sentiment_score = blob.sentiment.polarity
+    
+    # Комбинируем оба подхода
+    final_score = (positive_count - negative_count) + sentiment_score
+    
+    if final_score > 0:
         return 'positive'
-    elif negative_count > positive_count:
+    elif final_score < 0:
         return 'negative'
     return 'neutral'
 
 def extract_comment_data(comment_text):
     """
     Извлекает данные из отдельного комментария
-    Возвращает (username, comment_text, likes_count, week_number)
     """
     try:
+        # Проверка на скрытый комментарий
+        if 'Скрыто алгоритмами Instagram' in comment_text:
+            username_match = re.search(r"Фото профиля ([^\n]+)", comment_text)
+            if username_match:
+                return username_match.group(1).strip(), "", 0, 0
+        
         # Извлекаем имя пользователя
         username_match = re.search(r"Фото профиля ([^\n]+)", comment_text)
         if not username_match:
@@ -66,12 +79,12 @@ def extract_comment_data(comment_text):
         
         username = username_match.group(1).strip()
         
-        # Извлекаем текст комментария
-        comment_pattern = fr"{username}\n(.*?)(?:\d+ нед\.)"
+        # Улучшенное извлечение текста комментария
+        comment_pattern = fr"{re.escape(username)}\n(.*?)(?:\d+ нед\.)"
         comment_match = re.search(comment_pattern, comment_text, re.DOTALL)
         if comment_match:
             comment = clean_text(comment_match.group(1))
-            comment = re.sub(fr'^{username}\s*', '', comment)
+            comment = re.sub(fr'^{re.escape(username)}\s*', '', comment)
             comment = re.sub(r'^@[\w\.]+ ', '', comment)
         else:
             comment = ""
@@ -80,11 +93,12 @@ def extract_comment_data(comment_text):
         week_match = re.search(r'(\d+) нед\.', comment_text)
         weeks = int(week_match.group(1)) if week_match else 0
         
-        # Ищем количество лайков
+        # Извлекаем лайки с улучшенным поиском
         likes = 0
         likes_patterns = [
             r"(\d+) отметк[аи] \"Нравится\"",
             r"Нравится: (\d+)",
+            r"\"Нравится\": (\d+)",
         ]
         
         for pattern in likes_patterns:
@@ -100,8 +114,8 @@ def extract_comment_data(comment_text):
 
 def analyze_post(content_type, link_to_post, post_likes, post_date, description, comment_count, all_comments):
     try:
-        # Разделяем комментарии по "Фото профиля"
-        comments_blocks = re.split(r'(?=Фото профиля)', all_comments)
+        # Улучшенное разделение комментариев
+        comments_blocks = re.split(r'(?=Фото профиля|Скрыто алгоритмами Instagram)', all_comments)
         comments_blocks = [block for block in comments_blocks if block.strip()]
         
         # Основные списки для данных
@@ -117,12 +131,14 @@ def analyze_post(content_type, link_to_post, post_likes, post_date, description,
         comment_lengths = []
         words_per_comment = []
         all_words = []
-        user_engagement = {}  # Словарь для хранения статистики по пользователям
+        user_engagement = {}
+        reply_chains = []
+        current_chain = []
         
         # Обработка каждого комментария
         for block in comments_blocks:
             username, comment, like_count, week_number = extract_comment_data(block)
-            if username and comment:
+            if username and (comment is not None):
                 usernames.append(username)
                 comments.append(comment)
                 likes.append(str(like_count))
@@ -130,11 +146,20 @@ def analyze_post(content_type, link_to_post, post_likes, post_date, description,
                 
                 # Базовые метрики
                 total_emojis += count_emojis(comment)
-                mentions.extend(extract_mentions(comment))
+                comment_mentions = extract_mentions(comment)
+                mentions.extend(comment_mentions)
                 sentiment = analyze_sentiment(comment)
                 sentiments.append(sentiment)
                 comment_lengths.append(len(comment))
                 
+                # Анализ цепочек ответов
+                if comment_mentions:
+                    current_chain.append((username, comment_mentions[0]))
+                else:
+                    if current_chain:
+                        reply_chains.append(current_chain)
+                        current_chain = []
+                
                 # Расширенные метрики
                 words = get_comment_words(comment)
                 words_per_comment.append(len(words))
@@ -147,7 +172,10 @@ def analyze_post(content_type, link_to_post, post_likes, post_date, description,
                         'total_likes': 0,
                         'emoji_usage': 0,
                         'avg_length': 0,
-                        'sentiments': []
+                        'sentiments': [],
+                        'mentions_received': 0,
+                        'mentions_made': len(comment_mentions),
+                        'response_time': []
                     }
                 user_stats = user_engagement[username]
                 user_stats['comments'] += 1
@@ -156,139 +184,95 @@ def analyze_post(content_type, link_to_post, post_likes, post_date, description,
                 user_stats['avg_length'] += len(comment)
                 user_stats['sentiments'].append(sentiment)
         
-        # Аналитика
-        total_comments = len(comments)
-        if total_comments == 0:
-            raise ValueError("No valid comments found")
-            
+        # Финализируем цепочки ответов
+        if current_chain:
+            reply_chains.append(current_chain)
+        
         # Обновляем статистику пользователей
         for username in user_engagement:
             stats = user_engagement[username]
             stats['avg_length'] /= stats['comments']
             stats['engagement_rate'] = stats['total_likes'] / stats['comments']
             stats['sentiment_ratio'] = sum(1 for s in stats['sentiments'] if s == 'positive') / len(stats['sentiments'])
+            stats['mentions_received'] = sum(1 for m in mentions if m == f'@{username}')
         
-        # Базовая статистика
-        avg_comment_length = sum(comment_lengths) / total_comments
-        sentiment_distribution = Counter(sentiments)
-        most_active_users = Counter(usernames).most_common(5)
-        most_mentioned = Counter(mentions).most_common(5)
-        avg_likes = sum(map(int, likes)) / len(likes) if likes else 0
-        earliest_week = max(weeks) if weeks else 0
-        latest_week = min(weeks) if weeks else 0
-        
-        # Расширенная статистика
-        median_comment_length = statistics.median(comment_lengths)
-        avg_words_per_comment = sum(words_per_comment) / total_comments
-        common_words = Counter(all_words).most_common(10)
-        
-        # Анализ вовлеченности
-        engagement_metrics = {
-            'comments_with_likes': sum(1 for l in likes if int(l) > 0),
-            'comments_with_emoji': sum(1 for c in comments if count_emojis(c) > 0),
-            'comments_with_mentions': sum(1 for c in comments if extract_mentions(c)),
-            'avg_engagement_rate': statistics.mean([
-                stats['engagement_rate'] for stats in user_engagement.values()
-            ])
+        # Экспериментальная аналитика
+        experimental_metrics = {
+            'conversation_depth': len(max(reply_chains, key=len)) if reply_chains else 0,
+            'avg_response_time': np.mean([c['avg_length'] for c in user_engagement.values()]),
+            'engagement_consistency': np.std([c['comments'] for c in user_engagement.values()]),
+            'user_interaction_score': len([c for c in comments if any(mention in c for mention in mentions)]) / len(comments),
+            'sentiment_volatility': np.std([1 if s == 'positive' else -1 if s == 'negative' else 0 for s in sentiments]),
         }
         
-        # Временной анализ
-        week_distribution = Counter(weeks)
-        most_active_weeks = sorted(week_distribution.items(), key=lambda x: x[1], reverse=True)[:3]
+        # Форматируем данные для CSV
+        csv_data = {
+            'post_url': link_to_post,
+            'total_comments': len(comments),
+            'total_likes': sum(map(int, likes)),
+            'avg_likes_per_comment': sum(map(int, likes)) / len(comments),
+            'unique_users': len(set(usernames)),
+            'emoji_rate': total_emojis / len(comments),
+            'avg_comment_length': sum(comment_lengths) / len(comments),
+            'positive_sentiment_ratio': sum(1 for s in sentiments if s == 'positive') / len(sentiments),
+            'mention_rate': len(mentions) / len(comments),
+            'conversation_depth': experimental_metrics['conversation_depth'],
+            'user_interaction_score': experimental_metrics['user_interaction_score'],
+            'sentiment_volatility': experimental_metrics['sentiment_volatility'],
+        }
         
-        # Формируем выходные данные
-        usernames_output = "\n".join(usernames)
-        comments_output = "\n".join(comments)
-        likes_chronology_output = "\n".join(likes)
-        total_likes_sum = sum(map(int, likes))
+        # Форматируем вывод для CSV
+        csv_output = ",".join([f"{k}:{v}" for k, v in csv_data.items()])
         
-        # Расширенная аналитика
+        # Форматируем детальную аналитику
         analytics_summary = (
+            f"CSV_DATA\n{csv_output}\n\n"
+            f"DETAILED_ANALYTICS\n"
             f"Content Type: {content_type}\n"
             f"Link to Post: {link_to_post}\n\n"
-            f"ОСНОВНАЯ СТАТИСТИКА:\n"
-            f"- Всего комментариев: {total_comments}\n"
-            f"- Всего лайков на комментариях: {total_likes_sum}\n"
-            f"- Среднее количество лайков: {avg_likes:.1f}\n"
-            f"- Период активности: {earliest_week}-{latest_week} недель\n\n"
-            f"АНАЛИЗ КОНТЕНТА:\n"
-            f"- Средняя длина комментария: {avg_comment_length:.1f} символов\n"
-            f"- Медианная длина комментария: {median_comment_length} символов\n"
-            f"- Среднее количество слов: {avg_words_per_comment:.1f}\n"
-            f"- Всего эмодзи использовано: {total_emojis}\n"
-            f"- Тональность комментариев:\n"
-            f"  * Позитивных: {sentiment_distribution['positive']}\n"
-            f"  * Нейтральных: {sentiment_distribution['neutral']}\n"
-            f"  * Негативных: {sentiment_distribution['negative']}\n\n"
-            f"ПОПУЛЯРНЫЕ СЛОВА:\n"
-            + "\n".join([f"- {word}: {count} раз" for word, count in common_words]) + "\n\n"
-            f"АКТИВНОСТЬ ПОЛЬЗОВАТЕЛЕЙ:\n"
-            f"Самые активные комментаторы:\n"
-            + "\n".join([f"- {user}: {count} комментариев" for user, count in most_active_users]) + "\n\n"
-            f"Самые упоминаемые пользователи:\n"
-            + "\n".join([f"- {user}: {count} упоминаний" for user, count in most_mentioned if user]) + "\n\n"
-            f"ВОВЛЕЧЕННОСТЬ:\n"
-            f"- Процент комментариев с лайками: {(engagement_metrics['comments_with_likes'] / total_comments * 100):.1f}%\n"
-            f"- Процент комментариев с эмодзи: {(engagement_metrics['comments_with_emoji'] / total_comments * 100):.1f}%\n"
-            f"- Процент комментариев с упоминаниями: {(engagement_metrics['comments_with_mentions'] / total_comments * 100):.1f}%\n"
-            f"- Средний рейтинг вовлеченности: {engagement_metrics['avg_engagement_rate']:.2f}\n\n"
-            f"ВРЕМЕННАЯ АКТИВНОСТЬ:\n"
-            f"Самые активные недели:\n"
-            + "\n".join([f"- {week} неделя: {count} комментариев" for week, count in most_active_weeks])
+            f"BASIC_STATS\n"
+            f"Total Comments: {len(comments)}\n"
+            f"Total Likes: {sum(map(int, likes))}\n"
+            f"Unique Users: {len(set(usernames))}\n"
+            f"Activity Period: {max(weeks)}-{min(weeks)} weeks\n\n"
+            f"CONTENT_ANALYSIS\n"
+            f"Avg Comment Length: {sum(comment_lengths) / len(comments):.1f}\n"
+            f"Total Emojis: {total_emojis}\n"
+            f"Sentiment Distribution: {Counter(sentiments)}\n\n"
+            f"EXPERIMENTAL_METRICS\n"
+            f"Conversation Depth: {experimental_metrics['conversation_depth']}\n"
+            f"User Interaction Score: {experimental_metrics['user_interaction_score']:.2f}\n"
+            f"Sentiment Volatility: {experimental_metrics['sentiment_volatility']:.2f}\n"
+            f"Engagement Consistency: {experimental_metrics['engagement_consistency']:.2f}\n"
         )
         
-        return analytics_summary, usernames_output, comments_output, likes_chronology_output, str(total_likes_sum)
+        return analytics_summary, usernames_output, comments_output, likes_chronology_output, str(sum(map(int, likes)))
     
     except Exception as e:
         logger.error(f"Error in analyze_post: {e}", exc_info=True)
-        error_message = f"Произошла ошибка при обработке: {str(e)}\n{str(type(e))}"
-        return error_message, error_message, error_message, error_message, "0"
+        return str(e), "", "", "", "0"
 
 # Создаем интерфейс Gradio
 iface = gr.Interface(
     fn=analyze_post,
     inputs=[
-        gr.Radio(
-            choices=["Photo", "Video"],
-            label="Content Type",
-            value="Photo"
-        ),
-        gr.Textbox(
-            label="Link to Post",
-            placeholder="Введите ссылку на пост"
-        ),
-        gr.Number(
-            label="Likes",
-            value=0
-        ),
-        gr.Textbox(
-            label="Post Date",
-            placeholder="Введите дату публикации"
-        ),
-        gr.Textbox(
-            label="Description",
-            placeholder="Введите описание поста",
-            lines=3
-        ),
-        gr.Number(
-            label="Total Comment Count",
-            value=0
-        ),
-        gr.Textbox(
-            label="All Comments",
-            placeholder="Вставьте комментарии",
-            lines=10
-        )
+        gr.Radio(choices=["Photo", "Video"], label="Content Type", value="Photo"),
+        gr.Textbox(label="Link to Post"),
+        gr.Number(label="Likes", value=0),
+        gr.Textbox(label="Post Date"),
+        gr.Textbox(label="Description", lines=3),
+        gr.Number(label="Total Comment Count", value=0),
+        gr.Textbox(label="All Comments", lines=10)
     ],
     outputs=[
         gr.Textbox(label="Analytics Summary", lines=20),
-        gr.Textbox(label="Usernames (Output 1)", lines=5),
-        gr.Textbox(label="Comments (Output 2)", lines=5),
-        gr.Textbox(label="Likes Chronology (Output 3)", lines=5),
-        gr.Textbox(label="Total Likes on Comments (Output 4)")
+        gr.Textbox(label="Usernames"),
+        gr.Textbox(label="Comments"),
+        gr.Textbox(label="Likes Chronology"),
+        gr.Textbox(label="Total Likes on Comments")
     ],
-    title="Instagram Comment Analyzer Pro",
-    description="Расширенный анализатор комментариев Instagram с детальной аналитикой"
+    title="Enhanced Instagram Comment Analyzer",
+    description="Анализатор комментариев Instagram с расширенной аналитикой и CSV-форматированием"
 )
 
 if __name__ == "__main__":