Update app.py
Browse files
app.py
CHANGED
@@ -1,108 +1,87 @@
|
|
1 |
-
|
2 |
import re
|
3 |
-
from collections import Counter
|
4 |
-
from datetime import datetime
|
5 |
import emoji
|
6 |
-
import logging
|
7 |
-
from typing import Tuple, List, Optional
|
8 |
import statistics
|
9 |
-
import
|
|
|
|
|
10 |
from io import StringIO
|
|
|
11 |
|
12 |
-
# Настройка логирования
|
13 |
logging.basicConfig(level=logging.INFO)
|
14 |
logger = logging.getLogger(__name__)
|
15 |
|
16 |
-
|
17 |
-
"""
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
def count_emojis(text):
|
22 |
-
"""Подсчитывает количество эмодзи в тексте"""
|
23 |
-
return len([c for c in text if c in emoji.EMOJI_DATA])
|
24 |
-
|
25 |
-
def extract_mentions(text):
|
26 |
-
"""Извлекает упоминания пользователей из текста"""
|
27 |
-
return re.findall(r'@[\w\.]+', text)
|
28 |
-
|
29 |
-
def get_comment_words(text):
|
30 |
-
"""Получает список слов из комментария для анализа"""
|
31 |
-
words = re.findall(r'\w+', text.lower())
|
32 |
-
return [w for w in words if len(w) > 2]
|
33 |
-
|
34 |
-
def analyze_sentiment(text):
|
35 |
-
"""Расширенный анализ тональности по эмодзи и ключевым словам"""
|
36 |
-
positive_indicators = ['🔥', '❤️', '👍', '😊', '💪', '👏', '🎉', '♥️', '😍', '🙏',
|
37 |
-
'круто', 'супер', 'класс', 'огонь', 'пушка', 'отлично', 'здорово',
|
38 |
-
'прекрасно', 'молодец', 'красота', 'спасибо', 'топ', 'лучший',
|
39 |
-
'amazing', 'wonderful', 'great', 'perfect', 'love', 'beautiful']
|
40 |
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
'terrible', 'awful', 'sad', 'disappointed']
|
45 |
|
46 |
-
|
|
|
|
|
47 |
|
48 |
-
|
49 |
-
|
50 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
51 |
|
52 |
-
|
53 |
-
|
54 |
-
|
55 |
-
|
56 |
-
|
57 |
-
|
58 |
|
59 |
-
|
60 |
-
|
61 |
-
|
62 |
-
|
63 |
-
|
64 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
65 |
|
66 |
-
|
67 |
-
"""
|
68 |
-
|
69 |
-
|
70 |
-
username_patterns = [
|
71 |
r"Фото профиля ([^\n]+)",
|
72 |
r"^([^\s]+)\s+",
|
73 |
-
r"@([^\s]+)\s+"
|
74 |
-
]
|
75 |
-
|
76 |
-
time_patterns = [
|
77 |
r"(\d+)\s*(?:ч|нед)\.",
|
78 |
r"(\d+)\s*(?:h|w)",
|
79 |
-
r"(\d+)\s*(?:час|hour|week)"
|
80 |
-
]
|
81 |
-
|
82 |
-
likes_patterns = [
|
83 |
r"(\d+) отметк[аи] \"Нравится\"",
|
84 |
r"Нравится: (\d+)",
|
85 |
r"(\d+) отметка \"Нравится\"",
|
86 |
r"\"Нравится\": (\d+)",
|
87 |
-
r"likes?: (\d+)"
|
88 |
-
]
|
89 |
-
|
90 |
-
# Поиск имени пользователя
|
91 |
-
username = None
|
92 |
-
for pattern in username_patterns:
|
93 |
-
username_match = re.search(pattern, comment_text)
|
94 |
-
if username_match:
|
95 |
-
username = username_match.group(1).strip()
|
96 |
-
break
|
97 |
-
|
98 |
-
if not username:
|
99 |
-
return None, None, 0, 0
|
100 |
-
|
101 |
-
# Извлечение комментария
|
102 |
-
comment = comment_text
|
103 |
-
|
104 |
-
# Удаление метаданных
|
105 |
-
metadata_patterns = [
|
106 |
r"Фото профиля [^\n]+\n",
|
107 |
r"\d+\s*(?:ч|нед|h|w|час|hour|week)\.",
|
108 |
r"Нравится:?\s*\d+",
|
@@ -110,266 +89,198 @@ def extract_comment_data(comment_text):
|
|
110 |
r"Ответить",
|
111 |
r"Показать перевод",
|
112 |
r"Скрыть все ответы",
|
113 |
-
r"Смотреть все ответы \(\d+\)"
|
114 |
-
username
|
115 |
]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
116 |
|
117 |
-
|
118 |
-
|
|
|
|
|
|
|
|
|
119 |
|
120 |
-
|
121 |
-
|
122 |
-
|
123 |
-
|
124 |
-
|
125 |
-
|
126 |
-
|
127 |
-
time_value = int(time_match.group(1))
|
128 |
-
if any(unit in comment_text.lower() for unit in ['нед', 'w', 'week']):
|
129 |
-
weeks = time_value
|
130 |
-
else:
|
131 |
-
weeks = time_value / (24 * 7) # конвертация часов в недели
|
132 |
-
break
|
133 |
-
|
134 |
-
# Подсчет лайков
|
135 |
-
likes = 0
|
136 |
-
for pattern in likes_patterns:
|
137 |
-
likes_match = re.search(pattern, comment_text)
|
138 |
-
if likes_match:
|
139 |
-
likes = int(likes_match.group(1))
|
140 |
-
break
|
141 |
-
|
142 |
-
return username, comment.strip(), likes, weeks
|
143 |
|
144 |
-
|
145 |
-
|
146 |
-
|
|
|
|
|
|
|
|
|
|
|
147 |
|
148 |
def analyze_post(content_type: str, link_to_post: str, post_likes: int, post_date: str,
|
149 |
description: str, comment_count: int, all_comments: str) -> Tuple[str, str, str, str, str]:
|
150 |
-
"""
|
151 |
-
Анализирует пост Instagram и его комментарии
|
152 |
-
|
153 |
-
Args:
|
154 |
-
content_type: Тип контента (фото/видео)
|
155 |
-
link_to_post: Ссылка на пост
|
156 |
-
post_likes: Количество лайков поста
|
157 |
-
post_date: Дата публикации
|
158 |
-
description: Описание поста
|
159 |
-
comment_count: Ожидаемое количество комментариев
|
160 |
-
all_comments: Текст всех комментариев
|
161 |
-
|
162 |
-
Returns:
|
163 |
-
Tuple[str, str, str, str, str]: Кортеж с результатами анализа
|
164 |
-
"""
|
165 |
try:
|
166 |
-
# Разделение на
|
167 |
-
comment_patterns = [
|
168 |
r"(?=Фото профиля)",
|
169 |
r"(?=\n\s*[a-zA-Z0-9._]+\s+[^\n]+\n)",
|
170 |
r"(?=^[a-zA-Z0-9._]+\s+[^\n]+\n)",
|
171 |
r"(?=@[a-zA-Z0-9._]+\s+[^\n]+\n)"
|
172 |
-
]
|
|
|
|
|
173 |
|
174 |
-
|
175 |
-
|
176 |
-
|
177 |
|
178 |
-
|
179 |
-
usernames = []
|
180 |
-
comments = []
|
181 |
-
likes = []
|
182 |
-
weeks = []
|
183 |
-
total_emojis = 0
|
184 |
-
mentions = []
|
185 |
-
sentiments = []
|
186 |
-
comment_lengths = []
|
187 |
-
words_per_comment = []
|
188 |
-
all_words = []
|
189 |
-
user_engagement = {}
|
190 |
-
|
191 |
-
# Обработка комментариев
|
192 |
-
for block in comments_blocks:
|
193 |
-
if 'Скрыто алгоритмами Instagram' in block:
|
194 |
-
continue
|
195 |
-
|
196 |
-
username, comment, like_count, week_number = extract_comment_data(block)
|
197 |
-
if username and comment:
|
198 |
-
usernames.append(username)
|
199 |
-
comments.append(comment)
|
200 |
-
likes.append(str(like_count))
|
201 |
-
weeks.append(week_number)
|
202 |
-
|
203 |
-
# Сбор статистики
|
204 |
-
total_emojis += count_emojis(comment)
|
205 |
-
mentions.extend(extract_mentions(comment))
|
206 |
-
sentiment = analyze_sentiment(comment)
|
207 |
-
sentiments.append(sentiment)
|
208 |
-
comment_lengths.append(len(comment))
|
209 |
-
|
210 |
-
words = get_comment_words(comment)
|
211 |
-
words_per_comment.append(len(words))
|
212 |
-
all_words.extend(words)
|
213 |
-
|
214 |
-
# Обновление статистики пользователя
|
215 |
-
if username not in user_engagement:
|
216 |
-
user_engagement[username] = {
|
217 |
-
'comments': 0,
|
218 |
-
'total_likes': 0,
|
219 |
-
'emoji_usage': 0,
|
220 |
-
'avg_length': 0,
|
221 |
-
'sentiments': [],
|
222 |
-
'weeks': []
|
223 |
-
}
|
224 |
-
|
225 |
-
user_stats = user_engagement[username]
|
226 |
-
user_stats['comments'] += 1
|
227 |
-
user_stats['total_likes'] += like_count
|
228 |
-
user_stats['emoji_usage'] += count_emojis(comment)
|
229 |
-
user_stats['avg_length'] += len(comment)
|
230 |
-
user_stats['sentiments'].append(sentiment)
|
231 |
-
user_stats['weeks'].append(week_number)
|
232 |
-
|
233 |
-
# Расчет статистики
|
234 |
-
total_comments = len(comments)
|
235 |
-
if total_comments == 0:
|
236 |
return "No comments found", "", "", "", "0"
|
237 |
|
238 |
-
|
239 |
-
for
|
240 |
-
stats = user_engagement[username]
|
241 |
-
stats['avg_length'] /= stats['comments']
|
242 |
-
stats['engagement_rate'] = stats['total_likes'] / stats['comments']
|
243 |
-
stats['sentiment_ratio'] = sum(1 for s in stats['sentiments'] if s == 'positive') / len(stats['sentiments'])
|
244 |
-
stats['activity_period'] = max(stats['weeks']) - min(stats['weeks']) if stats['weeks'] else 0
|
245 |
-
|
246 |
-
# Базовая статистика
|
247 |
-
avg_comment_length = sum(comment_lengths) / total_comments
|
248 |
-
sentiment_distribution = Counter(sentiments)
|
249 |
-
most_active_users = Counter(usernames).most_common(5)
|
250 |
-
most_mentioned = Counter(mentions).most_common(5)
|
251 |
-
avg_likes = sum(map(int, likes)) / len(likes) if likes else 0
|
252 |
|
253 |
-
#
|
254 |
-
|
255 |
-
|
256 |
-
|
257 |
-
|
258 |
-
|
259 |
-
|
260 |
-
|
261 |
-
engagement_periods = {
|
262 |
-
'early': [],
|
263 |
-
'middle': [],
|
264 |
-
'late': []
|
265 |
-
}
|
266 |
-
|
267 |
-
for i, week in enumerate(weeks):
|
268 |
-
if week >= earliest_week - period_length:
|
269 |
-
engagement_periods['early'].append(i)
|
270 |
-
elif week >= earliest_week - 2 * period_length:
|
271 |
-
engagement_periods['middle'].append(i)
|
272 |
-
else:
|
273 |
-
engagement_periods['late'].append(i)
|
274 |
-
|
275 |
-
period_stats = {
|
276 |
-
period: {
|
277 |
-
'comments': len(indices),
|
278 |
-
'avg_likes': sum(int(likes[i]) for i in indices) / len(indices) if indices else 0,
|
279 |
-
'sentiment_ratio': sum(1 for i in indices if sentiments[i] == 'positive') / len(indices) if indices else 0
|
280 |
-
}
|
281 |
-
for period, indices in engagement_periods.items()
|
282 |
-
}
|
283 |
-
else:
|
284 |
-
period_stats = {}
|
285 |
-
earliest_week = 0
|
286 |
-
latest_week = 0
|
287 |
|
288 |
-
#
|
289 |
-
|
290 |
-
'
|
291 |
-
|
292 |
-
|
293 |
-
|
294 |
-
|
295 |
-
|
296 |
-
'expected_comments': comment_count
|
297 |
-
},
|
298 |
-
'basic_stats': {
|
299 |
-
'avg_comment_length': round(avg_comment_length, 2),
|
300 |
-
'median_comment_length': statistics.median(comment_lengths),
|
301 |
-
'avg_words': round(sum(words_per_comment) / total_comments, 2),
|
302 |
-
'total_emojis': total_emojis,
|
303 |
-
'avg_likes': round(avg_likes, 2)
|
304 |
-
},
|
305 |
-
'sentiment_stats': dict(Counter(sentiments)),
|
306 |
-
'period_analysis': period_stats,
|
307 |
-
'top_users': dict(most_active_users),
|
308 |
-
'top_mentioned': dict(most_mentioned)
|
309 |
}
|
310 |
|
311 |
-
#
|
312 |
-
|
313 |
-
writer = csv.writer(output)
|
314 |
-
for section, data in csv_data.items():
|
315 |
-
writer.writerow([section])
|
316 |
-
for key, value in data.items():
|
317 |
-
writer.writerow([key, value])
|
318 |
-
writer.writerow([])
|
319 |
-
csv_output = output.getvalue()
|
320 |
|
321 |
-
#
|
322 |
-
|
323 |
-
|
324 |
-
|
325 |
-
|
326 |
-
|
327 |
-
|
328 |
-
|
329 |
-
|
330 |
-
|
331 |
-
|
332 |
-
|
333 |
-
f"- Средняя длина комментария: {avg_comment_length:.1f} символов\n"
|
334 |
-
f"- Медиана длины: {statistics.median(comment_lengths)} символов\n"
|
335 |
-
f"- Среднее количество слов: {sum(words_per_comment) / total_comments:.1f}\n"
|
336 |
-
f"- Всего эмодзи: {total_emojis}\n"
|
337 |
-
f"- Тональность:\n"
|
338 |
-
f" * Позитивных: {sentiment_distribution['positive']}\n"
|
339 |
-
f" * Нейтральных: {sentiment_distribution['neutral']}\n"
|
340 |
-
f" * Негативных: {sentiment_distribution['negative']}\n\n"
|
341 |
-
f"АНАЛИЗ КОНТЕНТА:\n"
|
342 |
-
f"- Средняя длина: {avg_comment_length:.1f} символов\n"
|
343 |
-
f"- Медиана длины: {median_comment_length} символов\n"
|
344 |
-
f"- Среднее слов: {avg_words_per_comment:.1f}\n"
|
345 |
-
f"- Эмодзи: {total_emojis}\n"
|
346 |
-
f"- Тональность:\n"
|
347 |
-
f" * Позитив: {sentiment_distribution['positive']}\n"
|
348 |
-
f" * Нейтрально: {sentiment_distribution['neutral']}\n"
|
349 |
-
f" * Негатив: {sentiment_distribution['negative']}\n\n"
|
350 |
-
f"ПОПУЛЯРНЫЕ СЛОВА:\n"
|
351 |
-
+ "\n".join([f"- {word}: {count}" for word, count in common_words]) + "\n\n"
|
352 |
-
f"АКТИВНЫЕ ПОЛЬЗОВАТЕЛИ:\n"
|
353 |
-
+ "\n".join([f"- {user}: {count}" for user, count in most_active_users]) + "\n\n"
|
354 |
-
f"УПОМИНАНИЯ:\n"
|
355 |
-
+ "\n".join([f"- {user}: {count}" for user, count in most_mentioned if user]) + "\n\n"
|
356 |
-
f"АНАЛИЗ ПО ПЕРИОДАМ:\n"
|
357 |
-
+ "\n".join([f"- {period}: {stats['comments']} комментариев, {stats['avg_likes']:.1f} лайков/коммент, "
|
358 |
-
f"{stats['sentiment_ratio']*100:.1f}% позитивных"
|
359 |
-
for period, stats in period_stats.items()]) + "\n\n"
|
360 |
-
f"ЭКСПЕРИМЕНТАЛЬНАЯ АНАЛИТИКА:\n"
|
361 |
-
f"- Самый активный период: {max(period_stats.items(), key=lambda x: x[1]['comments'])[0]}\n"
|
362 |
-
f"- Наиболее позитивный период: {max(period_stats.items(), key=lambda x: x[1]['sentiment_ratio'])[0]}\n"
|
363 |
-
f"- Период с макс. вовлеченностью: {max(period_stats.items(), key=lambda x: x[1]['avg_likes'])[0]}"
|
364 |
)
|
365 |
|
366 |
-
return analytics_summary, "\n".join(usernames), "\n".join(comments), "\n".join(likes), str(sum(map(int, likes)))
|
367 |
-
|
368 |
except Exception as e:
|
369 |
logger.error(f"Error in analyze_post: {e}", exc_info=True)
|
370 |
return f"Error: {str(e)}", "", "", "", "0"
|
371 |
|
372 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
373 |
iface = gr.Interface(
|
374 |
fn=analyze_post,
|
375 |
inputs=[
|
@@ -389,7 +300,7 @@ iface = gr.Interface(
|
|
389 |
gr.Textbox(label="Total Likes on Comments")
|
390 |
],
|
391 |
title="Enhanced Instagram Comment Analyzer",
|
392 |
-
description="Анализатор комментариев Instagram с расширенной аналитикой
|
393 |
)
|
394 |
|
395 |
if __name__ == "__main__":
|
|
|
1 |
+
# analyzers.py
|
2 |
import re
|
|
|
|
|
3 |
import emoji
|
|
|
|
|
4 |
import statistics
|
5 |
+
from collections import Counter
|
6 |
+
from typing import Dict, List, Tuple, Optional
|
7 |
+
import logging
|
8 |
from io import StringIO
|
9 |
+
import csv
|
10 |
|
|
|
11 |
logging.basicConfig(level=logging.INFO)
|
12 |
logger = logging.getLogger(__name__)
|
13 |
|
14 |
+
class TextAnalyzer:
|
15 |
+
"""Класс для базового анализа текста"""
|
16 |
+
@staticmethod
|
17 |
+
def clean_text(text: str) -> str:
|
18 |
+
return re.sub(r'\s+', ' ', text).strip()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
|
20 |
+
@staticmethod
|
21 |
+
def count_emojis(text: str) -> int:
|
22 |
+
return len([c for c in text if c in emoji.EMOJI_DATA])
|
|
|
23 |
|
24 |
+
@staticmethod
|
25 |
+
def extract_mentions(text: str) -> List[str]:
|
26 |
+
return re.findall(r'@[\w\.]+', text)
|
27 |
|
28 |
+
@staticmethod
|
29 |
+
def get_words(text: str) -> List[str]:
|
30 |
+
return [w for w in re.findall(r'\w+', text.lower()) if len(w) > 2]
|
31 |
+
|
32 |
+
class SentimentAnalyzer:
|
33 |
+
"""Класс для анализа тональности"""
|
34 |
+
POSITIVE_INDICATORS = {
|
35 |
+
'emoji': ['🔥', '❤️', '👍', '😊', '💪', '👏', '🎉', '♥️', '😍', '🙏'],
|
36 |
+
'words': ['круто', 'супер', 'класс', 'огонь', 'пушка', 'отлично', 'здорово',
|
37 |
+
'прекрасно', 'молодец', 'красота', 'спасибо', 'топ', 'лучший',
|
38 |
+
'amazing', 'wonderful', 'great', 'perfect', 'love', 'beautiful']
|
39 |
+
}
|
40 |
|
41 |
+
NEGATIVE_INDICATORS = {
|
42 |
+
'emoji': ['👎', '😢', '😞', '😠', '😡', '💔', '😕', '😑'],
|
43 |
+
'words': ['плохо', 'ужас', 'отстой', 'фу', 'жесть', 'ужасно',
|
44 |
+
'разочарован', 'печаль', 'грустно', 'bad', 'worst',
|
45 |
+
'terrible', 'awful', 'sad', 'disappointed']
|
46 |
+
}
|
47 |
|
48 |
+
@classmethod
|
49 |
+
def analyze(cls, text: str) -> str:
|
50 |
+
text_lower = text.lower()
|
51 |
+
pos_count = sum(1 for ind in cls.POSITIVE_INDICATORS['emoji'] + cls.POSITIVE_INDICATORS['words']
|
52 |
+
if ind in text_lower)
|
53 |
+
neg_count = sum(1 for ind in cls.NEGATIVE_INDICATORS['emoji'] + cls.NEGATIVE_INDICATORS['words']
|
54 |
+
if ind in text_lower)
|
55 |
+
|
56 |
+
exclamation_boost = text.count('!') * 0.5
|
57 |
+
if pos_count > neg_count:
|
58 |
+
pos_count += exclamation_boost
|
59 |
+
elif neg_count > pos_count:
|
60 |
+
neg_count += exclamation_boost
|
61 |
+
|
62 |
+
return 'positive' if pos_count > neg_count else 'negative' if neg_count > pos_count else 'neutral'
|
63 |
|
64 |
+
class CommentExtractor:
|
65 |
+
"""Класс для извлечения данных из комментариев"""
|
66 |
+
PATTERNS = {
|
67 |
+
'username': [
|
|
|
68 |
r"Фото профиля ([^\n]+)",
|
69 |
r"^([^\s]+)\s+",
|
70 |
+
r"@([^\s]+)\s+"
|
71 |
+
],
|
72 |
+
'time': [
|
|
|
73 |
r"(\d+)\s*(?:ч|нед)\.",
|
74 |
r"(\d+)\s*(?:h|w)",
|
75 |
+
r"(\d+)\s*(?:час|hour|week)"
|
76 |
+
],
|
77 |
+
'likes': [
|
|
|
78 |
r"(\d+) отметк[аи] \"Нравится\"",
|
79 |
r"Нравится: (\d+)",
|
80 |
r"(\d+) отметка \"Нравится\"",
|
81 |
r"\"Нравится\": (\d+)",
|
82 |
+
r"likes?: (\d+)"
|
83 |
+
],
|
84 |
+
'metadata': [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
85 |
r"Фото профиля [^\n]+\n",
|
86 |
r"\d+\s*(?:ч|нед|h|w|час|hour|week)\.",
|
87 |
r"Нравится:?\s*\d+",
|
|
|
89 |
r"Ответить",
|
90 |
r"Показать перевод",
|
91 |
r"Скрыть все ответы",
|
92 |
+
r"Смотреть все ответы \(\d+\)"
|
|
|
93 |
]
|
94 |
+
}
|
95 |
+
|
96 |
+
@classmethod
|
97 |
+
def extract_data(cls, comment_text: str) -> Tuple[Optional[str], Optional[str], int, float]:
|
98 |
+
try:
|
99 |
+
# Извлечение имени пользователя
|
100 |
+
username = None
|
101 |
+
for pattern in cls.PATTERNS['username']:
|
102 |
+
if match := re.search(pattern, comment_text):
|
103 |
+
username = match.group(1).strip()
|
104 |
+
break
|
105 |
+
|
106 |
+
if not username:
|
107 |
+
return None, None, 0, 0
|
108 |
+
|
109 |
+
# Очистка комментария
|
110 |
+
comment = comment_text
|
111 |
+
for pattern in cls.PATTERNS['metadata'] + [username]:
|
112 |
+
comment = re.sub(pattern, '', comment)
|
113 |
+
comment = TextAnalyzer.clean_text(comment)
|
114 |
+
|
115 |
+
# Извлечение времени
|
116 |
+
weeks = 0
|
117 |
+
for pattern in cls.PATTERNS['time']:
|
118 |
+
if match := re.search(pattern, comment_text):
|
119 |
+
time_value = int(match.group(1))
|
120 |
+
if any(unit in comment_text.lower() for unit in ['нед', 'w', 'week']):
|
121 |
+
weeks = time_value
|
122 |
+
else:
|
123 |
+
weeks = time_value / (24 * 7)
|
124 |
+
break
|
125 |
+
|
126 |
+
# Извлечение лайков
|
127 |
+
likes = 0
|
128 |
+
for pattern in cls.PATTERNS['likes']:
|
129 |
+
if match := re.search(pattern, comment_text):
|
130 |
+
likes = int(match.group(1))
|
131 |
+
break
|
132 |
+
|
133 |
+
return username, comment, likes, weeks
|
134 |
+
|
135 |
+
except Exception as e:
|
136 |
+
logger.error(f"Error extracting comment data: {e}")
|
137 |
+
return None, None, 0, 0
|
138 |
+
|
139 |
+
class StatsCalculator:
|
140 |
+
"""Класс для расчета статистики"""
|
141 |
+
@staticmethod
|
142 |
+
def calculate_period_stats(weeks: List[float], likes: List[str], sentiments: List[str]) -> Dict:
|
143 |
+
if not weeks:
|
144 |
+
return {}
|
145 |
+
|
146 |
+
earliest_week = max(weeks)
|
147 |
+
latest_week = min(weeks)
|
148 |
+
week_range = earliest_week - latest_week
|
149 |
|
150 |
+
period_length = week_range / 3 if week_range > 0 else 1
|
151 |
+
engagement_periods = {
|
152 |
+
'early': [],
|
153 |
+
'middle': [],
|
154 |
+
'late': []
|
155 |
+
}
|
156 |
|
157 |
+
for i, week in enumerate(weeks):
|
158 |
+
if week >= earliest_week - period_length:
|
159 |
+
engagement_periods['early'].append(i)
|
160 |
+
elif week >= earliest_week - 2 * period_length:
|
161 |
+
engagement_periods['middle'].append(i)
|
162 |
+
else:
|
163 |
+
engagement_periods['late'].append(i)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
164 |
|
165 |
+
return {
|
166 |
+
period: {
|
167 |
+
'comments': len(indices),
|
168 |
+
'avg_likes': sum(int(likes[i]) for i in indices) / len(indices) if indices else 0,
|
169 |
+
'sentiment_ratio': sum(1 for i in indices if sentiments[i] == 'positive') / len(indices) if indices else 0
|
170 |
+
}
|
171 |
+
for period, indices in engagement_periods.items()
|
172 |
+
}
|
173 |
|
174 |
def analyze_post(content_type: str, link_to_post: str, post_likes: int, post_date: str,
|
175 |
description: str, comment_count: int, all_comments: str) -> Tuple[str, str, str, str, str]:
|
176 |
+
"""Основная функция анализа поста"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
177 |
try:
|
178 |
+
# Разделение на комментарии
|
179 |
+
comment_patterns = '|'.join([
|
180 |
r"(?=Фото профиля)",
|
181 |
r"(?=\n\s*[a-zA-Z0-9._]+\s+[^\n]+\n)",
|
182 |
r"(?=^[a-zA-Z0-9._]+\s+[^\n]+\n)",
|
183 |
r"(?=@[a-zA-Z0-9._]+\s+[^\n]+\n)"
|
184 |
+
])
|
185 |
+
comments_blocks = [block.strip() for block in re.split(comment_patterns, all_comments)
|
186 |
+
if block and block.strip() and 'Скрыто алгоритмами Instagram' not in block]
|
187 |
|
188 |
+
# Извлечение данных
|
189 |
+
data = [CommentExtractor.extract_data(block) for block in comments_blocks]
|
190 |
+
valid_data = [(u, c, l, w) for u, c, l, w in data if all((u, c))]
|
191 |
|
192 |
+
if not valid_data:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
193 |
return "No comments found", "", "", "", "0"
|
194 |
|
195 |
+
usernames, comments, likes, weeks = zip(*valid_data)
|
196 |
+
likes = [str(l) for l in likes]
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
197 |
|
198 |
+
# Анализ комментариев
|
199 |
+
comment_stats = {
|
200 |
+
'lengths': [len(c) for c in comments],
|
201 |
+
'words': [len(TextAnalyzer.get_words(c)) for c in comments],
|
202 |
+
'emojis': sum(TextAnalyzer.count_emojis(c) for c in comments),
|
203 |
+
'mentions': [m for c in comments for m in TextAnalyzer.extract_mentions(c)],
|
204 |
+
'sentiments': [SentimentAnalyzer.analyze(c) for c in comments]
|
205 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
|
207 |
+
# Расчет базовой статистики
|
208 |
+
basic_stats = {
|
209 |
+
'total_comments': len(comments),
|
210 |
+
'avg_length': statistics.mean(comment_stats['lengths']),
|
211 |
+
'median_length': statistics.median(comment_stats['lengths']),
|
212 |
+
'avg_words': statistics.mean(comment_stats['words']),
|
213 |
+
'total_likes': sum(map(int, likes)),
|
214 |
+
'avg_likes': statistics.mean(map(int, likes))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
215 |
}
|
216 |
|
217 |
+
# Расчет периодов
|
218 |
+
period_stats = StatsCalculator.calculate_period_stats(weeks, likes, comment_stats['sentiments'])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
219 |
|
220 |
+
# Создание отчета
|
221 |
+
csv_data = create_csv_report(content_type, link_to_post, post_likes, basic_stats,
|
222 |
+
comment_stats, period_stats, usernames, comment_stats['mentions'])
|
223 |
+
|
224 |
+
analytics_summary = create_text_report(basic_stats, comment_stats, period_stats, csv_data)
|
225 |
+
|
226 |
+
return (
|
227 |
+
analytics_summary,
|
228 |
+
"\n".join(usernames),
|
229 |
+
"\n".join(comments),
|
230 |
+
"\n".join(likes),
|
231 |
+
str(basic_stats['total_likes'])
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
232 |
)
|
233 |
|
|
|
|
|
234 |
except Exception as e:
|
235 |
logger.error(f"Error in analyze_post: {e}", exc_info=True)
|
236 |
return f"Error: {str(e)}", "", "", "", "0"
|
237 |
|
238 |
+
def create_csv_report(content_type, link, post_likes, basic_stats, comment_stats, period_stats, usernames, mentions):
|
239 |
+
"""Создание CSV отчета"""
|
240 |
+
csv_data = {
|
241 |
+
'metadata': {
|
242 |
+
'content_type': content_type,
|
243 |
+
'link': link,
|
244 |
+
'post_likes': post_likes
|
245 |
+
},
|
246 |
+
'basic_stats': basic_stats,
|
247 |
+
'sentiment_stats': dict(Counter(comment_stats['sentiments'])),
|
248 |
+
'period_analysis': period_stats,
|
249 |
+
'top_users': dict(Counter(usernames).most_common(5)),
|
250 |
+
'top_mentioned': dict(Counter(mentions).most_common(5))
|
251 |
+
}
|
252 |
+
|
253 |
+
output = StringIO()
|
254 |
+
writer = csv.writer(output)
|
255 |
+
for section, data in csv_data.items():
|
256 |
+
writer.writerow([section])
|
257 |
+
for key, value in data.items():
|
258 |
+
writer.writerow([key, value])
|
259 |
+
writer.writerow([])
|
260 |
+
return output.getvalue()
|
261 |
+
|
262 |
+
def create_text_report(basic_stats, comment_stats, period_stats, csv_data):
|
263 |
+
"""Создание текстового отчета"""
|
264 |
+
sentiment_dist = Counter(comment_stats['sentiments'])
|
265 |
+
return (
|
266 |
+
f"CSV DATA:\n{csv_data}\n\n"
|
267 |
+
f"СТАТИСТИКА:\n"
|
268 |
+
f"- Всего комментариев: {basic_stats['total_comments']}\n"
|
269 |
+
f"- Среднее лайков: {basic_stats['avg_likes']:.1f}\n"
|
270 |
+
f"АНАЛИЗ КОНТЕНТА:\n"
|
271 |
+
f"- Средняя длина: {basic_stats['avg_length']:.1f}\n"
|
272 |
+
f"- Медиана длины: {basic_stats['median_length']}\n"
|
273 |
+
f"- Среднее слов: {basic_stats['avg_words']:.1f}\n"
|
274 |
+
f"- Эмодзи: {comment_stats['emojis']}\n"
|
275 |
+
f"ТОНАЛЬНОСТЬ:\n"
|
276 |
+
f"- Позитив: {sentiment_dist['positive']}\n"
|
277 |
+
f"- Нейтрально: {sentiment_dist['neutral']}\n"
|
278 |
+
f"- Негатив: {sentiment_dist['negative']}\n"
|
279 |
+
)
|
280 |
+
|
281 |
+
# Создание интерфейса Gradio
|
282 |
+
import gradio as gr
|
283 |
+
|
284 |
iface = gr.Interface(
|
285 |
fn=analyze_post,
|
286 |
inputs=[
|
|
|
300 |
gr.Textbox(label="Total Likes on Comments")
|
301 |
],
|
302 |
title="Enhanced Instagram Comment Analyzer",
|
303 |
+
description="Анализатор комментариев Instagram с расширенной аналитикой"
|
304 |
)
|
305 |
|
306 |
if __name__ == "__main__":
|