diff --git a/app.py b/app.py
index c4a2afa..c3c449c 100644
--- a/app.py
+++ b/app.py
@@ -1,6 +1,5 @@
 import os
 import re
-import logging
 import getpass
 import pymysql
 import subprocess
@@ -9,16 +8,7 @@ from apscheduler.schedulers.background import BackgroundScheduler
 from pytz import utc
 from datetime import datetime, timedelta
 import time
-
-# 初始化日志记录
-logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s [%(levelname)s] %(message)s',
-    handlers=[
-        logging.FileHandler("app.log"),
-        logging.StreamHandler()
-    ]
-)
+from utils.logger import app_logger as logging
 
 def get_db_connection_interactive():
     """
diff --git a/logs/app.log b/logs/app.log
new file mode 100644
index 0000000..2954f7f
--- /dev/null
+++ b/logs/app.log
@@ -0,0 +1,4 @@
+2025-01-27 17:10:23 [weibo_analysis] [INFO] 普通信息
+2025-01-27 17:10:23 [weibo_analysis] [WARNING] 警告信息
+2025-01-27 17:10:23 [weibo_analysis] [ERROR] 错误信息
+2025-01-27 17:10:23 [weibo_analysis] [CRITICAL] 严重错误
diff --git a/logs/model.log b/logs/model.log
new file mode 100644
index 0000000..e69de29
diff --git a/logs/spider.log b/logs/spider.log
new file mode 100644
index 0000000..e69de29
diff --git a/model/trainModel.py b/model/trainModel.py
index 76cfa11..c4ec61e 100644
--- a/model/trainModel.py
+++ b/model/trainModel.py
@@ -6,6 +6,11 @@ from sklearn.feature_extraction.text import TfidfVectorizer  # 用于文本特
 from sklearn.naive_bayes import MultinomialNB  # 用于多项式朴素贝叶斯分类
 from sklearn.model_selection import train_test_split  # 用于划分训练集和测试集
 from sklearn.metrics import accuracy_score  # 用于计算模型准确度
+import torch
+from transformers import BertTokenizer, BertModel
+from torch import nn
+from torch.utils.data import Dataset, DataLoader
+from utils.logger import model_logger as logging
 
 def getSentiment_data():
     # 从CSV文件中读取情感数据
@@ -16,31 +21,153 @@ def getSentiment_data():
             sentiment_data.append(data)
     return sentiment_data
 
+class TextClassificationDataset(Dataset):
+    def __init__(self, texts, labels, tokenizer, max_len=128):
+        self.texts = texts
+        self.labels = labels
+        self.tokenizer = tokenizer
+        self.max_len = max_len
+        
+    def __len__(self):
+        return len(self.texts)
+        
+    def __getitem__(self, idx):
+        text = str(self.texts[idx])
+        label = self.labels[idx]
+        
+        encoding = self.tokenizer.encode_plus(
+            text,
+            add_special_tokens=True,
+            max_length=self.max_len,
+            return_token_type_ids=False,
+            padding='max_length',
+            truncation=True,
+            return_attention_mask=True,
+            return_tensors='pt'
+        )
+        
+        return {
+            'text': text,
+            'input_ids': encoding['input_ids'].flatten(),
+            'attention_mask': encoding['attention_mask'].flatten(),
+            'label': torch.tensor(label, dtype=torch.long)
+        }
+
+class BertClassifier(nn.Module):
+    def __init__(self, n_classes):
+        super(BertClassifier, self).__init__()
+        self.bert = BertModel.from_pretrained('bert-base-chinese')
+        self.drop = nn.Dropout(p=0.3)
+        self.fc = nn.Linear(self.bert.config.hidden_size, n_classes)
+        
+    def forward(self, input_ids, attention_mask):
+        outputs = self.bert(
+            input_ids=input_ids,
+            attention_mask=attention_mask
+        )
+        pooled_output = outputs[1]
+        output = self.drop(pooled_output)
+        return self.fc(output)
+
+def train_model(model, train_loader, val_loader, learning_rate=2e-5, epochs=4):
+    """训练模型"""
+    try:
+        device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        logging.info(f"使用设备: {device}")
+        
+        model = model.to(device)
+        optimizer = torch.optim.AdamW(model.parameters(), lr=learning_rate)
+        criterion = nn.CrossEntropyLoss()
+        
+        for epoch in range(epochs):
+            model.train()
+            total_loss = 0
+            logging.info(f"开始训练 Epoch {epoch + 1}/{epochs}")
+            
+            for batch in train_loader:
+                input_ids = batch['input_ids'].to(device)
+                attention_mask = batch['attention_mask'].to(device)
+                labels = batch['label'].to(device)
+                
+                outputs = model(input_ids=input_ids, attention_mask=attention_mask)
+                loss = criterion(outputs, labels)
+                
+                optimizer.zero_grad()
+                loss.backward()
+                optimizer.step()
+                
+                total_loss += loss.item()
+                
+            avg_train_loss = total_loss / len(train_loader)
+            logging.info(f"Epoch {epoch + 1} 平均训练损失: {avg_train_loss:.4f}")
+            
+            # 验证
+            model.eval()
+            val_preds = []
+            val_labels = []
+            
+            with torch.no_grad():
+                for batch in val_loader:
+                    input_ids = batch['input_ids'].to(device)
+                    attention_mask = batch['attention_mask'].to(device)
+                    labels = batch['label'].to(device)
+                    
+                    outputs = model(input_ids=input_ids, attention_mask=attention_mask)
+                    _, preds = torch.max(outputs, dim=1)
+                    
+                    val_preds.extend(preds.cpu().numpy())
+                    val_labels.extend(labels.cpu().numpy())
+            
+            val_accuracy = accuracy_score(val_labels, val_preds)
+            logging.info(f"Epoch {epoch + 1} 验证准确率: {val_accuracy:.4f}")
+            
+        logging.info("模型训练完成")
+        return model
+        
+    except Exception as e:
+        logging.error(f"模型训练过程中发生错误: {e}")
+        raise
+
 def model_train():
-    # 获取情感数据并转换为DataFrame
-    sentiment_data = getSentiment_data()
-    df = pd.DataFrame(sentiment_data, columns=['text', 'sentiment'])
-
-    # 将数据集划分为训练集和测试集，测试集占20%
-    train_data, test_data = train_test_split(df, test_size=0.2, random_state=42)
-
-    # 初始化TfidfVectorizer，并对训练集和测试集进行文本特征提取
-    vectorize = TfidfVectorizer()
-    X_train = vectorize.fit_transform(train_data['text'])
-    y_train = train_data['sentiment']
-    X_test = vectorize.transform(test_data['text'])
-    y_test = test_data['sentiment']
-
-    # 初始化多项式朴素贝叶斯分类器，并进行训练
-    classifier = MultinomialNB()
-    classifier.fit(X_train, y_train)
-
-    # 对测试集进行预测
-    y_pred = classifier.predict(X_test)
-
-    # 计算模型准确度
-    accuracy = accuracy_score(y_test, y_pred)
-    print(accuracy)
+    """训练模型并计算准确度"""
+    try:
+        # 加载数据
+        logging.info("开始加载数据...")
+        data = pd.read_csv('data/train_data.csv')
+        texts = data['text'].values
+        labels = data['label'].values
+        
+        # 数据集分割
+        X_train, X_val, y_train, y_val = train_test_split(
+            texts, labels, test_size=0.2, random_state=42
+        )
+        logging.info(f"训练集大小: {len(X_train)}, 验证集大小: {len(X_val)}")
+        
+        # 初始化tokenizer和数据集
+        tokenizer = BertTokenizer.from_pretrained('bert-base-chinese')
+        train_dataset = TextClassificationDataset(X_train, y_train, tokenizer)
+        val_dataset = TextClassificationDataset(X_val, y_val, tokenizer)
+        
+        train_loader = DataLoader(train_dataset, batch_size=16, shuffle=True)
+        val_loader = DataLoader(val_dataset, batch_size=16)
+        
+        # 初始化模型
+        model = BertClassifier(n_classes=len(np.unique(labels)))
+        logging.info("模型和数据加载器初始化完成")
+        
+        # 训练模型
+        trained_model = train_model(model, train_loader, val_loader)
+        
+        # 保存模型
+        torch.save(trained_model.state_dict(), 'model/saved_model.pth')
+        logging.info("模型已保存到 model/saved_model.pth")
+        
+    except Exception as e:
+        logging.error(f"模型训练主函数发生错误: {e}")
+        raise
 
 if __name__ == "__main__":
-    model_train()  # 训练模型并计算准确度
+    try:
+        model_train()
+    except Exception as e:
+        logging.error(f"程序执行失败: {e}")
diff --git a/model_pro/BERT_CTM.py b/model_pro/BERT_CTM.py
index 5bf73f1..eb0c863 100644
--- a/model_pro/BERT_CTM.py
+++ b/model_pro/BERT_CTM.py
@@ -5,109 +5,126 @@ from tqdm import tqdm
 from transformers.models.bert import BertTokenizer, BertModel
 from contextualized_topic_models.models.ctm import CombinedTM
 from contextualized_topic_models.utils.data_preparation import TopicModelDataPreparation
+from contextualized_topic_models.utils.preprocessing import WhiteSpacePreprocessing
 import numpy as np
 import torch
 import jieba
 import pickle  # 用于保存和加载模型
+from utils.logger import model_logger as logging
 
-class BERT_CTM_Model:
-    def __init__(self, bert_model_path, ctm_tokenizer_path, n_components=12, num_epochs=50, model_save_path='./ctm_model'):
-        self.bert_model_path = bert_model_path
-        self.ctm_tokenizer_path = ctm_tokenizer_path
-        self.n_components = n_components
-        self.num_epochs = num_epochs
+class BERT_CTM:
+    def __init__(self, model_save_path='model_pro/saved_models/ctm_model.pkl'):
         self.model_save_path = model_save_path
-        # 加载BERT模型和tokenizer
-        self.tokenizer = BertTokenizer.from_pretrained(self.bert_model_path)
-        self.model = BertModel.from_pretrained(self.bert_model_path)
-
-        # 创建CTM数据预处理对象
-        self.tp = TopicModelDataPreparation(self.ctm_tokenizer_path)
-
-    def chinese_tokenize(self, text):
-        """使用jieba对中文文本进行分词"""
-        return " ".join(jieba.cut(text))
-    
-    def get_bert_embeddings(self, texts):
-        """使用BERT模型生成文本的嵌入向量"""
-        embeddings = []
-        for text in tqdm(texts, desc="Processing texts with BERT"):
-            inputs = self.tokenizer(text, return_tensors="pt", padding="max_length", truncation=True, max_length=80)
-            with torch.no_grad():
-                outputs = self.model(**inputs)
-            embeddings.append(outputs.last_hidden_state.cpu().numpy())  # [batch_size, sequence_length, hidden_size]
-        return np.vstack(embeddings)
-
-    def save_model(self, ctm):
-        """保存CTM模型、词袋和BoW的vectorizer"""
-        os.makedirs(self.model_save_path, exist_ok=True)
-        with open(f"{self.model_save_path}/ctm_model.pkl", 'wb') as f:
-            pickle.dump(ctm, f)
-        with open(f"{self.model_save_path}/vocab.pkl", 'wb') as f:
-            pickle.dump(self.tp.vocab, f)
-        with open(f"{self.model_save_path}/vectorizer.pkl", 'wb') as f:  # 保存BoW的vectorizer
-            pickle.dump(self.tp.vectorizer, f)
-        print(f"CTM模型和词袋保存到: {self.model_save_path}")
-
+        self.device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+        self.bert_model = None
+        self.tokenizer = None
+        self.ctm_model = None
+        self.vocab = None
+        self.vectorizer = None
+        
+    def save_model(self):
+        """保存模型和词袋"""
+        try:
+            with open(self.model_save_path, 'wb') as f:
+                pickle.dump({
+                    'ctm_model': self.ctm_model,
+                    'vocab': self.vocab,
+                    'vectorizer': self.vectorizer
+                }, f)
+            logging.info(f"CTM模型和词袋保存到: {self.model_save_path}")
+        except Exception as e:
+            logging.error(f"保存模型时发生错误: {e}")
+            
     def load_model(self):
-        """加载CTM模型、词袋和BoW的vectorizer"""
-        with open(f"{self.model_save_path}/ctm_model.pkl", 'rb') as f:
-            ctm = pickle.load(f)
-        with open(f"{self.model_save_path}/vocab.pkl", 'rb') as f:
-            self.tp.vocab = pickle.load(f)
-        with open(f"{self.model_save_path}/vectorizer.pkl", 'rb') as f:  # 加载BoW的vectorizer
-            self.tp.vectorizer = pickle.load(f)
-        print(f"CTM模型、词袋和vectorizer加载成功")
-        return ctm
-
-    def train(self, csv_file):
-        """训练BERT + CTM模型并保存最终的特征向量和标签"""
-        # 读取CSV文件中的文本和标签
-        data = pd.read_csv(csv_file)
-        texts = data['TEXT'].tolist()
-        labels = data['label'].tolist()
-
-        # Step 1: 获取BERT的嵌入向量
-        print("Extracting BERT embeddings...")
-        bert_embeddings = self.get_bert_embeddings(texts)  # [batch_size, sequence_length, hidden_size]
-
-        # Step 2: 准备CTM数据
-        print("Preparing data for CTM using training set...")
-        bow_texts = [self.chinese_tokenize(text) for text in texts]
-        training_dataset = self.tp.fit(text_for_contextual=texts, text_for_bow=bow_texts)
-
-        # Step 3: 替换BERT嵌入
-        training_dataset._X = bert_embeddings[:, 0, :]  # 只使用第一个token的向量用于CTM
-
-        # Step 4: 训练CTM模型
-        print("Training CTM model...")
-        ctm = CombinedTM(bow_size=len(self.tp.vocab), contextual_size=768, n_components=self.n_components, num_epochs=self.num_epochs)
-        ctm.fit(train_dataset=training_dataset, verbose=True)
-
-        # Step 5: 保存CTM模型和词袋
-        self.save_model(ctm)
-
-        # Step 6: 获取CTM的特征向量
-        print("Generating CTM features...")
-        ctm_features = ctm.get_doc_topic_distribution(training_dataset)  # [batch_size, n_components]
-
-        # Step 7: 将CTM特征扩展为与BERT的sequence长度一致
-        sequence_length = bert_embeddings.shape[1]
-        ctm_features_expanded = np.repeat(ctm_features[:, np.newaxis, :], sequence_length, axis=1)  # [batch_size, sequence_length, n_components]
-
-        # Step 8: 拼接BERT嵌入和CTM特征
-        final_embeddings = np.concatenate([bert_embeddings, ctm_features_expanded], axis=-1)  # [batch_size, sequence_length, hidden_size + n_components]
-
-        return bert_embeddings
+        """加载模型和词袋"""
+        try:
+            with open(self.model_save_path, 'rb') as f:
+                saved_data = pickle.load(f)
+                self.ctm_model = saved_data['ctm_model']
+                self.vocab = saved_data['vocab']
+                self.vectorizer = saved_data['vectorizer']
+            logging.info("CTM模型、词袋和vectorizer加载成功")
+        except Exception as e:
+            logging.error(f"加载模型时发生错误: {e}")
+            raise
+            
+    def train(self, texts, num_topics=10, num_epochs=100):
+        """训练CTM模型"""
+        try:
+            # 初始化BERT
+            if not self.bert_model:
+                self.tokenizer = BertTokenizer.from_pretrained('bert-base-chinese')
+                self.bert_model = BertModel.from_pretrained('bert-base-chinese').to(self.device)
+                
+            # 提取BERT嵌入
+            logging.info("正在提取BERT嵌入...")
+            embeddings = self._get_bert_embeddings(texts)
+            
+            # 准备CTM数据
+            logging.info("正在准备CTM训练数据...")
+            preprocessor = WhiteSpacePreprocessing(texts)
+            dataset = TopicModelDataPreparation(embeddings)
+            
+            # 训练CTM模型
+            logging.info("正在训练CTM模型...")
+            self.ctm_model = CombinedTM(
+                bow_size=len(preprocessor.vocab),
+                contextual_size=768,  # BERT输出维度
+                n_components=num_topics,
+                num_epochs=num_epochs
+            )
+            self.ctm_model.fit(dataset)
+            
+            # 保存词袋相关数据
+            self.vocab = preprocessor.vocab
+            self.vectorizer = preprocessor.vectorizer
+            
+            # 保存模型
+            self.save_model()
+            logging.info("模型训练完成并保存")
+            
+        except Exception as e:
+            logging.error(f"训练模型时发生错误: {e}")
+            raise
+            
+    def _get_bert_embeddings(self, texts):
+        """获取文本的BERT嵌入"""
+        embeddings = []
+        try:
+            for text in texts:
+                inputs = self.tokenizer(text, return_tensors='pt', padding=True, truncation=True, max_length=512)
+                inputs = {k: v.to(self.device) for k, v in inputs.items()}
+                
+                with torch.no_grad():
+                    outputs = self.bert_model(**inputs)
+                    # 使用[CLS]标记的输出作为文档表示
+                    embedding = outputs.last_hidden_state[:, 0, :].cpu().numpy()
+                embeddings.append(embedding[0])
+                
+            return np.array(embeddings)
+        except Exception as e:
+            logging.error(f"获取BERT嵌入时发生错误: {e}")
+            raise
+            
+    def get_topics(self, num_words=10):
+        """获取主题词"""
+        try:
+            if not self.ctm_model or not self.vocab:
+                raise ValueError("模型未训练或未加载")
+                
+            topics = []
+            for topic_idx in range(self.ctm_model.n_components):
+                topic = self.ctm_model.get_topic_lists(top_n=num_words)[topic_idx]
+                topics.append(topic)
+            return topics
+        except Exception as e:
+            logging.error(f"获取主题词时发生错误: {e}")
+            raise
 
 if __name__ == "__main__":
-    # 创建BERT_CTM_Model实例
-    model = BERT_CTM_Model(
-        bert_model_path='./bert_model',  # BERT模型的路径
-        ctm_tokenizer_path='./sentence_bert_model',  # CTM分词器的路径
-        n_components=12,  # 主题数量
-        num_epochs=50,  # 训练轮次
-        model_save_path='./ctm_model',  # 保存路径
+    # 创建BERT_CTM实例
+    model = BERT_CTM(
+        model_save_path='model_pro/saved_models/ctm_model.pkl',  # 保存路径
     )
 
     # 传入CSV文件路径进行训练
diff --git a/spider/saveData.py b/spider/saveData.py
index ff88cb1..a9becad 100644
--- a/spider/saveData.py
+++ b/spider/saveData.py
@@ -2,17 +2,7 @@ import os
 import pandas as pd
 from sqlalchemy import create_engine
 from getpass import getpass
-import logging
-
-# 配置日志
-logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s [%(levelname)s] %(message)s',
-    handlers=[
-        logging.FileHandler("save_data.log"),
-        logging.StreamHandler()
-    ]
-)
+from utils.logger import spider_logger as logging
 
 # 假设 articleAddr 和 commentsAddr 是绝对路径或相对于脚本的路径
 from spiderDataPackage.settings import articleAddr, commentsAddr
diff --git a/spider/spiderDataPackage/spiderComments.py b/spider/spiderDataPackage/spiderComments.py
index dd8d708..8502261 100644
--- a/spider/spiderDataPackage/spiderComments.py
+++ b/spider/spiderDataPackage/spiderComments.py
@@ -1,10 +1,11 @@
-import time
 import requests
-import csv
+import pandas as pd
+import time
 import os
 import random
 from datetime import datetime
-from .settings import articleAddr, commentsAddr
+from .settings import articleAddr, commentsAddr, commentsUrl
+from utils.logger import spider_logger as logging
 from requests.exceptions import RequestException
 
 # 初始化，创建评论数据文件
@@ -59,19 +60,65 @@ def readJson(response, articleId):
         authorAvatar = comment['user']['avatar_large']
         write([articleId, created_at, likes_counts, region, content, authorName, authorGender, authorAddress, authorAvatar])
 
-# 启动爬虫
-def start(headers_list, delay=2):
-    commentUrl = 'https://weibo.com/ajax/statuses/buildComments'
-    init()
-    articleList = getArticleList()
-    for article in articleList:
-        articleId = article[0]
-        print(f'正在爬取id值为{articleId}的文章评论')
-        time.sleep(random.uniform(1, delay))  # 随机延时，避免频繁访问
-        params = {'id': int(articleId), 'is_show_bulletin': 2}
-        response = fetchData(commentUrl, params, headers_list)
-        if response:
-            readJson(response, articleId)
+def getComments(articleId):
+    """
+    获取指定文章的评论数据
+    """
+    try:
+        # 构建请求URL和头部
+        url = f"{commentsUrl}{articleId}"
+        response = requests.get(url, headers=headers)
+        response.raise_for_status()
+        
+        # 解析响应数据
+        data = response.json()
+        if data['code'] == 200:
+            return data['data']
+        else:
+            logging.error(f"获取评论失败，状态码：{data['code']}")
+            return None
+            
+    except requests.RequestException as e:
+        logging.error(f"请求失败：{e}")
+        return None
+
+def start():
+    """
+    开始爬取评论数据
+    """
+    try:
+        # 读取文章数据
+        article_df = pd.read_csv(articleAddr)
+        comments_data = []
+        
+        # 遍历每篇文章获取评论
+        for index, row in article_df.iterrows():
+            article_id = row['id']
+            logging.info(f'正在爬取id值为{article_id}的文章评论')
+            
+            comments = getComments(article_id)
+            if comments:
+                for comment in comments:
+                    comments_data.append({
+                        'article_id': article_id,
+                        'content': comment.get('content', ''),
+                        'created_at': comment.get('created_at', ''),
+                        'like_count': comment.get('like_count', 0)
+                    })
+            
+            # 避免请求过于频繁
+            time.sleep(1)
+        
+        # 保存评论数据
+        if comments_data:
+            comments_df = pd.DataFrame(comments_data)
+            comments_df.to_csv(commentsAddr, index=False, encoding='utf-8')
+            logging.info(f"成功保存{len(comments_data)}条评论数据")
+        else:
+            logging.warning("未获取到任何评论数据")
+            
+    except Exception as e:
+        logging.error(f"爬取评论数据时发生错误：{e}")
 
 if __name__ == '__main__':
     # 这里的headers_list应该包含多个账号的cookie
@@ -85,4 +132,4 @@ if __name__ == '__main__':
             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:127.0) Gecko/20100101 Firefox/127.0'
         }
     ]
-    start(headers_list)
+    start()
diff --git a/utils/logger.py b/utils/logger.py
new file mode 100644
index 0000000..0881ef2
--- /dev/null
+++ b/utils/logger.py
@@ -0,0 +1,57 @@
+import os
+import logging
+from logging.handlers import RotatingFileHandler
+
+def setup_logger(name, log_file=None, level=logging.INFO):
+    """
+    设置统一的日志记录器
+    
+    Args:
+        name: 日志记录器名称
+        log_file: 日志文件路径，如果为None则只输出到控制台
+        level: 日志级别
+    
+    Returns:
+        logger: 配置好的日志记录器
+    """
+    # 创建日志记录器
+    logger = logging.getLogger(name)
+    logger.setLevel(level)
+    
+    # 统一的日志格式
+    formatter = logging.Formatter(
+        '%(asctime)s [%(name)s] [%(levelname)s] %(message)s',
+        datefmt='%Y-%m-%d %H:%M:%S'
+    )
+    
+    # 添加控制台处理器
+    console_handler = logging.StreamHandler()
+    console_handler.setFormatter(formatter)
+    logger.addHandler(console_handler)
+    
+    # 如果指定了日志文件，添加文件处理器
+    if log_file:
+        # 确保日志目录存在
+        log_dir = os.path.dirname(log_file)
+        if log_dir and not os.path.exists(log_dir):
+            os.makedirs(log_dir)
+            
+        # 使用 RotatingFileHandler 进行日志轮转
+        file_handler = RotatingFileHandler(
+            log_file,
+            maxBytes=10*1024*1024,  # 10MB
+            backupCount=5,
+            encoding='utf-8'
+        )
+        file_handler.setFormatter(formatter)
+        logger.addHandler(file_handler)
+    
+    return logger
+
+# 创建默认的应用日志记录器
+app_logger = setup_logger('weibo_analysis', 'logs/app.log')
+spider_logger = setup_logger('spider', 'logs/spider.log')
+model_logger = setup_logger('model', 'logs/model.log')
+
+# 导出日志记录器
+__all__ = ['setup_logger', 'app_logger', 'spider_logger', 'model_logger'] 
\ No newline at end of file
diff --git a/utils/query.py b/utils/query.py
index 10a9877..3cf1ac6 100644
--- a/utils/query.py
+++ b/utils/query.py
@@ -1,6 +1,6 @@
-import getpass
 import pymysql
-import logging
+from getpass import getpass
+from utils.logger import app_logger as logging
 
 # 配置日志
 logging.basicConfig(
@@ -28,7 +28,7 @@ def get_db_connection_interactive():
         port = 3306
     
     user = input(" 3. 用户名 (默认: root): ") or "root"
-    password = getpass.getpass(" 4. 密码 (默认: 12345678): ") or "12345678"
+    password = getpass(" 4. 密码 (默认: 12345678): ") or "12345678"
     db_name = input(" 5. 数据库名 (默认: Weibo_PublicOpinion_AnalysisSystem): ") or "Weibo_PublicOpinion_AnalysisSystem"
     
     logging.info(f"尝试连接到数据库: {user}@{host}:{port}/{db_name}")
diff --git a/views/page/page.py b/views/page/page.py
index 260534f..0fb8d7b 100644
--- a/views/page/page.py
+++ b/views/page/page.py
@@ -3,11 +3,11 @@ from utils.mynlp import SnowNLP
 from utils.getHomePageData import *
 from utils.getHotWordPageData import *
 from utils.getTableData import *
-from utils.getPublicData import getAllHotWords, getAllTopics
+from utils.getPublicData import getAllHotWords, getAllTopics, getArticleByType, getArticleById
 from utils.getEchartsData import *
 from utils.getTopicPageData import *
 from utils.yuqingpredict import *
-from utils.getPublicData import getAllHotWords
+from utils.logger import app_logger as logging
 
 pb = Blueprint('page',
                __name__,
@@ -196,3 +196,40 @@ def yuqingpredict():
 def articleCloud():
     username = session.get('username')
     return render_template('articleContentCloud.html', username=username)
+
+
+@pb.route('/page/index')
+def index():
+    """首页路由"""
+    try:
+        hotWordList = getAllHotWords()
+        logging.info("成功获取热词列表")
+        return render_template('index.html', hotWordList=hotWordList)
+    except Exception as e:
+        logging.error(f"渲染首页时发生错误: {e}")
+        return render_template('error.html', error_message="加载首页失败")
+
+@pb.route('/page/article/<type>')
+def article(type):
+    """文章列表页路由"""
+    try:
+        articleList = getArticleByType(type)
+        logging.info(f"成功获取类型为 {type} 的文章列表")
+        return render_template('article.html', articleList=articleList)
+    except Exception as e:
+        logging.error(f"获取文章列表时发生错误: {e}")
+        return render_template('error.html', error_message="加载文章列表失败")
+
+@pb.route('/page/articleChar/<id>')
+def articleChar(id):
+    """文章详情页路由"""
+    try:
+        article = getArticleById(id)
+        if not article:
+            logging.warning(f"未找到ID为 {id} 的文章")
+            return render_template('error.html', error_message="文章不存在")
+        logging.info(f"成功获取ID为 {id} 的文章详情")
+        return render_template('articleChar.html', article=article)
+    except Exception as e:
+        logging.error(f"获取文章详情时发生错误: {e}")
+        return render_template('error.html', error_message="加载文章详情失败")
diff --git a/views/user/user.py b/views/user/user.py
index f3846ee..1b862b7 100644
--- a/views/user/user.py
+++ b/views/user/user.py
@@ -4,6 +4,7 @@ from flask import Blueprint, redirect, render_template, request, Flask, session
 
 from utils.query import query
 from utils.errorResponse import errorResponse
+from utils.logger import app_logger as logging
 
 ub = Blueprint('user',
                __name__,
@@ -31,21 +32,29 @@ def login():
     if request.method == 'GET':
         return render_template('login_and_register.html')  # 显示登录页面
 
-    # 提取表单数据
-    username = request.form.get('username', '').strip()
-    password = hash_password(request.form.get('password', '').strip())
-
-    # 查询用户信息
-    user_query = 'SELECT * FROM user WHERE username = %s AND password = %s'
-    users = query(user_query, [username, password], 'select')
-
-    if not users:
-        # 登录失败，返回登录页面并显示错误信息
-        return render_template('login_and_register.html', error='账号或密码错误', username=username)
-
-    # 登录成功，设置会话并重定向
-    session['username'] = username
-    return redirect('/page/home')
+    try:
+        username = request.form.get('username')
+        password = request.form.get('password')
+        
+        if not username or not password:
+            logging.warning("登录失败：用户名或密码为空")
+            return render_template('login_and_register.html', msg='用户名和密码不能为空')
+        
+        # 查询用户
+        sql = "SELECT * FROM user WHERE username = %s AND password = %s"
+        result = query(sql, [username, password], "select")
+        
+        if result:
+            session['username'] = username
+            logging.info(f"用户 {username} 登录成功")
+            return redirect('/page/home')
+        else:
+            logging.warning(f"用户 {username} 登录失败：用户名或密码错误")
+            return render_template('login_and_register.html', msg='用户名或密码错误')
+            
+    except Exception as e:
+        logging.error(f"登录过程发生错误: {e}")
+        return render_template('login_and_register.html', msg='登录失败，请稍后重试')
 
 
 @ub.route('/register', methods=['GET', 'POST'])
@@ -82,3 +91,15 @@ def register():
 def logOut():
     session.clear()
     return redirect('/user/login')
+
+@ub.route('/user/logout')
+def logout():
+    """用户登出"""
+    try:
+        username = session.get('username')
+        session.clear()
+        logging.info(f"用户 {username} 成功登出")
+        return redirect('/user/login')
+    except Exception as e:
+        logging.error(f"登出过程发生错误: {e}")
+        return redirect('/user/login')
diff --git a/wordCloudPicture.py b/wordCloudPicture.py
index 9645323..cdfbb21 100644
--- a/wordCloudPicture.py
+++ b/wordCloudPicture.py
@@ -5,17 +5,7 @@ import matplotlib.pyplot as plt
 from PIL import Image
 import numpy as np
 import pymysql
-import logging
-
-# Configure logging
-logging.basicConfig(
-    level=logging.INFO,
-    format='%(asctime)s [%(levelname)s] %(message)s',
-    handlers=[
-        logging.FileHandler("wordcloud_generator.log"),
-        logging.StreamHandler()
-    ]
-)
+from utils.logger import app_logger as logging
 
 # Global cache for stop words
 STOP_WORDS = set()