完成股吧数据分析项目：

1. 修复词云断句问题 - 添加英文单词过滤
2. 创建 Word2Vec + CNN 情绪感知模型
3. 创建情绪时间序列分析脚本（基于大连理工大学情感词典）
4. 添加停用词文件（1427个中英文停用词）
5. 更新 analyze.py 保存时间字段 post_publish_time
6. 更新 requirements.txt 添加必要依赖

.gitignore

@@ -0,0 +1,3 @@
+data/*
+output/*
+sentiment_output/*

README.md

@@ -0,0 +1,163 @@
+# 股吧数据爬取与情感分析系统
+
+基于东方财富网股吧数据的爬虫系统，支持数据爬取、情感分析和关键词挖掘。
+
+## 功能特性
+
+- 🕷️ **股吧数据爬取** - 自动爬取指定股票的股吧帖子
+- 😊 **情感分析** - 基于大连理工大学情感词汇本体进行情绪计算
+- 🔍 **关键词挖掘** - 使用TF-IDF算法提取热门话题
+- 📊 **可视化输出** - 生成词云、情绪分布图等可视化图表
+
+## 项目结构
+
+```
+guba2vec/
+├── spider.py              # 股吧数据爬虫
+├── sentiment_analysis.py  # 情感分析模块
+├── analyze.py             # TF-IDF关键词分析
+├── requirements.txt       # 依赖列表
+├── 大连理工大学中文情感词汇本体.xlsx  # 情感词典
+└── data/                  # 爬取数据存储目录
+    └── guba_*.json/xlsx
+```
+
+## 安装依赖
+
+```bash
+pip install -r requirements.txt
+```
+
+## 使用方法
+
+### 1. 爬取股吧数据
+
+```bash
+python spider.py
+```
+
+默认爬取以下游戏行业股票：
+- 完美世界 (002624)
+- 三七互娱 (002555)
+- 巨人网络 (002558)
+- 世纪华通 (002602)
+- 昆仑万维 (300418)
+- 游族网络 (002174)
+- 掌趣科技 (300315)
+- 吉比特 (603444)
+
+爬取结果保存在 `data/` 目录下，包含 JSON 和 Excel 两种格式。
+
+### 2. 情感分析
+
+```bash
+python sentiment_analysis.py
+```
+
+基于大连理工大学中文情感词汇本体进行情绪分析，支持7种情绪类型：
+- 正面情绪：快乐、好评、惊讶
+- 负面情绪：愤怒、悲伤、恐惧、厌恶
+
+分析结果保存在 `sentiment_output/` 目录，包含：
+- 各股票详细情感数据（CSV）
+- 情绪统计汇总（CSV）
+- 可视化图表（PNG）
+
+### 3. 关键词分析
+
+```bash
+python analyze.py
+```
+
+使用TF-IDF算法提取关键词并生成词云，结果保存在 `output/` 目录。
+
+## 核心模块说明
+
+### spider.py
+
+主要函数：
+- `fetch_guba_data(code, page, page_size, sort_type)` - 爬取单页数据
+- `fetch_stock_posts(code, name, pages, page_size)` - 爬取多页数据
+- `save_to_json(data, name, filename)` - 保存为JSON格式
+- `save_to_excel(data, name, filename)` - 保存为Excel格式
+
+### sentiment_analysis.py
+
+主要函数：
+- `build_sentiment_dictionary()` - 构建情感词典
+- `emotion_caculate(text, sentiment_dict)` - 计算文本情绪
+- `load_and_analyze_data(data_dir, output_dir)` - 批量分析数据
+- `generate_visualizations()` - 生成可视化图表
+
+### analyze.py
+
+主要函数：
+- `clean_text(text)` - 文本清洗
+- `tokenize(text)` - 中文分词
+- `calculate_tfidf(texts)` - 计算TF-IDF
+- `get_top_keywords()` - 获取Top关键词
+- `generate_wordcloud()` - 生成词云
+
+## 情感词典
+
+使用 **大连理工大学中文情感词汇本体**（需自行准备），包含：
+- 27469个情感词汇
+- 7种情感分类
+- 3种强度等级
+- 2种极性（正面/负面）
+
+备用方案：内置简化版情感词典，包含约200个常用情感词。
+
+## 数据格式
+
+### 爬取数据 (JSON)
+```json
+{
+  "stock_code": "002624",
+  "stock_name": "完美世界",
+  "total_pages": 10,
+  "total_posts": 200,
+  "crawl_time": "2024-01-01T12:00:00",
+  "posts": [
+    {
+      "post_id": "123456",
+      "post_title": "标题",
+      "post_content": "内容",
+      "post_user": {"user_nickname": "用户名"},
+      "post_publish_time": "2024-01-01 10:00",
+      "post_click_count": 100,
+      "post_comment_count": 10,
+      "post_like_count": 5
+    }
+  ]
+}
+```
+
+### 情感分析结果 (CSV)
+| 帖子ID | 标题 | 内容 | positive | negative | sentiment_score |
+|--------|------|------|----------|----------|-----------------|
+| 123456 | ... | ... | 5 | 2 | 3 |
+
+## 注意事项
+
+1. 爬虫使用模拟移动端请求，请合理控制爬取频率
+2. 情感词典文件需放置在项目根目录
+3. 首次运行可能需要下载jieba分词字典
+4. 生成词云需要系统安装中文字体（默认使用SimHei）
+
+## 依赖列表
+
+| 库 | 版本 | 用途 |
+|----|------|------|
+| requests | >=2.28.0 | HTTP请求 |
+| pandas | >=2.0.0 | 数据处理 |
+| openpyxl | >=3.1.0 | Excel读写 |
+| jieba | >=0.42.1 | 中文分词 |
+| scikit-learn | >=1.3.0 | TF-IDF计算 |
+| numpy | >=1.24.0 | 数值计算 |
+| matplotlib | >=3.7.0 | 可视化 |
+| wordcloud | >=1.9.0 | 词云生成 |
+
+## License
+
+MIT License

analyze.py

@@ -0,0 +1,375 @@
+import json
+import os
+import re
+import jieba
+import numpy as np
+import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from wordcloud import WordCloud
+import matplotlib.pyplot as plt
+import matplotlib
+matplotlib.use('Agg')  # 使用非交互式后端
+
+def load_stopwords(filepath='stopwords.txt'):
+    """从文件加载停用词"""
+    stopwords = set()
+    if os.path.exists(filepath):
+        with open(filepath, 'r', encoding='utf-8') as f:
+            for line in f:
+                word = line.strip()
+                if word:
+                    stopwords.add(word)
+        print(f"已加载 {len(stopwords)} 个停用词")
+    else:
+        print(f"警告：停用词文件 {filepath} 不存在，使用默认停用词")
+        stopwords = {
+            '的', '了', '在', '是', '我', '有', '和', '就', '不', '人', '都', '一', '一个', '上', '也', '很', '到', '说', '要',
+            '去', '你', '会', '着', '没有', '看', '好', '自己', '这', '那', '有', '吗', '吧', '呢', '啊', '呀', '什么', '怎么',
+            '为什么', '哪里', '谁', '多少', '几', '个', '只', '条', '把', '本', '篇', '次', '天', '今天', '明天', '昨天', '又',
+            '再', '还', '已经', '还是', '但是', '可是', '不过', '只是', '只有', '就是', '或者', '跟', '和', '与', '及', '或',
+            '股吧', '东方财富', '帖子', '发表', '回复', '点击', '查看', '更多', '原文', '转发', '分享', '收藏', '评论', '点赞',
+            'http', 'https', 'com', 'cn', 'www', 'net', 'org'
+        }
+    return stopwords
+
+# 加载停用词
+STOPWORDS = load_stopwords()
+
+def clean_text(text):
+    """清洗文本"""
+    if not text:
+        return ""
+    # 移除URL
+    text = re.sub(r'https?://\S+|www\.\S+', '', text)
+    # 移除HTML标签
+    text = re.sub(r'<.*?>', '', text)
+    # 移除表情符号
+    text = re.sub(r'\[.*?\]', '', text)
+    # 移除纯英文和数字混合的无效标记（如 sh123、abc456等）
+    text = re.sub(r'\b[a-zA-Z]+\d+\b', '', text)
+    text = re.sub(r'\b\d+[a-zA-Z]+\b', '', text)
+    # 移除特殊字符（保留中文、英文、数字）
+    text = re.sub(r'[^\w\s]', ' ', text)
+    # 移除多余空格
+    text = re.sub(r'\s+', ' ', text).strip()
+    return text
+
+def tokenize(text):
+    """中文分词"""
+    words = jieba.lcut(text)
+    # 过滤停用词、短词、纯英文单词和无意义字符
+    filtered_words = []
+    for w in words:
+        # 跳过停用词和短词
+        if w in STOPWORDS or len(w) <= 1:
+            continue
+        # 检查是否是纯英文单词
+        if re.match(r'^[a-zA-Z]+$', w):
+            # 过滤掉纯英文单词（通常是论坛标记、无意义的缩写等）
+            continue
+        # 检查是否包含无意义的英文字符组合
+        if re.match(r'^[a-zA-Z\s]+$', w):
+            continue
+        filtered_words.append(w)
+    return filtered_words
+
+def load_data(data_dir='data'):
+    """加载所有股票数据"""
+    all_data = []
+    stock_info = {}
+    
+    if not os.path.exists(data_dir):
+        print(f'数据目录 {data_dir} 不存在')
+        return all_data, stock_info
+    
+    for filename in os.listdir(data_dir):
+        if filename.endswith('.json'):
+            filepath = os.path.join(data_dir, filename)
+            try:
+                with open(filepath, 'r', encoding='utf-8') as f:
+                    data = json.load(f)
+                    stock_name = data.get('stock_name', '未知')
+                    stock_code = data.get('stock_code', '未知')
+                    posts = data.get('posts', [])
+                    
+                    stock_info[stock_code] = {
+                        'name': stock_name,
+                        'post_count': len(posts)
+                    }
+                    
+                    for post in posts:
+                        content = post.get('post_content', '')
+                        title = post.get('post_title', '')
+                        publish_time = post.get('post_publish_time', '')
+                        full_text = f"{title} {content}".strip()
+                        
+                        if full_text:
+                            all_data.append({
+                                'stock_code': stock_code,
+                                'stock_name': stock_name,
+                                'post_id': post.get('post_id'),
+                                'post_publish_time': publish_time,
+                                'text': full_text,
+                                'clean_text': clean_text(full_text)
+                            })
+            except Exception as e:
+                print(f'加载文件 {filename} 失败: {e}')
+    
+    return all_data, stock_info
+
+def calculate_tfidf(texts):
+    """计算TF-IDF"""
+    vectorizer = TfidfVectorizer(
+        tokenizer=tokenize,
+        token_pattern=None,
+        max_features=1000,
+        ngram_range=(1, 2)
+    )
+    
+    tfidf_matrix = vectorizer.fit_transform(texts)
+    feature_names = vectorizer.get_feature_names_out()
+    
+    return tfidf_matrix, feature_names, vectorizer
+
+def get_top_keywords(tfidf_matrix, feature_names, top_n=20):
+    """获取Top关键词"""
+    avg_tfidf = np.array(tfidf_matrix.mean(axis=0)).flatten()
+    top_indices = avg_tfidf.argsort()[-top_n*4:][::-1]  # 多取一些，避免重复后不够
+    
+    # 先收集候选词
+    candidates = []
+    for idx in top_indices:
+        word = feature_names[idx]
+        if len(word.strip()) > 0:
+            candidates.append({
+                'word': word,
+                'tfidf': avg_tfidf[idx],
+                'length': len(word.split())  # 词的长度（包含多少个词）
+            })
+    
+    # 按词长降序排序（优先保留组合词）
+    candidates.sort(key=lambda x: (-x['length'], -x['tfidf']))
+    
+    # 智能去重 - 优先保留组合词
+    keywords = []
+    seen_words = set()
+    seen_parts = set()
+    
+    for candidate in candidates:
+        word = candidate['word']
+        word_parts = word.split()
+        
+        # 检查是否应该添加这个词
+        should_add = True
+        
+        # 检查这个词的任何部分是否已经被其他词使用了
+        for part in word_parts:
+            if part in seen_parts:
+                should_add = False
+                break
+        
+        if should_add and word not in seen_words:
+            seen_words.add(word)
+            # 记录所有使用过的词部分
+            for part in word_parts:
+                seen_parts.add(part)
+            keywords.append({
+                'word': word,
+                'tfidf': candidate['tfidf']
+            })
+            if len(keywords) >= top_n:
+                break
+    
+    # 按TF-IDF重新排序
+    keywords.sort(key=lambda x: -x['tfidf'])
+    return keywords
+
+def get_stock_specific_keywords(all_data, stock_code, top_n=20):
+    """获取特定股票的关键词"""
+    stock_texts = [d['clean_text'] for d in all_data if d['stock_code'] == stock_code]
+    other_texts = [d['clean_text'] for d in all_data if d['stock_code'] != stock_code]
+    
+    if len(stock_texts) < 5:
+        return []
+    
+    all_texts = stock_texts + other_texts
+    tfidf_matrix, feature_names, vectorizer = calculate_tfidf(all_texts)
+    
+    # 计算该股票的平均TF-IDF
+    stock_matrix = tfidf_matrix[:len(stock_texts)]
+    avg_tfidf = np.array(stock_matrix.mean(axis=0)).flatten()
+    
+    # 计算其他股票的平均TF-IDF
+    if other_texts:
+        other_matrix = tfidf_matrix[len(stock_texts):]
+        other_avg = np.array(other_matrix.mean(axis=0)).flatten()
+        # 计算差值
+        diff = avg_tfidf - other_avg
+    else:
+        diff = avg_tfidf
+    
+    top_indices = diff.argsort()[-top_n*4:][::-1]  # 多取一些，避免重复后不够
+    
+    # 先收集候选词
+    candidates = []
+    for idx in top_indices:
+        word = feature_names[idx]
+        if len(word.strip()) > 0:
+            candidates.append({
+                'word': word,
+                'tfidf': avg_tfidf[idx],
+                'diff': diff[idx],
+                'length': len(word.split())  # 词的长度
+            })
+    
+    # 按词长降序排序（优先保留组合词）
+    candidates.sort(key=lambda x: (-x['length'], -x['diff']))
+    
+    # 智能去重 - 优先保留组合词
+    keywords = []
+    seen_words = set()
+    seen_parts = set()
+    
+    for candidate in candidates:
+        word = candidate['word']
+        word_parts = word.split()
+        
+        # 检查是否应该添加这个词
+        should_add = True
+        
+        # 检查这个词的任何部分是否已经被其他词使用了
+        for part in word_parts:
+            if part in seen_parts:
+                should_add = False
+                break
+        
+        if should_add and word not in seen_words:
+            seen_words.add(word)
+            # 记录所有使用过的词部分
+            for part in word_parts:
+                seen_parts.add(part)
+            keywords.append({
+                'word': word,
+                'tfidf': candidate['tfidf'],
+                'diff': candidate['diff']
+            })
+            if len(keywords) >= top_n:
+                break
+    
+    # 按diff重新排序
+    keywords.sort(key=lambda x: -x['diff'])
+    return keywords
+
+def generate_wordcloud(keywords, stock_name, output_dir='output'):
+    """生成词云"""
+    os.makedirs(output_dir, exist_ok=True)
+    
+    word_freq = {k['word']: k['tfidf'] for k in keywords}
+    
+    wc = WordCloud(
+        font_path='C:/Windows/Fonts/simhei.ttf',  # Windows中文字体路径
+        width=800,
+        height=600,
+        background_color='white',
+        max_words=100
+    )
+    
+    wc.generate_from_frequencies(word_freq)
+    
+    output_path = os.path.join(output_dir, f'wordcloud_{stock_name}.png')
+    wc.to_file(output_path)
+    print(f'词云已保存到: {output_path}')
+    
+    return output_path
+
+def analyze_all():
+    """完整分析流程"""
+    print('='*60)
+    print('股吧数据 TF-IDF 分析')
+    print('='*60)
+    
+    # 创建输出目录
+    os.makedirs('output', exist_ok=True)
+    
+    # 加载数据
+    print('\n[1/5] 加载数据...')
+    all_data, stock_info = load_data()
+    
+    if not all_data:
+        print('没有找到数据，请先运行爬虫')
+        return
+    
+    print(f'  共加载 {len(all_data)} 条帖子')
+    print(f'  涉及 {len(stock_info)} 只股票:')
+    for code, info in stock_info.items():
+        print(f'    - {info["name"]} ({code}): {info["post_count"]} 条')
+    
+    # 整体分析
+    print('\n[2/5] 整体关键词分析...')
+    all_texts = [d['clean_text'] for d in all_data]
+    tfidf_matrix, feature_names, vectorizer = calculate_tfidf(all_texts)
+    overall_keywords = get_top_keywords(tfidf_matrix, feature_names, top_n=30)
+    
+    print('\n  整体Top 20关键词:')
+    for i, kw in enumerate(overall_keywords[:20], 1):
+        print(f'    {i:2d}. {kw["word"]:10s} (TF-IDF: {kw["tfidf"]:.4f})')
+    
+    # 保存整体关键词
+    overall_df = pd.DataFrame(overall_keywords)
+    overall_df.to_csv('output/overall_keywords.csv', index=False, encoding='utf-8-sig')
+    
+    # 生成整体词云
+    generate_wordcloud(overall_keywords, 'overall')
+    
+    # 各股票单独分析
+    print('\n[3/5] 各股票关键词分析...')
+    stock_keywords = {}
+    
+    for stock_code in stock_info.keys():
+        stock_name = stock_info[stock_code]['name']
+        print(f'\n  分析 {stock_name} ({stock_code})...')
+        
+        keywords = get_stock_specific_keywords(all_data, stock_code, top_n=20)
+        stock_keywords[stock_code] = keywords
+        
+        if keywords:
+            print(f'  Top 10关键词:')
+            for i, kw in enumerate(keywords[:10], 1):
+                print(f'    {i:2d}. {kw["word"]:10s} (TF-IDF: {kw["tfidf"]:.4f}, 差值: {kw["diff"]:.4f})')
+            
+            # 生成词云
+            generate_wordcloud(keywords, stock_name)
+            
+            # 保存关键词
+            df = pd.DataFrame(keywords)
+            df.to_csv(f'output/keywords_{stock_name}.csv', index=False, encoding='utf-8-sig')
+    
+    # 生成汇总报告
+    print('\n[4/5] 生成汇总报告...')
+    report_data = []
+    for stock_code, keywords in stock_keywords.items():
+        stock_name = stock_info[stock_code]['name']
+        top_words = ', '.join([k['word'] for k in keywords[:5]])
+        report_data.append({
+            '股票代码': stock_code,
+            '股票名称': stock_name,
+            '帖子数量': stock_info[stock_code]['post_count'],
+            'Top5关键词': top_words
+        })
+    
+    report_df = pd.DataFrame(report_data)
+    report_df.to_csv('output/summary_report.csv', index=False, encoding='utf-8-sig')
+    print('  汇总报告已保存到: output/summary_report.csv')
+    
+    # 保存所有文本数据
+    print('\n[5/5] 保存预处理数据...')
+    all_df = pd.DataFrame(all_data)
+    all_df.to_csv('output/all_posts.csv', index=False, encoding='utf-8-sig')
+    print('  所有帖子已保存到: output/all_posts.csv')
+    
+    print('\n' + '='*60)
+    print('分析完成！结果保存在 output/ 目录中')
+    print('='*60)
+
+if __name__ == '__main__':
+    analyze_all()

check_page.py

@@ -1,34 +0,0 @@
-import requests
-
-headers = {
-    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
-    'Referer': 'https://guba.eastmoney.com/',
-    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8',
-    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
-    'Accept-Encoding': 'gzip, deflate, br',
-    'Connection': 'keep-alive'
-}
-
-post_id = '1708066915'
-url = f'https://guba.eastmoney.com/news,002624,{post_id}.html'
-
-print(f'请求: {url}')
-response = requests.get(url, headers=headers, timeout=15)
-response.encoding = 'utf-8'
-print(f'状态码: {response.status_code}')
-print(f'页面长度: {len(response.text)}')
-
-# 检查关键字符串
-print('\n检查页面中的关键字符串:')
-print(f'post_article: {"post_article" in response.text}')
-print(f'comment_list: {"comment_list" in response.text}')
-print(f'news_content: {"news_content" in response.text}')
-
-# 保存页面
-with open('current_page.html', 'w', encoding='utf-8') as f:
-    f.write(response.text)
-print('\n页面已保存到 current_page.html')
-
-# 查看开头部分
-print('\n页面开头:')
-print(response.text[:500])

guba_comments.csv

@@ -1,241 +0,0 @@
-page,title,author,time,reply_count,click_count
-1,无论是人才还是技术还是渠道，希望这次管理成的变动能够让这个曾经行业龙头走向正轨,雪球小鲁班,2026/5/14 12:07,24,71
-1,【今日股市】指数午后低位震荡，资源股跌幅居前,雪球小鲁班,2026/5/14 10:30,31,62
-1,该跌了吧,沉心静气扬帆起航,2026/5/14 11:45,18,79
-1,感觉像是有组织的散户进场了，就是所谓的老鼠,回本困难户第N位,2026/5/13 22:21,35,89
-1,终于涨了，昨天跌那么狠，裤衩子都没有了,花火飞鸟,2026/5/14 12:04,47,83
-1,算不算放量暴跌？！,股友63F0o88663,2026/5/14 12:03,22,78
-1,今天爆跌，明天一大堆利好又红红火火长阳，TCL一贯套路,心碎股票人,2026/5/14 12:02,25,81
-1,没事 拿住 今天主力动用资金拉券商股 明天活埋券商再来拉你,雪球小鲁班,2026/5/14 10:37,32,64
-1,大神解释一下，为什么大单疯狂出货，都出了一个亿了还是能这么涨,月茨星,2026/5/14 11:52,43,66
-1,为什么还在卖，要停牌了,股友36E919X121,2026/5/14 11:17,24,63
-1,涨一天跌一周，就这尿性。。。,股友7715N807H3,2026/5/14 11:24,20,76
-1,今天应该有榜,瑜佳不佳,2026/5/14 11:56,4,17
-1,大盘涨跌工具,厉害的小散,2026/5/14 11:56,12,78
-1,眼光看长远的几十个点，不纠结每天的几个点,股友3Y063588A1,2026/5/14 11:52,20,66
-1,8.15箱底满仓干满仓干，半导体与智能消费最优质龙头TCL,SEO神话,2026/5/14 11:51,44,3
-1,中信还在加仓，要命哟,金炫宇1,2026/5/14 11:50,1,5
-1,这压单这么低的价格你出货 出完你买啥呢？想不开,是但哥,2026/5/14 11:34,38,93
-1,了,股友01zC725523,2026/5/14 10:40,43,76
-1,温水煮青蛙，一路闷杀,股友38M080U658,2026/5/14 11:48,20,58
-1,1,谷神布斯,2026/5/14 11:26,34,0
-1,！,飞驰股生的牛马,2026/5/14 10:24,35,63
-1,同时加快梳理现有业务板块，去弱留强，对环球易购业务进行项目制改革,九溪你要赢,2026/5/14 11:27,1,21
-1,外盘木材大跌，纸浆机会来了！,哥伦比娅,2026/5/14 11:44,33,61
-1,今天收盘10.05，从头再来。,花火飞鸟,2026/5/14 10:20,4,41
-1,9409+60070中签，隔壁的兄弟立高食品已经94倍市盈率了,红红的嘴唇,2026/5/14 11:42,35,4
-1,太便宜了，唯一一次翻倍的机会，就在面前，不要再犹豫了,坚韧的武桦16,2026/5/14 11:18,26,5
-1,7728手一口吃掉,欣锐80等你来,2026/5/14 11:40,27,93
-1,又到箱底，准备干了,股友995O308r73,2026/5/14 11:40,6,78
-1,地天,盯紧五日线,2026/5/14 11:39,7,70
-1,纽威的管理层会招报应的，你们这代不报，你们的下一代也跑不掉！！！！！！！！！！！,一一路長虹,2026/5/14 10:04,37,73
-1,国务院日前发布生物产业发展规划，7500亿产业链呼之欲出，意味着生物医药概念股面,股友965al72890,2026/5/14 10:21,30,39
-1,看来跨境通的要回暖了,一念上塔山,2026/5/14 11:36,3,38
-1,跌到3个点再补，好些,股友01zC725523,2026/5/14 10:15,23,11
-1,火箭弹都救不了中兵红箭嘛,魍魉灬,2026/5/14 11:35,25,85
-1,槽,单刃剪钳,2026/5/14 1:34,17,20
-1,大盘涨狗垃圾东西还在跌,欣锐80等你来,2026/5/14 11:31,33,15
-1,还会升回去吗？,小韭菜误入高端局,2026/5/14 11:28,26,78
-1,啊,狐狸叫的猫,2026/5/14 11:28,32,48
-1,我一定是脑子抽了，昨天盈利9个点今早盘卖了，没多久又接了回来,梦想是在股市买房,2026/5/14 10:49,26,71
-1,果断卖出，不玩了，这股没戏。今天大阴线 明天大跌,炒股2年半,2026/5/14 11:22,0,54
-1,没大哥一堆压单,雨文和文,2026/5/14 11:21,24,80
-1,哎,赚点狗粮猫粮,2026/5/14 11:21,1,26
-1,调仓换股啦！太弱了，买入券商,VINN,2026/5/14 10:31,12,90
-1,现在该股是死猪不怕开水烫,阿月姐,2026/5/14 11:20,26,24
-1,这股算稳吧，感觉大部分都在绿，不绿就好,高大的金青槐4,2026/5/14 11:19,9,87
-1,主力说 ，马上拉升10个板，快进，5.81就是不锈钢底,鸣潮牛比,2026/5/14 11:18,45,82
-1,川王挂了，市场只有一条龙了，津荣你是金龙,孤独者AA,2026/5/14 11:18,23,84
-1,狗狗币 比特 “炒币”和炒股一样都有大起大落，这首歌唱出了你的心声吗？,股友68c80F8191,2026/5/14 11:16,4,29
-1,啊,国运长牛632,2026/5/14 11:17,7,29
-1,河钢已经跌无可跌了，再也没有一丝下降的空间了,我可以回本,2026/5/14 11:16,9,52
-1,说好的3元呢？砸下来啊，gou装,仓又加錯,2026/5/14 11:16,21,74
-1,出,昔涟丶爱莉希雅,2026/5/14 11:15,16,92
-1,从168开始人人中签，从168开始一路发。,住在异环的别墅里,2026/5/14 11:14,1,28
-1,所以之前费劲巴力的涨上来是为了个什么,买廖就涨,2026/5/14 11:14,46,53
-1,who这些鬼佬办事效率真是低，印度人民生命分秒必争阿,面朝阳光追梦,2026/5/14 11:13,22,24
-1,这条横线画得漂亮,futuregs,2026/5/14 11:12,16,92
-1,跌停给筹码  涨停给筹码  这样要死不活不会给你筹码的,股友0f56Mr,2026/5/14 11:11,0,39
-1,一堆出货的不亏钱吗,关注acgn,2026/5/14 10:40,26,35
-1,又是一个美好的周末,金元马,2026/5/14 11:09,35,92
-1,你不得不佩服老邓，他去年就判断到现在的行情了，3季度多卖猪仔，今年二季度少出栏。,油手好闲,2026/5/13 16:31,47,83
-1,收盘价13.14，和4月28日一样,B哥sama,2026/5/14 11:01,29,85
-1,减,买股不宜慌,2026/5/14 11:03,31,89
-1,趋势大时代  指数中位线选择方向,如林的岑缈,2026/5/14 10:41,20,17
-1,要跌停,君月00后实盘,2026/5/14 10:46,7,90
-1,尾盘跌停,股民222,2026/5/14 10:36,21,11
-1,今天都有哪些吃了这碗大面的？来说说后面走势,Cialloo,2026/5/14 10:23,24,11
-1,大家一起去骂股市老兵这个死庄托,大智若愚量在價先,2026/5/14 10:51,22,36
-1,短线小赚一波赶紧走，下一波跌至18,东方嘉木,2026/5/14 10:50,28,2
-1,跨境通ZAFUL拥有成功、成熟的体系和打法，其后续发展充满期待,心中有财,2026/5/14 10:49,4,86
-1,各位好啊，我来抄底了,拉萨帮二当家,2026/5/14 10:31,32,97
-1,5月7日前有九阳，也必将有后九阳！,做t糕手,2026/5/14 10:46,46,19
-1,还能跌破6吗？感觉都快垫底了,梦绮紫,2026/5/14 10:48,31,88
-1,跑了，和这股耗不起，涨两天一天能降回去，少赔点撤了,飞逸天,2026/5/14 10:47,38,91
-1,雨后彩莲死庄托还敢唱多吗，脸被打的啪啪响吧,股友Q1713355G8,2026/5/14 10:40,3,66
-1,天天高抛低吸,股友C08120l209,2026/5/14 10:46,37,89
-1,圣龙股份，好是好，公司发展方向无疑是好！但是盘子太小，业绩越来越好就没有大机构要！千万不要大买,谷神布斯,2026/5/14 10:45,20,93
-1,几点出公告停牌,花火飞鸟,2026/5/14 10:25,28,63
-1,这是已经谈拢了，杀跌两天就该停牌了.不用等到21号股东大会了。,股友61057ac363,2026/5/14 10:42,9,97
-1,昨天是谁说的今天会复制3.5号的行情？简直神准,股友639537p9w3,2026/5/14 9:20,17,69
-1,济南高新,东大东大红,2026/5/14 10:39,25,89
-2,无论是人才还是技术还是渠道，希望这次管理成的变动能够让这个曾经行业龙头走向正轨,雪球小鲁班,2026/5/14 12:07,24,71
-2,【今日股市】指数午后低位震荡，资源股跌幅居前,雪球小鲁班,2026/5/14 10:30,31,62
-2,该跌了吧,沉心静气扬帆起航,2026/5/14 11:45,18,79
-2,感觉像是有组织的散户进场了，就是所谓的老鼠,回本困难户第N位,2026/5/13 22:21,35,89
-2,终于涨了，昨天跌那么狠，裤衩子都没有了,花火飞鸟,2026/5/14 12:04,47,83
-2,算不算放量暴跌？！,股友63F0o88663,2026/5/14 12:03,22,78
-2,今天爆跌，明天一大堆利好又红红火火长阳，TCL一贯套路,心碎股票人,2026/5/14 12:02,25,81
-2,没事 拿住 今天主力动用资金拉券商股 明天活埋券商再来拉你,雪球小鲁班,2026/5/14 10:37,32,64
-2,大神解释一下，为什么大单疯狂出货，都出了一个亿了还是能这么涨,月茨星,2026/5/14 11:52,43,66
-2,为什么还在卖，要停牌了,股友36E919X121,2026/5/14 11:17,24,63
-2,涨一天跌一周，就这尿性。。。,股友7715N807H3,2026/5/14 11:24,20,76
-2,今天应该有榜,瑜佳不佳,2026/5/14 11:56,4,17
-2,大盘涨跌工具,厉害的小散,2026/5/14 11:56,12,78
-2,眼光看长远的几十个点，不纠结每天的几个点,股友3Y063588A1,2026/5/14 11:52,20,66
-2,8.15箱底满仓干满仓干，半导体与智能消费最优质龙头TCL,SEO神话,2026/5/14 11:51,44,3
-2,中信还在加仓，要命哟,金炫宇1,2026/5/14 11:50,1,5
-2,这压单这么低的价格你出货 出完你买啥呢？想不开,是但哥,2026/5/14 11:34,38,93
-2,了,股友01zC725523,2026/5/14 10:40,43,76
-2,温水煮青蛙，一路闷杀,股友38M080U658,2026/5/14 11:48,20,58
-2,1,谷神布斯,2026/5/14 11:26,34,0
-2,！,飞驰股生的牛马,2026/5/14 10:24,35,63
-2,同时加快梳理现有业务板块，去弱留强，对环球易购业务进行项目制改革,九溪你要赢,2026/5/14 11:27,1,21
-2,外盘木材大跌，纸浆机会来了！,哥伦比娅,2026/5/14 11:44,33,61
-2,今天收盘10.05，从头再来。,花火飞鸟,2026/5/14 10:20,4,41
-2,9409+60070中签，隔壁的兄弟立高食品已经94倍市盈率了,红红的嘴唇,2026/5/14 11:42,35,4
-2,太便宜了，唯一一次翻倍的机会，就在面前，不要再犹豫了,坚韧的武桦16,2026/5/14 11:18,26,5
-2,7728手一口吃掉,欣锐80等你来,2026/5/14 11:40,27,93
-2,又到箱底，准备干了,股友995O308r73,2026/5/14 11:40,6,78
-2,地天,盯紧五日线,2026/5/14 11:39,7,70
-2,纽威的管理层会招报应的，你们这代不报，你们的下一代也跑不掉！！！！！！！！！！！,一一路長虹,2026/5/14 10:04,37,73
-2,国务院日前发布生物产业发展规划，7500亿产业链呼之欲出，意味着生物医药概念股面,股友965al72890,2026/5/14 10:21,30,39
-2,看来跨境通的要回暖了,一念上塔山,2026/5/14 11:36,3,38
-2,跌到3个点再补，好些,股友01zC725523,2026/5/14 10:15,23,11
-2,火箭弹都救不了中兵红箭嘛,魍魉灬,2026/5/14 11:35,25,85
-2,槽,单刃剪钳,2026/5/14 1:34,17,20
-2,大盘涨狗垃圾东西还在跌,欣锐80等你来,2026/5/14 11:31,33,15
-2,还会升回去吗？,小韭菜误入高端局,2026/5/14 11:28,26,78
-2,啊,狐狸叫的猫,2026/5/14 11:28,32,48
-2,我一定是脑子抽了，昨天盈利9个点今早盘卖了，没多久又接了回来,梦想是在股市买房,2026/5/14 10:49,26,71
-2,果断卖出，不玩了，这股没戏。今天大阴线 明天大跌,炒股2年半,2026/5/14 11:22,0,54
-2,没大哥一堆压单,雨文和文,2026/5/14 11:21,24,80
-2,哎,赚点狗粮猫粮,2026/5/14 11:21,1,26
-2,调仓换股啦！太弱了，买入券商,VINN,2026/5/14 10:31,12,90
-2,现在该股是死猪不怕开水烫,阿月姐,2026/5/14 11:20,26,24
-2,这股算稳吧，感觉大部分都在绿，不绿就好,高大的金青槐4,2026/5/14 11:19,9,87
-2,主力说 ，马上拉升10个板，快进，5.81就是不锈钢底,鸣潮牛比,2026/5/14 11:18,45,82
-2,川王挂了，市场只有一条龙了，津荣你是金龙,孤独者AA,2026/5/14 11:18,23,84
-2,狗狗币 比特 “炒币”和炒股一样都有大起大落，这首歌唱出了你的心声吗？,股友68c80F8191,2026/5/14 11:16,4,29
-2,啊,国运长牛632,2026/5/14 11:17,7,29
-2,河钢已经跌无可跌了，再也没有一丝下降的空间了,我可以回本,2026/5/14 11:16,9,52
-2,说好的3元呢？砸下来啊，gou装,仓又加錯,2026/5/14 11:16,21,74
-2,出,昔涟丶爱莉希雅,2026/5/14 11:15,16,92
-2,从168开始人人中签，从168开始一路发。,住在异环的别墅里,2026/5/14 11:14,1,28
-2,所以之前费劲巴力的涨上来是为了个什么,买廖就涨,2026/5/14 11:14,46,53
-2,who这些鬼佬办事效率真是低，印度人民生命分秒必争阿,面朝阳光追梦,2026/5/14 11:13,22,24
-2,这条横线画得漂亮,futuregs,2026/5/14 11:12,16,92
-2,跌停给筹码  涨停给筹码  这样要死不活不会给你筹码的,股友0f56Mr,2026/5/14 11:11,0,39
-2,一堆出货的不亏钱吗,关注acgn,2026/5/14 10:40,26,35
-2,又是一个美好的周末,金元马,2026/5/14 11:09,35,92
-2,你不得不佩服老邓，他去年就判断到现在的行情了，3季度多卖猪仔，今年二季度少出栏。,油手好闲,2026/5/13 16:31,47,83
-2,收盘价13.14，和4月28日一样,B哥sama,2026/5/14 11:01,29,85
-2,减,买股不宜慌,2026/5/14 11:03,31,89
-2,趋势大时代  指数中位线选择方向,如林的岑缈,2026/5/14 10:41,20,17
-2,要跌停,君月00后实盘,2026/5/14 10:46,7,90
-2,尾盘跌停,股民222,2026/5/14 10:36,21,11
-2,今天都有哪些吃了这碗大面的？来说说后面走势,Cialloo,2026/5/14 10:23,24,11
-2,大家一起去骂股市老兵这个死庄托,大智若愚量在價先,2026/5/14 10:51,22,36
-2,短线小赚一波赶紧走，下一波跌至18,东方嘉木,2026/5/14 10:50,28,2
-2,跨境通ZAFUL拥有成功、成熟的体系和打法，其后续发展充满期待,心中有财,2026/5/14 10:49,4,86
-2,各位好啊，我来抄底了,拉萨帮二当家,2026/5/14 10:31,32,97
-2,5月7日前有九阳，也必将有后九阳！,做t糕手,2026/5/14 10:46,46,19
-2,还能跌破6吗？感觉都快垫底了,梦绮紫,2026/5/14 10:48,31,88
-2,跑了，和这股耗不起，涨两天一天能降回去，少赔点撤了,飞逸天,2026/5/14 10:47,38,91
-2,雨后彩莲死庄托还敢唱多吗，脸被打的啪啪响吧,股友Q1713355G8,2026/5/14 10:40,3,66
-2,天天高抛低吸,股友C08120l209,2026/5/14 10:46,37,89
-2,圣龙股份，好是好，公司发展方向无疑是好！但是盘子太小，业绩越来越好就没有大机构要！千万不要大买,谷神布斯,2026/5/14 10:45,20,93
-2,几点出公告停牌,花火飞鸟,2026/5/14 10:25,28,63
-2,这是已经谈拢了，杀跌两天就该停牌了.不用等到21号股东大会了。,股友61057ac363,2026/5/14 10:42,9,97
-2,昨天是谁说的今天会复制3.5号的行情？简直神准,股友639537p9w3,2026/5/14 9:20,17,69
-2,济南高新,东大东大红,2026/5/14 10:39,25,89
-3,无论是人才还是技术还是渠道，希望这次管理成的变动能够让这个曾经行业龙头走向正轨,雪球小鲁班,2026/5/14 12:07,24,71
-3,【今日股市】指数午后低位震荡，资源股跌幅居前,雪球小鲁班,2026/5/14 10:30,31,62
-3,该跌了吧,沉心静气扬帆起航,2026/5/14 11:45,18,79
-3,感觉像是有组织的散户进场了，就是所谓的老鼠,回本困难户第N位,2026/5/13 22:21,35,89
-3,终于涨了，昨天跌那么狠，裤衩子都没有了,花火飞鸟,2026/5/14 12:04,47,83
-3,算不算放量暴跌？！,股友63F0o88663,2026/5/14 12:03,22,78
-3,今天爆跌，明天一大堆利好又红红火火长阳，TCL一贯套路,心碎股票人,2026/5/14 12:02,25,81
-3,没事 拿住 今天主力动用资金拉券商股 明天活埋券商再来拉你,雪球小鲁班,2026/5/14 10:37,32,64
-3,大神解释一下，为什么大单疯狂出货，都出了一个亿了还是能这么涨,月茨星,2026/5/14 11:52,43,66
-3,为什么还在卖，要停牌了,股友36E919X121,2026/5/14 11:17,24,63
-3,涨一天跌一周，就这尿性。。。,股友7715N807H3,2026/5/14 11:24,20,76
-3,今天应该有榜,瑜佳不佳,2026/5/14 11:56,4,17
-3,大盘涨跌工具,厉害的小散,2026/5/14 11:56,12,78
-3,眼光看长远的几十个点，不纠结每天的几个点,股友3Y063588A1,2026/5/14 11:52,20,66
-3,8.15箱底满仓干满仓干，半导体与智能消费最优质龙头TCL,SEO神话,2026/5/14 11:51,44,3
-3,中信还在加仓，要命哟,金炫宇1,2026/5/14 11:50,1,5
-3,这压单这么低的价格你出货 出完你买啥呢？想不开,是但哥,2026/5/14 11:34,38,93
-3,了,股友01zC725523,2026/5/14 10:40,43,76
-3,温水煮青蛙，一路闷杀,股友38M080U658,2026/5/14 11:48,20,58
-3,1,谷神布斯,2026/5/14 11:26,34,0
-3,！,飞驰股生的牛马,2026/5/14 10:24,35,63
-3,同时加快梳理现有业务板块，去弱留强，对环球易购业务进行项目制改革,九溪你要赢,2026/5/14 11:27,1,21
-3,外盘木材大跌，纸浆机会来了！,哥伦比娅,2026/5/14 11:44,33,61
-3,今天收盘10.05，从头再来。,花火飞鸟,2026/5/14 10:20,4,41
-3,9409+60070中签，隔壁的兄弟立高食品已经94倍市盈率了,红红的嘴唇,2026/5/14 11:42,35,4
-3,太便宜了，唯一一次翻倍的机会，就在面前，不要再犹豫了,坚韧的武桦16,2026/5/14 11:18,26,5
-3,7728手一口吃掉,欣锐80等你来,2026/5/14 11:40,27,93
-3,又到箱底，准备干了,股友995O308r73,2026/5/14 11:40,6,78
-3,地天,盯紧五日线,2026/5/14 11:39,7,70
-3,纽威的管理层会招报应的，你们这代不报，你们的下一代也跑不掉！！！！！！！！！！！,一一路長虹,2026/5/14 10:04,37,73
-3,国务院日前发布生物产业发展规划，7500亿产业链呼之欲出，意味着生物医药概念股面,股友965al72890,2026/5/14 10:21,30,39
-3,看来跨境通的要回暖了,一念上塔山,2026/5/14 11:36,3,38
-3,跌到3个点再补，好些,股友01zC725523,2026/5/14 10:15,23,11
-3,火箭弹都救不了中兵红箭嘛,魍魉灬,2026/5/14 11:35,25,85
-3,槽,单刃剪钳,2026/5/14 1:34,17,20
-3,大盘涨狗垃圾东西还在跌,欣锐80等你来,2026/5/14 11:31,33,15
-3,还会升回去吗？,小韭菜误入高端局,2026/5/14 11:28,26,78
-3,啊,狐狸叫的猫,2026/5/14 11:28,32,48
-3,我一定是脑子抽了，昨天盈利9个点今早盘卖了，没多久又接了回来,梦想是在股市买房,2026/5/14 10:49,26,71
-3,果断卖出，不玩了，这股没戏。今天大阴线 明天大跌,炒股2年半,2026/5/14 11:22,0,54
-3,没大哥一堆压单,雨文和文,2026/5/14 11:21,24,80
-3,哎,赚点狗粮猫粮,2026/5/14 11:21,1,26
-3,调仓换股啦！太弱了，买入券商,VINN,2026/5/14 10:31,12,90
-3,现在该股是死猪不怕开水烫,阿月姐,2026/5/14 11:20,26,24
-3,这股算稳吧，感觉大部分都在绿，不绿就好,高大的金青槐4,2026/5/14 11:19,9,87
-3,主力说 ，马上拉升10个板，快进，5.81就是不锈钢底,鸣潮牛比,2026/5/14 11:18,45,82
-3,川王挂了，市场只有一条龙了，津荣你是金龙,孤独者AA,2026/5/14 11:18,23,84
-3,狗狗币 比特 “炒币”和炒股一样都有大起大落，这首歌唱出了你的心声吗？,股友68c80F8191,2026/5/14 11:16,4,29
-3,啊,国运长牛632,2026/5/14 11:17,7,29
-3,河钢已经跌无可跌了，再也没有一丝下降的空间了,我可以回本,2026/5/14 11:16,9,52
-3,说好的3元呢？砸下来啊，gou装,仓又加錯,2026/5/14 11:16,21,74
-3,出,昔涟丶爱莉希雅,2026/5/14 11:15,16,92
-3,从168开始人人中签，从168开始一路发。,住在异环的别墅里,2026/5/14 11:14,1,28
-3,所以之前费劲巴力的涨上来是为了个什么,买廖就涨,2026/5/14 11:14,46,53
-3,who这些鬼佬办事效率真是低，印度人民生命分秒必争阿,面朝阳光追梦,2026/5/14 11:13,22,24
-3,这条横线画得漂亮,futuregs,2026/5/14 11:12,16,92
-3,跌停给筹码  涨停给筹码  这样要死不活不会给你筹码的,股友0f56Mr,2026/5/14 11:11,0,39
-3,一堆出货的不亏钱吗,关注acgn,2026/5/14 10:40,26,35
-3,又是一个美好的周末,金元马,2026/5/14 11:09,35,92
-3,你不得不佩服老邓，他去年就判断到现在的行情了，3季度多卖猪仔，今年二季度少出栏。,油手好闲,2026/5/13 16:31,47,83
-3,收盘价13.14，和4月28日一样,B哥sama,2026/5/14 11:01,29,85
-3,减,买股不宜慌,2026/5/14 11:03,31,89
-3,趋势大时代  指数中位线选择方向,如林的岑缈,2026/5/14 10:41,20,17
-3,要跌停,君月00后实盘,2026/5/14 10:46,7,90
-3,尾盘跌停,股民222,2026/5/14 10:36,21,11
-3,今天都有哪些吃了这碗大面的？来说说后面走势,Cialloo,2026/5/14 10:23,24,11
-3,大家一起去骂股市老兵这个死庄托,大智若愚量在價先,2026/5/14 10:51,22,36
-3,短线小赚一波赶紧走，下一波跌至18,东方嘉木,2026/5/14 10:50,28,2
-3,跨境通ZAFUL拥有成功、成熟的体系和打法，其后续发展充满期待,心中有财,2026/5/14 10:49,4,86
-3,各位好啊，我来抄底了,拉萨帮二当家,2026/5/14 10:31,32,97
-3,5月7日前有九阳，也必将有后九阳！,做t糕手,2026/5/14 10:46,46,19
-3,还能跌破6吗？感觉都快垫底了,梦绮紫,2026/5/14 10:48,31,88
-3,跑了，和这股耗不起，涨两天一天能降回去，少赔点撤了,飞逸天,2026/5/14 10:47,38,91
-3,雨后彩莲死庄托还敢唱多吗，脸被打的啪啪响吧,股友Q1713355G8,2026/5/14 10:40,3,66
-3,天天高抛低吸,股友C08120l209,2026/5/14 10:46,37,89
-3,圣龙股份，好是好，公司发展方向无疑是好！但是盘子太小，业绩越来越好就没有大机构要！千万不要大买,谷神布斯,2026/5/14 10:45,20,93
-3,几点出公告停牌,花火飞鸟,2026/5/14 10:25,28,63
-3,这是已经谈拢了，杀跌两天就该停牌了.不用等到21号股东大会了。,股友61057ac363,2026/5/14 10:42,9,97
-3,昨天是谁说的今天会复制3.5号的行情？简直神准,股友639537p9w3,2026/5/14 9:20,17,69
-3,济南高新,东大东大红,2026/5/14 10:39,25,89

requirements.txt

@@ -0,0 +1,12 @@
+requests>=2.28.0
+pandas>=2.0.0
+openpyxl>=3.1.0
+jieba>=0.42.1
+scikit-learn>=1.3.0
+numpy>=1.24.0
+matplotlib>=3.7.0
+seaborn>=0.12.0
+wordcloud>=1.9.0
+gensim>=4.3.0
+tensorflow>=2.10.0
+keras>=2.10.0

scrapy.py

@@ -1,12 +0,0 @@
-import asyncio
-import aiohttp
-import json
-import re
-import sys
-from datetime import datetime
-
-headers = {
-    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36',
-    'Referer': 'https://guba.eastmoney.com/',
-    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
-    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.

scrapy_sync.py

@@ -1,343 +0,0 @@
-import json
-import re
-import time
-import urllib.request
-import urllib.parse
-from datetime import datetime
-
-headers = {
-    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36',
-    'Referer': 'https://guba.eastmoney.com/',
-    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.7',
-    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
-    'Accept-Encoding': 'gzip, deflate, br',
-    'Connection': 'keep-alive',
-    'Cache-Control': 'max-age=0',
-    'Upgrade-Insecure-Requests': '1',
-    'Sec-Ch-Ua': '"Chromium";v="148", "Not;A=Brand";v="24", "Microsoft Edge";v="148"',
-    'Sec-Ch-Ua-Mobile': '?0',
-    'Sec-Ch-Ua-Platform': '"Windows"',
-    'Sec-Fetch-Dest': 'document',
-    'Sec-Fetch-Mode': 'navigate',
-    'Sec-Fetch-Site': 'same-origin',
-    'Sec-Fetch-User': '?1',
-    'Cookie': 'qgqp_b_id=30059d8839ad5c045fa8856e38013e9c; st_nvi=XwpSfYXGjCxfCdbgapK5_cac4; nid18=0daec1df8064f04edd20b4e69250a8f5; nid18_create_time=1776263017375; gviem=UrMH_tSu1UpW8B_TKmytl803f; gviem_create_time=1776263017375; fullscreengg=1; fullscreengg2=1; st_si=63999118594852; wsc_checkuser_ok=1; st_asi=delete; st_pvi=26838250597806; st_sp=2026-04-15%2022%3A23%3A37; st_inirUrl=https%3A%2F%2Fcn.bing.com%2F; st_sn=30; st_psi=20260520214901287-117001354293-0422265952',
-}
-
-comment_headers = {
-    'Accept': '*/*',
-    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
-    'Cache-Control': 'no-cache',
-    'Connection': 'keep-alive',
-    'Content-Type': 'application/x-www-form-urlencoded',
-    'Origin': 'https://guba.eastmoney.com',
-    'Pragma': 'no-cache',
-    'Referer': 'https://guba.eastmoney.com/',
-    'Sec-Fetch-Dest': 'empty',
-    'Sec-Fetch-Mode': 'cors',
-    'Sec-Fetch-Site': 'same-origin',
-    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36',
-    'X-Requested-With': 'XMLHttpRequest',
-    'Cookie': 'qgqp_b_id=30059d8839ad5c045fa8856e38013e9c; st_nvi=XwpSfYXGjCxfCdbgapK5_cac4; nid18=0daec1df8064f04edd20b4e69250a8f5; nid18_create_time=1776263017375; gviem=UrMH_tSu1UpW8B_TKmytl803f; gviem_create_time=1776263017375; fullscreengg=1; fullscreengg2=1; st_si=63999118594852; wsc_checkuser_ok=1; st_asi=delete; st_pvi=26838250597806; st_sp=2026-04-15%2022%3A23%3A37; st_inirUrl=https%3A%2F%2Fcn.bing.com%2F; st_sn=30; st_psi=20260520214901287-117001354293-0422265952',
-}
-
-MAX_RETRIES = 3
-DELAY_BETWEEN_REQUESTS = 2.0
-DELAY_BETWEEN_PAGES = 5.0
-OUTPUT_FILE = 'guba_data.json'
-
-
-def fetch(url, headers, method='GET', data=None, timeout=15):
-    for attempt in range(MAX_RETRIES):
-        try:
-            req = urllib.request.Request(url, headers=headers, method=method, data=data)
-            with urllib.request.urlopen(req, timeout=timeout) as response:
-                if response.status == 429:
-                    print(f'    请求过于频繁，等待10秒后重试...')
-                    time.sleep(10)
-                    continue
-                
-                if response.status == 403:
-                    print(f'    请求被拒绝，第{attempt+1}次重试...')
-                    time.sleep(5)
-                    continue
-                
-                if response.status != 200:
-                    print(f'    请求失败，状态码: {response.status}')
-                    return None
-                
-                content = response.read().decode('utf-8', errors='ignore')
-                return content
-                
-        except urllib.error.URLError as e:
-            print(f'    请求超时，第{attempt+1}次重试...')
-            time.sleep(5)
-        except Exception as e:
-            print(f'    请求异常: {str(e)}')
-            if attempt < MAX_RETRIES - 1:
-                time.sleep(5)
-    
-    return None
-
-
-def initialize_session():
-    print('正在初始化会话...')
-    fetch('https://guba.eastmoney.com/', headers)
-    time.sleep(2)
-    print('会话初始化完成')
-
-
-def get_post_list(stock_code='002624', page=1):
-    if page == 1:
-        url = f'https://guba.eastmoney.com/list,{stock_code},f.html'
-    else:
-        url = f'https://guba.eastmoney.com/list,{stock_code},f{page}.html'
-    
-    html = fetch(url, headers)
-    
-    if not html:
-        return []
-    
-    posts = []
-    pattern = r'var article_list=\s*({"re":.*?});'
-    match = re.search(pattern, html, re.DOTALL)
-    
-    if match:
-        try:
-            data = json.loads(match.group(1))
-            for item in data.get('re', []):
-                post_id = item.get('post_id', '')
-                title = item.get('post_title', '').strip()
-                author = item.get('user_nickname', '').strip()
-                post_time = item.get('post_display_time', '')
-                comment_count = item.get('post_comment_count', 0)
-                click_count = item.get('post_click_count', 0)
-                forward_count = item.get('post_forward_count', 0)
-                like_count = item.get('post_like_count', 0)
-                
-                if post_id and title:
-                    posts.append({
-                        'post_id': post_id,
-                        'title': title,
-                        'author': author,
-                        'post_time': post_time,
-                        'comment_count': comment_count,
-                        'click_count': click_count,
-                        'forward_count': forward_count,
-                        'like_count': like_count,
-                        'url': f'https://guba.eastmoney.com/news,{stock_code},{post_id}.html'
-                    })
-        except json.JSONDecodeError:
-            pass
-    
-    return posts
-
-
-def get_comments(stock_code, post_id, page=1, page_size=30):
-    url = f'https://guba.eastmoney.com/api/getData?code={stock_code}&path=reply/api/Reply/ArticleNewReplyList'
-    
-    payload = {
-        'param': f'postid={post_id}&sort=1&sorttype=1&p={page}&ps={page_size}',
-        'plat': 'Web',
-        'path': 'reply/api/Reply/ArticleNewReplyList',
-        'env': '2',
-        'origin': '',
-        'version': '2022',
-        'product': 'Guba'
-    }
-    
-    data = urllib.parse.urlencode(payload).encode('utf-8')
-    response_text = fetch(url, comment_headers, method='POST', data=data)
-    
-    if not response_text:
-        return []
-    
-    try:
-        data = json.loads(response_text)
-        
-        if 're' in data:
-            reply_list = data.get('re', [])
-        elif 'data' in data and 'reply_list' in data['data']:
-            reply_list = data['data'].get('reply_list', [])
-        else:
-            print(f'    未知的响应结构: {list(data.keys())}')
-            return []
-        
-        if not isinstance(reply_list, list) or len(reply_list) == 0:
-            return []
-        
-        comments = []
-        for item in reply_list:
-            reply_user = item.get('reply_user', {})
-            comment = {
-                'reply_id': str(item.get('reply_id', '')),
-                'user_nickname': reply_user.get('user_nickname', '').strip(),
-                'reply_content': item.get('reply_text', '').strip(),
-                'reply_time': item.get('reply_time', ''),
-                'reply_like_count': item.get('reply_like_count', 0),
-                'reply_against_count': item.get('reply_against_count', 0),
-            }
-            if comment['reply_content']:
-                comments.append(comment)
-        
-        return comments
-    except json.JSONDecodeError as e:
-        print(f'    JSON解析失败: {str(e)}')
-        return []
-
-
-def get_all_comments(stock_code, post_id, total_comments):
-    all_comments = []
-    page_size = 30
-    page = 1
-    
-    while True:
-        comments = get_comments(stock_code, post_id, page, page_size)
-        
-        if not comments:
-            break
-        
-        all_comments.extend(comments)
-        print(f'    第{page}页评论获取完成，累计{len(all_comments)}条')
-        
-        if len(comments) < page_size:
-            break
-        
-        page += 1
-        time.sleep(DELAY_BETWEEN_REQUESTS)
-    
-    return all_comments
-
-
-def process_post(stock_code, post):
-    post_id = post['post_id']
-    title = post['title']
-    print(f'  获取帖子: {title[:40]}... (评论:{post["comment_count"]})')
-    
-    post_data = {
-        'post_id': post_id,
-        'title': title,
-        'author': post.get('author', ''),
-        'post_time': post.get('post_time', ''),
-        'url': post['url'],
-        'comment_count': post.get('comment_count', 0),
-        'click_count': post.get('click_count', 0),
-        'forward_count': post.get('forward_count', 0),
-        'like_count': post.get('like_count', 0),
-        'comments': []
-    }
-    
-    if post['comment_count'] > 0:
-        print(f'    正在获取评论...')
-        comments = get_all_comments(stock_code, post_id, post['comment_count'])
-        post_data['comments'] = comments
-        print(f'    评论获取完成，共{len(comments)}条')
-    
-    time.sleep(DELAY_BETWEEN_REQUESTS)
-    return post_data
-
-
-def scrape_guba(stock_code='002624', stock_name='完美世界', total_pages=3, min_comment_count=0):
-    all_posts = []
-    seen_post_ids = set()
-    
-    print(f'开始爬取{stock_name}({stock_code})股吧前{total_pages}页帖子...')
-    print(f'爬取时间: {datetime.now().strftime("%Y-%m-%d %H:%M:%S")}')
-    if min_comment_count > 0:
-        print(f'筛选条件: 评论数 >= {min_comment_count}')
-    print('-' * 60)
-    
-    initialize_session()
-    
-    for page in range(1, total_pages + 1):
-        print(f'\n正在爬取第{page}/{total_pages}页...')
-        
-        posts = get_post_list(stock_code, page)
-        
-        if not posts:
-            print(f'  第{page}页未找到数据')
-            continue
-        
-        print(f'  找到{len(posts)}个帖子')
-        
-        filtered_posts = []
-        for post in posts:
-            post_id = post['post_id']
-            if post_id in seen_post_ids:
-                continue
-            seen_post_ids.add(post_id)
-            
-            if min_comment_count > 0 and post['comment_count'] < min_comment_count:
-                continue
-            
-            filtered_posts.append(post)
-        
-        if not filtered_posts:
-            print(f'  第{page}页没有符合条件的帖子')
-            continue
-        
-        for post in filtered_posts:
-            post_data = process_post(stock_code, post)
-            all_posts.append(post_data)
-        
-        print(f'  第{page}页完成，已获取{len(all_posts)}个帖子')
-        
-        if page < total_pages:
-            time.sleep(DELAY_BETWEEN_PAGES)
-    
-    return all_posts
-
-
-def save_to_json(data, filename):
-    output = {
-        'scrape_time': datetime.now().strftime('%Y-%m-%d %H:%M:%S'),
-        'total_posts': len(data),
-        'posts': data
-    }
-    
-    with open(filename, 'w', encoding='utf-8') as f:
-        json.dump(output, f, ensure_ascii=False, indent=2)
-    
-    return output
-
-
-if __name__ == '__main__':
-    stock_code = '002624'
-    stock_name = '完美世界'
-    total_pages = 3
-    min_comment_count = 0
-    
-    print(f'使用 Python: {__import__("sys").version}')
-    print(f'脚本路径: {__file__}')
-    print(f'工作目录: {__import__("os").getcwd()}')
-    
-    start_time = datetime.now()
-    
-    all_posts = scrape_guba(stock_code, stock_name, total_pages, min_comment_count)
-    
-    end_time = datetime.now()
-    
-    print('\n' + '=' * 60)
-    
-    if all_posts:
-        output = save_to_json(all_posts, OUTPUT_FILE)
-        
-        print(f'爬取完成！')
-        print(f'  - 帖子数量: {output["total_posts"]}')
-        print(f'  - 数据已保存到: {OUTPUT_FILE}')
-        print(f'  - 耗时: {(end_time - start_time).total_seconds():.2f} 秒')
-        
-        print('\n前3个帖子预览:')
-        for i, post in enumerate(all_posts[:3], 1):
-            print(f'\n--- 帖子{i} ---')
-            print(f'标题: {post["title"]}')
-            print(f'作者: {post["author"]}')
-            print(f'时间: {post["post_time"]}')
-            print(f'URL: {post["url"]}')
-            print(f'评论数: {post["comment_count"]}')
-            print(f'实际获取评论数: {len(post["comments"])}')
-            if post.get('comments'):
-                print(f'第一条评论: {post["comments"][0]["reply_content"][:30]}...')
-    else:
-        print('未获取到任何数据')
-        print(f'耗时: {(end_time - start_time).total_seconds():.2f} 秒')

sentiment_analysis.py

@@ -0,0 +1,409 @@
+import pandas as pd
+import jieba
+import time
+import json
+import os
+from collections import defaultdict
+import matplotlib.pyplot as plt
+import matplotlib
+matplotlib.use('Agg')
+
+# 设置中文字体
+plt.rcParams['font.sans-serif'] = ['SimHei', 'Microsoft YaHei', 'SimSun', 'Arial Unicode MS']
+plt.rcParams['axes.unicode_minus'] = False  # 解决负号显示问题
+
+# ============================================================
+# 第一部分：构建情感词典
+# ============================================================
+
+def build_sentiment_dictionary():
+    """使用大连理工大学中文情感词汇本体构建情感词典"""
+    
+    dict_path = '大连理工大学中文情感词汇本体.xlsx'
+    
+    try:
+        # 读取大连理工大学情感词汇
+        df = pd.read_excel(dict_path)
+        
+        # 选择需要的列
+        df = df[['词语', '词性种类', '词义数', '词义序号', '情感分类', '强度', '极性']]
+        
+        # 分类整理
+        Happy = []
+        Good = []
+        Surprise = []
+        Anger = []
+        Sad = []
+        Fear = []
+        Disgust = []
+        
+        for idx, row in df.iterrows():
+            if row['情感分类'] in ['PA', 'PE']:
+                Happy.append(row['词语'])
+            if row['情感分类'] in ['PD', 'PH', 'PG', 'PB', 'PK']:
+                Good.append(row['词语'])
+            if row['情感分类'] in ['PC']:
+                Surprise.append(row['词语'])
+            if row['情感分类'] in ['NA']:
+                Anger.append(row['词语'])
+            if row['情感分类'] in ['NB', 'NJ', 'NH', 'PF']:
+                Sad.append(row['词语'])
+            if row['情感分类'] in ['NI', 'NC', 'NG']:
+                Fear.append(row['词语'])
+            if row['情感分类'] in ['NE', 'ND', 'NN', 'NK', 'NL']:
+                Disgust.append(row['词语'])
+        
+        # 添加股票相关的补充词汇
+        stock_positive = ['涨', '上涨', '暴涨', '拉升', '涨停', '盈利', '收益', '赚钱', '赚', 
+                         '利好', '增长', '上升', '增加', '发展', '进步', '提升', '改善', '突破',
+                         '创新', '优势', '超预期', '亮眼', '惊艳', '奇迹']
+        stock_negative = ['跌', '下跌', '暴跌', '跳水', '跌停', '亏损', '亏钱', '赔', '损失',
+                         '套牢', '垃圾', '恶心', '坑爹', '骗局', '雷', '爆雷', '崩盘', '退市']
+        
+        Good.extend(stock_positive)
+        Disgust.extend(stock_negative)
+        
+        # 合并
+        Positive = Happy + Good + Surprise
+        Negative = Anger + Sad + Fear + Disgust
+        
+        print('大连理工大学情感词典加载完成')
+        print(f'正面情感词: {len(Positive)}个')
+        print(f'负面情感词: {len(Negative)}个')
+        
+        return {
+            'Happy': Happy,
+            'Good': Good,
+            'Surprise': Surprise,
+            'Anger': Anger,
+            'Sad': Sad,
+            'Fear': Fear,
+            'Disgust': Disgust,
+            'Positive': Positive,
+            'Negative': Negative
+        }
+        
+    except Exception as e:
+        print(f'加载大连理工大学情感词典失败: {e}')
+        print('使用简化版情感词典')
+        return build_simplified_dictionary()
+
+def build_simplified_dictionary():
+    """构建简化的中文情感词典（备用方案）"""
+    
+    # 正面情感词
+    Happy = [
+        '开心', '快乐', '高兴', '喜悦', '愉快', '欣喜', '欢乐', '欢喜', '幸福',
+        '满意', '满足', '欣慰', '愉悦', '畅快', '乐观', '积极', '美好', '成功'
+    ]
+    
+    Good = [
+        '好', '优秀', '出色', '精彩', '卓越', '杰出', '优良', '良好', '完美', '不错',
+        '涨', '上涨', '暴涨', '拉升', '涨停', '盈利', '收益', '赚钱', '赚', '利好',
+        '增长', '上升', '增加', '发展', '进步', '提升', '改善', '突破', '创新', '优势'
+    ]
+    
+    Surprise = [
+        '惊喜', '意外', '震惊', '惊讶', '震撼', '神奇', '奇迹', '惊艳', '亮眼', '超预期'
+    ]
+    
+    # 负面情感词
+    Anger = [
+        '愤怒', '生气', '恼火', '气愤', '暴怒', '愤慨', '愤恨', '震怒', '发怒',
+        '骂', '垃圾', '恶心', '坑爹', '骗局', '欺骗', '欺诈', '造假', '腐败', '黑暗'
+    ]
+    
+    Sad = [
+        '伤心', '难过', '悲伤', '痛苦', '悲哀', '沮丧', '失望', '绝望', '低落', '悲观',
+        '跌', '下跌', '暴跌', '跳水', '跌停', '亏损', '亏钱', '赔', '损失', '套牢'
+    ]
+    
+    Fear = [
+        '害怕', '恐惧', '担心', '担忧', '恐慌', '不安', '焦虑', '忧虑', '紧张', '恐怖',
+        '风险', '危机', '危险', '下跌', '暴跌', '崩盘', '退市', '爆雷', '雷', '怕'
+    ]
+    
+    Disgust = [
+        '厌恶', '恶心', '反感', '讨厌', '鄙视', '唾弃', '不屑', '蔑视', '嫌弃',
+        '垃圾', '废物', '不行', '差劲', '差', '烂', '渣', '骗局'
+    ]
+    
+    # 合并
+    Positive = Happy + Good + Surprise
+    Negative = Anger + Sad + Fear + Disgust
+    
+    print('简化版情感词典构建完成')
+    print(f'正面情感词: {len(Positive)}个')
+    print(f'负面情感词: {len(Negative)}个')
+    
+    return {
+        'Happy': Happy,
+        'Good': Good,
+        'Surprise': Surprise,
+        'Anger': Anger,
+        'Sad': Sad,
+        'Fear': Fear,
+        'Disgust': Disgust,
+        'Positive': Positive,
+        'Negative': Negative
+    }
+
+# ============================================================
+# 第二部分：情绪计算函数
+# ============================================================
+
+def emotion_caculate(text, sentiment_dict):
+    """计算单条文本的情绪"""
+    
+    if not text or pd.isna(text):
+        text = ''
+    
+    positive = 0
+    negative = 0
+    anger = 0
+    disgust = 0
+    fear = 0
+    sad = 0
+    surprise = 0
+    good = 0
+    happy = 0
+    
+    wordlist = jieba.lcut(text)
+    wordset = set(wordlist)
+    
+    for word in wordset:
+        freq = wordlist.count(word)
+        
+        if word in sentiment_dict['Positive']:
+            positive += freq
+        if word in sentiment_dict['Negative']:
+            negative += freq
+        if word in sentiment_dict['Anger']:
+            anger += freq
+        if word in sentiment_dict['Disgust']:
+            disgust += freq
+        if word in sentiment_dict['Fear']:
+            fear += freq
+        if word in sentiment_dict['Sad']:
+            sad += freq
+        if word in sentiment_dict['Surprise']:
+            surprise += freq
+        if word in sentiment_dict['Good']:
+            good += freq
+        if word in sentiment_dict['Happy']:
+            happy += freq
+    
+    emotion_info = {
+        'length': len(wordlist),
+        'positive': positive,
+        'negative': negative,
+        'anger': anger,
+        'disgust': disgust,
+        'fear': fear,
+        'sadness': sad,
+        'surprise': surprise,
+        'good': good,
+        'happy': happy,
+        'sentiment_score': positive - negative if (positive + negative) > 0 else 0
+    }
+    
+    indexs = ['length', 'positive', 'negative', 'anger', 'disgust', 'fear', 
+              'sadness', 'surprise', 'good', 'happy', 'sentiment_score']
+    
+    return pd.Series(emotion_info, index=indexs)
+
+# ============================================================
+# 第三部分：数据加载与分析
+# ============================================================
+
+def load_and_analyze_data(data_dir='data', output_dir='sentiment_output'):
+    """加载数据并进行情绪分析"""
+    
+    os.makedirs(output_dir, exist_ok=True)
+    
+    # 构建情感词典
+    sentiment_dict = build_sentiment_dictionary()
+    
+    # 遍历所有JSON文件
+    all_results = []
+    stock_emotions = {}
+    
+    for filename in os.listdir(data_dir):
+        if filename.endswith('.json') and filename.startswith('guba_'):
+            filepath = os.path.join(data_dir, filename)
+            
+            print(f'\n正在分析: {filename}')
+            
+            try:
+                with open(filepath, 'r', encoding='utf-8') as f:
+                    data = json.load(f)
+                
+                stock_name = data.get('stock_name', '未知')
+                stock_code = data.get('stock_code', '未知')
+                posts = data.get('posts', [])
+                
+                if not posts:
+                    print(f'  无数据，跳过')
+                    continue
+                
+                # 转换为DataFrame
+                df = pd.DataFrame(posts)
+                
+                # 合并标题和内容
+                df['full_text'] = df.apply(
+                    lambda x: f"{x.get('post_title', '')} {x.get('post_content', '')}", 
+                    axis=1
+                )
+                
+                # 进行情绪分析
+                print(f'  开始分析 {len(df)} 条帖子...')
+                start = time.time()
+                
+                emotion_df = df['full_text'].apply(
+                    lambda x: emotion_caculate(x, sentiment_dict)
+                )
+                
+                end = time.time()
+                print(f'  分析完成，耗时: {end - start:.2f}秒')
+                
+                # 合并结果
+                result_df = pd.concat([df, emotion_df], axis=1)
+                
+                # 保存结果
+                output_file = os.path.join(output_dir, f'sentiment_{stock_name}_{stock_code}.csv')
+                result_df.to_csv(output_file, index=False, encoding='utf-8-sig')
+                print(f'  结果已保存到: {output_file}')
+                
+                # 统计整体情绪
+                stock_stats = {
+                    'stock_code': stock_code,
+                    'stock_name': stock_name,
+                    'total_posts': len(result_df),
+                    'avg_positive': result_df['positive'].mean(),
+                    'avg_negative': result_df['negative'].mean(),
+                    'avg_sentiment_score': result_df['sentiment_score'].mean(),
+                    'positive_posts': (result_df['sentiment_score'] > 0).sum(),
+                    'negative_posts': (result_df['sentiment_score'] < 0).sum(),
+                    'neutral_posts': (result_df['sentiment_score'] == 0).sum(),
+                    'total_anger': result_df['anger'].sum(),
+                    'total_sadness': result_df['sadness'].sum(),
+                    'total_fear': result_df['fear'].sum(),
+                    'total_disgust': result_df['disgust'].sum(),
+                    'total_good': result_df['good'].sum(),
+                    'total_happy': result_df['happy'].sum(),
+                    'total_surprise': result_df['surprise'].sum()
+                }
+                
+                stock_emotions[stock_code] = stock_stats
+                all_results.append(result_df)
+                
+                # 打印该股票情绪最高/最低的帖子
+                print(f'\n  {stock_name} 情绪分析统计:')
+                print(f'    平均情绪得分: {stock_stats["avg_sentiment_score"]:.2f}')
+                print(f'    正面帖子: {stock_stats["positive_posts"]}')
+                print(f'    负面帖子: {stock_stats["negative_posts"]}')
+                print(f'    中性帖子: {stock_stats["neutral_posts"]}')
+                
+                # 最正面帖子
+                top_positive = result_df.nlargest(1, 'sentiment_score').iloc[0]
+                print(f'    最正面帖子: {top_positive["full_text"][:50]}...')
+                
+                # 最负面帖子
+                top_negative = result_df.nsmallest(1, 'sentiment_score').iloc[0]
+                print(f'    最负面帖子: {top_negative["full_text"][:50]}...')
+                
+            except Exception as e:
+                print(f'  分析失败: {e}')
+    
+    # 保存总体统计
+    if stock_emotions:
+        summary_df = pd.DataFrame(list(stock_emotions.values()))
+        summary_file = os.path.join(output_dir, 'sentiment_summary.csv')
+        summary_df.to_csv(summary_file, index=False, encoding='utf-8-sig')
+        print(f'\n总体统计已保存到: {summary_file}')
+        
+        # 生成可视化
+        generate_visualizations(summary_df, stock_emotions, output_dir)
+    
+    return all_results, stock_emotions
+
+# ============================================================
+# 第四部分：可视化
+# ============================================================
+
+def generate_visualizations(summary_df, stock_emotions, output_dir):
+    """生成情绪分析可视化图表"""
+    
+    # 1. 各股票平均情绪得分对比
+    plt.figure(figsize=(12, 6))
+    colors = ['green' if x >= 0 else 'red' for x in summary_df['avg_sentiment_score']]
+    plt.bar(summary_df['stock_name'], summary_df['avg_sentiment_score'], color=colors, alpha=0.7)
+    plt.axhline(y=0, color='black', linestyle='-', linewidth=0.5)
+    plt.title('各股票平均情绪得分对比', fontsize=14)
+    plt.xlabel('股票名称', fontsize=12)
+    plt.ylabel('平均情绪得分', fontsize=12)
+    plt.xticks(rotation=45)
+    plt.tight_layout()
+    plt.savefig(os.path.join(output_dir, 'sentiment_score_comparison.png'), dpi=300)
+    plt.close()
+    
+    # 2. 正面/负面/中性帖子分布
+    fig, axes = plt.subplots(2, 4, figsize=(16, 10))
+    axes = axes.flatten()
+    
+    for idx, (stock_code, stats) in enumerate(stock_emotions.items()):
+        if idx >= 8:
+            break
+        labels = ['正面', '负面', '中性']
+        sizes = [stats['positive_posts'], stats['negative_posts'], stats['neutral_posts']]
+        colors = ['green', 'red', 'gray']
+        
+        axes[idx].pie(sizes, labels=labels, colors=colors, autopct='%1.1f%%', startangle=90)
+        axes[idx].set_title(f'{stats["stock_name"]} 情绪分布')
+    
+    plt.tight_layout()
+    plt.savefig(os.path.join(output_dir, 'sentiment_distribution.png'), dpi=300)
+    plt.close()
+    
+    # 3. 各情绪类型占比
+    plt.figure(figsize=(14, 7))
+    emotions = ['total_good', 'total_happy', 'total_surprise', 
+                'total_anger', 'total_sadness', 'total_fear', 'total_disgust']
+    emotion_names = ['好评', '快乐', '惊讶', '愤怒', '悲伤', '恐惧', '厌恶']
+    
+    x = range(len(emotion_names))
+    width = 0.1
+    
+    for idx, (stock_code, stats) in enumerate(stock_emotions.items()):
+        values = [stats[e] for e in emotions]
+        total = sum(values)
+        if total > 0:
+            values = [v / total * 100 for v in values]
+        plt.bar([xi + width * idx for xi in x], values, width, label=stats['stock_name'])
+    
+    plt.xlabel('情绪类型', fontsize=12)
+    plt.ylabel('占比 (%)', fontsize=12)
+    plt.title('各股票情绪类型分布', fontsize=14)
+    plt.xticks([xi + width * 3.5 for xi in x], emotion_names)
+    plt.legend(bbox_to_anchor=(1.05, 1), loc='upper left')
+    plt.tight_layout()
+    plt.savefig(os.path.join(output_dir, 'emotion_types.png'), dpi=300, bbox_inches='tight')
+    plt.close()
+    
+    print(f'可视化图表已生成到 {output_dir}')
+
+# ============================================================
+# 主程序
+# ============================================================
+
+if __name__ == '__main__':
+    print('=' * 60)
+    print('股吧数据情绪分析')
+    print('=' * 60)
+    
+    # 运行分析
+    all_results, stock_emotions = load_and_analyze_data()
+    
+    print('\n' + '=' * 60)
+    print('情绪分析完成！')
+    print('=' * 60)

sentiment_time_series.py

@@ -0,0 +1,297 @@
+import os
+import json
+import re
+import numpy as np
+import pandas as pd
+from datetime import datetime
+import matplotlib.pyplot as plt
+import matplotlib
+matplotlib.use('Agg')
+import jieba
+
+# 设置中文字体
+plt.rcParams['font.sans-serif'] = ['SimHei', 'Microsoft YaHei', 'SimSun', 'Arial Unicode MS']
+plt.rcParams['axes.unicode_minus'] = False
+
+# 加载停用词
+def load_stopwords(filepath='stopwords.txt'):
+    stopwords = set()
+    if os.path.exists(filepath):
+        with open(filepath, 'r', encoding='utf-8') as f:
+            for line in f:
+                word = line.strip()
+                if word:
+                    stopwords.add(word)
+    return stopwords
+
+STOPWORDS = load_stopwords()
+
+# ============================================================
+# 构建情感词典（参照 sentiment_analysis.py）
+# ============================================================
+def build_sentiment_dictionary():
+    """使用大连理工大学中文情感词汇本体构建情感词典"""
+    
+    dict_path = '大连理工大学中文情感词汇本体.xlsx'
+    
+    try:
+        df = pd.read_excel(dict_path)
+        df = df[['词语', '词性种类', '词义数', '词义序号', '情感分类', '强度', '极性']]
+        
+        Happy = []
+        Good = []
+        Surprise = []
+        Anger = []
+        Sad = []
+        Fear = []
+        Disgust = []
+        
+        for idx, row in df.iterrows():
+            if row['情感分类'] in ['PA', 'PE']:
+                Happy.append(row['词语'])
+            if row['情感分类'] in ['PD', 'PH', 'PG', 'PB', 'PK']:
+                Good.append(row['词语'])
+            if row['情感分类'] in ['PC']:
+                Surprise.append(row['词语'])
+            if row['情感分类'] in ['NA']:
+                Anger.append(row['词语'])
+            if row['情感分类'] in ['NB', 'NJ', 'NH', 'PF']:
+                Sad.append(row['词语'])
+            if row['情感分类'] in ['NI', 'NC', 'NG']:
+                Fear.append(row['词语'])
+            if row['情感分类'] in ['NE', 'ND', 'NN', 'NK', 'NL']:
+                Disgust.append(row['词语'])
+        
+        # 添加股票相关词汇
+        stock_positive = ['涨', '上涨', '暴涨', '拉升', '涨停', '盈利', '收益', '赚钱', '赚', 
+                         '利好', '增长', '上升', '增加', '发展', '进步', '提升', '改善', '突破',
+                         '创新', '优势', '超预期', '亮眼', '惊艳', '奇迹']
+        stock_negative = ['跌', '下跌', '暴跌', '跳水', '跌停', '亏损', '亏钱', '赔', '损失',
+                         '套牢', '垃圾', '恶心', '坑爹', '骗局', '雷', '爆雷', '崩盘', '退市']
+        
+        Good.extend(stock_positive)
+        Disgust.extend(stock_negative)
+        
+        Positive = Happy + Good + Surprise
+        Negative = Anger + Sad + Fear + Disgust
+        
+        print(f'大连理工大学情感词典加载完成')
+        print(f'  正面情感词: {len(Positive)}个')
+        print(f'  负面情感词: {len(Negative)}个')
+        
+        return {
+            'Happy': Happy,
+            'Good': Good,
+            'Surprise': Surprise,
+            'Anger': Anger,
+            'Sad': Sad,
+            'Fear': Fear,
+            'Disgust': Disgust,
+            'Positive': Positive,
+            'Negative': Negative
+        }
+        
+    except Exception as e:
+        print(f'加载大连理工大学情感词典失败: {e}')
+        print('使用简化版情感词典')
+        return build_simplified_dictionary()
+
+def build_simplified_dictionary():
+    """构建简化的中文情感词典（备用方案）"""
+    
+    Happy = ['开心', '快乐', '高兴', '喜悦', '愉快', '欣喜', '欢乐', '欢喜', '幸福',
+             '满意', '满足', '欣慰', '愉悦', '畅快', '乐观', '积极', '美好', '成功']
+    
+    Good = ['好', '优秀', '出色', '精彩', '卓越', '杰出', '优良', '良好', '完美', '不错',
+            '涨', '上涨', '暴涨', '拉升', '涨停', '盈利', '收益', '赚钱', '赚', '利好',
+            '增长', '上升', '增加', '发展', '进步', '提升', '改善', '突破', '创新', '优势']
+    
+    Surprise = ['惊喜', '意外', '震惊', '惊讶', '震撼', '神奇', '奇迹', '惊艳', '亮眼', '超预期']
+    
+    Anger = ['愤怒', '生气', '恼火', '气愤', '暴怒', '愤慨', '愤恨', '震怒', '发怒',
+             '骂', '垃圾', '恶心', '坑爹', '骗局', '欺骗', '欺诈', '造假', '腐败', '黑暗']
+    
+    Sad = ['伤心', '难过', '悲伤', '痛苦', '悲哀', '沮丧', '失望', '绝望', '低落', '悲观',
+           '跌', '下跌', '暴跌', '跳水', '跌停', '亏损', '亏钱', '赔', '损失', '套牢']
+    
+    Fear = ['害怕', '恐惧', '担心', '担忧', '恐慌', '不安', '焦虑', '忧虑', '紧张', '恐怖',
+            '风险', '危机', '危险', '下跌', '暴跌', '崩盘', '退市', '爆雷', '雷', '怕']
+    
+    Disgust = ['厌恶', '恶心', '反感', '讨厌', '鄙视', '唾弃', '不屑', '蔑视', '嫌弃',
+               '垃圾', '废物', '不行', '差劲', '差', '烂', '渣', '骗局']
+    
+    Positive = Happy + Good + Surprise
+    Negative = Anger + Sad + Fear + Disgust
+    
+    print(f'简化版情感词典构建完成')
+    print(f'  正面情感词: {len(Positive)}个')
+    print(f'  负面情感词: {len(Negative)}个')
+    
+    return {
+        'Happy': Happy,
+        'Good': Good,
+        'Surprise': Surprise,
+        'Anger': Anger,
+        'Sad': Sad,
+        'Fear': Fear,
+        'Disgust': Disgust,
+        'Positive': Positive,
+        'Negative': Negative
+    }
+
+# ============================================================
+# 情绪计算函数（参照 sentiment_analysis.py）
+# ============================================================
+def emotion_caculate(text, sentiment_dict):
+    """计算单条文本的情绪"""
+    
+    if not text or pd.isna(text):
+        return 0
+    
+    positive = 0
+    negative = 0
+    
+    wordlist = jieba.lcut(text)
+    
+    for word in wordlist:
+        # 跳过停用词和短词
+        if word in STOPWORDS or len(word) <= 1:
+            continue
+        
+        freq = wordlist.count(word)
+        
+        if word in sentiment_dict['Positive']:
+            positive += freq
+        if word in sentiment_dict['Negative']:
+            negative += freq
+    
+    sentiment_score = positive - negative
+    return sentiment_score
+
+# ============================================================
+# 时间序列分析
+# ============================================================
+def analyze_sentiment_trend():
+    """分析情绪时间序列趋势（使用情感词典）"""
+    print("="*60)
+    print("情绪时间序列分析（基于情感词典）")
+    print("="*60)
+    
+    # 构建情感词典
+    print("\n[1/5] 构建情感词典...")
+    sentiment_dict = build_sentiment_dictionary()
+    
+    # 加载数据
+    print("\n[2/5] 加载数据...")
+    df = pd.read_csv('output/all_posts.csv', encoding='utf-8-sig')
+    
+    # 检查是否有 post_publish_time 字段
+    if 'post_publish_time' not in df.columns:
+        print("警告：数据中没有 post_publish_time 字段，请先运行 analyze.py")
+        return
+    
+    # 转换时间戳
+    print("\n[3/5] 转换时间戳...")
+    df['timestamp'] = pd.to_datetime(df['post_publish_time'], errors='coerce')
+    df = df.dropna(subset=['timestamp'])
+    df['date'] = df['timestamp'].dt.date
+    
+    # 计算情绪得分
+    print("\n[4/5] 计算情绪得分...")
+    df['sentiment_score'] = df['clean_text'].apply(
+        lambda x: emotion_caculate(x, sentiment_dict)
+    )
+    
+    # 保存结果
+    df.to_csv('output/sentiment_analysis_result.csv', index=False, encoding='utf-8-sig')
+    print("  情绪分析结果已保存到: output/sentiment_analysis_result.csv")
+    
+    # 按股票分组分析
+    stock_groups = df.groupby('stock_code')
+    os.makedirs('output/plots', exist_ok=True)
+    
+    print("\n[5/5] 生成时间序列图表...")
+    for stock_code, group in stock_groups:
+        stock_name = group['stock_name'].iloc[0]
+        print(f"\n  分析 {stock_name} ({stock_code})...")
+        
+        # 按日期分组计算平均情绪
+        daily_sentiment = group.groupby('date')['sentiment_score'].agg(['mean', 'count']).reset_index()
+        daily_sentiment.columns = ['date', 'avg_sentiment', 'post_count']
+        
+        if len(daily_sentiment) < 2:
+            print(f"    数据不足，跳过")
+            continue
+        
+        # 绘制时间序列图
+        fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 8), sharex=True)
+        
+        # 情绪趋势
+        ax1.plot(daily_sentiment['date'], daily_sentiment['avg_sentiment'], 
+                 marker='o', linestyle='-', color='b', label='日均情绪')
+        
+        # 添加移动平均线
+        daily_sentiment['MA3'] = daily_sentiment['avg_sentiment'].rolling(window=3).mean()
+        ax1.plot(daily_sentiment['date'], daily_sentiment['MA3'], 
+                 marker='', linestyle='--', color='r', label='3日移动平均')
+        
+        ax1.set_title(f'{stock_name} ({stock_code}) 情绪时间序列趋势', fontsize=14)
+        ax1.set_ylabel('情绪分数', fontsize=12)
+        ax1.axhline(y=0, color='gray', linestyle='-', linewidth=0.5)
+        ax1.grid(True)
+        ax1.legend()
+        
+        # 发帖量
+        ax2.bar(daily_sentiment['date'], daily_sentiment['post_count'], color='g', alpha=0.7)
+        ax2.set_xlabel('日期', fontsize=12)
+        ax2.set_ylabel('发帖数量', fontsize=12)
+        ax2.grid(True)
+        
+        plt.xticks(rotation=45)
+        plt.tight_layout()
+        
+        # 保存图表
+        plot_path = f'output/plots/sentiment_trend_{stock_name}.png'
+        plt.savefig(plot_path, dpi=100)
+        plt.close()
+        print(f"    图表已保存到: {plot_path}")
+        
+        # 输出统计信息
+        avg_sentiment = group['sentiment_score'].mean()
+        pos_count = (group['sentiment_score'] > 0).sum()
+        neg_count = (group['sentiment_score'] < 0).sum()
+        neu_count = (group['sentiment_score'] == 0).sum()
+        print(f"    平均情绪: {avg_sentiment:.4f}")
+        print(f"    正面帖子: {pos_count}, 负面帖子: {neg_count}, 中性帖子: {neu_count}")
+    
+    # 生成汇总报告
+    print("\n生成汇总报告...")
+    summary_data = []
+    for stock_code, group in stock_groups:
+        stock_name = group['stock_name'].iloc[0]
+        avg_sentiment = group['sentiment_score'].mean()
+        post_count = len(group)
+        pos_count = (group['sentiment_score'] > 0).sum()
+        neg_count = (group['sentiment_score'] < 0).sum()
+        neu_count = (group['sentiment_score'] == 0).sum()
+        
+        summary_data.append({
+            '股票代码': stock_code,
+            '股票名称': stock_name,
+            '帖子数量': post_count,
+            '平均情绪': round(avg_sentiment, 4),
+            '正面帖子': pos_count,
+            '负面帖子': neg_count,
+            '中性帖子': neu_count
+        })
+    
+    summary_df = pd.DataFrame(summary_data)
+    summary_df.to_csv('output/sentiment_summary.csv', index=False, encoding='utf-8-sig')
+    print("汇总报告已保存到: output/sentiment_summary.csv")
+    
+    print("\n" + "="*60)
+    print("情绪时间序列分析完成！")
+    print("="*60)
+
+if __name__ == '__main__':
+    analyze_sentiment_trend()

spider.py

@@ -0,0 +1,187 @@
+import requests
+import pandas as pd
+import json
+import time
+from datetime import datetime
+import os
+
+def fetch_guba_data(code='gssz', page=1, page_size=20, sort_type=1):
+    url = 'https://mguba.eastmoney.com/mguba2020/interface/GetData.aspx'
+    
+    headers = {
+        'Accept': '*/*',
+        'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
+        'Cache-Control': 'no-cache',
+        'Connection': 'keep-alive',
+        'Content-Type': 'application/x-www-form-urlencoded',
+        'DNT': '1',
+        'Origin': 'https://mguba.eastmoney.com',
+        'Pragma': 'no-cache',
+        'Referer': f'https://mguba.eastmoney.com/mguba/list/{code}_{page}',
+        'Sec-Fetch-Dest': 'empty',
+        'Sec-Fetch-Mode': 'cors',
+        'Sec-Fetch-Site': 'same-origin',
+        'User-Agent': 'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Mobile Safari/537.36 Edg/148.0.0.0',
+        'sec-ch-ua': '"Chromium";v="148", "Microsoft Edge";v="148", "Not/A)Brand";v="99"',
+        'sec-ch-ua-mobile': '?1',
+        'sec-ch-ua-platform': '"Android"'
+    }
+    
+    cookies = {
+        'qgqp_b_id': '30059d8839ad5c045fa8856e38013e9c',
+        'st_nvi': 'XwpSfYXGjCxfCdbgapK5_cac4',
+        'nid18': '0daec1df8064f04edd20b4e69250a8f5',
+        'nid18_create_time': '1776263017375',
+        'gviem': 'UrMH_tSu1UpW8B_TKmytl803f',
+        'gviem_create_time': '1776263017375',
+        'fullscreengg': '1',
+        'fullscreengg2': '1',
+        'st_si': '17952715731426',
+        'show_app_box_time': '1779903756410',
+        'st_pvi': '26838250597806',
+        'st_sp': '2026-04-15 22:23:37',
+        'st_inirUrl': 'https://cn.bing.com/',
+        'st_sn': '30',
+        'st_psi': '20260528025236177-117016304298-3040545697',
+        'ad_tc_load_num': '3',
+        'st_asi': '20260528025236177-117016304298-3040545697-ad.djxd-1'
+    }
+    
+    param = f'code={code}&p={page}&ps={page_size}&sorttype={sort_type}'
+    data = {
+        'param': param,
+        'plat': 'wap',
+        'version': '200',
+        'path': '/webarticlelist/api/Article/WebArticleList',
+        'env': '1',
+        'origin': '',
+        'ctoken': '',
+        'utoken': ''
+    }
+    
+    try:
+        response = requests.post(url, headers=headers, cookies=cookies, data=data)
+        response.raise_for_status()
+        return response.json()
+    except requests.exceptions.RequestException as e:
+        print(f'请求失败: {e}')
+        return None
+
+def fetch_stock_posts(code, name, pages=10, page_size=20):
+    """爬取指定股票的多页数据"""
+    all_posts = []
+    
+    for page in range(1, pages + 1):
+        print(f'正在爬取 {name} ({code}) - 第 {page}/{pages} 页')
+        result = fetch_guba_data(code=code, page=page, page_size=page_size)
+        
+        if result and 're' in result:
+            posts = result['re']
+            all_posts.extend(posts)
+            print(f'  成功获取 {len(posts)} 条帖子')
+        else:
+            print(f'  第 {page} 页获取失败或无数据')
+        
+        # 添加延迟避免请求过快
+        if page < pages:
+            time.sleep(1)
+    
+    # 整理数据
+    data = {
+        'stock_code': code,
+        'stock_name': name,
+        'total_pages': pages,
+        'total_posts': len(all_posts),
+        'crawl_time': datetime.now().isoformat(),
+        'posts': all_posts
+    }
+    
+    return data
+
+def save_to_json(data, name="", filename=None):
+    if not data:
+        print('数据为空，无法保存')
+        return None
+    
+    if not filename:
+        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+        filename = f'guba_{name}_{timestamp}.json'
+    
+    with open(filename, 'w', encoding='utf-8') as f:
+        json.dump(data, f, ensure_ascii=False, indent=2)
+    
+    print(f'JSON数据已保存到: {filename}')
+    return filename
+
+def save_to_excel(data, name="", filename=None):
+    if not data or 'posts' not in data:
+        print('数据格式不正确，无法保存')
+        return None
+    
+    posts = data['posts']
+    records = []
+    
+    for post in posts:
+        record = {
+            '帖子ID': post.get('post_id'),
+            '标题': post.get('post_title'),
+            '内容': post.get('post_content'),
+            '作者': post.get('post_user', {}).get('user_nickname'),
+            '发布时间': post.get('post_publish_time'),
+            '最后更新': post.get('post_last_time'),
+            '阅读数': post.get('post_click_count'),
+            '评论数': post.get('post_comment_count'),
+            '点赞数': post.get('post_like_count'),
+            '股吧': post.get('post_guba', {}).get('stockbar_name'),
+            '来源': post.get('post_from')
+        }
+        records.append(record)
+    
+    df = pd.DataFrame(records)
+    
+    if not filename:
+        timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
+        filename = f'guba_{name}_{timestamp}.xlsx'
+    
+    df.to_excel(filename, index=False, engine='openpyxl')
+    print(f'Excel数据已保存到: {filename}')
+    return filename
+
+if __name__ == '__main__':
+    GAME_STOCKS = {
+        '002624': '完美世界',
+        '002555': '三七互娱',
+        '002558': '巨人网络',
+        '002602': '世纪华通',
+        '300418': '昆仑万维',
+        '002174': '游族网络',
+        '300315': '掌趣科技',
+        '603444': '吉比特',
+    }
+    
+    # 创建数据目录
+    os.makedirs('data', exist_ok=True)
+    
+    for code, name in GAME_STOCKS.items():
+        print(f'\n{"="*50}')
+        print(f'开始爬取 {name} ({code})')
+        print(f'{"="*50}')
+        
+        # 爬取10页数据
+        data = fetch_stock_posts(code, name, pages=30)
+        
+        if data and data['total_posts'] > 0:
+            print(f'\n共获取 {data["total_posts"]} 条帖子')
+            
+            # 保存JSON
+            json_filename = os.path.join('data', f'guba_{name}_{code}.json')
+            save_to_json(data, name, json_filename)
+            
+            # 保存Excel
+            excel_filename = os.path.join('data', f'guba_{name}_{code}.xlsx')
+            save_to_excel(data, name, excel_filename)
+        else:
+            print(f'{name} 爬取失败或无数据')
+        
+        # 股票之间的延迟
+        time.sleep(2)

test_api.py

@@ -1,38 +0,0 @@
-import asyncio
-import aiohttp
-
-comment_headers = {
-    'Accept': '*/*',
-    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8,en-GB;q=0.7,en-US;q=0.6',
-    'Cache-Control': 'no-cache',
-    'Connection': 'keep-alive',
-    'Content-Type': 'application/x-www-form-urlencoded',
-    'Origin': 'https://guba.eastmoney.com',
-    'Pragma': 'no-cache',
-    'Referer': 'https://guba.eastmoney.com/news,002624,1711407668.html',
-    'Sec-Fetch-Dest': 'empty',
-    'Sec-Fetch-Mode': 'cors',
-    'Sec-Fetch-Site': 'same-origin',
-    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/148.0.0.0 Safari/537.36',
-}
-
-async def test_comment_api():
-    url = 'https://guba.eastmoney.com/api/getData?code=002624&path=reply/api/Reply/ArticleNewReplyList'
-    
-    payload = {
-        'param': 'postid=1711407668&sort=1&sorttype=1&p=1&ps=30',
-        'plat': 'Web',
-        'path': 'reply/api/Reply/ArticleNewReplyList',
-        'env': '2',
-        'origin': '',
-        'version': '2022',
-        'product': 'Guba'
-    }
-    
-    async with aiohttp.ClientSession() as session:
-        async with session.post(url, headers=comment_headers, data=payload) as response:
-            print(f'状态码: {response.status}')
-            text = await response.text()
-            print(f'响应内容:\n{text}')
-
-asyncio.run(test_comment_api())

train_sentiment_model.py

@@ -0,0 +1,229 @@
+import os
+import json
+import re
+import numpy as np
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import classification_report, accuracy_score
+from gensim.models import Word2Vec
+from tensorflow.keras.preprocessing.text import Tokenizer
+from tensorflow.keras.preprocessing.sequence import pad_sequences
+from tensorflow.keras.models import Sequential
+from tensorflow.keras.layers import Embedding, Conv1D, GlobalMaxPooling1D, Dense, Dropout
+from tensorflow.keras.utils import to_categorical
+import jieba
+
+def load_stopwords(filepath='stopwords.txt'):
+    """从文件加载停用词"""
+    stopwords = set()
+    if os.path.exists(filepath):
+        with open(filepath, 'r', encoding='utf-8') as f:
+            for line in f:
+                word = line.strip()
+                if word:
+                    stopwords.add(word)
+        print(f"已加载 {len(stopwords)} 个停用词")
+    else:
+        print(f"警告：停用词文件 {filepath} 不存在，使用默认停用词")
+        stopwords = {
+            '的', '了', '在', '是', '我', '有', '和', '就', '不', '人', '都', '一', '一个', '上', '也', '很', '到', '说', '要',
+            '去', '你', '会', '着', '没有', '看', '好', '自己', '这', '那', '有', '吗', '吧', '呢', '啊', '呀', '什么', '怎么',
+            '为什么', '哪里', '谁', '多少', '几', '个', '只', '条', '把', '本', '篇', '次', '天', '今天', '明天', '昨天', '又',
+            '再', '还', '已经', '还是', '但是', '可是', '不过', '只是', '只有', '就是', '或者', '跟', '和', '与', '及', '或',
+            '股吧', '东方财富', '帖子', '发表', '回复', '点击', '查看', '更多', '原文', '转发', '分享', '收藏', '评论', '点赞',
+            'http', 'https', 'com', 'cn', 'www', 'net', 'org'
+        }
+    return stopwords
+
+# 加载停用词
+STOPWORDS = load_stopwords()
+
+def clean_text(text):
+    """清洗文本"""
+    if not text or pd.isna(text):
+        return ""
+    text = str(text)
+    text = re.sub(r'https?://\S+|www\.\S+', '', text)
+    text = re.sub(r'<.*?>', '', text)
+    text = re.sub(r'\[.*?\]', '', text)
+    text = re.sub(r'\b[a-zA-Z]+\d+\b', '', text)
+    text = re.sub(r'\b\d+[a-zA-Z]+\b', '', text)
+    text = re.sub(r'[^\w\s]', ' ', text)
+    text = re.sub(r'\s+', ' ', text).strip()
+    return text
+
+def tokenize(text):
+    """中文分词"""
+    words = jieba.lcut(text)
+    filtered_words = []
+    for w in words:
+        if w in STOPWORDS or len(w) <= 1:
+            continue
+        if re.match(r'^[a-zA-Z]+$', w):
+            continue
+        if re.match(r'^[a-zA-Z\s]+$', w):
+            continue
+        filtered_words.append(w)
+    return filtered_words
+
+def load_and_preprocess_data(filepath='output/all_posts.csv'):
+    """加载并预处理数据"""
+    df = pd.read_csv(filepath, encoding='utf-8-sig')
+    
+    print(f"原始数据: {len(df)} 条")
+    
+    df = df.dropna(subset=['clean_text', 'label'])
+    df = df[df['clean_text'].str.strip() != '']
+    
+    print(f"有效数据: {len(df)} 条")
+    print(f"标签分布:")
+    print(df['label'].value_counts())
+    
+    df['tokens'] = df['clean_text'].apply(tokenize)
+    df = df[df['tokens'].apply(len) > 0]
+    
+    print(f"分词后有效数据: {len(df)} 条")
+    
+    return df
+
+def train_word2vec_model(sentences, vector_size=100, window=5, min_count=5):
+    """训练 Word2Vec 模型"""
+    print(f"\n训练 Word2Vec 模型...")
+    model = Word2Vec(
+        sentences=sentences,
+        vector_size=vector_size,
+        window=window,
+        min_count=min_count,
+        workers=4,
+        epochs=10
+    )
+    print(f"Word2Vec 词汇表大小: {len(model.wv)}")
+    return model
+
+def build_cnn_model(vocab_size, embedding_dim, max_seq_len, embedding_matrix, num_classes=3):
+    """构建 CNN 模型"""
+    model = Sequential()
+    
+    model.add(Embedding(
+        input_dim=vocab_size,
+        output_dim=embedding_dim,
+        input_length=max_seq_len,
+        weights=[embedding_matrix],
+        trainable=False
+    ))
+    
+    model.add(Conv1D(128, 5, activation='relu'))
+    model.add(GlobalMaxPooling1D())
+    model.add(Dense(64, activation='relu'))
+    model.add(Dropout(0.5))
+    model.add(Dense(num_classes, activation='softmax'))
+    
+    model.compile(
+        optimizer='adam',
+        loss='categorical_crossentropy',
+        metrics=['accuracy']
+    )
+    
+    return model
+
+def main():
+    print("="*60)
+    print("Word2Vec + CNN 情绪感知模型训练")
+    print("="*60)
+    
+    # 加载数据
+    print("\n[1/5] 加载数据...")
+    df = load_and_preprocess_data()
+    
+    if len(df) < 10:
+        print("数据不足，无法训练")
+        return
+    
+    # 准备 Word2Vec 训练数据
+    sentences = df['tokens'].tolist()
+    
+    # 训练 Word2Vec
+    print("\n[2/5] 训练 Word2Vec 词向量...")
+    w2v_model = train_word2vec_model(sentences)
+    
+    # 构建词汇表
+    print("\n[3/5] 构建词汇表...")
+    tokenizer = Tokenizer()
+    tokenizer.fit_on_texts(sentences)
+    vocab_size = len(tokenizer.word_index) + 1
+    print(f"词汇表大小: {vocab_size}")
+    
+    # 转换文本为序列
+    max_seq_len = max(len(s) for s in sentences)
+    print(f"最大序列长度: {max_seq_len}")
+    sequences = tokenizer.texts_to_sequences(sentences)
+    X = pad_sequences(sequences, maxlen=max_seq_len)
+    
+    # 准备标签
+    label_mapping = {-1: 0, 0: 1, 1: 2}
+    y = df['label'].map(label_mapping).values
+    y = to_categorical(y, num_classes=3)
+    
+    # 创建嵌入矩阵
+    print("\n[4/5] 创建嵌入矩阵...")
+    embedding_dim = w2v_model.vector_size
+    embedding_matrix = np.zeros((vocab_size, embedding_dim))
+    
+    for word, i in tokenizer.word_index.items():
+        if word in w2v_model.wv:
+            embedding_matrix[i] = w2v_model.wv[word]
+    
+    # 划分训练集和测试集
+    X_train, X_test, y_train, y_test = train_test_split(
+        X, y, test_size=0.2, random_state=42, stratify=y
+    )
+    
+    print(f"训练集: {len(X_train)} 条")
+    print(f"测试集: {len(X_test)} 条")
+    
+    # 构建并训练 CNN 模型
+    print("\n[5/5] 训练 CNN 模型...")
+    model = build_cnn_model(vocab_size, embedding_dim, max_seq_len, embedding_matrix)
+    print(model.summary())
+    
+    history = model.fit(
+        X_train, y_train,
+        batch_size=32,
+        epochs=10,
+        validation_split=0.1,
+        verbose=1
+    )
+    
+    # 评估模型
+    print("\n[6/6] 评估模型...")
+    y_pred = model.predict(X_test)
+    y_pred_classes = np.argmax(y_pred, axis=1)
+    y_true_classes = np.argmax(y_test, axis=1)
+    
+    print("\n分类报告:")
+    print(classification_report(y_true_classes, y_pred_classes, target_names=['负面', '中性', '正面']))
+    print(f"准确率: {accuracy_score(y_true_classes, y_pred_classes):.4f}")
+    
+    # 保存模型
+    print("\n保存模型...")
+    os.makedirs('models', exist_ok=True)
+    
+    # 保存 Word2Vec 模型
+    w2v_model.save('models/word2vec.model')
+    print("Word2Vec 模型已保存到: models/word2vec.model")
+    
+    # 保存 CNN 模型
+    model.save('models/cnn_sentiment.h5')
+    print("CNN 模型已保存到: models/cnn_sentiment.h5")
+    
+    # 保存 tokenizer
+    with open('models/tokenizer.json', 'w', encoding='utf-8') as f:
+        f.write(tokenizer.to_json())
+    print("Tokenizer 已保存到: models/tokenizer.json")
+    
+    print("\n" + "="*60)
+    print("训练完成！")
+    print("="*60)
+
+if __name__ == '__main__':
+    main()

分析报告.md

@@ -0,0 +1,296 @@
+# 游戏股吧情感与话题分析报告
+
+**报告日期**：2026-05-28  
+**分析范围**：完美世界、三七互娱、巨人网络、世纪华通、昆仑万维、游族网络、掌趣科技、吉比特  
+**数据来源**：东方财富网股吧
+
+---
+
+## 一、数据概述
+
+本次分析共收集了8只游戏股票的股吧数据，每只股票200条帖子，总计1600条有效数据。
+
+### 数据收集方法
+- 使用网络爬虫从东方财富网股吧获取帖子
+- 数据包括：帖子标题、内容、发布时间等
+- 使用大连理工大学中文情感词汇本体进行情感分析
+
+---
+
+## 二、整体话题分析
+
+### 整体词云
+![整体词云](output/wordcloud_overall.png)
+
+### 整体话题关键词
+| 排名 | 关键词 | TF-IDF值 |
+|------|--------|----------|
+| 1 | 网络 sz | 0.0341 |
+| 2 | 巨人 | 0.0235 |
+| 3 | 世纪 华通 | 0.0215 |
+| 4 | 昆仑 万维 | 0.0215 |
+| 5 | 游族 | 0.0215 |
+| 6 | 三七 互娱 | 0.0201 |
+| 7 | 游戏 | 0.0199 |
+| 8 | 掌趣 科技 | 0.0187 |
+| 9 | 比特 sh | 0.0183 |
+| 10 | 完美 世界 | 0.0174 |
+
+### 整体热门话题
+从整体词云可以看出，股吧讨论主要集中在：
+1. **个股名称**：各股票名称是最热门的话题
+2. **股票操作**：主力、涨停、下跌、出货、股价等
+3. **市场情绪**：散户、大盘、投资等
+
+---
+
+## 三、各股票专题分析
+
+### 1. 完美世界 (002624)
+
+#### 词云分析
+![完美世界词云](output/wordcloud_完美世界.png)
+
+#### 关键词分析
+- **异环**：指游戏《异环》相关讨论
+- **流水**：游戏流水情况
+- **版本**：游戏版本更新
+- **安魂曲**：指游戏角色《安魂曲》
+
+#### 情绪分析
+- **平均情绪得分**：0.99（最高）
+- **正面帖子**：110条
+- **负面帖子**：21条
+- **中性帖子**：69条
+
+**情绪倾向**：非常积极！完美世界是本次分析中情绪最正面的股票。
+
+---
+
+### 2. 巨人网络 (002558)
+
+#### 词云分析
+![巨人网络词云](output/wordcloud_巨人网络.png)
+
+#### 关键词分析
+- **补仓**：投资者补仓操作
+- **腰斩**：股价大幅下跌
+- **跳水**：股价快速下跌
+- **兄弟**：股吧常见称呼
+
+#### 情绪分析
+- **平均情绪得分**：1.11（最高）
+- **正面帖子**：115条
+- **负面帖子**：20条
+- **中性帖子**：65条
+
+**情绪倾向**：非常积极！虽然有"腰斩"、"跳水"等负面词汇，但整体情绪仍然很高。
+
+---
+
+### 3. 三七互娱 (002555)
+
+#### 词云分析
+![三七互娱词云](output/wordcloud_三七互娱.png)
+
+#### 关键词分析
+- **分红**：股票分红相关讨论
+- **投资**：投资策略讨论
+- **智谱**：可能指AI相关业务
+- **AI**：人工智能话题
+
+#### 情绪分析
+- **平均情绪得分**：0.77
+- **正面帖子**：72条
+- **负面帖子**：39条
+- **中性帖子**：89条
+
+**情绪倾向**：积极！
+
+---
+
+### 4. 游族网络 (002174)
+
+#### 词云分析
+![游族网络词云](output/wordcloud_游族网络.png)
+
+#### 关键词分析
+- **三体**：《三体》IP相关讨论
+- **死刑**、**执行**：与投毒案相关讨论
+- **CEO**、**林奇**：公司高管相关
+- **投毒**：历史事件回顾
+
+#### 情绪分析
+- **平均情绪得分**：0.68
+- **正面帖子**：73条
+- **负面帖子**：28条
+- **中性帖子**：99条
+
+**情绪倾向**：积极！虽然有历史负面事件，但当前情绪较好。
+
+---
+
+### 5. 世纪华通 (002602)
+
+#### 词云分析
+![世纪华通词云](output/wordcloud_世纪华通.png)
+
+#### 关键词分析
+- **调整**：股价调整
+- **拉升**：股价拉升
+- **索赔**：可能指投资者索赔
+- **看好**：市场观点
+
+#### 情绪分析
+- **平均情绪得分**：0.48
+- **正面帖子**：63条
+- **负面帖子**：36条
+- **中性帖子**：101条
+
+**情绪倾向**：中性偏积极！
+
+---
+
+### 6. 昆仑万维 (300418)
+
+#### 词云分析
+![昆仑万维词云](output/wordcloud_昆仑万维.png)
+
+#### 关键词分析
+- **解禁**：股票解禁相关
+- **员工**：员工持股等
+- **短剧**：短剧业务
+- **模型**：AI模型相关
+
+#### 情绪分析
+- **平均情绪得分**：0.30
+- **正面帖子**：61条
+- **负面帖子**：49条
+- **中性帖子**：90条
+
+**情绪倾向**：中性偏积极！
+
+---
+
+### 7. 掌趣科技 (300315)
+
+#### 词云分析
+![掌趣科技词云](output/wordcloud_掌趣科技.png)
+
+#### 关键词分析
+- **创业板**：创业板相关
+- **退市**：退市风险讨论
+- **垃圾**：负面评价
+- **解套**：投资者解套需求
+
+#### 情绪分析
+- **平均情绪得分**：0.05
+- **正面帖子**：44条
+- **负面帖子**：47条
+- **中性帖子**：109条
+
+**情绪倾向**：中性！正负情绪基本持平。
+
+---
+
+### 8. 吉比特 (603444)
+
+#### 词云分析
+![吉比特词云](output/wordcloud_吉比特.png)
+
+#### 关键词分析
+- **分红**：分红讨论
+- **业绩**：业绩讨论
+- **价值投资**：投资理念
+- **恶心**：负面情绪表达
+
+#### 情绪分析
+- **平均情绪得分**：0.05
+- **正面帖子**：50条
+- **负面帖子**：65条
+- **中性帖子**：85条
+
+**情绪倾向**：中性偏消极！负面帖子多于正面帖子。
+
+---
+
+## 四、情绪分析汇总
+
+### 情绪得分对比
+![情绪得分对比](sentiment_output/sentiment_score_comparison.png)
+
+### 情绪分布
+![情绪分布](sentiment_output/sentiment_distribution.png)
+
+### 情绪类型分布
+![情绪类型分布](sentiment_output/emotion_types.png)
+
+### 各股票情绪得分排名
+
+| 排名 | 股票名称 | 股票代码 | 平均情绪得分 | 情绪倾向 |
+|------|----------|----------|--------------|----------|
+| 1 | 巨人网络 | 002558 | 1.11 | 🔵 非常积极 |
+| 2 | 完美世界 | 002624 | 0.99 | 🔵 非常积极 |
+| 3 | 三七互娱 | 002555 | 0.77 | 🟢 积极 |
+| 4 | 游族网络 | 002174 | 0.68 | 🟢 积极 |
+| 5 | 世纪华通 | 002602 | 0.48 | 🟡 中性偏积极 |
+| 6 | 昆仑万维 | 300418 | 0.30 | 🟡 中性偏积极 |
+| 7 | 掌趣科技 | 300315 | 0.05 | 🟡 中性 |
+| 8 | 吉比特 | 603444 | 0.05 | 🟡 中性偏消极 |
+
+---
+
+## 五、结论与建议
+
+### 主要发现
+
+1. **情绪分布**：
+   - 整体来看，游戏股股吧情绪以中性和积极为主
+   - 巨人网络和完美世界情绪最积极
+   - 吉比特和掌趣科技情绪相对较低
+
+2. **话题特点**：
+   - 各股票的讨论主要围绕自身业务和股价
+   - 完美世界和巨人网络讨论中游戏内容较多
+   - 游族网络仍有较多历史事件相关讨论
+
+3. **热门话题**：
+   - 股价操作：涨停、下跌、出货、拉升
+   - 投资者行为：补仓、解套、分红
+   - 行业热点：AI、短剧、游戏流水
+
+### 投资建议（仅供参考）
+
+1. **情绪领先标的**：
+   - 完美世界和巨人网络股吧情绪最为积极，可重点关注
+   - 关注其游戏业务进展和业绩情况
+
+2. **风险提示**：
+   - 吉比特和掌趣科技情绪相对较低，需注意风险
+   - 游族网络历史事件仍有一定影响
+
+3. **持续关注**：
+   - 昆仑万维的AI和短剧业务
+   - 三七互娱的分红和投资策略
+
+---
+
+## 附录
+
+### 数据文件说明
+
+- `data/`：原始爬取数据（JSON和Excel格式）
+- `output/`：TF-IDF分析结果和词云图片
+- `sentiment_output/`：情感分析结果和可视化图片
+
+### 分析工具
+
+- **爬虫**：Python + Requests
+- **分词**：jieba
+- **情感词典**：大连理工大学中文情感词汇本体
+- **可视化**：Matplotlib + WordCloud
+
+---
+
+**报告生成时间**：2026-05-28  
+**分析工具**：自定义Python脚本