from collections import Counter

# 读取TXT文件并统计AI相关关键词
def count_ai_keywords(file_path):
    # 定义与AI技术相关的关键词列表
    ai_keywords = [
        "AI", "人工智能", "Machine learning", "机器学习", "Deep learning", "深度学习", 
        "Neural network", "神经网络", "自然语言处理", "Natural language processing", 
        "计算机视觉", "Computer vision", "Robotics", "机器人", "自动化", "Automation",
        "人脸识别", "Face recognition", "大数据", "数据挖掘", "智能系统", "自动驾驶", "无人驾驶","AI技术"
    ]

    # 用来存储统计结果的Counter
    keyword_count = Counter()

    # 读取文件
    with open(file_path, 'r', encoding='utf-8') as file:
        for line in file:
            # 遍历每个关键词，统计弹幕中包含关键词的数量
            for keyword in ai_keywords:
                if keyword.lower() in line.lower():  # 统计关键词忽略大小写
                    keyword_count[keyword] += 1
    
    # 输出排名前8的关键词及其对应的数量
    top_keywords = keyword_count.most_common(8)
    
    print("AI 技术相关的前8条弹幕关键词统计：")
    for keyword, count in top_keywords:
        print(f"{keyword}: {count} 条弹幕")

# 文件路径
file_path = "danmakus_2024_olympics.txt"

# 调用函数并统计
count_ai_keywords(file_path)