import pandas as pd
from collections import Counter

# 读取TXT文件并统计AI相关关键词
def count_ai_keywords(file_path, output_excel):
    # 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"
    ]

    # 用来存储统计结果的Counter
    keyword_count = Counter()
    keyword_danmakus = {keyword: [] for keyword in ai_keywords}  # 存储含有每个关键词的弹幕

    # 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，并记录弹幕
            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
                    keyword_danmakus[keyword].append(line.strip())  # 将弹幕加入对应关键词列表

    # 获取排名前8的关键词
    top_keywords = [keyword for keyword, _ in 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 keyword_count.most_common(8):
        print(f"{keyword}: {count} 条弹幕")

    # 创建一个DataFrame，将前8名关键词的弹幕按列存储
    df_dict = {}
    for keyword in top_keywords:
        df_dict[keyword] = keyword_danmakus[keyword]

    # 将弹幕写入Excel，每个关键词作为一列
    df = pd.DataFrame(dict([(k, pd.Series(v)) for k, v in df_dict.items()]))
    df.to_excel(output_excel, index=False)

    print(f"弹幕已保存至 {output_excel}")

# 文件路径
file_path = "danmakus_2024_olympics.txt"
output_excel = "top_ai_danmakus.xlsx"

# 调用函数并统计并保存至Excel
count_ai_keywords(file_path, output_excel)