import collections
import openpyxl

# AI相关的关键词列表
ai_keywords = ['AI', '人工智能','机器学习', '深度学习', '自动化', '大数据','大模型','机器人','计算机','智能',]


# 读取弹幕文件并过滤与AI相关的弹幕
def filter_ai_comments(file_path, keywords):
    with open(file_path, 'r', encoding='utf-8') as file:
        comments = file.readlines()

    # 移除换行符并过滤含有AI相关关键词的弹幕
    filtered_comments = [comment.strip() for comment in comments if any(keyword in comment for keyword in keywords)]
    return filtered_comments


# 统计弹幕出现次数
def count_bullet_comments(comments):
    return collections.Counter(comments).most_common(8)  # 返回前8个出现最多的弹幕


# 保存结果到Excel
def save_to_excel(data, output_file):
    workbook = openpyxl.Workbook()
    sheet = workbook.active
    sheet.title = "AI Bullet Comment Ranking"

    # 写入标题行
    sheet.append(["Rank", "Comment", "Count"])

    # 写入数据
    for index, (comment, count) in enumerate(data, start=1):
        sheet.append([index, comment, count])

    # 保存Excel文件
    workbook.save(output_file)


# 主函数，执行统计和保存
file_path = '弹幕.txt'  # 替换为弹幕文件的路径
output_file = 'ai_bullet_comment_ranking.xlsx'  # 输出的Excel文件

# 筛选AI相关弹幕
ai_comments = filter_ai_comments(file_path, ai_keywords)

# 统计弹幕出现次数
ai_bullet_comments = count_bullet_comments(ai_comments)

# 保存统计结果到Excel
save_to_excel(ai_bullet_comments, output_file)

print(f"统计结果已保存到 {output_file}")