|
|
|
|
|
"""
|
|
|
|
|
|
统计AI相关的弹幕数据，并将前8项结果保存到Excel文件中
|
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
|
|
import pandas as pd
|
|
|
|
|
|
from concurrent.futures import ThreadPoolExecutor
|
|
|
|
|
|
|
|
|
|
|
|
def load_danmu(file_path):
|
|
|
|
|
|
"""从文件中读取弹幕数据"""
|
|
|
|
|
|
with open(file_path, 'r', encoding='utf-8') as f:
|
|
|
|
|
|
return f.readlines()
|
|
|
|
|
|
|
|
|
|
|
|
def filter_and_count_danmu(danmu_list):
|
|
|
|
|
|
"""统计AI相关的弹幕频率"""
|
|
|
|
|
|
all_danmus = {}
|
|
|
|
|
|
ai_keywords = ['ai', '智能', '技术', '应用', '人机', 'AI', '人工智能', '机器学习', '深度学习', '神经网络']
|
|
|
|
|
|
with ThreadPoolExecutor() as executor:
|
|
|
|
|
|
for danmu in executor.map(str.strip, danmu_list):
|
|
|
|
|
|
if any(keyword in danmu for keyword in ai_keywords):
|
|
|
|
|
|
all_danmus[danmu] = all_danmus.get(danmu, 0) + 1
|
|
|
|
|
|
return all_danmus
|
|
|
|
|
|
|
|
|
|
|
|
def save_to_excel(all_danmus, excel_file):
|
|
|
|
|
|
"""将统计的AI相关弹幕保存到Excel文件中"""
|
|
|
|
|
|
sorted_danmus = sorted(all_danmus.items(), key=lambda x: x[1], reverse=True)[:8]
|
|
|
|
|
|
df = pd.DataFrame(sorted_danmus, columns=['danmu', 'count'])
|
|
|
|
|
|
df.to_excel(excel_file, index=False)
|
|
|
|
|
|
|
|
|
|
|
|
def main():
|
|
|
|
|
|
"""读取弹幕数据、统计AI相关弹幕并保存到Excel"""
|
|
|
|
|
|
danmu_file_path = '/output/danmu.txt'
|
|
|
|
|
|
excel_file = '/output/Top8_Danmu.xlsx'
|
|
|
|
|
|
|
|
|
|
|
|
danmu_list = load_danmu(danmu_file_path)
|
|
|
|
|
|
all_danmus = filter_and_count_danmu(danmu_list)
|
|
|
|
|
|
save_to_excel(all_danmus, excel_file)
|
|
|
|
|
|
|
|
|
|
|
|
print("与AI相关的弹幕数据统计完成，并已保存到Excel表格")
|
|
|
|
|
|
|
|
|
|
|
|
if __name__ == '__main__':
|
|
|
|
|
|
main()
|
