You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
21 lines
899 B
21 lines
899 B
2 months ago
|
import pandas as pd
|
||
|
|
from collections import Counter
|
||
|
|
|
||
|
|
# 读取弹幕文件
|
||
|
|
with open('danmu.txt', 'r', encoding='utf-8') as f:
|
||
|
|
danmu_all = f.readlines()
|
||
|
|
|
||
|
|
# 筛选包含关键词的弹幕
|
||
|
|
keywords = ['人工智能','ai音效','ai视频','AI视频','AI音效','AI技术','ai技术','AI教练','AI训练','AI大模型','ai教练','ai训练','ai大模型',
|
||
|
|
'AI解说','AI裁判','ai解说','ai裁判','云计算','AI设计','AI图','ai设计','ai图','AI作画','AI助手','ai还能帮运动员训练']
|
||
|
|
ai_danmu = [danmu for danmu in danmu_all if any(keyword in danmu for keyword in keywords)]
|
||
|
|
|
||
|
|
# 统计弹幕数量
|
||
|
|
num = Counter(ai_danmu)
|
||
|
|
most_common = num.most_common(8)
|
||
|
|
|
||
|
|
df = pd.DataFrame(most_common, columns=['弹幕内容', '数量'])
|
||
|
|
|
||
|
|
# 保存为Excel文件
|
||
|
|
excel_path = 'top8_danmu.xlsx' # 定义Excel文件的保存路径
|
||
|
|
df.to_excel(excel_path, index=False)
|