From 422e1fe9dbd1618a29ce41b602a444f7f33232bd Mon Sep 17 00:00:00 2001
From: ptkbf2lr5 <18759452262@163.com>
Date: Wed, 18 Sep 2024 15:53:44 +0800
Subject: [PATCH] =?UTF-8?q?=E7=AD=9B=E9=80=89AI=E6=9C=89=E5=85=B3=E5=BC=B9?=
 =?UTF-8?q?=E5=B9=95?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 select_content.py | 21 +++++++++++++++++++++
 1 file changed, 21 insertions(+)
 create mode 100644 select_content.py

diff --git a/select_content.py b/select_content.py
new file mode 100644
index 0000000..a83cb54
--- /dev/null
+++ b/select_content.py
@@ -0,0 +1,21 @@
+import pandas as pd
+from collections import Counter
+
+# 读入所有弹幕
+with open('all_content.txt', mode='r', encoding='utf-8') as f:
+    data_list = f.readlines()
+# AI技术应用有关关键词
+keywords = ['AI','人工智能','ai音效','ai视频','ai技术','机器学习', '深度学习', '自然语言处理','ai训练',
+            '大模型','自然语言处理','云计算','AI设计','AI图','神经网络', '自动驾驶','ai设计','ai图','AI软件',]
+# 筛选有关AI的弹幕
+selectdanmu = [danmu for danmu in data_list if any(keyword in danmu for keyword in keywords)]
+
+# 统计弹幕数量
+num = Counter(selectdanmu)
+top_common = num.most_common(8)
+# 展示数量前八条弹幕
+print(top_common)
+t = pd.DataFrame(top_common, columns=['弹幕内容', '数量'])
+# 导出excel文件
+excel_path = 'top8_ai_danmu.xlsx'  
+t.to_excel(excel_path, index=False)
\ No newline at end of file