From 7baa620aefb39d8c2a5b14ffb1fdd1e57bed311b Mon Sep 17 00:00:00 2001
From: phmycqkit <656078035@qq.com>
Date: Wed, 18 Sep 2024 19:51:47 +0800
Subject: [PATCH] =?UTF-8?q?=E7=BB=9F=E8=AE=A1AI=E6=8A=80=E6=9C=AF=E5=BA=94?=
 =?UTF-8?q?=E7=94=A8=E6=96=B9=E9=9D=A2=E7=9A=84=E6=AF=8F=E7=A7=8D=E5=BC=B9?=
 =?UTF-8?q?=E5=B9=95=E6=95=B0=E9=87=8F=EF=BC=8C=E5=B9=B6=E8=BE=93=E5=87=BA?=
 =?UTF-8?q?=E6=95=B0=E9=87=8F=E6=8E=92=E5=90=8D=E5=89=8D8=E7=9A=84?=
 =?UTF-8?q?=E5=BC=B9=E5=B9=95?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 GetAI.py | 28 ++++++++++++++++++++++++++++
 1 file changed, 28 insertions(+)
 create mode 100644 GetAI.py

diff --git a/GetAI.py b/GetAI.py
new file mode 100644
index 0000000..e94dcd4
--- /dev/null
+++ b/GetAI.py
@@ -0,0 +1,28 @@
+import pandas as pd
+from collections import Counter
+
+def GetAI():
+    # 读取弹幕文件
+    with open('danmu.csv', 'r', encoding='utf-8-sig') as f:
+        danmus = f.readlines()
+        
+    # 筛选与AI技术应用相关的弹幕
+    keywords = ['ai','Ai','AI']
+    ai_danmu = [danmu for danmu in danmus if any(keyword in danmu for keyword in keywords)]
+
+    # 统计弹幕数量
+    ai_danmu_counter = Counter(ai_danmu)
+    ai_danmu_most_common = ai_danmu_counter.most_common(8)
+    ai_danmu_all = ai_danmu_counter.most_common(100)
+
+    # 保存为Excel文件
+    df = pd.DataFrame(ai_danmu_most_common, columns=['弹幕', '数量'])
+    filename = 'ai_danmu_most_common.xlsx'  
+    df.to_excel(filename, index=False)
+    
+    df = pd.DataFrame(ai_danmu_all, columns=['弹幕', '数量'])
+    filename = 'ai_danmu.xlsx'  
+    df.to_excel(filename, index=False)
+    
+if __name__  == '__main__':
+    GetAI()
\ No newline at end of file