From 872a9d2fde117898c390195bdcdc80846f945471 Mon Sep 17 00:00:00 2001
From: ptkbf2lr5 <18759452262@163.com>
Date: Wed, 18 Sep 2024 16:08:39 +0800
Subject: [PATCH] =?UTF-8?q?=E5=AF=B9=E4=BA=BA=E4=BB=AC=E5=AF=B9=E7=90=83?=
 =?UTF-8?q?=E7=B1=BB=E9=A1=B9=E7=9B=AE=E7=9A=84=E5=96=9C=E5=A5=BD=E7=A8=8B?=
 =?UTF-8?q?=E5=BA=A6=E5=88=86=E6=9E=90?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 ballgame.py | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)
 create mode 100644 ballgame.py

diff --git a/ballgame.py b/ballgame.py
new file mode 100644
index 0000000..5aa5b9c
--- /dev/null
+++ b/ballgame.py
@@ -0,0 +1,20 @@
+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()
+# 六项球类关键词
+keywords = ['乒乓球','羽毛球','排球','篮球','足球','网球']
+# 筛选有关球类的弹幕
+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(20)
+# 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 = 'top_ball_danmu.xlsx'  
+t.to_excel(excel_path, index=False)
\ No newline at end of file