From d1d6817279301df00acd12752dd941658d144116 Mon Sep 17 00:00:00 2001
From: p2fx74kt6 <2671606322@qq.com>
Date: Wed, 18 Sep 2024 20:55:11 +0800
Subject: [PATCH] =?UTF-8?q?=E7=AD=9B=E9=80=89AI=E7=9B=B8=E5=85=B3=E4=B9=8B?=
 =?UTF-8?q?=E5=BC=B9=E5=B9=95?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 Get_AI_Danmaku.py | 26 ++++++++++++++++++++++++++
 1 file changed, 26 insertions(+)
 create mode 100644 Get_AI_Danmaku.py

diff --git a/Get_AI_Danmaku.py b/Get_AI_Danmaku.py
new file mode 100644
index 0000000..14d2455
--- /dev/null
+++ b/Get_AI_Danmaku.py
@@ -0,0 +1,26 @@
+import re
+import pandas as pd
+from collections import Counter
+
+keywords = [
+        r"\bAI\b", "人工智能", r"\bai\b", "大模型", "ai视频", "AI视频", "AI配音", "ai配音", "AI作图", "ai图片", "自动生成", "生成", "ai生成", "AI生成", "大数据", "深度学习"
+    ]
+
+with open("danmu.txt", 'r', encoding='utf-8') as f:
+    danmu_list = f.readlines()
+
+#筛选符合关键词的弹幕
+pattern = re.compile(r'|'.join(keywords))
+filtered_danmu = [danmu for danmu in danmu_list if pattern.search(danmu)]
+
+#统计数量
+danmu_counter = Counter(filtered_danmu)
+
+# 获取数量排名前8的弹幕
+top_danmu = danmu_counter.most_common(8)
+
+# 将结果写入Excel文档
+df = pd.DataFrame(top_danmu, columns=['弹幕内容', '数量'])
+df.to_excel('top_AI_danmu.xlsx', index=False)
+
+print("处理完成，结果已写入文件。")
\ No newline at end of file