From d94d4794da18a929dbfaacbf03f694c160464bb8 Mon Sep 17 00:00:00 2001
From: piw4f8lbj <1836196924@qq.com>
Date: Wed, 18 Sep 2024 23:01:10 +0800
Subject: [PATCH] ADD file via upload

---
 count.py | 36 ++++++++++++++++++++++++++++++++++++
 1 file changed, 36 insertions(+)
 create mode 100644 count.py

diff --git a/count.py b/count.py
new file mode 100644
index 0000000..899f22b
--- /dev/null
+++ b/count.py
@@ -0,0 +1,36 @@
+import os
+import re
+from collections import Counter
+import pandas as pd
+
+
+#提取txt文件里面的弹幕，并存于列表中
+def read_danmu_files(directory):
+    danmu_data = []
+    for filename in os.listdir(directory):
+        if filename.endswith('paris_olympics_danmak.txt'):
+            with open(os.path.join(directory, filename), 'r', encoding='utf-8') as file:
+                danmu_data.extend(file.readlines())
+    return danmu_data
+
+def count_danmu():
+    danmu_data = read_danmu_files('./')  # 当前目录下
+    #用正则表达式提取含有ai的弹幕
+    ai_danmaku = [danmaku for danmaku in danmu_data if
+                  re.search(r'(?<![a-zA-Z])((?:AI|人工智能))(?![a-zA-Z])', danmaku)]
+    unique_ai_danmaku = list(set(ai_danmaku))
+    #获取与ai弹幕相关的数量
+    danmaku_counts = [(danmaku, ai_danmaku.count(danmaku)) for danmaku in unique_ai_danmaku]
+    #对与ai相关弹幕按照数量数量进行排序
+    sorted_danmaku_counts = sorted(danmaku_counts, key=lambda x: x[1], reverse=True)
+    #得出排名前八的弹幕
+    top_8_danmaku = sorted_danmaku_counts[:8]
+    #将数据导入excel表
+    data = {'弹幕内容': [danmaku[0] for danmaku in top_8_danmaku]}
+    df = pd.DataFrame(data)
+    df.to_excel('2025巴黎奥运AI弹幕统计.xlsx', index=False)
+
+
+
+
+