Update select_content.py

select_content.py

@@ -1,21 +1,21 @@
-import pandas as pd
+import pandas as pd
-from collections import Counter
+from collections import Counter
-
+
-# 读入所有弹幕
+# 读入所有弹幕
-with open('all_content.txt', mode='r', encoding='utf-8') as f:
+with open('all_content.txt', mode='r', encoding='utf-8') as f:
-    data_list = f.readlines()
+    data_list = f.readlines()
-# AI技术应用有关关键词
+# 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',
+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',]
+            '大模型','自然语言处理','云计算','神经网络', '自动驾驶','ai设计','ai图','ai软件',]
-# 筛选有关AI的弹幕
+# 筛选有关AI的弹幕
-selectdanmu = [danmu for danmu in data_list if any(keyword in danmu for keyword in keywords)]
+selectdanmu = [danmu for danmu in data_list if any(keyword in danmu for keyword in keywords)]
-
+
-# 统计弹幕数量
+# 统计弹幕数量
-num = Counter(selectdanmu)
+num = Counter(selectdanmu)
-top_common = num.most_common(8)
+top_common = num.most_common(8)
-# 展示数量前八条弹幕
+# 展示数量前八条弹幕
-print(top_common)
+print(top_common)
-t = pd.DataFrame(top_common, columns=['弹幕内容', '数量'])
+t = pd.DataFrame(top_common, columns=['弹幕内容', '数量'])
-# 导出excel文件
+# 导出excel文件
-excel_path = 'top8_ai_danmu.xlsx'  
+excel_path = 'top8_ai_danmu.xlsx'  
 t.to_excel(excel_path, index=False)