From c3a30ae0b33efd3cc0fdfc8881d73628558a9df9 Mon Sep 17 00:00:00 2001
From: 64457072af1fe407c29f45ae <64457072af1fe407c29f45ae@devide>
Date: Sun, 23 Apr 2023 17:56:51 +0000
Subject: [PATCH] Auto commit

---
 ...1\271\351\207\217\347\273\237\350\256\241" | 65 +++++++++++++++++++
 1 file changed, 65 insertions(+)
 create mode 100644 "\346\211\271\351\207\217\347\273\237\350\256\241"

diff --git "a/\346\211\271\351\207\217\347\273\237\350\256\241" "b/\346\211\271\351\207\217\347\273\237\350\256\241"
new file mode 100644
index 0000000..8727c3b
--- /dev/null
+++ "b/\346\211\271\351\207\217\347\273\237\350\256\241"
@@ -0,0 +1,65 @@
+import pandas as pd
+import os
+from threading import Thread
+
+# 遍历多个文件夹获取所有excel文件
+path1 = r''
+path2 = r''
+path3 = r''
+path4 = r''
+path5 = r''
+path6 = r''
+path7 = r''
+path8 = r''
+files1 = []
+files2 = []
+folder_paths1 = [path1, path2, path3, path4]
+folder_paths2 = [path5, path6, path7, path8]
+
+for folder_path in folder_paths1:
+    for root, dirs, filenames in os.walk(folder_path):
+        for filename in filenames:
+            if filename.endswith('.xlsx'):
+                files1.append(os.path.join(root, filename))
+                print('正在处理:', os.path.join(root, filename))
+
+for folder_path in folder_paths2:
+    for root, dirs, filenames in os.walk(folder_path):
+        for filename in filenames:
+            if filename.endswith('.xlsx'):
+                files2.append(os.path.join(root, filename))
+                print('正在处理:', os.path.join(root, filename))
+
+
+# 线程1执行
+def thread1():
+    results1 = []
+    for file in files1:
+        df = pd.read_excel(file)
+        print(file)
+        count = df.iloc[:, 0].value_counts().shape[0]
+        results1.append([file, count])
+    result1_df = pd.DataFrame(results1, columns=['文件名', '第一列数量'])
+    result1_df.to_excel(os.path.join('', '结果1.xlsx'), index=False)
+    print('线程1执行完成!')
+
+
+# 线程2执行
+def thread2():
+    results2 = []
+    for file in files2:
+        df = pd.read_excel(file)
+        print(file)
+        count = df.iloc[:, 0].value_counts().shape[0]
+        results2.append([file, count])
+    result2_df = pd.DataFrame(results2, columns=['文件名', '第一列数量'])
+    result2_df.to_excel(os.path.join('B:\keyanshuju', '结果2.xlsx'), index=False)
+    print('线程2执行完成!')
+
+
+# 执行线程
+t1 = Thread(target=thread1)
+t1.start()
+
+t2 = Thread(target=thread2)
+t2.start()
\ No newline at end of file
-- 
GitLab