2025-09-10:仓库迁移

4.迭代器与生成器/13.创建处理数据的管道.py

@@ -0,0 +1,41 @@
+import os
+from fnmatch import fnmatchcase
+
+if __name__ == "__main__":
+    base_path = "D:\Code\Learn\practice"
+
+    # 想要建立一个处理管道，需要将几个生成器函数堆叠，比如，我现在要输出所有practice文件夹下的注释行内容
+    # 1.首先生成文件夹路径
+    def gen_dir_path(fpath):
+        for path, dir, files in os.walk(fpath):
+            for file in files:
+                if (not fnmatchcase(path, "*.[git][idea]*")) and (not fnmatchcase(file, "*.md")):
+                    yield os.path.join(path, file)
+
+    # 2.打开文件
+    def gen_file(paths):
+        for path in paths:
+            f = open(path, 'rt', encoding='utf-8')
+            yield f
+            f.close()
+
+    # 3.读取文件内容
+    def gen_file_txt(opened_files):
+        for file in opened_files:
+            yield from file
+            print("done")
+
+    # 4.匹配符合条件的文件行
+    def read_file_lines(file_lines):
+        for line in file_lines:
+            if "#" in line:
+                print(line)
+
+    # 将这些函数堆在一起就组成了一条管道，每次生成一个对象进行流水线处理，
+    # 这样避免了for循环的嵌套
+    paths = gen_dir_path(base_path)
+    files = gen_file(paths)
+    lines = gen_file_txt(files)
+    read_file_lines(lines)
+
+