2025-09-10:仓库迁移

6.数据编码与处理/4.以增量方式解析大型XML文件.py

@@ -0,0 +1,45 @@
+from xml.etree.ElementTree import iterparse
+from urllib.request import urlopen
+
+
+# 在尤其关注节省内存时，牺牲运行速度，使用增量生成的方式读取XML文档
+def parse_and_remove(filename, path):
+    # 将节点路径划分
+    path_parts = path.split('/')
+    # 通过迭代的方式解析XML文件
+    doc = iterparse(filename, events=('start', 'end'))
+    # 跳过根节点
+    next(doc)
+
+    # 设置存储栈
+    tag_stack = []
+    elem_stack = []
+
+    for event, elem in doc:
+        # iterparse会输出event和elem元组，表示状态和元素
+        if event == 'start':
+            # 如果检测状态是start就入栈
+            tag_stack.append(elem.tag)
+            elem_stack.append(elem)
+        elif event == 'end':
+            # 如果检测状态是end就出栈
+            # print(tag_stack, path_parts)
+
+            # 如果路径和需要寻找的标签相同，就生成并从栈中抹除
+            if tag_stack == path_parts:
+                yield elem
+                elem_stack[-2].remove(elem)
+            try:
+                tag_stack.pop()
+                elem_stack.pop()
+            except IndexError:
+                pass
+
+
+
+if __name__ == '__main__':
+    u = urlopen('http://planet.python.org/rss20.xml')
+    data = parse_and_remove(u, 'channel/item/title')
+    # print(data)
+    for d in data:
+        print(d.text)