1 for student in root.findall('student'):
2 no = student.get('no')
3 name = student.find('name').text
4 print(no, name)
输出为:
2009081097 Hongten
2009081098 DuDu
2009081099 Sum
当然,我们也可以修改XML文件的内容:
1 for age in root.iter('age'):
2 new_age = int(age.text) + 1
3 age.text = str(new_age)
4 age.set('updated', 'yes')
5 tree.write('c:\\test\\hongten_update.xml')
修改后的XML文件内容如下:
1
2
3 Hongten
4 M
5 21
6 97
7 90
8
9
10 DuDu
11 W
12 22
13 87
14 96
15
16
17 Sum
18 M
19 20
20 64
21 98
22
23 ================================================================== 以下是我对xml.etree.ElementTree模块进行了一些封装 ==================================================================
1 # -*- coding: utf-8 -*-
2 #python xml.etree.ElementTree
3
4 #Author : Hongten
5 #Mailto : hongtenzone@foxmail.com
6 #Blog : http://www.iyunv.com/hongten
7 #QQ : 648719819
8 #Version : 1.0
9 #Create : 2013-09-03
10
11 import os
12 import xml.etree.ElementTree as ET
13
14 '''
15 在python中,解析XML文件有很多中方法
16 本文中要使用的方法是:xml.etree.ElementTree
17 '''
18 #global var
19 #show log
20 SHOW_LOG = True
21 #XML file
22 XML_PATH = None
23
24 def get_root(path):
25 '''parse the XML file,and get the tree of the XML file
26 finally,return the root element of the tree.
27 if the XML file dose not exist,then print the information'''
28 if os.path.exists(path):
29 if SHOW_LOG:
30 print('start to parse the file : [{}]'.format(path))
31 tree = ET.parse(path)
32 return tree.getroot()
33 else:
34 print('the path [{}] dose not exist!'.format(path))
35
36 def get_element_tag(element):
37 '''return the element tag if the element is not None.'''
38 if element is not None:
39 if SHOW_LOG:
40 print('begin to handle the element : [{}]'.format(element))
41 return element.tag
42 else:
43 print('the element is None!')
44
45 def get_element_attrib(element):
46 '''return the element attrib if the element is not None.'''
47 if element is not None:
48 if SHOW_LOG:
49 print('begin to handle the element : [{}]'.format(element))
50 return element.attrib
51 else:
52 print('the element is None!')
53
54 def get_element_text(element):
55 '''return the text of the element.'''
56 if element is not None:
57 return element.text
58 else:
59 print('the element is None!')
60
61 def get_element_children(element):
62 '''return the element children if the element is not None.'''
63 if element is not None:
64 if SHOW_LOG:
65 print('begin to handle the element : [{}]'.format(element))
66 return [c for c in element]
67 else:
68 print('the element is None!')
69
70 def get_elements_tag(elements):
71 '''return the list of tags of element's tag'''
72 if elements is not None:
73 tags = []
74 for e in elements:
75 tags.append(e.tag)
76 return tags
77 else:
78 print('the elements is None!')
79
80 def get_elements_attrib(elements):
81 '''return the list of attribs of element's attrib'''
82 if elements is not None:
83 attribs = []
84 for a in elements:
85 attribs.append(a.attrib)
86 return attribs
87 else:
88 print('the elements is None!')
89
90 def get_elements_text(elements):
91 '''return the dict of element'''
92 if elements is not None:
93 text = []
94 for t in elements:
95 text.append(t.text)
96 return dict(zip(get_elements_tag(elements), text))
97 else:
98 print('the elements is None!')
99
100 def init():
101 global SHOW_LOG
102 SHOW_LOG = True
103 global XML_PATH
104 XML_PATH = 'c:\\test\\hongten.xml'
105
106 def main():
107 init()
108 #root
109 root = get_root(XML_PATH)
110 root_tag = get_element_tag(root)
111 print(root_tag)
112 root_attrib = get_element_attrib(root)
113 print(root_attrib)
114 #children
115 children = get_element_children(root)
116 print(children)
117 children_tags = get_elements_tag(children)
118 print(children_tags)
119 children_attribs = get_elements_attrib(children)
120 print(children_attribs)
121
122 print('#' * 50)
123 #获取二级元素的每一个子节点的名称和值
124 for c in children:
125 c_children = get_element_children(c)
126 dict_text = get_elements_text(c_children)
127 print(dict_text)
128
129 if __name__ == '__main__':
130 main()
运行效果:
Python 3.3.2 (v3.3.2:d047928ae3f6, May 16 2013, 00:03:43) [MSC v.1600 32 bit (Intel)] on win32
Type "copyright", "credits" or "license()" for more information.
>>> ================================ RESTART ================================
>>>
start to parse the file : [c:\test\hongten.xml]
begin to handle the element : []
students
begin to handle the element : []
{}
begin to handle the element : []
[, , ]
['student', 'student', 'student']
[{'no': '2009081097'}, {'no': '2009081098'}, {'no': '2009081099'}]
##################################################
begin to handle the element : []
{'score': '90', 'gender': 'M', 'name': 'Hongten', 'age': '20'}
begin to handle the element : []
{'score': '96', 'gender': 'W', 'name': 'DuDu', 'age': '21'}
begin to handle the element : []
{'score': '98', 'gender': 'M', 'name': 'Sum', 'age': '19'}
>>>