dom 模块读取XML文件
#-*- coding:utf-8 -*-import sys
reload(sys)
sys.setdefaultencoding('utf-8')
from xml.dom.minidom import parse
import xml.dom.minidom
# 使用minidom解析器打开 XML 文档
DOMTree = xml.dom.minidom.parse("user.xml")
collection = DOMTree.documentElement
if collection.hasAttribute("a"):
print "Root element : %s" % collection.getAttribute("a")
movies = collection.getElementsByTagName("user")
for movie in movies:
print "*****Movie*****"
if movie.hasAttribute("id"):
print "Title: %s" % movie.getAttribute("id")
type = movie.getElementsByTagName('username')
print "Type: %s" % type.childNodes.data
format = movie.getElementsByTagName('email')
print "Format: %s" % format.childNodes.data
rating = movie.getElementsByTagName('age')
print "Rating: %s" % rating.childNodes.data
description = movie.getElementsByTagName('sex')
print "Description: %s" % description.childNodes.data.encode('gbk')
xml:
<<xml version="1.0" encoding="gbk" <>
<users a="1">
<user id="1000001">
<username>Admin</username>
<email>admin@live.cn</email>
<age>23</age>
<sex>闂</sex>
</user>
<user id="1000002">
<username>Admin2</username>
<email>admin2@live.cn</email>
<age>22</age>
<sex>闂</sex>
</user>
<user id="1000003">
<username>Admin3</username>
<email>admin3@live.cn</email>
<age>27</age>
<sex>闂</sex>
</user>
<user id="1000004">
<username>Admin4</username>
<email>admin4@live.cn</email>
<age>25</age>
<sex>婵</sex>
</user>
<user id="1000005">
<username>Admin5</username>
<email>admin5@live.cn</email>
<age>20</age>
<sex>1/sex>
</user>
<user id="1000006">
<username>Admin6</username>
<email>admin6@live.cn</email>
<age>23</age>
<sex>1/sex>
</user>
</users>
运行报错:
Traceback (most recent call last):
File "G:\pydev\b.py", line 10, in <module>
DOMTree = xml.dom.minidom.parse("user.xml")
File "C:\Python27\lib\xml\dom\minidom.py", line 1918, in parse
return expatbuilder.parse(file)
File "C:\Python27\lib\xml\dom\expatbuilder.py", line 924, in parse
result = builder.parseFile(fp)
File "C:\Python27\lib\xml\dom\expatbuilder.py", line 207, in parseFile
parser.Parse(buffer, 0)
xml.parsers.expat.ExpatError: not well-formed (invalid token): line 1, column 2
本帖最后由 Linux_manne 于 2014-11-10 09:57 编辑
not well-formed
是不是xml格式有问题?貌似xml 要改成utf8的编码
页:
[1]