Python 解析xml
1、获取xml树
|
import xml.etree.ElementTree as ET
def getTree(xmlName):
xmlName = xmlName.strip()
try:
tree = ET.parse(xmlName)
except:
tree = None
print 'Analysis xml file fail,file name: {}'.format(xmlName)
return tree
|
2、获取根节点
|
def getRoot(tree):
if tree is not None:
root = tree.getroot()
else:
root = None
print 'Get root fail'
return root
|
3、查看根节点
|
def seeRoot(root):
'''<country name="tan">我是小明</country>'''
if root is not None:
print 'root tag:', root.tag # 标签（country）
print 'root attrib:', root.attrib # 屬性（name="tan"）
print 'root text:', root.text # 文本（我是小明）
print 'root tail:', root.tail # 尾字符串（未涉及）
|
4、从根开始遍历树
|
def traverseRoot(root):
if root is not None:
for label1 in root:
print 'label1 tag:', label1.tag
print 'label1 attrib:', label1.attrib
print 'label1 text:', label1.text
print 'label1 tail:', label1.tail
print '=================='
for label2 in label1:
print 'label2 tag:', label2.tag
print 'label2 attrib:', label2.attrib
print 'label2 text:', label2.text
print 'label2 tail:', label2.tail
print '=================='
for label3 in label2:
print 'label3 tag:', label3.tag
print 'label3 attrib:', label3.attrib
print 'label3 text:', label3.text
print 'label3 tail:', label3.tail
print '=================='
|
5、找到2012年的gdppc和neighbor下的b标签（找到同层有条件的同层另一个tag的文本）
|
def findYouNedd(root):
'''查找year为2012下的b标签的文本'''
if root is not None:
for label1 in root:
for label2 in label1:
if label1.tag == 'country' and label2.text == '2012': # 找到本层标签为country且下一层有2012文本
print 'Find tag为country and next year=2012'
for child in label1:
if child.tag == 'gdppc':
print child.text
for youNeed in child:
if youNeed.tag == 'b':
print 'You need:', youNeed.text
|
6、查找父节点下的子节点
|
def findChildNode(fatherNode, childNode):
childNode = childNode.strip()
if fatherNode is not None:
childs = fatherNode.findall(childNode)
print childs
print len(childs)
|
7、另一种办法实现第4点
|
def findYouNedd2(root):
countryNodes = root.findall('country')
if root is not None:
for countryNode in countryNodes:
if countryNode.find('year').text == '2012':
print countryNode.find('gdppc').text
|
8、移除节点
|
def delNode(tree, nodeName):
nodeName = nodeName.strip()
if tree is not None:
root = tree.getroot()
findNode = root.find(nodeName)
if findNode is not None and findNode.tag == nodeName:
root.remove(findNode)
tree.write('removeNode.xml') # 移除节点后新的xml
|
9、xml样例（xmlDemo.xml）
|
<?xml version="1.0"?>
<data>
<country name="Liechtenstein">
<rank>1</rank>
<year>2008</year>
<gdppc>141100</gdppc>
<neighbor name="Austria" direction="E"/>
<neighbor name="Switzerland" direction="W"/>
</country>
<country name="Singapore">
<rank>4</rank>
<year>2011</year>
<gdppc>59900</gdppc>
<neighbor name="Malaysia" direction="N">123
<a name="a"> aaa </a>
</neighbor>
</country>
<country name="Singapore">
<rank>68</rank>
<year>2012</year>
<gdppc>13600</gdppc>
<neighbor name="Costa Rica" direction="W"/>
<neighbor name="Colombia" direction="E">456
<b name="b"> bbb </b>
</neighbor>
</country>
<city>789</city>
</data>
|
