xml处理
xml的格式如下,就是通过<>节点来区别数据结构的:
<?xml version="1.0"?> <data> <country name="Liechtenstein"> <rank updated="yes">2</rank> <year>2008</year> <gdppc>141100</gdppc> <neighbor name="Austria" direction="E"/> <neighbor name="Switzerland" direction="W"/> </country> <country name="Singapore"> <rank updated="yes">5</rank> <year>2011</year> <gdppc>59900</gdppc> <neighbor name="Malaysia" direction="N"/> </country> <country name="Panama"> <rank updated="yes">69</rank> <year>2011</year> <gdppc>13600</gdppc> <neighbor name="Costa Rica" direction="W"/> <neighbor name="Colombia" direction="E"/> </country> </data>
xml协议在各个语言里的都 是支持的,在python中可以用以下模块操作xml
import xml.etree.ElementTree as ET tree = ET.parse("xmltest.xml") root = tree.getroot() print(root.tag) #遍历xml文档 for child in root: print(child.tag, child.attrib) for i in child: print(i.tag,i.text) #只遍历year 节点 for node in root.iter('year'): print(node.tag,node.text)
修改和删除xml文档内容
1 import xml.etree.ElementTree as ET 2 3 tree = ET.parse("xmltest.xml") 4 root = tree.getroot() 5 6 #修改 7 for node in root.iter('year'): 8 new_year = int(node.text) + 1 9 node.text = str(new_year) 10 node.set("updated","yes") 11 12 tree.write("xmltest.xml") 13 14 15 #删除node 16 for country in root.findall('country'): 17 rank = int(country.find('rank').text) 18 if rank > 50: 19 root.remove(country) 20 21 tree.write('output.xml')
自己创建xml文档
import xml.etree.ElementTree as ET new_xml = ET.Element("namelist") personinfo = ET.SubElement(new_xml,"personinfo",attrib={"enrolled":"yes"}) name = ET.SubElement(personinfo,"name") name.text = ''Mr Sun'' age = ET.SubElement(personinfo,"age",attrib={"checked":"no"}) sex = ET.SubElement(personinfo,"sex") age.text = '33' personinfo2 = ET.SubElement(new_xml,"personinfo",attrib={"enrolled":"no"}) name = ET.SubElement(personinfo2,"name") name.text = ''Mis Chen'' age = ET.SubElement(personinfo2,"age") age.text = '19' et = ET.ElementTree(new_xml) #生成文档对象 et.write("test.xml", encoding="utf-8",xml_declaration=True) ET.dump(new_xml) #打印生成的格式