工作中遇到解析jenkins的配置文件,通过python-jenkins取到的是 xml 对象,正好 复习了一下 xml的解析。如下(参考官方文档):
官方链接:
https://docs.python.org/2.7/library/xml.etree.elementtree.html
xmltest.xml 内容如下
<?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文件处理
# -*- coding: utf-8 -*- # author: hiro import xml.etree.ElementTree as ET tree = ET.parse("xmltest.xml") root = tree.getroot() print(root) 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 for node in root.iter('year'): new_year = int(node.text) + 1 node.text = str(new_year) node.set("updated", "yes") tree.write("xmltest01.xml") #删除node for country in root.findall('country'): rank = int(country.find('rank').text) if rank > 50: root.remove(country) tree.write('output.xml')
xml文件生成
# -*- coding: utf-8 -*- # author: hiro import xml.etree.ElementTree as ET new_xml = ET.Element("personinfolist") personinfo = ET.SubElement(new_xml, "personinfo", attrib={"enrolled": "yes"}) name = ET.SubElement(personinfo, "name") name.text = 'oldboy' 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"}) name2 = ET.SubElement(personinfo2, "name") name2.text = 'hiro' age2 = ET.SubElement(personinfo2, "age") age2.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