XML模块
http://baike.baidu.com/link?url=-mBgvMdEDU7F05Pw7h_hBt7A0ctYiPm5a_WvKVLknydnRXKRIyydcVZWRjd_5HE2fMW5Ic45Nb4DiuH1azLjjfs1HBMER-4j38pqFgmj4z4spRud6DrmYimbttjfSB105KHP2pDzaVKmfFvL1JrZ4cpmHqEiFiuSZ_LehN3Hp5GqLdEb6mohzYRyFIZadILH3iDqyvAjCbEXGr4qLMLZEq
可扩展标记语言,标准通用标记语言的子集,是一种用于标记电子文件使其具有结构性的标记语言。
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>
tree = ET.parse("xmltest.xml")#解析xml文件
root = tree.getroot()#获取根节点
node.tag
node.attrib
node.text
node.tag = "years" #修改tag的值
node.text = str(new_year) #赋予node元素新的值
node.set("updated","no") #设置node元素的属性值
root.remove(country)
在python中可以用以下模块操作xml(import xml.etree.ElementTree as ET
)
import xml.etree.ElementTree as ET tree = ET.parse("xmltest.xml")#解析xml文件 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.attrib,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
# import xml.etree.ElementTree as ET # # tree = ET.parse("xmltest.xml")#解析xml文件 # 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.attrib,i.text) # # # 只遍历year 节点 # for node in root.iter('year'): # print(node.tag, node.text) import xml.etree.ElementTree as ET tree = ET.parse("xmltest.xml") root = tree.getroot() # 修改 for node in root.iter("year"): new_year = int(node.text) + 1 node.text = str(new_year)#赋予node元素新的值 node.set("updated","no")#设置node元素的属性值 tree.write("xmltest.xml") #删除 for country in root.findall("country"): rank = int(country.find('rank').text) if rank > 50: root.remove(country) tree.write("output.xml")
自己创建XML文件
import xml.etree.ElementTree as ET new_xml = ET.Element("namelist") name = ET.SubElement(new_xml,"name",attrib={"enrolled":"yes"}) age = ET.SubElement(name,"age",attrib={"checked":"no"}) sex = ET.SubElement(name,"sex") name.text = '陈泰成' age.text = "22" sex.text = '男' name = ET.SubElement(new_xml,"name",attrib={"enrolled":"no"}) age = ET.SubElement(name,"age") name.text = "哈利路亚" age.set("is_privary","yes") age.text = "18" et = ET.ElementTree(new_xml) et.write("test.xml",encoding = "utf-8",xml_declaration = True) ET.dump(new_xml)