處理XML文檔

遍歷xml文檔

 1 #遍歷xml文檔的子標簽
 2 for child in root:
 3     print(child.tag,child.attrib)
 4              #子標簽名       屬性
 5     for i in child:
 6         print(i.tag,i.text)
 7              #子標簽名   屬性
 8              #字節數標簽不能遍歷出屬性，輸出為空
 9         #改進
10         print(i.tag,i.text,i.attrib)
11 
12 #
 
遍歷自己需要的 例如只遍歷‘year‘節點
13 for node in root.iter(‘year‘):
14     print(node.tag,node.text)

修改 

 1 import xml.etree.ElementTree as ET
 2 
 3 tree=ET.parse(‘xml_test.xml‘)  
 4 root=tree.getroot()
 5 
 6 for node in root.iter(‘year‘):
 7     new_year=int(node.text)+1
 8     node.text=str(new_year)
 9         #
 
賦值
10     node.set(‘updated‘,‘yes‘)
11           給year標簽增加屬性
12 
13 tree.write(‘xml_test.xml‘)

刪除node

1 tree=ET.parse(‘xml_test.xml‘)  
2 root=tree.getroot()
3 
4 for country in root.findall(‘country‘):  #遍歷country
5     rank = int(country.find(‘rank‘).text)  #找出rank
6     if rank > 50:
7         root.remove(country)
 
8 
9 tree.write(‘output.xml‘) #寫入文件為output.xml文件中

新建xml文件

 1 import xml.etree.ElementTree as ET
 2 
 3 new_xml = ET.Element("personinfolist")  #創建根節點
 4 personinfo = ET.SubElement(new_xml, "personinfo", attrib={"enrolled": "yes"})
 5                           #是new_xml的子節點
 6 name = ET.SubElement(personinfo, "name")
 7 name.text=‘Jeck‘
 8 age = ET.SubElement(personinfo, "age", attrib={"checked": "no"})
 9                    #是personnifo的子節點
10 sex = ET.SubElement(personinfo, "sex")
11 sex.text=‘Men‘
12 age.text = ‘33‘ #給age節點賦值
13 personinfo2 = ET.SubElement(new_xml, "personinfo", attrib={"enrolled": "no"})
14 name = ET.SubElement(personinfo2, "name")
15 name.text=‘Ailice‘
16 age = ET.SubElement(personinfo2, "age")
17 age.text = ‘19‘
18 
19 et = ET.ElementTree(new_xml)  # 生成文檔對象
20 et.write("test.xml", encoding="utf-8", xml_declaration=True)
21         #寫入到test.xml文件中              聲明是xml格式的
22 
23 ET.dump(new_xml)  # 打印生成的格式

學習筆記-模塊之xml文件處理