python之lxml.etree模块

from lxml import etree      # 导入etree模块
root=etree.Element('root',interesting='totatlly')  #  创建一个节点对象，即标签对象，节点名为root，节点属性为interesting
root.set('set','30')        # 添加节点属性，属性名为set
root.text='data'            # 设置对象的text属性为data，即标签中的文本
x=etree.tostring(root)      # 将节点对象转化为bytes类型
one=etree.fromstring(x)     # 将字符串转化为节点对象
two=etree.XML(x)            #  xml类型
thr=etree.HTML(x)           # html类型
print(root)  
print(root.tag)             #  root节点对象的标签名
print(root.text)            #  root节点对象的文本
print(type(root))         
print(etree.tostring(one))  # 显示节点对象转化为bytes类型的数据
print(etree.tostring(two)) 
print(thr.text)                     
print(etree.tostring(thr))     

<div>
    <ul>
         <li class="item-0"><a href="link1.html">first item</a></li>
         <li class="item-1"><a href="link2.html">second item</a></li>
         <li class="item-inactive"><a href="link3.html">haha<span class="bold">third item</span></a></li>
         <li class="item-1"><a href="link4.html">fourth item</a></li>
         <li class="item-0"><a href="link5.html">fifth item</a></li>
     </ul>
 </div>

html=etree.parse('./hello.html')
result=etree.tostring(html,pretty_print=True)
res=html.xpath('//li/@class')
re1=html.xpath('//li[1]/@class')
re2=html.xpath('//li[last()]/@class')
re3=html.xpath('//li[last()-1]/@class')
re4=html.xpath('//li[last()-1]/a')
print(html)
print(result)
print(res)
print(re1)
print(re2[0])
print(type(re3[0]))
print(re4[0].text)

r=etree.XML(result)
print(r.find('ul'))
print(r.findall('.//li[@class]'))
for i in r.iterfind('.//li[@class]'):
    print(i.tag)

html=etree.parse('./hello.html')
result=etree.tostring(html)
xml=etree.XML(result)
r1=xml.findall('.//li')
r2=html.xpath('//li/@class')
r3=xml.find(".//li/a[@href='link1.html']")
print(r1)
print(r2)
print(r3)

xml_doc = r'''<?xml version="1.0" ?>

 <bookstore>

 <book category="COOKING">
   <title lang="en">Everyday Italian</title>
   <author>Giada De Laurentiis</author>
   <year>2005</year>
   <price>30.00</price>
 </book>

 <book category="CHILDREN">
   <title lang="en">Harry Potter</title>
   <author>J K. Rowling</author>
   <year>2005</year>
   <price>29.99</price>
 </book>

 <book category="WEB">
   <title lang="en">XQuery Kick Start</title>
   <author>James McGovern</author>
   <author>Per Bothner</author>
   <author>Kurt Cagle</author>
   <author>James Linn</author>
   <author>Vaidyanathan Nagarajan</author>
   <year>2003</year>
   <price>49.99</price>
 </book>

 <book category="WEB">
   <title lang="en">Learning XML</title>
   <author>Erik T. Ray</author>
   <year>2003</year>
   <price>39.95</price>
 </book>
 <book category="WEB">
   helloworld
   <title lang="en">Learning XML</title>
   <author>Erik T. Ray</author>
   <year>2003</year>
   <price>39.95
   <tt>
   haha
   </tt>
   </price>
 </book>

 </bookstore> '''

tree=etree.XML(xml_doc)
r1=tree.xpath('/bookstore/book[price>30]/title')
for i in r1:
    print(i.text)