一、常用Xpath
1.获取标签中的文本
a/text() # 获取a标签中的文本
a//text() # 获取a标签下所有标签中的文本
2.获取标签的某个属性值
a/@属性名xxx # 获取a标签中属性xxx的值
3.当前位置开始
//a # 选择页面上所有的a标签
二、lxml中基本知识
1.修正html数据----返回element对象
from lxml import etree
html = etree.HTML(修正文本)
from lxml import etree
test = ''' <div> <ul>
<li class="item-1"><a>first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</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>
</ul> </div> '''
html = etree.HTML(test) # 返回一个element对象
# 打印数据
print(type(html))
print(html)
运行结果
<class 'lxml.etree._Element'>
<Element html at 0x226fad44448>
2.获取修正后的html数据 —返回bytes字节类型数据
html_bytes = etree.tostring(html)
转换为str类型
html_str =html_bytes.decode()
html_by = etree.tostring(html) # 返回字节bytes类型的数据
print(html_by)
html_str = html_by.decode() # 将bytes类型的数据转换为str型
print('html_str:',html_str)
运行结果
html_by: b'<html><body><div> <ul> \n <li class="item-1"><a>first item</a></li> \n <li class="item-1"><a href="link2.html">second item</a></li> \n <li class="item-inactive"><a href="link3.html">third item</a></li> \n <li class="item-1"><a href="link4.html">fourth item</a></li> \n <li class="item-0"><a href="link5.html">fifth item</a> \n </li></ul> </div> </body></html>'
html_str: <html><body><div> <ul>
<li class="item-1"><a>first item</a></li>
<li class="item-1"><a href="link2.html">second item</a></li>
<li class="item-inactive"><a href="link3.html">third item</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> </body></html>
3.使用Xpath匹配对修正后的element匹配—返回列表或element对象
html _data = html.xpath(xpath语句)
# 通过Xpath获取html(element对象)中a标签中的href属性值
href_list = html.xpath("//li[@class='item-1']/a/@href") # 返回列表类型,如果没有匹配到就返回空列表
print(href_list)
#通过Xpath获取html(element对象)中a标签中的文本
text_list= html.xpath("//li[@class='item-1']/a/text()")
print(text_list)
# 选择class属性值为item-1的li标签
li_list = html.xpath("//li[@class='item-1']")
print(li_ist)
运行结果
['link2.html', 'link4.html']
['first item', 'second item', 'fourth item']
[<Element li at 0x226fad62f48>, <Element li at 0x226fad62f88>, <Element li at 0x226faca8308>]
4.分组
for li in li_list:
item= {}
item["title"] = i.xpath("a/text()")[0] if len(i.xpath("./a/text()"))>0 else None
item["href"] = i.xpath("./a/@href")[0] if len( i.xpath("./a/@href"))>0 else None
print(item)
运行结果
{'title': 'first item', 'href': None}
{'title': 'second item', 'href': 'link2.html'}
{'title': 'fourth item', 'href': 'link4.html'}