爬虫-获取数据xpath

1. 安装lxml

   pip3 install lxml
   

2. 基本用法

   import reauests
   from lxml import etree
   url = 'xxx'
   res = reuests.get(url).text
   html = etree.HTML(res)
   # 获取所有div标签
   xpath = '//div'
   print(html.xpath(xpath))
   #获取id=xx的div标签下的class=yy的span标签
   xpath = '//div[@id="xx"]//span[@class="yy"]'
   print(html.xpath(xpath))
   #获取文本
   xpath = '//div[@id="xx"]//span[@class="yy"]//text()'
   print(html.xpath(xpath))
   #获取属性 href
   xpath = '//div[@id="xx"]//span[@class="yy"]//@href'
   print(html.xpath