lxml与xpath使用demo

点击进入文章
点击进入文章

from lxml import etree
if __name__ == '__main__':
    text = '''
    <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">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>
    '''

    # 将文本转成html对象
    html = etree.HTML(text)
    # 将对象转成html文本
    result = etree.tostring(html)
    # 打印输出
    print(result.decode('utf-8'))

• xpath

from lxml import etree


if __name__ == '__main__':

    html = etree.parse('text.html')
    result = html.xpath('//li[@class="item-1"]')
    for item in result:
        print(etree.tostring(item).decode('utf-8'))

• 选取若干路径
  通过在路径表达式中使用“|”运算符，您可以选取若干个路径。
• demo

r = requests.get(url, headers=headers)
# print(r.text)
html = etree.HTML(r.text)
r_1 = html.xpath("//div[@class='main-content clearfix']/div[@class='product-list']")[0]
 # 兼容 首页推荐
r_2 = r_1.xpath("//div[@class='product-recommend']/div | // div[@class='product-item clearfix']")

• xpath的 contains 使用

# 注册时间    （..为上一级节点，在本例中em的上一级节点）
reg_time = response.xpath('//em[contains(text(), "注册时间")]/../text()').extract_first()

• xpath提取当前节点的所有父节点

# ancestor::*[@id="flightCardContent"]
//*[@id="flightCardsContainer"]/div//span[contains(text(), 'aaa')]/ancestor::*[@id="flightCardContent"]