import requests

from lxml import etree   # 导入xpath

headers = {

    'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/89.0.4389.128 Safari/537.36'

}

tree = etree.parse('./相关/test.html')

#定位标签

# print(tree.xpath('//div')) #定位指定的所有标签

#属性定位

# print(tree.xpath('//div[@class="tang"]'))

#索引定位:索引是从1开始的

# print(tree.xpath('//div[1]'))

#层级定位:/表示一个层级,//表示多个层级

# print(tree.xpath('//div[@class="tang"]/ul/li[4]/a'))

# print(tree.xpath('//div[@class="tang"]//li[4]/a'))

#内容提取:/text(),//text()

# print(tree.xpath('//div[@class="tang"]/ul/li[4]/a/text()')[0])

#取属性值:/@atrrName

# print(tree.xpath('//div[@class="tang"]/ul/li[4]/a/@href')[0])