Xpath使用

# 安装支持解析html和XML的解析库
# pip install lxml
# form lxml import etree
import requests
from lxml import  etree
url = "http://news.baidu.com"
headers = {
    "User-Agent": "Opera/9.80 (Windows NT 6.0) Presto/2.12.388 Version/12.14"
}
data = requests.get(url, headers=headers).content.decode()
# 1.转换解析类型
xpath_data = etree.HTML(data)
# 2.调用xpath方法
# 语法 1.节点 /
# 跨节点：//
# 精准的标签://a[@属性="属性值"]
# 属性： @href
# xpath的下标从1开始
# 找到顺序就可以找到标签
# result = xpath_data.xpath('/html/head/title/text()')
result = xpath_data.xpath('//a/text()')
result = xpath_data.xpath('//a[@mon="r=1"]/text()')
result = xpath_data.xpath('//a/@href')
result = xpath_data.xpath("//li/a/text()")
print(result)
# print(data)

Xpath