from lxml import etree
#/获取子节点
#//获取所有子孙节点
#.当前节点
#..当前节点的父节点
#@选取属性
#*所有节点
#text()节点文本
#last()最后
#position()=1第一个
#last()-1倒二
# parse()
# parser = etree.HTMLParser()
# html = etree.parse('ex1.html', parser=parser)
# html_text=etree.tostring(html,encoding='utf-8')
# print(html_text.decode('UTF-8'))
# HTML()
# html = etree.HTML(open('ex1.html', 'r').read()) #解析html字符串
# html_text = etree.tostring(html, encoding='utf-8') #转换字符串类型
# print(html_text.decode('utf-8'))
# html = etree.HTML(open('ex1.html', 'r').read())
# node = html.xpath('//t2')
# a_txt = etree.tostring(node[0], encoding='utf-8').decode('utf-8') #指定节点及下文所有节点
# print(node)
# print(a_txt)
# # print([i.tag for i in node]) #.tag获取节点名称
html=etree.HTML(open('ex1.html').read())
alla=html.xpath('//audio')
print(alla)
txt=etree.tostring(alla[0],encoding='utf-8').decode('utf-8')
print(txt)
xpath解析
最新推荐文章于 2024-09-29 14:13:49 发布