解析库的使用——使用XPath

from lxml import etree

html = etree.parse('./test.html',etree.HTMLParser())
result = etree.tostring(html)#可自动补全标签
print(result.decode('utf-8'))

#获取所有节点
html = etree.parse('./test.html',etree.HTMLParser())
result = html.xpath('//*')
print(result)

#获取所有div节点

html = etree.parse('./test.html',etree.HTMLParser())
result = html.xpath('//div')
print(result)

#通过/或//即可查找元素的子节点或子孙节点
html = etree.parse('./test.html',etree.HTMLParser())
result = html.xpath('//div/script')#此处的/用于选取直接子节点，如果要获取所有子孙节点，就可以使用//
print(result)

#查找父节点用..来实现
html = etree.parse('./test.html',etree.HTMLParser())
#result = html.xpath('//a[@')
print(result)

#属性匹配
html = etree.parse('./test.html',etree.HTMLParser())
result = html.xpath('//li[@class="item-0"]')#选取class为item-1的li节点
print(result)

#文本获取，获取节点中的文本text()
html = etree.parse('./test.html',etree.HTMLParser())
result = html.xpath('//li[@class="item-0"]/text()')
print(result)

#节点属性，获取比如li节点下所有a节点的href属性
html = etree.parse('./test.html',etree.HTMLParser)
result = html.xpath('//li/a/@href')
print(result)

#属性多值匹配,比如class="li li-first"，上边的就无法实现
text = '''
<li class="li li-first" name="item"><a href="link.html">first item</a></li>
'''
html = etree.HTML(text)
result = html.xpath('//li[contains(@class,"li")]/a/text()')#第一个参数属性名称,第二个属性值
#多属性
result = html.xpath('//li[contains(@class,"li") and @name="item"]/a/text()')
print(result)