1 from lxml import etree
2 text = "<div><p>nmsl</p><span>nmsl</span></div>"
3 def htmlstree(text):
4 html = etree.HTML(text)
5 result = etree.tostring(html)
6 print(result)
7 return result.decode(‘utf-8‘)
8 #解析html字符串并且会为标签自动加上<html><body></body></html>
9 def parseetree():
10 parser = etree.HTMLParser(encoding=‘utf-8‘)
11 html = etree.parse("index111.html",parser=parser)
12 result = etree.tostring(html,encoding=‘utf-8‘).decode("utf-8")
13 print(result)
14 #解析xml 由于某写html标签会不全用普通的xml解析器会出错 如<br/> 所以要指定html解析器
15 if __name__ == ‘__main__‘:
16 parseetree()
以上为etree的使用范例
分别解析了html字符串和html文件
from lxml import etree
def parseetree():
parser = etree.HTMLParser(encoding=‘utf-8‘)
html = etree.parse("index111.html",parser=parser)
trs = html.xpath("//a[@onclick][@id]")
for tr in trs:
result = etree.tostring(tr,encoding=‘utf-8‘).decode("utf-8")
print(result)
def parseetree1():
parser = etree.HTMLParser(encoding=‘utf-8‘)
html = etree.parse("index111.html",parser=parser)
tr = html.xpath("//a[@onclick][@id]")[3]
result = etree.tostring(tr,encoding=‘utf-8‘).decode("utf-8")
print(result)
if __name__ == "__main__":
parseetree()
print("***************")
parseetree1()
以上为运用xpath来对html进行解析
以下是运行结果
附：https://www.w3school.com.cn/xpath/xpath_syntax.asp xpath语法
原文地址：https://www.cnblogs.com/jswf/p/12287819.html
时间： 2024-08-29 18:56:05