from lxml import etree
 
html_str = """
this from blog.csdn.net/lncxydjq , DO NOT COPY!
  
*****
    
  

"""
 
html = etree.HTML(html_str)
 
print html.xpath('//div[@id="box1"]/div/node()')[1]
print type(html.xpath('//div[@id="box1"]/div/node()')[1])
print html.xpath('//div[@id="box1"]/div/node()')[1].text
 
"""output:


can u get me, bitch?
"""