Task4 学习xpath

题目：学习xpath，使用lxml+xpath提取内容。 使用xpath提取丁香园论坛的回复内容。 

from lxml import etree
import requests

def main():
    url='http://www.dxy.cn/bbs/thread/626626'
    headers={'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3521.2 Safari/537.36'}
    html=get_html(url,headers)
    get_A(html)
    
def get_html(url,headers):
    response=requests.get(url,headers=headers)
    return response.text

def get_A(html):
    tree=etree.HTML(html)
    ids=tree.xpath('//*/table/tbody/tr/td/div/a/text()')
    comments=tree.xpath('//*/table/tbody/tr/td/div/div/table/tbody/tr/td/text()')
    
    for id,comment in zip(ids,comments):
        print('用户：'+id,'评价:'+comment.strip())
    
if __name__=='__main__':
    main()