XPath爬取丁香论坛回复评论

import requests
import csv
import lxml
from lxml import etree

url = "http://www.dxy.cn/bbs/thread/626626#626626"
headers = {"User-Agent":"Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"}
re = requests.get(url, headers)
text = re.text
print()
html = etree.HTML(text)  #调用HTML类初始化。构成XPath解析对象
#result = etree.tostring(ht) #对ht进行修正补齐，但是结果是BYTE型，要转换成str类型
#result = result.decode("utf-8")#转换成str型    也可以直接进行文本解析，不用这三步
#tml  = etree.parse('./text.html',etree.HTMLParser()) #直接调用文本进行分析
result1 = html.xpath('//div[@class="auth"]')
result2 = html.xpath('//tbody//td[@class="postbody"]') #取出对应的回复评论  都是list型
result3 = html.xpath('//div[@class="post-info"]/span[1]')
#创建空列表存放数据
user = []
content = []
time = []
with ope