BeautifulSoup 爬取丁香论坛评论回复内容
具体代码如下l
爬取评论用户名、评论、时间
import requests
import csv
from bs4 import BeautifulSoup
import lxml
import re
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)
html = re.text
soup = BeautifulSoup(html,'lxml')
#print(soup.find_all("tr")) #瞧瞧它在哪里啊
user = [] #为后面存放创建列表
content = []
time = []
with open("dingxiang.csv",'a',encoding='utf-8') as csvfile:
writer = csv.writer(csvfile)
writer.writerow(["user","评论","时间"])
for data in soup.select('.auth'):
x = data.get_text(strip=True) # strip 加在这里 删除空格
# writer.writerow(re)
user.append(x) #做成字典型
for data in soup.select(".postbody"):