爬取糗事百科段子

import urllib.request
import urllib.error
import re

page = 1
url = 'https://www.qiushibaike.com/8hr/page/'+str(page)
user_agent = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36 LBBROWSER'
headers = {'User-Agent':user_agent}
try:
    request = urllib.request.Request(url,headers = headers)
    response = urllib.request.urlopen(request)
    #print(response.read())
except urllib.error.URLError as e:
    if hasattr(e,'code'):
        print(e.code)
    if hasattr(e,'reason'):
        print(e.reason)

content = response.read().decode('utf_8')
pattern = re.compile('<h2>(.*?)</h2>.*?<div.*?content">.*?<span>(.*?)</span>',re.S)
items = re.findall(pattern,content)
for item in items:
    print("用户名:"+item[0])
    print("评论内容："+item[1])