关于糗事百科段子爬取

909646372

import urllib.request
import re
def getcontent(url,page):
    headers = ("User-Agent" ,"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/51.0.2704.103 Safari/537.36")
   
    opener = urllib.request.build_opener()
    opener.addheaders = [headers]
    urllib.request.install_opener(opener)
   
    data = urllib.request.urlopen(url).read().decode("utf-8")
   
    userpat = 'target="_blank" title="(.*?)">'
    contentpat = '<div class="content">(.*?)</div>'
    userlist=re.compile(userpat,re.S).findall(data)
    contentlist=re.compile(contentpat,re.S).findall(data)

    x=1
    for content in contentlist:
        
        content = content.replace("\n","")
        name = "content"+str(x)
        exec(name+'=content')
        x+=1
    y=1
    for user in userlist:
        name = "content" + str(y)
        print('user' + str(page) +str(y) + "is:" + user)
        print("the content is ")
        exec("print("+name+")")
        print('\n')
        y+=1
for i in range(1,30):
    url = 'http://www.qiushibaike.com/8hr/page/'+str(i)
    getcontent(url,i)






现在网站好像在升级进不去 有没有大神能解答下下面那个exec的问题QAQ

909646372

为啥跑起来什么都不显示

909646372

不是特别明白exec("print('+name+')") 为什么name前后要放加号