糗事百科多线程介绍

最新推荐文章于 2020-07-06 15:25:54 发布

wangxihe2012

最新推荐文章于 2020-07-06 15:25:54 发布

阅读量302

点赞数

分类专栏： Python

本文链接：https://blog.csdn.net/wangxihe2012/article/details/80529038

版权

Python 专栏收录该内容

30 篇文章

订阅专栏

import urllib.request
import urllib.error
import re
import threading
headers = ("User-Agent","Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36")
opener = urllib.request.build_opener()
opener.addheaders = [headers]
urllib.request.install_opener(opener)
class one(threading.Thread): #爬取奇数页内容
   def __init__(self):
       threading.Thread.__init__(self)
   def run(self):
       for i in range(1,52,2):
           try:
               url = "https://www.qiushibaike.com/8hr/page/"+str(i)+"/"
               pagedata = urllib.request.urlopen(url).read().decode("utf-8","ignore")
               pattern = '<div class="content">.*?<span>(.*?)</span>(.*?)</div>'
               datalist = re.compile(pattern,re.S).findall(pagedata)
               for j in range(0,len(datalist)):
                  print("第"+str(i)+"页第"+str(j)+"段子内容为：")
                  print(datalist[j])
           except Exception as e:
               print(e)

class two(threading.Thread): #爬取偶数页内容
   def __init__(self):
       threading.Thread.__init__(self)
   def run(self):
       for i in range(2,53,2):
           try:
               url = "https://www.qiushibaike.com/8hr/page/"+str(i)+"/"
               pagedata = urllib.request.urlopen(url).read().decode("utf-8","ignore")
               pattern = '<div class="content">.*?<span>(.*?)</span>(.*?)</div>'
               datalist = re.compile(pattern,re.S).findall(pagedata)
               for j in range(0,len(datalist)):
                  print("第"+str(i)+"页第"+str(j)+"段子内容为：")
                  print(datalist[j])
           except Exception as e:
               print(e)
t1 = one()
t2 = two()
t1.start()
t2.start()