【Python爬虫实战】多线程爬虫---糗事百科段子爬取

时间：2023-03-09 06:07:00
【Python爬虫实战】多线程爬虫---糗事百科段子爬取 
多线程爬虫：即程序中的某些程序段并行执行，
合理地设置多线程，可以让爬虫效率更高
糗事百科段子普通爬虫和多线程爬虫
分析该网址链接得出：
https://www.qiushibaike.com/8hr/page/页码/

多线程爬虫也就和JAVA的多线程差不多，直接上代码

 '''

 #此处代码为普通爬虫

 import urllib.request

 import urllib.error

 import re

 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)

 for i in range(1,2):

     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)+"个段子内容是：")

         print(datalist[j])

 '''

 '''

 #此处为多线程介绍代码

 import threading   #导入多线程包

 class A(threading.Thread):  #创建一个多线程A

     def __init__(self):     #必须包含的两个方法之一:初始化线程

         threading.Thread.__init__(self)

     def run(self):          #必须包含的两个方法之一：线程运行方法

         for i in range(0,11):

             print("我是线程A")

 class B(threading.Thread):  #创建一个多线程A

     def __init__(self):     #必须包含的两个方法之一:初始化线程

         threading.Thread.__init__(self)

     def run(self):          #必须包含的两个方法之一：线程运行方法

         for i in range(0,11):

             print("我是线程B")

 t1 = A()    #线程实例化

 t1.start()  #线程运行

 t2 = B()

 t2.start()

 '''

 #此处为修改后的多线程爬虫

 #使用多线程进行奇偶页的爬取

 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(1,12,2):

             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])

 class two(threading.Thread):   #爬取奇数页内容

     def __init__(self):

         threading.Thread.__init__(self)

     def run(self):

         for i in range(2,12,2):

             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])

 t1 = one()

 t2 = two()

 t1.start()

 t2.start()
 

相关文章