首页 > > 网络编程 > 其它 >

【Python爬虫实战】多线程爬虫---糗事百科段子爬…

2018-06-17 23:53:01来源：未知阅读 ()

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

 1 '''
 2 #此处代码为普通爬虫
 3 import urllib.request
 4 import urllib.error
 5 import re
 6 
 7 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")
 8 opener = urllib.request.build_opener()
 9 opener.addheaders = [headers]
10 urllib.request.install_opener(opener)
11 for i in range(1,2):
12     url = "https://www.qiushibaike.com/8hr/page/"+str(i)+"/"
13     pagedata = urllib.request.urlopen(url).read().decode("utf-8","ignore")
14     pattern = '<div class="content">.*?<span>(.*?)</span>(.*?)</div>'
15     datalist = re.compile(pattern,re.S).findall(pagedata)
16     for j in range(0,len(datalist)):
17         print("第"+str(i)+"页第"+str(j)+"个段子内容是：")
18         print(datalist[j])
19 '''
20 
21 '''
22 #此处为多线程介绍代码
23 import threading   #导入多线程包
24 class A(threading.Thread):  #创建一个多线程A
25     def __init__(self):     #必须包含的两个方法之一:初始化线程
26         threading.Thread.__init__(self)
27     def run(self):          #必须包含的两个方法之一：线程运行方法
28         for i in range(0,11):
29             print("我是线程A")
30 
31 class B(threading.Thread):  #创建一个多线程A
32     def __init__(self):     #必须包含的两个方法之一:初始化线程
33         threading.Thread.__init__(self)
34     def run(self):          #必须包含的两个方法之一：线程运行方法
35         for i in range(0,11):
36             print("我是线程B")
37 
38 t1 = A()    #线程实例化
39 t1.start()  #线程运行
40 t2 = B()
41 t2.start()
42 '''
43 
44 
45 #此处为修改后的多线程爬虫
46 #使用多线程进行奇偶页的爬取
47 import urllib.request
48 import urllib.error
49 import re
50 import threading
51 
52 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")
53 opener = urllib.request.build_opener()
54 opener.addheaders = [headers]
55 urllib.request.install_opener(opener)
56 class one(threading.Thread):   #爬取奇数页内容
57     def __init__(self):
58         threading.Thread.__init__(self)
59     def run(self):
60         for i in range(1,12,2):
61             url = "https://www.qiushibaike.com/8hr/page/"+str(i)+"/"
62             pagedata = urllib.request.urlopen(url).read().decode("utf-8","ignore")
63             pattern = '<div class="content">.*?<span>(.*?)</span>(.*?)</div>'
64             datalist = re.compile(pattern,re.S).findall(pagedata)
65             for j in range(0,len(datalist)):
66                 print("第"+str(i)+"页第"+str(j)+"段子内容为：")
67                 print(datalist[j])
68 
69 
70 class two(threading.Thread):   #爬取奇数页内容
71     def __init__(self):
72         threading.Thread.__init__(self)
73     def run(self):
74         for i in range(2,12,2):
75             url = "https://www.qiushibaike.com/8hr/page/"+str(i)+"/"
76             pagedata = urllib.request.urlopen(url).read().decode("utf-8","ignore")
77             pattern = '<div class="content">.*?<span>(.*?)</span>(.*?)</div>'
78             datalist = re.compile(pattern,re.S).findall(pagedata)
79             for j in range(0,len(datalist)):
80                 print("第"+str(i)+"页第"+str(j)+"段子内容为：")
81                 print(datalist[j])
82 t1 = one()
83 t2 = two()
84 t1.start()
85 t2.start()