爬虫入门学习 贴吧小案例

Posted 2021-02-10 wen-kang

 1 import urllib.request
 2 import urllib.parse
 3 import random
 4 
 5 #目标地址
 6 url="http://tieba.baidu.com/f"
 7 
 8 #伪造客户端 http请求头
 9 ua_list = [
10     "User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.6; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
11     "User-Agent: Mozilla/5.0 (Windows NT 6.1; rv:2.0.1) Gecko/20100101 Firefox/4.0.1",
12     "User-Agent: Opera/9.80 (Macintosh; Intel Mac OS X 10.6.8; U; en) Presto/2.8.131 Version/11.11",
13     "User-Agent: Opera/9.80 (Windows NT 6.1; U; en) Presto/2.8.131 Version/11.11",
14     "User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_0) AppleWebKit/535.11 (Khtml, like Gecko) Chrome/17.0.963.56 Safari/535.11",
15     "User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.109 Safari/537.36"
16 ]
17 #随机选择一个作为请求头
18 user_agent=random.choice(ua_list)
19 def doWrite(html,f_name):
20     """
21     :param html: 请求得到响应后收到的数据
22     :param f_name: 用于保存写操作的文件名
23     :return:   E:Demopyswt
24     """
25     with open(f_name,"w",encoding=‘utf8‘)as f:
26         f.write(html)
27     print(">"*30)
28 
29 def loadPage(f_url,f_name):
30     #对目标地址进行请求
31     request=urllib.request.Request(f_url)
32     #设置http请求头
33     request.add_header("User-Agent",user_agent)
34     #获取响应数据
35     response=urllib.request.urlopen(request)
36     html=response.read().decode("utf-8")
37     #下载并保存
38     print("准备写入数据....")
39     doWrite(html,f_name)
40 
41 def doCode(url,kwd):
42     ‘‘‘
43     对搜索关键字进行编码
44     :return: 
45     ‘‘‘
46     kw={"kw":kwd}
47     kw=urllib.parse.urlencode(kw)
48     #关键字拼接
49     full_url=url+"?"+kw
50     return full_url
51 
52 
53 def doUrl(url,star,end):
54     ‘‘‘
55     拼接url地址
56     ‘‘‘
57     for pages in range(star,end+1):
58         page=(pages-1)*50
59 
60         f_url=url+"&pn="+str(page)
61         f_name="第"+str(pages)+"页"+".html"
62         print("即将加载第{0}页数据".format(pages))
63         loadPage(f_url,f_name)
64     print("下载完成，谢谢使用！")
65 
66 if __name__ == ‘__main__‘:
67     tb_name=input("请输入要访问的贴吧名:
")
68     starPage=int(input("请输入起始页"))
69     endPage=int(input("请输入结束页"))
70 
71     full_url=doCode(url,tb_name)
72     doUrl(full_url,starPage,endPage)