简单百度贴吧网页爬取get方式

Posted 2020-11-26 lizhihoublog

 1 from urllib import request,parse
 2 import os
 3 # https://tieba.baidu.com/f?kw=lol&ie=utf-8&pn=0
 4 # https://tieba.baidu.com/f?kw=lol&ie=utf-8&pn=50
 5 # https://tieba.baidu.com/f?kw=lol&ie=utf-8&pn=100
 6 # https://tieba.baidu.com/f?kw=lol&ie=utf-8&pn=150
 7 # 分析：
 8 # kw是搜索关键字pn是它的网页序号
 9 # 所以1---0
10 #     2---50
11 #     3---100
12 #      n...(n-1)*50
13 
14 
15 def query(base_url,kw,start,end):
16     ‘‘‘
17     :param base_url: 网址
18     :param kw: 搜索贴吧关键字
19     :param start: 起始页码
20     :param end: 终止页码
21     :return: 输出网页信息到指定文件夹
22     ‘‘‘
23     dir_name = ‘./teiba/‘+kw+‘/‘
24     header = {
25         ‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:68.0) Gecko/20100101 Firefox/68.0‘
26     }
27     if not os.path.exists(dir_name):
28         os.makedirs(dir_name)
29     for i in range(start,end+1):
30         pn = (i-1)*50
31         query_msg = {
32             ‘kw‘:kw,
33             ‘ie‘:‘utf-8‘,
34             ‘pn‘:pn,
35         }
36         msg = parse.urlencode(query_msg)
37         url = base_url+msg
38         req = request.Request(url,headers=header)
39         response = request.urlopen(req).read().decode()
40         with open(dir_name+str(i)+‘.html‘,‘w‘,encoding=‘utf-8‘)as files:
41             files.write(response)
42 
43 if __name__ == ‘__main__‘:
44     base_url = ‘https://tieba.baidu.com/f?‘
45     kw = input(‘输入查询的贴吧>>‘)
46     start = int(input(‘输入起始页码>>‘))
47     end = int(input(‘输入终止页码>>‘))
48     query(base_url,kw,start,end)