Python3——爬取淘宝评论

 1 # -*- coding:utf-8 -*-
 2 
 3 # _ksTS=1526545121518_1881时间戳滞后了 ∴要动态的传参数——(导入time模块)
 4 # callback=jsonp1882
 5 import requests
 6 import time
 7 import random
 8 import re
 9 import json
10 
11 url = ‘https://rate.tmall.com/list_detail_rate.htm?itemId=539137284584&spuId=701871908&sellerId=929347050&order=3&append=0&content=1&tagId=&posi=&picture=&ua=098%23E1hvsvvLvZIvUpCkvvvvvjiPPFdZ6jtPPLqOzjivPmPh1jDRRFchAjYbPsMh6jYWR46Cvvyv2vZjwchvJCurvpvEvvkUCgR2vV2LdphvmpvhOQb3gpCU4UhCvCLwMCHJGaMwznAY8xS50YAizRl4k46CvvyvCWgmYNZvECojvpvhvvpvvvGCvvpvvPMMuphvmvvv9bhrvjKCkphvC99vvOClpbyCvm9vvvvvphvvvvvv9F1vpvkjvvmmZhCv2CUvvUEpphvWwpvv9DCvpv11mphvLvp%2F6QvjWz7%2BkU97%2B3%2BraNBraB4AVAElYWmQrEt1pwLU%2BnezrmphQRAn3feAOHcIAXcBKFyK2ixrQj7Jymx%2F1j7QiXTAVArlMR29VEQCvpvVvvpvvhCvRphvCvvvvvm5vpvhvvmv9u6CvvyvCV4mRLyvVbervpvEvvBxvkgKv2kqRphvCvvvvvmCvpvZz2sm4VdNznswvCDfY0IwXaAv7Ihtvpvhvvvvvv%3D%3D&isg=BBgYp5ys9ga0jdox7XxaDMe26UbZGXLdB_e3zlII19NS7bvX-hKvGsuvISVdfTRj&needFold=0‘
12 
13 # 发送 http://请求
14 # t = time.time() 时间戳time()函数
15 # csv文件 excle 可以打开
16 
17 f = open(‘votes.csv‘,‘w‘,encoding=‘gbk‘)
18 f.write(‘评价内容，店家回复，昵称\n‘)
19 for i in range(99):
20     t = str(time.time()).split(‘.‘)
21 
22     # 构造url的过程，get请求的参数
23     pagram = {
24         ‘currentPage‘: i+1,
25         ‘_ksTS‘: ‘%s_%s‘ % (t[0], t[1]),
26         ‘callback‘: ‘jsonp%s‘ %(int(t[1])+1)
27     }
28 
29     # 随机休眠，行为分析，防止访问过快，避免被网站检测到有问题
30     time.sleep(random.random())
31 
32     response = requests.get(url, params=pagram)
33     # 数据持久化——入库、文件
34     # csv文件:通过‘,‘区分
35     data = response.text
36 
37     # 解析数据
38     data = re.findall(r‘{.*}‘, data)[0]
39     # json模块可以将  Json数据<——>为字典 互相转换
40 
41     # Json数据——>转为字典
42     data = json.loads(data)
43     data = data[‘rateDetail‘][‘rateList‘]
44     print(data)
45     for item in data:
46         f.write(‘%s,%s,%s‘% (
47             item[‘rateContent‘].replace(‘,‘, ‘，‘),
48             item[‘reply‘].replace(‘,‘, ‘，‘),
49             item[‘displayUserNick‘]))