爬取-姓名测试打分

从姓名测试网站 爬去，所有‘李金’开头的三个字的名字对应的得分，取拍分比较高的名字。

 1 # -*- coding: utf-8 -*-
 2 """
 3 Created on Thu Jan 30 12:45:02 2020
 4 
 5 @author: Administrator
 6 """
 7 
 8 #获取所有中文汉字
 9 chineses = [chr(i) for i in range(0x4e00,0x9fa6)]
10 print(len(chineses)) #20902
11 
12 #爬取网站姓名评分
13 import requests
14 from bs4 import BeautifulSoup
15 import time
16  
17 
18 def get_score(name_str):
19     data = {'xm': name_str,
20     'dxfx': 1,
21     'Input': '开始测算'}
22     # 发送一个 HTTP POST 请求：
23     r = requests.post("http://m.name321.com/xm.php",data = data)
24     try:
25         soup = BeautifulSoup(r.text, features="lxml")
26         c2 = soup.select('div.c_c h4')[0].text
27         c2 = c2.split('：')
28         c2_2 = int(c2[1].replace(' ','').replace('分',''))
29         return {'name':name_str,'score':c2_2,'status_code':r.status_code}
30     except Exception as e:
31         return {'name':name_str,'score':-1,'status_code':r.status_code}
32 dict0 = get_score(' ')
33 
34 
35 
36 def writ(dict0):
37     time0 = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
38     with open('score.csv','a') as f:
39         f.write(dict0.get('name')+','+str(dict0.get('score'))+','+time0+','+str(dict0.get('status_code'))+'\n')
40     pass
41 writ(dict0)
42 
43 
44 #
45 #list0=[]
46 #list0.append(list0)
47 #11000
48 for i,j in enumerate(chineses):
49     if i>8803:
50         dict0 = get_score('李金'+j)
51         writ(dict0)
52         print(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()),i,'20902')
53         print(dict0)
54     else:
55         pass
56     time.sleep(0.1)
57

 

posted on 2022-01-22 11:13  andy_1  阅读(81)  评论(0)    收藏  举报

导航