一个爬取疫情数据的小爬虫

叙白

自学了一个多月的python，这几天学到爬虫了，写一个爬疫情数据的爬虫，
ps:需要安装requests库

1. import requests
   
2. 
   
3. import json
   
4. 
   
5. """请求头文件和url"""
   
6. headers = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'}
   
7. url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5&callback=jQuery3410666023933987975_1584781205909&_=1584781205910'
   
8. 
   
9. """解析网页"""
   
10. 
    
11. response = requests.get(url,headers = headers)
    
12. data = response.text
    
13. 
    
14. dic_data = data[40:-1]
    
15. #获取请求到的data文件
    
16. 
    
17. dic_data = json.loads(dic_data)
    
18. dic_data['data'] = json.loads(dic_data['data'])
    
19. #讲请求到的json字符串转换为字典
    
20. 
    
21. def country():
    
22. 
    
23.     """中国"""
    
24.     china = dic_data['data']['chinaTotal']
    
25.     #截取字典中的中国部分
    
26. 
    
27.     # print(dic_data['data']['lastUpdateTime'])测试用
    
28. 
    
29.     """获取确诊治愈等信息"""
    
30. 
    
31.     confirm = china['confirm']
    
32.     heal = china['heal']
    
33.     nowConfirm = china['nowConfirm']
    
34.     nowSevere = china['nowSevere']
    
35.     importedCase = china['importedCase']
    
36.     dead = china['dead']
    
37.     time = dic_data['data']['lastUpdateTime']
    
38. 
    
39.     #防止输入错误或者未请求到文件报错
    
40.    
    
41.     try:
    
42.         print('截止到%s\n国内\n累计确诊：%s\n累计治愈：%s\n累计死亡：%s\n现有确诊：%s\n现有重症：%s\n境外输入：%s' % (time,confirm,heal,dead,nowConfirm,nowSevere,importedCase))
    
43.     except:
    
44.         print('出错了！！！')
    
45. 
    
46. def provinces():
    
47.     """省份"""
    
48.     back_data = None
    
49.     while back_data == None:
    
50.         area_name = input('请输入要查询的省份')
    
51.         children = dic_data['data']['areaTree'][0]['children']
    
52. 
    
53.         for i in children:
    
54. 
    
55.             if i["name"] == area_name:
    
56.                 back_data = i
    
57.                 print("查找成功")
    
58. 
    
59.     """获取省份数据"""
    
60.     nowconfirm = back_data['today']['confirm']
    
61.     total = back_data['total']
    
62.     confirm = total['confirm']
    
63.     dead = total['dead']
    
64.     deadRate = total['deadRate']
    
65.     heal = total['heal']
    
66.     healRate = total['healRate']
    
67. 
    
68.     try:
    
69.         print(area_name + '\n新增确诊：%d\n累计确诊：%d\n累计死亡：%d\n累计治愈：%d\n死亡率：%s \n治愈率：%s' % (nowconfirm,confirm,dead,heal,deadRate,healRate))
    
70. 
    
71.     except:
    
72.       print('输入错误！/未查询到数据！！！')
    
73. 
    
74. def start():
    
75.     while True:
    
76.         search = input('请输入需要查询的类型（国家(g)/省市(s)/0为退出）：')
    
77. 
    
78.         if search == '国家' or search == 'g':
    
79.             country()
    
80. 
    
81.         elif search == '省市' or search == 's':
    
82.             provinces()
    
83. 
    
84.         elif search == '0':
    
85.             break
    
86. 
    
87.         else:
    
88.             print('输入错误，请重新输入')
    
89. 
    
90. if __name__ == "__main__":
    
91.     start()

复制代码

yinshujie

老哥, 求教url怎么解析出来的

叙白

yinshujie 发表于 2020-3-23 16:26
老哥, 求教url怎么解析出来的

网页右键检查，找到network刷新一下就看到了