python 爬取疫情数据的源码

疫情数据

程序源码

1. // An highlighted block
2. import requests
3. import json
4. class epidemic_data():
5. def __init__(self, province):
6. self.url = url
7. self.header = header
8. self.text = {}
9. self.province = province
10. # self.r=None
11. def down_page(self):
12. r = requests.get(url=url, headers=header)
13. self.text = r.text
14. # self.r = r
15. def parse_page(self):
16. # print(type(self.r.json()['data']))
17. # 因为解析数据为 data 前有一个""，所以数据类型为string
18. data_str = json.loads(self.text)['data'] #sring
19. # print(type(data_dict))
20. # print(type(data_dict['data']))
21. # 将str 转化为对象
22. data_json = json.loads(data_str)
23. data_tree_dict = data_json['areaTree'][0]['children'] # 取中国的省列表
24. prt_str = []
25. prt_str.append("数据更新时间："+data_json['lastUpdateTime'])
26. prt_str.append("全国" + ":" + "累计确诊病例：" + str(data_json['chinaTotal']['confirm']) + \
27. "累计疑似病例：" + str(data_json['chinaTotal']['suspect']) + \
28. "累计死亡病例：" + str(data_json['chinaTotal']['dead']) + \
29. "累计出院病例：" + str(data_json['chinaTotal']['heal']) + \
30. "今日新增确诊病例：" + str(data_json['chinaAdd']['confirm']) + \
31. "今日新增疑似病例：" + str(data_json['chinaAdd']['suspect']) + \
32. "今日新增死亡病例：" + str(data_json['chinaAdd']['dead']) + \
33. "今日新增出院病例：" + str(data_json['chinaAdd']['heal']))
34. for province_list in data_tree_dict:
35. for provice_name in self.province:
36. if provice_name in province_list['name']:
37. city_list = province_list['children']
38. prt_str.append(province_list['name'] + ":" + "累计确诊病例：" + str(province_list['total']['confirm']) + \
39. "累计死亡病例：" + str(province_list['total']['dead']) + \
40. "累计出院病例：" + str(province_list['total']['heal']) + \
41. "今日新增确诊病例：" + str(province_list['today']['confirm']) + \
42. "今日新增死亡病例：" + str(province_list['today']['dead']) + \
43. "今日新增出院病例：" + str(province_list['today']['heal']))
44. if provice_name == '山东':
45. for data_dict in city_list:
46. prt_str.append(data_dict['name'] + ":" + "累计确诊病例：" + str(data_dict['total']['confirm']) +\
47. "累计死亡病例：" + str(data_dict['total']['dead']) + \
48. "累计出院病例：" + str(data_dict['total']['heal']) + \
49. "今日确诊病例：" + str(data_dict['today']['confirm']) + \
50. "今日死亡病例：" + str(data_dict['today']['dead']) + \
51. "今日出院病例：" + str(data_dict['today']['heal']))
52. for item in prt_str:
53. print(item)
54. a = data_tree_dict
55. # print(type(data_tree_dict['chinaTotal']))
56. # print(data_tree_dict.keys())
57. def write_page(self):
58. pass
59. def show(self):
60. pass
61. def show(self):
62. self.down_page()
63. self.parse_page()
64. if __name__ == '__main__':
65. url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5'
66. header = {
67. 'user - agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/79.0.3945.130 Safari/537.36'
68. }
69. province = ['湖北','山东']
70. wf = epidemic_data(province)
71. wf.show()

总结

以上所述是小编给大家介绍的python 爬取疫情数据的源码，希望对大家有所帮助！