Python爬取腾讯疫情实时数据并存储到mysql数据库
思路:
在腾讯疫情数据网站F12解析网站结构,使用Python爬取当日疫情数据和历史疫情数据,分别存储到details和history两个mysql表。
①此方法用于爬取每日详细疫情数据
1 import requests 2 import json 3 import time 4 def get_details(): 5 url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_h5&callback=jQuery34102848205531413024_1584924641755&_=1584924641756' 6 headers ={ 7 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400' 8 } 9 res = requests.get(url,headers=headers) 10 #输出全部信息 11 # print(res.text) 12 response_data = json.loads(res.text.replace('jQuery34102848205531413024_1584924641755(','')[:-1]) 13 #输出这个字典的键值 dict_keys(['ret', 'data'])ret是响应值,0代表请求成功,data里是我们需要的数据 14 # print(response_data.keys()) 15 """上面已经转化过一次字典,然后获取里面的data,因为data是字符串,所以需要再次转化字典 16 print(json.loads(reponse_data['data']).keys()) 17 结果: 18 dict_keys(['lastUpdateTime', 'chinaTotal', 'chinaAdd', 'isShowAdd', 'showAddSwitch', 19 'areaTree', 'chinaDayList', 'chinaDayAddList', 'dailyNewAddHistory', 'dailyHistory', 20 'wuhanDayList', 'articleList']) 21 lastUpdateTime是最新更新时间,chinaTotal是全国疫情总数,chinaAdd是全国新增数据, 22 isShowAdd代表是否展示新增数据,showAddSwitch是显示哪些数据,areaTree中有全国疫情数据 23 """ 24 areaTree_data = json.loads(response_data['data'])['areaTree'] 25 temp=json.loads(response_data['data']) 26 # print(temp.keys()) 27 # print(areaTree_data[0].keys()) 28 """ 29 获取上一级字典里的areaTree 30 然后查看里面中国键值 31 print(areaTree_data[0].keys()) 32 dict_keys(['name', 'today', 'total', 'children']) 33 name代表国家名称,today代表今日数据,total代表总数,children里有全国各地数据,我们需要获取全国各地数据,查看children数据 34 print(areaTree_data[0]['children']) 35 这里面是 36 name是地区名称,today是今日数据,total是总数,children是市级数据, 37 我们通过这个接口可以获取每个地区的总数据。我们遍历这个列表,取出name,这个是省级的数据,还需要获取市级数据, 38 需要取出name,children(市级数据)下的name、total(历史总数)下的confirm、heal、dead,today(今日数据)下的confirm(增加数), 39 这些就是我们需要的数据 40 """ 41 # print(areaTree_data[0]['children']) 42 # for province_data in areaTree_data[0]['children']: 43 # print(province_data) 44 45 ds= temp['lastUpdateTime'] 46 details=[] 47 for pro_infos in areaTree_data[0]['children']: 48 province_name = pro_infos['name'] # 省名 49 for city_infos in pro_infos['children']: 50 city_name = city_infos['name'] # 市名 51 confirm = city_infos['total']['confirm']#历史总数 52 confirm_add = city_infos['today']['confirm']#今日增加数 53 heal = city_infos['total']['heal']#治愈 54 dead = city_infos['total']['dead']#死亡 55 # print(ds,province_name,city_name,confirm,confirm_add,heal,dead) 56 details.append([ds,province_name,city_name,confirm,confirm_add,heal,dead]) 57 return details
单独测试方法:
1 # d=get_details() 2 # print(d)
②此方法用于爬取历史详细数据
1 import requests 2 import json 3 import time 4 def get_history(): 5 url = 'https://view.inews.qq.com/g2/getOnsInfo?name=disease_other&callback=jQuery341026745307075030955_1584946267054&_=1584946267055' 6 headers ={ 7 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400' 8 } 9 res = requests.get(url,headers=headers) 10 # print(res.text) 11 response_data = json.loads(res.text.replace('jQuery341026745307075030955_1584946267054(','')[:-1]) 12 # print(response_data) 13 data = json.loads(response_data['data']) 14 # print(data.keys()) 15 chinaDayList = data['chinaDayList']#历史记录 16 chinaDayAddList = data['chinaDayAddList']#历史新增记录 17 history = {} 18 for i in chinaDayList: 19 ds = '2021.' + i['date']#时间 20 tup = time.strptime(ds,'%Y.%m.%d') 21 ds = time.strftime('%Y-%m-%d',tup)#改变时间格式,插入数据库 22 confirm = i['confirm'] 23 suspect = i['suspect'] 24 heal = i['heal'] 25 dead = i['dead'] 26 history[ds] = {'confirm':confirm,'suspect':suspect,'heal':heal,'dead':dead} 27 for i in chinaDayAddList: 28 ds = '2021.' + i['date']#时间 29 tup = time.strptime(ds,'%Y.%m.%d') 30 ds = time.strftime('%Y-%m-%d',tup)#改变时间格式,插入数据库 31 confirm_add = i['confirm'] 32 suspect_add = i['suspect'] 33 heal_add = i['heal'] 34 dead_add = i['dead'] 35 history[ds].update({'confirm_add':confirm_add,'suspect_add':suspect_add,'heal_add':heal_add,'dead_add':dead_add}) 36 return history
单独测试此方法:
1 # h=get_history() 2 # print(h)
③此方法用于数据库的连接与关闭:
1 import time 2 import pymysql 3 import traceback 4 def get_conn(): 5 """ 6 :return: 连接,游标 7 """ 8 # 创建连接 9 conn = pymysql.connect(host="127.0.0.1", 10 user="root", 11 password="000429", 12 db="mydb", 13 charset="utf8") 14 # 创建游标 15 cursor = conn.cursor() # 执行完毕返回的结果集默认以元组显示 16 return conn, cursor 17 def close_conn(conn, cursor): 18 if cursor: 19 cursor.close() 20 if conn: 21 conn.close()
④此方法用于更新并插入每日详细数据到数据库表:
1 def update_details(): 2 """ 3 更新 details 表 4 :return: 5 """ 6 cursor = None 7 conn = None 8 try: 9 li = get_details() 10 conn, cursor = get_conn() 11 sql = "insert into details(update_time,province,city,confirm,confirm_add,heal,dead) values(%s,%s,%s,%s,%s,%s,%s)" 12 sql_query = 'select %s=(select update_time from details order by id desc limit 1)' #对比当前最大时间戳 13 cursor.execute(sql_query,li[0][0]) 14 if not cursor.fetchone()[0]: 15 print(f"{time.asctime()}开始更新最新数据") 16 for item in li: 17 cursor.execute(sql, item) 18 conn.commit() # 提交事务 update delete insert操作 19 print(f"{time.asctime()}更新最新数据完毕") 20 else: 21 print(f"{time.asctime()}已是最新数据!") 22 except: 23 traceback.print_exc() 24 finally: 25 close_conn(conn, cursor)
单独测试能否插入数据到details表:
1 update_details()
⑤此方法用于插入历史数据到history表
1 def insert_history(): 2 """ 3 插入历史数据 4 :return: 5 """ 6 cursor = None 7 conn = None 8 try: 9 dic = get_history() 10 print(f"{time.asctime()}开始插入历史数据") 11 conn, cursor = get_conn() 12 sql = "insert into history values(%s,%s,%s,%s,%s,%s,%s,%s,%s)" 13 for k, v in dic.items(): 14 # item 格式 {'2021-01-13': {'confirm': 41, 'suspect': 0, 'heal': 0, 'dead': 1} 15 cursor.execute(sql, [k, v.get("confirm"), v.get("confirm_add"), v.get("suspect"), 16 v.get("suspect_add"), v.get("heal"), v.get("heal_add"), 17 v.get("dead"), v.get("dead_add")]) 18 19 conn.commit() # 提交事务 update delete insert操作 20 print(f"{time.asctime()}插入历史数据完毕") 21 except: 22 traceback.print_exc() 23 finally: 24 close_conn(conn, cursor)
单独测试能否插入数据到history表:
1 # insert_history()
⑥此方法用于根据时间来更新历史数据表的内容:
1 def update_history(): 2 """ 3 更新历史数据 4 :return: 5 """ 6 cursor = None 7 conn = None 8 try: 9 dic = get_history() 10 print(f"{time.asctime()}开始更新历史数据") 11 conn, cursor = get_conn() 12 sql = "insert into history values(%s,%s,%s,%s,%s,%s,%s,%s,%s)" 13 sql_query = "select confirm from history where ds=%s" 14 for k, v in dic.items(): 15 # item 格式 {'2020-01-13': {'confirm': 41, 'suspect': 0, 'heal': 0, 'dead': 1} 16 if not cursor.execute(sql_query, k): 17 cursor.execute(sql, [k, v.get("confirm"), v.get("confirm_add"), v.get("suspect"), 18 v.get("suspect_add"), v.get("heal"), v.get("heal_add"), 19 v.get("dead"), v.get("dead_add")]) 20 conn.commit() # 提交事务 update delete insert操作 21 print(f"{time.asctime()}历史数据更新完毕") 22 except: 23 traceback.print_exc() 24 finally: 25 close_conn(conn, cursor)
单独测试更新历史数据表的方法:
1 # update_history()
最后是两个数据表的详细建立代码(也可以使用mysql可视化工具直接建立):
1 create table history( 2 ds datetime not null comment '日期', 3 confirm int(11) default null comment '累计确诊', 4 confirm_add int(11) default null comment '当日新增确诊', 5 suspect int(11) default null comment '剩余疑似', 6 suspect_add int(11) default null comment '当日新增疑似', 7 heal int(11) default null comment '累计治愈', 8 heal_add int(11) default null comment '当日新增治愈', 9 dead int(11) default null comment '累计死亡', 10 dead_add int(11) default null comment '当日新增死亡', 11 primary key(ds) using btree 12 )engine=InnoDB DEFAULT charset=utf8mb4; 13 create table details( 14 id int(11) not null auto_increment, 15 update_time datetime default null comment '数据最后更新时间', 16 province varchar(50) default null comment '省', 17 city varchar(50) default null comment '市', 18 confirm int(11) default null comment '累计确诊', 19 confirm_add int(11) default null comment '新增确诊', 20 heal int(11) default null comment '累计治愈', 21 dead int(11) default null comment '累计死亡', 22 primary key(id) 23 )engine=InnoDB default charset=utf8mb4;
Tomorrow the birds will sing.
好看请赞,养成习惯:) 本文来自博客园,作者:靠谱杨, 转载请注明原文链接:https://www.cnblogs.com/rainbow-1/p/14550221.html
欢迎来我的51CTO博客主页踩一踩 我的51CTO博客
文章中的公众号名称可能有误,请统一搜索:靠谱杨的秘密基地