Python爬取腾讯疫情实时数据并存储到mysql数据库的⽰例代码
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
import requests
import json
import time
def get_details():
url = 'view.inews.qq/g2/getOnsInfo?name=disease_h5&callback=jQuery34102848205531413024_1584924641755&_=1584924641756'
headers ={
python请求并解析json数据'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chr
ome/70.0.3538.25 Safari/537.36 Core/1.70.3741.400 QQBrowser/10.5.3863.400' }
res = (url,headers=headers)
#输出全部信息
# )
response_data = json.eplace('jQuery34102848205531413024_1584924641755(','')[:-1])
#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
# print(response_data.keys())
"""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
print(json.loads(reponse_data['data']).keys())
结果:
dict_keys(['lastUpdateTime', 'chinaTotal', 'chinaAdd', 'isShowAdd', 'showAddSwitch',
'areaTree', 'chinaDayList', 'chinaDayAddList', 'dailyNewAddHistory', 'dailyHistory',
'wuhanDayList', 'articleList'])
lastUpdateTime是最新更新时间,chinaTotal是全国疫情总数,chinaAdd是全国新增数据,
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
"""
areaTree_data = json.loads(response_data['data'])['areaTree']
temp=json.loads(response_data['data'])
# print(temp.keys())
# print(areaTree_data[0].keys())
"""
获取上⼀级字典⾥的areaTree
然后查看⾥⾯中国键值
print(areaTree_data[0].keys())
dict_keys(['name', 'today', 'total', 'children'])
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
print(areaTree_data[0]['children'])
这⾥⾯是
name是地区名称,today是今⽇数据,total是总数,children是市级数据,
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,
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),
这些就是我们需要的数据
"""
# print(areaTree_data[0]['children'])
# for province_data in areaTree_data[0]['children']:
# print(province_data)
ds= temp['lastUpdateTime']
details=[]
for pro_infos in areaTree_data[0]['children']:
province_name = pro_infos['name'] # 省名
for city_infos in pro_infos['children']:
city_name = city_infos['name'] # 市名
confirm = city_infos['total']['confirm']#历史总数
confirm_add = city_infos['today']['confirm']#今⽇增加数
heal = city_infos['total']['heal']#治愈
dead = city_infos['total']['dead']#死亡
# print(ds,province_name,city_name,confirm,confirm_add,heal,dead)
details.append([ds,province_name,city_name,confirm,confirm_add,heal,dead])
return details
单独测试⽅法:
# d=get_details()
# print(d)
②此⽅法⽤于爬取历史详细数据
import requests
import json
import time
def get_history():
url = 'view.inews.qq/g2/getOnsInfo?name=disease_other&callback=jQuery341026745307075030955_1584946267054&_=1584946267055'
headers ={
'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' }
res = (url,headers=headers)
# )
response_data = json.eplace('jQuery341026745307075030955_1584946267054(','')[:-
1])
# print(response_data)
data = json.loads(response_data['data'])
# print(data.keys())
chinaDayList = data['chinaDayList']#历史记录
chinaDayAddList = data['chinaDayAddList']#历史新增记录
history = {}
for i in chinaDayList:
ds = '2021.' + i['date']#时间
tup = time.strptime(ds,'%Y.%m.%d')
ds = time.strftime('%Y-%m-%d',tup)#改变时间格式,插⼊数据库
confirm = i['confirm']
suspect = i['suspect']
heal = i['heal']
dead = i['dead']
history[ds] = {'confirm':confirm,'suspect':suspect,'heal':heal,'dead':dead}
for i in chinaDayAddList:
ds = '2021.' + i['date']#时间
tup = time.strptime(ds,'%Y.%m.%d')
ds = time.strftime('%Y-%m-%d',tup)#改变时间格式,插⼊数据库
confirm_add = i['confirm']
suspect_add = i['suspect']
heal_add = i['heal']
dead_add = i['dead']
history[ds].update({'confirm_add':confirm_add,'suspect_add':suspect_add,'heal_add':heal_add,'dead_add':dead_add})
return history
单独测试此⽅法:
# h=get_history()
# print(h)
③此⽅法⽤于数据库的连接与关闭:
数据库系统概论设计存储过程题import time
import pymysql
import traceback
def get_conn():
"""
:return: 连接,游标
"""
# 创建连接
conn = t(host="127.0.0.1",
user="root",
password="000429",
db="mydb",
charset="utf8")
# 创建游标
cursor = conn.cursor() # 执⾏完毕返回的结果集默认以元组显⽰
return conn, cursor
def close_conn(conn, cursor):
if cursor:
cursor.close()
if conn:
conn.close()
④此⽅法⽤于更新并插⼊每⽇详细数据到数据库表:
def update_details():
"""
更新 details 表
:
return:
"""
cursor = None
conn = None
try:
li = get_details()
conn, cursor = get_conn()
sql = "insert into details(update_time,province,city,confirm,confirm_add,heal,dead) values(%s,%s,%s,%s,%s,%s,%s)" sql_query = 'select %s=(select update_time from details order by id desc limit 1)' #对⽐当前最⼤时间戳
if not cursor.fetchone()[0]:
print(f"{time.asctime()}开始更新最新数据")
成品免费网站源码for item in li:
connmit() # 提交事务 update delete insert操作
print(f"{time.asctime()}更新最新数据完毕")
else:
print(f"{time.asctime()}已是最新数据!")
except:
traceback.print_exc()
finally:
close_conn(conn, cursor)
单独测试能否插⼊数据到details表:
update_details()
⑤此⽅法⽤于插⼊历史数据到history表
def insert_history():
"""
插⼊历史数据
:return:
"""
cursor = None
conn = None
try:
dic = get_history()
print(f"{time.asctime()}开始插⼊历史数据")
conn, cursor = get_conn()
sql = "insert into history values(%s,%s,%s,%s,%s,%s,%s,%s,%s)"
for k, v in dic.items():
# item 格式 {'2021-01-13': {'confirm': 41, 'suspect': 0, 'heal': 0, 'dead': 1}
<("suspect_add"), v.get("heal"), v.get("heal_add"),
<("dead"), v.get("dead_add")])
connmit() # 提交事务 update delete insert操作
print(f"{time.asctime()}插⼊历史数据完毕")
except:
traceback.print_exc()
finally:
close_conn(conn, cursor)
单独测试能否插⼊数据到history表:
# insert_history()
⑥此⽅法⽤于根据时间来更新历史数据表的内容:
def update_history():
"""
更新历史数据
:return:
"""
cursor = None
conn = None
try:
dic = get_history()
pipeline发布dotnetprint(f"{time.asctime()}开始更新历史数据")
conn, cursor = get_conn()
sql = "insert into history values(%s,%s,%s,%s,%s,%s,%s,%s,%s)"
sql_query = "select confirm from history where ds=%s"
for k, v in dic.items():
# item 格式 {'2020-01-13': {'confirm': 41, 'suspect': 0, 'heal': 0, 'dead': 1}
if ute(sql_query, k):
<("suspect_add"), v.get("heal"), v.get("heal_add"),
<("dead"), v.get("dead_add")])
connmit() # 提交事务 update delete insert操作
print(f"{time.asctime()}历史数据更新完毕")
except:
traceback.print_exc()
finally:
close_conn(conn, cursor)
单独测试更新历史数据表的⽅法:
# 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):
powermill怎么读create table history(
ds datetime not null comment '⽇期',
confirm int(11) default null comment '累计确诊',
confirm_add int(11) default null comment '当⽇新增确诊',
suspect int(11) default null comment '剩余疑似',
suspect_add int(11) default null comment '当⽇新增疑似',
heal int(11) default null comment '累计治愈',
heal_add int(11) default null comment '当⽇新增治愈',
dead int(11) default null comment '累计死亡',
dead_add int(11) default null comment '当⽇新增死亡',
primary key(ds) using btree
)engine=InnoDB DEFAULT charset=utf8mb4;
oracle节点create table details(
id int(11) not null auto_increment,
update_time datetime default null comment '数据最后更新时间',
province varchar(50) default null comment '省',
city varchar(50) default null comment '市',
confirm int(11) default null comment '累计确诊',
confirm_add int(11) default null comment '新增确诊',
heal int(11) default null comment '累计治愈',
dead int(11) default null comment '累计死亡',
primary key(id)
)engine=InnoDB default charset=utf8mb4;
Tomorrowthe birds will singing.
到此这篇关于Python爬取腾讯疫情实时数据并存储到mysql数据库的⽂章就介绍到这了,更多相关Python爬取数据存储到mysql数据库内容请搜索以前的⽂章或继续浏览下⾯的相关⽂章希望⼤家以后多多⽀持!
版权声明:本站内容均来自互联网,仅供演示用,请勿用于商业和其他非法用途。如果侵犯了您的权益请与我们联系QQ:729038198,我们将在24小时内删除。
发表评论