Python实现实时数据采集新型冠状病毒数据实例
作者:angryTom 发布时间:2021-04-23 14:18:38
标签:Python,数据采集,新型冠状病毒
Python实时数据采集-新型冠状病毒
源代码 来源:https://github.com/Programming-With-Love/2019-nCoV
疫情数据时间为:2020.2.1
项目相关截图:
全国数据展示
国内数据展示
国外数据展示
查看指定区域详细数据
源代码,注意安装所需模块(例如 pip install 模块名)
import requests
import re
from bs4 import BeautifulSoup
from time import sleep
import json
from prettytable import ALL
from prettytable import PrettyTable
hubei = {}
guangdong = {}
zhejiang = {}
beijing = {}
shanghai = {}
hunan = {}
anhui = {}
chongqing = {}
sichuan = {}
shandong = {}
guangxi = {}
fujian = {}
jiangsu = {}
henan = {}
hainan = {}
tianjin = {}
jiangxi = {}
shanxi1 = {} # 陕西
guizhou = {}
liaoning = {}
xianggang = {}
heilongjiang = {}
aomen = {}
xinjiang = {}
gansu = {}
yunnan = {}
taiwan = {}
shanxi2 = {} # 山西
jilin = {}
hebei = {}
ningxia = {}
neimenggu = {}
qinghai = {} # none
xizang = {} # none
provinces_idx = [hubei, guangdong, zhejiang, chongqing, hunan, anhui, beijing,
shanghai, henan, guangxi, shandong, jiangxi, jiangsu, sichuan,
liaoning, fujian, heilongjiang, hainan, tianjin, hebei, shanxi2,
yunnan, xianggang, shanxi1, guizhou, jilin, gansu, taiwan,
xinjiang, ningxia, aomen, neimenggu, qinghai, xizang]
map = {
'湖北':0, '广东':1, '浙江':2, '北京':3, '上海':4, '湖南':5, '安徽':6, '重庆':7,
'四川':8, '山东':9, '广西':10, '福建':11, '江苏':12, '河南':13, '海南':14,
'天津':15, '江西':16, '陕西':17, '贵州':18, '辽宁':19, '香港':20, '黑龙江':21,
'澳门':22, '新疆':23, '甘肃':24, '云南':25, '台湾':26, '山西':27, '吉林':28,
'河北':29, '宁夏':30, '内蒙古':31, '青海':32, '西藏':33
}
def getTime(text):
TitleTime = str(text)
TitleTime = re.findall('<span>(.*?)</span>', TitleTime)
return TitleTime[0]
def getAllCountry(text):
AllCountry = str(text)
AllCountry = AllCountry.replace("[<p class=\"confirmedNumber___3WrF5\"><span class=\"content___2hIPS\">", "")
AllCountry = AllCountry.replace("<span style=\"color: #4169e2\">", "")
AllCountry = re.sub("</span>", "", AllCountry)
AllCountry = AllCountry.replace("</p>]", "")
AllCountry = AllCountry.replace("<span style=\"color: rgb(65, 105, 226);\">", "")
AllCountry = re.sub("<span>", "", AllCountry)
AllCountry = re.sub("<p>", "", AllCountry)
AllCountry = re.sub("</p>", "", AllCountry)
return AllCountry
def query(province):
table = PrettyTable(['地区', '确诊', '死亡', '治愈'])
for (k, v) in province.items():
name = k
table.add_row([name, v[0] if v[0] != 0 else '-', v[1] if v[1] != 0 else '-', v[2] if v[2] != 0 else '-'])
if len(province.keys()) != 0:
print(table)
else:
print("暂无")
def getInfo(text):
text = str(text)
text = re.sub("<p class=\"descText___Ui3tV\">", "", text)
text = re.sub("</p>", "", text)
return text
def is_json(json_str):
try:
json.loads(json_str)
except ValueError:
return False
return True
def ff(str, num):
return str[:num] + str[num+1:]
def main():
url = "https://3g.dxy.cn/newh5/view/pneumonia"
try:
headers = {}
headers['user-agent'] = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36' #http头大小写不敏感
headers['accept'] = 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8'
headers['Connection'] = 'keep-alive'
headers['Upgrade-Insecure-Requests'] = '1'
r = requests.get(url, headers=headers)
r.raise_for_status()
r.encoding = r.apparent_encoding
soup = BeautifulSoup(r.text,'lxml')
table = PrettyTable(['地区', '确诊', '死亡', '治愈'])
table.hrules = ALL
#### 截至时间
# TitleTime = getTime(soup.select('.title___2d1_B'))
print()
# print(" ",TitleTime + "\n")
while True:
r = requests.get("https://service-f9fjwngp-1252021671.bj.apigw.tencentcs.com/release/pneumonia")
json_str = json.loads(r.text)
if json_str['error'] == 0:
break
print("==================================全国数据==================================")
print()
print(" 确诊 " + str(json_str['data']['statistics']['confirmedCount']) + " 例"
+ " " + "疑似 " + str(json_str['data']['statistics']['suspectedCount']) + " 例"
+ " " + "死亡" + str(json_str['data']['statistics']['deadCount']) + " 例"
+ " " + "治愈" + str(json_str['data']['statistics']['curedCount']) + " 例\n")
print("==================================相关情况==================================")
print()
print("传染源:" + json_str['data']['statistics']['infectSource'])
print("病毒:" + json_str['data']['statistics']['virus'])
print("传播途径:" + json_str['data']['statistics']['passWay'])
print(json_str['data']['statistics']['remark1'])
print(json_str['data']['statistics']['remark2'] + "\n")
print("==================================国内情况==================================")
print()
json_provinces = re.findall("{\"provinceName\":(.*?)]}", str(soup))
idx = 0
for province in json_provinces:
if is_json(province):
pass
else:
province = "{\"provinceName\":" + province + "]}"
province = json.loads(province)
province_name = province['provinceShortName'] if province['provinceShortName'] != 0 else '-'
confirmed = province['confirmedCount'] if province['confirmedCount'] != 0 else '-'
suspected = province['suspectedCount'] if province['suspectedCount'] != 0 else '-'
cured = province['curedCount'] if province['curedCount'] != 0 else '-'
dead = province['deadCount'] if province['deadCount'] != 0 else '-'
table.add_row([province_name, confirmed, dead, cured])
map[province_name] = idx
idx = idx + 1
for city in province['cities']:
provinces_idx[map[province_name]][city['cityName']] = [city['confirmedCount'], city['deadCount'], city['curedCount']]
print(table)
print()
print("==================================国外情况==================================")
print()
json_provinces = str(re.findall("\"id\":949(.*?)]}", str(soup)))
json_provinces = json_provinces[:1] + "{\"id\":949" + json_provinces[2:]
json_provinces = json_provinces[:len(json_provinces) - 2] + json_provinces[len(json_provinces) - 1:]
provinces = json.loads(json_provinces)
table = PrettyTable(['地区', '确诊', '死亡', '治愈'])
for province in provinces:
confirmed = province['confirmedCount'] if province['confirmedCount'] != 0 else '-'
dead = province['deadCount'] if province['deadCount'] != 0 else '-'
cured = province['curedCount'] if province['curedCount'] != 0 else '-'
table.add_row([province['provinceName'], confirmed, dead, cured])
print(table)
print()
print("==================================最新消息==================================")
print()
idx = 0
for news in json_str['data']['timeline']:
if idx == 5:
break
print(news['pubDateStr'] + " " + news['title'])
idx = idx + 1
print()
key = input("请输入您想查询详细信息的省份,例如 湖北\n")
print()
if key in map.keys():
query(provinces_idx[map[key]])
else:
print("暂无相关信息")
print("\n欢迎提出各种意见")
except:
print("连接失败")
if __name__ == '__main__':
main()
sleep(30)
来源:https://www.php.cn/python-tutorials-442007.html


猜你喜欢
- 自定义序列的相关魔法方法允许我们自己创建的类拥有序列的特性,让其使用起来就像 python 的内置序列(dict,tuple,list,st
- 目录索引模型B+Tree索引选择索引优化索引选择性覆盖索引最左前缀原则+索引下推前缀索引唯一索引索引失效总结索引模型哈希表适用于只有等值查询
- ROC曲线绘制要点(仅记录)1、ROC用于度量模型性能2、用于二分类问题,如若遇到多分类也以二分类的思想进行操作。3、二分类问题代码实现(至
- 在上一篇Python接口自动化测试系列文章:Python接口自动化之浅析requests模块get请求,介绍了requests模块、get请
- MySQL插件式存储引擎是MySQL数据库服务器中的组件,负责为数据库执行实际的数据I/O操作,并能允许和强制执行面向特殊应用需求的特定特性
- xml_to_csv代码如下:import osimport globimport pandas as pdimport xml.etree
- MYSQL模块暂时还不支持python3.0以上的版本,由于我下载的python是3.0版本的,所以想要连接数据库只能利用其它的方法。Pyt
- “Be conservative in what you send; be liberal in what you accept. &nbs
- SQL查询输出,根据表内某字段为准,输出不重复记录,或删除掉重复的记录,保留所需要的记录。今儿见一朋友在蓝色里问起(查询不重复记录~),想想
- 在输出代码行中,加入“index=False”如下:m_pred_survived.to_csv("clasified.csv&q
- 1.展开服务器对象-->链接服务器-->右击"新建链接服务器"注意:必须以数据库管理员身份登录(通常也就是s
- 任务队列主线程:正在执行的代码,会生成函数调用栈。macro-task(宏任务,新名:task)包括:script(整体代码), setTi
- 本文实例讲述了Python高级变量类型。分享给大家供大家参考,具体如下:目标列表元组字典字符串公共方法变量高级知识点回顾Python 中数据
- 本文实例讲述了Python流行ORM框架sqlalchemy安装与使用。分享给大家供大家参考,具体如下:安装http://docs.sqla
- 一、使用css缩写使用缩写可以帮助减少你CSS文件的大小,更加容易阅读。css缩写的主要规则请参看《常用css缩写语法总结》,这里就不展开描
- 如下所示:import numpy as np a=np.random.randint(0,10,size=[3,3,3])print(a)
- 下面是在深度学习数据集处理过程中可能会用到的一个小程序,帮助我们根据图片文件的名字来分开图片:import osimport shutilp
- 是扫盲文章, 其实我自己就是个被扫对象, 为了学习W3C标准地设计网页, 想到写这个系列的文章当作自己的学习笔记, 不求每篇都写很好, 只求
- 01 实现背景1、PHPdict.txt,一个文本文件,包含可能的敏感目录后缀2、HackRequests模块,安全测试人员专用的类Requ
- 在浏览天极RSS订阅页面时,可以看到天极网为方便用户定制站点内容而设立的各个RSS频道。浏览者通过订阅不同的RSS(可同时订阅多个网站),就