Python实现实时数据采集新型冠状病毒数据实例

所属分类: 脚本专栏 / python 阅读数: 345
收藏 0 赞 0 分享

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)

以上就是Python实时数据采集-新型冠状病毒的详细内容,大家出门要做好安全措施,感谢对脚本之家的支持。

更多精彩内容其他人还在看

pandas的qcut()方法详解

这篇文章主要介绍了pandas的qcut()方法详解,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学习学习吧
收藏 0 赞 0 分享

从列表或字典创建Pandas的DataFrame对象的方法

这篇文章主要介绍了从列表或字典创建Pandas的DataFrame对象的方法,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学习学习吧
收藏 0 赞 0 分享

pandas.DataFrame的pivot()和unstack()实现行转列

这篇文章主要介绍了pandas.DataFrame的pivot()和unstack()实现行转列,小编觉得挺不错的,现在分享给大家,也给大家做个参考。一起跟随小编过来看看吧
收藏 0 赞 0 分享

pandas中的series数据类型详解

这篇文章主要介绍了pandas中的series数据类型详解,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学习学习吧
收藏 0 赞 0 分享

pandas 时间格式转换的实现

这篇文章主要介绍了pandas 时间格式转换的实现,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学习学习吧
收藏 0 赞 0 分享

python中时间、日期、时间戳的转换的实现方法

这篇文章主要介绍了python中时间、日期、时间戳的转换的实现方法,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学习学习吧
收藏 0 赞 0 分享

pandas进行时间数据的转换和计算时间差并提取年月日

这篇文章主要介绍了pandas进行时间数据的转换和计算时间差并提取年月日,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学习学习吧
收藏 0 赞 0 分享

详解将Pandas中的DataFrame类型转换成Numpy中array类型的三种方法

这篇文章主要介绍了详解将Pandas中的DataFrame类型转换成Numpy中array类型的三种方法,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学习学习吧
收藏 0 赞 0 分享

python和c语言的主要区别总结

在本篇文章里小编给各位整理了关于python和c语言的主要区别的相关知识帖内容,有需要的朋友们学习阅读下。
收藏 0 赞 0 分享

选择Python写网络爬虫的优势和理由

在本篇文章里小编给各位整理了一篇关于选择Python写网络爬虫的优势和理由以及相关代码实例,有兴趣的朋友们阅读下吧。
收藏 0 赞 0 分享
查看更多