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
0
投稿
猜你喜欢
- 最近在查看asp之家的访客统计时,发现访客使用firefox浏览器的占了10%-15%,而大部分的访客使用的是IE6,呵呵我也是用IE6。而
- 1.获取所有数据库名: SELECT Name FROM Master..SysDatabases ORDER BY Name 2.获取所有
- 目录1.函数的介绍2.函数的定义和调用3.函数的参数4.参数的分类4.1.位置参数4.2.关键字参数4.3.缺省参数4.4.不定长参数1.不
- 不知道算不算DW4的大BUG. DW4实际的运行如下: 读注册表中HKEY_CURRENT_USER/
- 有助于效率的类型选择1、使你的数据尽可能小最基本的优化之一是使你的数据(和索引)在磁盘上(并且在内存中)占据的空间尽可能小。这能给出巨大的改
- Microsoft建立了一种既灵活又强大的安全管理机制,它能够对用户访问SQL Server服务器系统和数据库的安全进行全面地管理。按照本文
- 任务1、将指定的十进制转换为二进制、八进制、十六进制二进制转换第一种和第二种写法:num=int(input('请输入一个十进制的整
- 前言ThinkPHP,是为了简化企业级应用开发和敏捷WEB应用开发而诞生的开源轻量级PHP框架。随着框架代码量的增加,一些潜在的威胁也逐渐暴
- 一直以来,Web 字体背着单调的恶名,因为想在网页上显示一种字体,该字体文件本身必须存在于用户的电脑中,由于这个限制,加上 Web 用户可能
- 神经网络玩得越久就越会尝试一些网络结构上的大改动。先说意图有两个模型:模型A和模型B。模型A的输出可以连接B的输入。将两个小模型连接成一个大
- 方法1: 将shell执行的结果保存到字符串def run_cmd(cmd): result_str='' process
- 1.请实现一个装饰器,把函数的返回值+100然后返回def wapper(func):def innner(*args,**kwargs):
- PS:这段时间有点不在状态,刚刚找回那个状态,那么我们继续曾经的梦想今天我们来补充一下文件的上传的几种方式:首先我们先补充的一个知识点:一、
- 要求安装:1.Python2.7z解压软件backup_2.py# Filename: backup_2.py'''
- 仿豆瓣分页原型(Javascript版)写了个分页的样式。自我感觉,这样的分页前后兼顾,对于用户的体验是蛮好使的Javascript分页代码
- 前言接口在面向对象编程中是经常使用的招式,也是体现多态很重要的手段。是的。Golang中也有接口这玩意儿。1.为什么需要接口?多数情况下,数
- 本文介绍了几种常用的python下载文件的方法,具体使用到了htttplib2,urllib等包,希望对大家有帮忙。1.简单文件下载使用ht
- 数组我们已经提到过,对象是无序数据的集合,而数组则是有序数据的集合,数组中的数据(元素)通过索引(从0开始)来访问,数组中的数据可以是任何的
- tensorflow作为google开源的项目,现在赶超了caffe,好像成为最受欢迎的深度学习框架。确实在编写的时候更能感受到代码的真实存
- 如何 在Access中选择指定日期前的记录?我知道,在Access中不能使用DateDiff,那么我们怎样才能选择指定日期前的若干记录呢?虽