获取具体当地的疫情数据

此文件为一个脚本，肯定需要调用的
用户输入具体省份
txt = “广东”
getDetailCityInfo(txt) 即可。

#爬取具体的县数据需要丁香医生，但是丁香医生是需要手机微信看，只能通过手机下载fiddler证书然后设置代理本机WiFi，才能在电脑上面抓包
#后来发现了 pc端的页面，可以抓取到丁香医生的数据，数据在js里面，我们直接urllib.request整个网页，然后用bs4进行获取具体细节
import json
import time
import urllib.request
import urllib.parse
import json
import csv
import time
from bs4 import BeautifulSoup
def getDetailCityInfo(txt):
	headers = {
		'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
	}
	url = 'https://ncov.dxy.cn/ncovh5/view/pneumonia?from=timeline&isappinstalled=0'
	request = urllib.request.Request(url=url,headers=headers)
	# 获得响应内容
	response = urllib.request.urlopen(request)
	#拿到字符串类型了
	str1 = response.read().decode()
	soup = BeautifulSoup(str1,'lxml')
	res = soup.find('script',id="getAreaStat")
	# print(res.string)
	resStr = res.string
	resStr = str(resStr)
	# print(resStr)
	s = resStr.replace('try { window.getAreaStat = ',' ')
	s = s.replace('}catch(e){}',' ')
	cityData = json.loads(s)
	cityDataLength = len(cityData)
	# print("可查询省份有",cityDataLength)

	# txt = '天津'
	# txt的各个区县市
	detailCity = []
	for i in range(0,cityDataLength):
		# print(cityData[i])
		if(cityData[i]['provinceShortName'] == txt):
			# print(cityData[i]['cities'])
			detailCity.append(cityData[i]['cities'])
	# print("--------------------------------------------")

	finalDetailData = []

	# 这个北京有多少个具体的县市呢
	#
	detailCityLength = len(detailCity[0])
	# 由于最后一个的cityName是待明确地区，所以length-1，但有的不是，
	for i in range(0,detailCityLength):
		# print(detailCity[0][i])
		# print(detailCity[0][i]['cityName'])
		#因为current确诊太少 了，导致数据为0，我们就拿累计确诊人数吧
		# print(detailCity[0][i]['confirmedCount'])
		t =(detailCity[0][i]['cityName'],detailCity[0][i]['confirmedCount'])
		finalDetailData.append(t)
	# print(finalDetailData)
	return finalDetailData