完成国外疫情信息的获取

数据采集/GrapSpider.py

@@ -14,6 +14,10 @@ class Spider():
         self.news=[]
         #网站消息更新时间
         self.modifytime=''
+        #国外疫情信息
+        self.foreignCountry=[]
+        #国内疫情信息
+        self.provinces=[]
 
 
     # 获取实时新闻
@@ -66,7 +70,7 @@ class Spider():
         timestr = time.strftime("%Y-%m-%d %H:%M:%S", localt)
 
         self.modifytime=timestr
-        print(timestr)
+
 
     # 获取国内疫情
     def grapchina(self):
@@ -111,6 +115,8 @@ class Spider():
                 cityinfo.deadCount=cj['deadCount']
                 province.cities.append(cityinfo)
             provinces.append(province)
+
+        self.provinces=provinces
         return provinces
 
 
@@ -124,7 +130,27 @@ class Spider():
         #查找数据
         tag=soup.find('script',attrs={'id':'getListByCountryTypeService2true'})
         yiqinginfo=str(tag)
-
+        # 使用正则表达式匹配
+        results = re.findall(r'(\{"id".*?"showRank".*?\})', yiqinginfo)
+        all_countries = []
+        for item in results:
+            country = ForeignCountry()
+            itemJson = json.loads(item)
+            country.provinceName = itemJson['provinceName']
+            country.provinceShortName = itemJson['provinceShortName']
+            country.currentConfirmedCount=int(itemJson['currentConfirmedCount'])
+            country.confirmedCount = int(itemJson['confirmedCount'])
+            country.suspectedCount = int(itemJson['suspectedCount'])
+            country.curedCount = int(itemJson['curedCount'])
+            country.deadCount = int(itemJson['deadCount'])
+            country.deadRate = float(itemJson['deadRate'])
+            country.countryShortCode = itemJson['countryShortCode']
+            country.countryFullName = itemJson['countryFullName']
+            country.continents = itemJson['continents']
+            all_countries.append(country)
+
+        self.foreignCountry=all_countries
+        return all_countries
 
 
 #news类用来存储实时新闻的信息
@@ -184,3 +210,22 @@ class Provinceinfo():
         self.deadCount = 0
         # 各个市的疫情信息，通过一个字典存储
         self.cities = []
+
+#国外疫情信息存储类
+class ForeignCountry:
+    def __init__(self):
+        self.provinceName = ''
+        self.provinceShortName = ''
+        self.currentConfirmedCount = 0
+        self.confirmedCount = 0
+        self.suspectedCount = 0
+        self.curedCount = 0
+        self.deadCount = 0
+        self.deadRate = 0
+        self.countryShortCode = ''
+        self.countryFullName = ''
+        self.continents = ''
+    def __str__(self):
+        return '%s,当前确诊:%d,累计确诊:%d,疑似:%d, 治愈: %d, 死亡: %d, 死亡率: %s,洲: %s'\
+        %(self.provinceName,self.currentConfirmedCount,self.confirmedCount,
+         self.suspectedCount, self.curedCount, self.deadCount, self.deadRate,self.continents)

数据采集/grapdata.py

@@ -8,10 +8,7 @@ def main():
     #网站首页
     url="https://ncov.dxy.cn/ncovh5/view/pneumonia"
     spider=Spider(url)
-    provinces= spider.grapchina()
-    print(provinces[5].provinceName)
-    for i in range(len(provinces[4].cities)):
-        print(provinces[4].cities[i])
+    spider.grapforign()