From 81a00d68af8ea54374a1d9e670acdc8d355f78a5 Mon Sep 17 00:00:00 2001
From: egg23333 <806261011@qq.com>
Date: Thu, 13 Aug 2020 23:31:59 +0800
Subject: [PATCH] merge caigy

---
 国外概况class.py | 25 +++++++++++++++++++++++++
 新闻class.py       | 33 +++++++++++++++++++++++++++++++++
 爬新闻main.py     | 24 ++++++++++++++++++++++++
 爬概况main.py     | 34 ++++++++++++++++++++++++++++++++++
 4 files changed, 116 insertions(+)
 create mode 100644 国外概况class.py
 create mode 100644 新闻class.py
 create mode 100644 爬新闻main.py
 create mode 100644 爬概况main.py

diff --git a/国外概况class.py b/国外概况class.py
new file mode 100644
index 0000000..9eca84b
--- /dev/null
+++ b/国外概况class.py
@@ -0,0 +1,25 @@
+class summaryDataOut:
+    confirmed=0
+    died=0
+    curConfirm=0
+    cured=0
+    confirmedRelative=0
+    curedRelative=0
+    diedRelative=0
+    curConfirmRelative=0
+    relativeTime=0
+    time=''
+
+    def blankNum (self,object):
+        return ' '*(12-len(str(object)))
+
+    def PrintOut(self):
+        print("截至%s国外疫情概况："%self.time)
+        print("现有确诊：%d" % self.curConfirm, end=self.blankNum(self.curConfirm))
+        print("相对昨日新增：%d"%self.curConfirmRelative)
+        print("累计确诊：%d"%self.confirmed,end=self.blankNum(self.confirmed))
+        print("相对昨日新增：%d"%self.confirmedRelative)
+        print("累计治愈：%d"%self.cured,end=self.blankNum(self.cured))
+        print("相对昨日新增：%d"%self.curedRelative)
+        print("累计死亡：%d"%self.died,end=self.blankNum(self.died))
+        print("相对昨日新增：%d"%self.diedRelative)
diff --git a/新闻class.py b/新闻class.py
new file mode 100644
index 0000000..d6d41e2
--- /dev/null
+++ b/新闻class.py
@@ -0,0 +1,33 @@
+import requests
+import json
+from bs4 import BeautifulSoup
+import re
+import time
+
+
+class InNews:
+    def __init__(self):
+        self.eventDescription=''
+        self.eventTime=''
+        self.eventUrl=''
+        self.siteName=''
+        self.Artical=''
+
+    def printArtical(self):
+        req = requests.get(self.eventUrl)
+        content = req.content.decode('utf-8')
+        contentBs = BeautifulSoup(content, 'html.parser')
+        tag = contentBs.findAll('span', attrs={'class': 'bjh-p'})
+        artical = ''
+        for item in tag:
+            artical=artical+('    '+item.get_text())+'\n'
+        return artical
+
+    def time(self):
+        ts = float(self.eventTime)
+        localt = time.localtime(ts)  # 转换为localtime对象
+        timestr = time.strftime("%Y-%m-%d %H:%M:%S", localt)  # 格式化
+        return(timestr)
+
+    def toString(self):
+        print('%s\n原网：%s\n%s\n\n%s\n%s'%(self.eventDescription,self.eventUrl,self.time(),self.printArtical(),self.siteName))
diff --git a/爬新闻main.py b/爬新闻main.py
new file mode 100644
index 0000000..189a733
--- /dev/null
+++ b/爬新闻main.py
@@ -0,0 +1,24 @@
+import requests
+import json
+from bs4 import BeautifulSoup
+import re
+from 新闻类 import InNews
+
+req = requests.get('https://opendata.baidu.com/data/inner?tn=reserved_all_res_tn&dspName=iphone&from_sf=1&dsp=iphone&resource_id=28565&alr=1&query=%E6%96%B0%E5%86%A0%E8%82%BA%E7%82%8E%E5%9B%BD%E5%A4%96%E7%96%AB%E6%83%85&cb=jsonp_1597232049116_92879')
+content = req.content.decode('utf-8')
+conDic = re.findall('\{.*\}',content)[0]
+results = json.loads(conDic)['Result'][0]['DisplayData']['result']['items']
+
+allNews=[]
+for news in results:
+    # print (news['eventUrl'])
+    inNews = InNews()
+    inNews.eventDescription=news['eventDescription']
+    inNews.eventTime=news['eventTime']
+    inNews.eventUrl=news['eventUrl']
+    inNews.siteName=news['siteName']
+    allNews.append(inNews)
+
+for news in allNews:
+    news.toString()
+    print('************'*6)
\ No newline at end of file
diff --git a/爬概况main.py b/爬概况main.py
new file mode 100644
index 0000000..9b6c46a
--- /dev/null
+++ b/爬概况main.py
@@ -0,0 +1,34 @@
+import requests
+import re
+from bs4 import BeautifulSoup
+import json
+
+from 国外总数据 import summaryDataOut
+
+# 获取数据
+req = requests.get ('https://voice.baidu.com/act/newpneumonia/newpneumonia/?from=osari_pc_3#tab4')
+content = req.content.decode('utf-8')
+soup = BeautifulSoup(content,'html.parser')
+
+# 过滤筛选
+tag = soup.find('script',attrs={'type':'application/json','id':'captain-config'})
+tagstr=tag.string   #标签转化为字符串
+tagdic=json.loads(tagstr)   #标签字符串转化为字典
+component=tagdic['component'][0]    #获得疫情状况字典
+time= component['mapLastUpdatedTime']   #字典中找出时间
+result = component['summaryDataOut']   #字典中找出'component'key下的'summaryDataOut'key内容
+
+# 存储
+OutData=summaryDataOut()
+
+OutData.confirmed=int(result['confirmed'])
+OutData.confirmedRelative=int(result['confirmedRelative'])
+OutData.cured=int(result['cured'])
+OutData.curedRelative=int(result['curedRelative'])
+OutData.died=int(result['died'])
+OutData.diedRelative=int(result['diedRelative'])
+OutData.curConfirm=int(result['curConfirm'])
+OutData.curConfirmRelative=int(result['curConfirmRelative'])
+OutData.time=time
+
+OutData.PrintOut()
\ No newline at end of file