爬取所有校园新闻

1. 获取单条新闻的#标题#链接#时间#来源#内容 #点击次数，并包装成一个函数。

   import requests
   import re
   from bs4 import BeautifulSoup
   from datetime import datetime
   news='http://news.gzcc.cn/html/xiaoyuanxinwen/'
   res=requests.get(news)
   res.encoding='utf-8'
   soup=BeautifulSoup(res.text,'html.parser')
   
   def getdetail(url):
       resd=requests.get(url)
       resd.encoding='utf-8'
       soup=BeautifulSoup(resd.text,'html.parser')
       return(soup.select('.show-content')[0].text)
   def getclick(newsurl):
       id=re.match('http://news.gzcc.cn/html/2017/xiaoyuanxinwen_(.*).html',newsurl).groups()[0].split('/')[1]
       clickurl=('http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80').format(id)
       click=int(requests.get(clickurl).text.split('.')[-1].lstrip("html('").rstrip("');"))
       return(click)
       
   for news in soup.select ('li'):
       if len(news.select('.news-list-title'))>0:
           title=news.select('.news-list-title')[0].text #标题
           url=news.select('a')[0]['href'] #链接
           time=(news.select('.news-list-info')[0].contents[0].text) #时间
           dt=datetime.strptime(time,'%Y-%m-%d')
           where=(news.select('.news-list-info')[0].contents[1].text) #来源
           resd=requests.get(url)
           resd.encoding='utf-8'
           soup=BeautifulSoup(resd.text,'html.parser')
           detail=getdetail(url) #详情
           click=getclick(url)#点击次数
           print(title,url,time,dt,where,click)
   
           
           

2. 获取一个新闻列表页的所有新闻的上述详情，并包装成一个函数。

   import requests
   import re
   from bs4 import BeautifulSoup
   from datetime import datetime
   news='http://news.gzcc.cn/html/xiaoyuanxinwen/'
   res=requests.get(news)
   res.encoding='utf-8'
   soup=BeautifulSoup(res.text,'html.parser')
   
   def getdetail(url):
       resd=requests.get(url)
       resd.encoding='utf-8'
       soup=BeautifulSoup(resd.text,'html.parser')
       return(soup.select('.show-content')[0].text)
   def getclick(newsurl):
       id=re.search('_(.*).html',newsurl).group(1).split('/')[1]
       clickurl=('http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80').format(id)
       click=int(requests.get(clickurl).text.split('.')[-1].lstrip("html('").rstrip("');"))
       return(click)
   def getonepage(listurl):
       resd=requests.get(listurl)
       resd.encoding='utf-8'
       soup=BeautifulSoup(resd.text,'html.parser')
       
       for news in soup.select ('li'):
           if len(news.select('.news-list-title'))>0:
               title=news.select('.news-list-title')[0].text #标题
               a=news.select('a')[0]['href'] #链接
               time=(news.select('.news-list-info')[0].contents[0].text) #时间
               dt=datetime.strptime(time,'%Y-%m-%d')
               where=(news.select('.news-list-info')[0].contents[1].text) #来源
               detail=getdetail(a) #详情
               click=getclick(a)#点击次数
               print(title,time,dt,a,where,click)
   getonepage('http://news.gzcc.cn/html/xiaoyuanxinwen/index.html')
   res=requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
   res.encoding='utf-8'
   soup=BeautifulSoup(res.text,'html.parser')
   page=int(soup.select('.a1')[0].text.rstrip('条'))//10+1                 
   for i in range(2,page):
       gzccurl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
       getonepage(gzccurl)