爬取新闻列表

Posted 2020-10-10 哥哥让你爽

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。
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。
3. 获取所有新闻列表页的网址，调用上述函数。
4. 完成所有新闻的爬取。

   import requests
   from bs4 import BeautifulSoup
   
   res = requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
   res.encoding=‘utf-8‘
   soup = BeautifulSoup(res.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
           url=news.select(‘a‘)[0][‘href‘]
           time=news.select(‘.news-list-info‘)[0].contents[0].text
           dt=datetime.strptime(time,‘%Y-%m-%d‘)
           source=news.select(‘.news-list-info‘)[0].contents[1].text
   
           resd=requests.get(url)
           resd.encoding=‘utf-8‘
           soupd=BeautifulSoup(resd.text,‘html.parser‘)
   
           print(time,title,url)

   import requests
   from bs4 import BeautifulSoup
   from datetime import datetime
   
   gzccurl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
   res = requests.get(gzccurl)
   res.enconding=‘utf-8‘
   soup = BeautifulSoup(res.text,‘html.parser‘)
   
   for news in soup.select(‘li‘):
       if len (news.select(‘.news-list-litle‘))>0:
           title = news.select(‘.news-list-title‘)[0].text
           url = news.select(‘a‘)[0][‘href‘]
           time = news.select(‘.news-list-info‘)[0].contents[0].text
           dt = datetime.strptime(time,‘%Y-%m-%d‘)
           source = news.select(‘.news-list-info‘)[0].contents[1].text
   
           resd=requests.get(url)
           resd.encoding=‘utf-8‘
           soupd = BeautifulSoup(read.text,‘html.parser‘)
           detail = soupd.select(‘.show-content‘)[0].text
           click = requests.get(‘http://oa.gzcc.cn/api.php?op=count&id=8249&modelid=80‘).text.split(‘.‘)[-1].lstrip(html(‘‘))
   
           print(click)
           break

    

   import requests
   import re
   from bs4 import BeautifulSoup
   def getclick(newurl):    #函数：采用匹配方式，动态获取每一文章点击次数
       id=re.search(‘_(.*).html‘,newurl).group(1).split(‘/‘)[1]
       clickurl=‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(id)
       click=int(requests.get(‘http://oa.gzcc.cn/api.php?op=count&id=4662&modelid=80‘).text.split(‘.‘)[-1].lstrip("html(‘").rstrip("‘);"))
       return click
   
   def getonepages(eveylisturl):  #函数：每一页的每一文章
       res=requests.get(eveylisturl)
       res.encoding=‘utf-8‘
       soup=BeautifulSoup(res.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
               url=news.select(‘a‘)[0][‘href‘]#网址
               time=news.select(‘.news-list-info‘)[0].contents[0].text#时间
               bumen=news.select(‘.news-list-info‘)[0].contents[1].text#院系
               #txt=news.select(‘.news-list-description‘)[0].text #正文
   
               resd=requests.get(url)
               resd.encoding=‘utf-8‘
               soupd=BeautifulSoup(resd.text,‘html.parser‘)
               detail=soupd.select(‘.show-content‘)[0].text #获取正文
               count=getclick(url)      #调用函数获得文章的点击次数
     
               print(title,count)
   
   gzcc=‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘  #函数开头
   res=requests.get(gzcc)
   res.encoding=‘utf-8‘
   soup=BeautifulSoup(res.text,‘html.parser‘)
   
           
        
   n=int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘))
   pages=n//10+1                    #计算多少条多少页
   for i in range(2,5):
       pagesurl=‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
       getonepages(pagesurl)