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
from bs4 import BeautifulSoup


a=requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
a.encoding='utf-8'
soup=BeautifulSoup(a.text,'html.parser')
for xinwen in soup.select('li'):
    if len(xinwen.select('.news-list-description'))>0:
            title = xinwen.select('.news-list-description')[0].text
            url = xinwen.select('a')[0]['href']
            time = xinwen.select('.news-list-info')[0].contents[0].text
            neirong = xinwen.select('.news-list-description')[0].text
            adiv=requests.get(url)
            adiv.encoding='utf-8'
            soupdiv=BeautifulSoup(adiv.text,'html.parser')
            detail=soupdiv.select('.show-content')[0].text
            click = int(requests.get('http://oa.gzcc.cn/api.php?op=count&id=7821&modelid=80').text.split('.')[-1].lstrip("html('").rstrip("');"))
            print(time,title,neirong,url,detail,click)
            break

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
from bs4 import BeautifulSoup
import re
def getclick(1url):    
    id=re.search('_(.*).html',1url).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=8249&modelid=80').text.split('.')[-1].lstrip("html('").rstrip("');"))
    return click

def getonepages(eveylisturl):  
    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 
            url=news.select('a')[0]['href']
            time=news.select('.news-list-info')[0].contents[0].text
            bm=news.select('.news-list-info')[0].contents[1].text
            

            resd=requests.get(url)
            resd.encoding='utf-8'
            soupd=BeautifulSoup(resd.text,'html.parser')
            detail=soupd.select('.show-content')[0].text 
            count=getclick(url)      
  
            print(title,count)

hpk='http://news.gzcc.cn/html/xiaoyuanxinwen/'  
res=requests.get(hpk)
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')   
a=int(soup.select('.a1')[0].text.rstrip(''))
pages=a//10+1                   
for i in range(1,9):
    pagesurl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    getonepages(pagesurl)

3、获取所有新闻列表页的网址,调用上述函数。

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
url='http://news.gzcc.cn/html/xiaoyuanxinwen/'
res=requests.get(url)
res.encoding='utf-8'   
soup=BeautifulSoup(res.text,'html.parser')

        


def getonepage(listurl):
    res=requests.get(listurl)
    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')
        ar=soupd.select('.show-content')[0].text

        print(title,url,time,dt,source)

getonepage('http://news.gzcc.cn/html/xiaoyuanxinwen/index.html')
res.encoding='utf-8'   
soup=BeautifulSoup(res.text,'html.parser')
page= int(soup.select('.a1')[0].text.rstrip(''))//10+1
for i in range(2,page+1):
    listurl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    getonepage(listurl)

4、完成所有校园新闻的爬取工作。

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
url='http://news.gzcc.cn/html/xiaoyuanxinwen/'
res=requests.get(url)
res.encoding='utf-8'   
soup=BeautifulSoup(res.text,'html.parser')

        

def getclick(newurl):
    id = re.match('http://news.gzcc.cn/html/2017/xiaoyuanxinwen_(.*).html',newurl).groups()[0].split('/')[1]
    clickurl = 'http://oa.gzcc.cn/api.php?op=count&id=8301&modelid=80'.format(id)
    click = int(requests.get(clickurl).text.split('.')[-1].lstrip("html('").rstrip("');"))
    return(click)

def getonepage(listurl):
    res=requests.get(listurl)
    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')
        ar=soupd.select('.show-content')[0].text

        click=getclick(url)
        print(title,url,time,dt,source,click)

getonepage('http://news.gzcc.cn/html/xiaoyuanxinwen/index.html')
res.encoding='utf-8'   
soup=BeautifulSoup(res.text,'html.parser')
page= int(soup.select('.a1')[0].text.rstrip(''))//10+1
for i in range(2,4):
    listurl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    getonepage(listurl)

5、完成自己所选其他主题相应数据的爬取工作

import requests
import re
from bs4 import BeautifulSoup
from datetime import datetime

def getdetail(url):
    resd = requests.get(url)
    resd.encoding='utf-8'
    soupd = BeautifulSoup(resd.text,'html.parser')
    detail = soupd.select('.show-content')[0].text
    return(detail)
def getchick(newsurl):
    id = re.match('http://news.gzcc.cn/html/2017/meitishijie_(.*).html',newsurl).groups()[-1].split('/')[1]
    chickurl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id)
    chick = int(requests.get(chickurl).text.split('.')[-1].lstrip("html('").rstrip("');"))
    return(chick)
def getonepage(listurl):
    res = requests.get(listurl)
    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'] #路径
            time = news.select('.news-list-info')[0].contents[0].text #时间
            dt = datetime.strptime(time,'%Y-%m-%d')
        #正文
            detail = getdetail(url)
            chick = getchick(url)
            print(title,chick,url,dt,detail)

getonepage('http://news.gzcc.cn/html/meitishijie/index.html')
gzccurl = 'http://news.gzcc.cn/html/meitishijie/'
res = requests.get(gzccurl)
res.encoding='utf-8'
soup = BeautifulSoup(res.text,'html.parser')

page = int(soup.select('.a1')[0].text.rstrip(''))//10+1
for i in range(2,page+1):
    getonepage('http://news.gzcc.cn/html/meitishijie/{}.html'.format(i))

 

posted @ 2017-10-12 20:11  lesssharp  阅读(140)  评论(0编辑  收藏  举报