爬取所有校园新闻

Posted 2020-10-10 祝朝荣

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

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
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‘)

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,ar)
        break

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(‘条‘))//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(‘条‘))//10+1
for i in range(2,4):
    listurl=‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    getonepage(listurl)