爬取校园网新闻

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。

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.完成所有校园新闻的爬取工作。

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



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)

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:
            t = news.select('.news-list-title')[0].text
            a = news.select('a')[0]['href']
            d = news.select('.news-list-info')[0].contents[0].text
            dt = datetime.strptime(d,'%Y-%m-%d')
            s = news.select('.news-list-info')[0].contents[1].text
            #print(t,a,d,s)

            resl = requests.get(a)
            resl.encoding = 'utf-8'
            soupl = BeautifulSoup(resl.text,'html.parser')
            ar = soupl.select('.show-content')[0].text
            click = getclick(a)
            print(click,t,dt,s,a)
getonepage('http://news.gzcc.cn/html/xiaoyuanxinwen/index.html')

res=requests.get('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)

　　

转载于:https://www.cnblogs.com/yingja-hong/p/7658144.html