爬取全部的校园新闻

作业要求来自：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE2/homework/2941

1.从新闻url获取新闻详情： 字典,anews

2.从列表页的url获取新闻url：列表append(字典) alist

3.生成所页列表页的url并获取全部新闻 ：列表extend(列表) allnews

*每个同学爬学号尾数开始的10个列表页

4.设置合理的爬取间隔

源代码如下：

import requests
import re
from bs4 import BeautifulSoup
from datetime import datetime
import pandas as pd
import time
import random

#从新闻url获取新闻详情： 字典,anews
def click(url):#获取点击次数
    id=re.findall('(\d{1,5})',url)[-1]
    clickUrl='http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id)
    res=requests.get(clickUrl)
    newsClick=res.text.split('.html')[-1].lstrip("('").rstrip("');")
    return newsClick

def newsdt(showinfo):#转换成datetime类型
    newsDate=showinfo.split()[0].split(':')[1]
    newsTime=showinfo.split()[1]
    newsDT=newsDate+' '+newsTime
    dt=datetime.strptime(newsDT,'%Y-%m-%d %H:%M:%S')
    return dt


def new(url):#获取校园的点击次数，时间，标题
    newsDetail={}
    res=requests.get(url)
    res.encoding='utf-8'
    soup=BeautifulSoup(res.text,'html.parser')
    newsDetail['nenewsTitle']=soup.select('.show-title')[0].text
    showinfo=soup.select('.show-info')[0].text
    newsDetail['newsDT']=newsdt(showinfo)
    newsDetail['newsClick']=click(url)
    #newsDetail['newDesc']=soup.select('.news-list-description')[0].text
    return newsDetail


#listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/'

#print(soup)
def alist(url):#从列表页的url获取新闻url：列表append(字典) alist
    res=requests.get(listUrl)
    res.encoding='utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    newsList = []
    for news in soup.select('li'):
        if len(news.select('.news-list-title'))>0:
           newsUrl=news.select('a')[0]['href']#获取链接
           #print(newsUrl)
           newsDesc=news.select('.news-list-description')[0].text
           newsDict=new(newsUrl)
           newsDict['description']=newsDesc
           newsList.append(newsDict)
    return newsList
        #print(newsList)
        
        
#alist(listUrl)

i=int(soup.select('#pages')[0].text.split('..')[1].rstrip(' 下一页 '))#获取校园新闻的页数，去除多余的东西

allnews=[]
for i in range(96,106):#获取96~106页数的校园新闻的各项信息，生成所页列表页的url并获取全部新闻 ：列表extend(列表) allnews
    listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))    
    
    for i in range(5):#设置合理的爬取间隔
        time.sleep(random.random()*3)
        
newsdf = pd.DataFrame(allnews)#转化为二维的表格型数据结构
newsdf

运行结果如下图所示：

 

5.用pandas做简单的数据处理并保存

保存到csv或excel文件 

import sqlite3
newsdf.to_csv(r'F:\gzccnews.csv')

 

运行结果：

成功保存到了F盘中的gzccnews5.csv中

 

保存到数据库

import sqlite3
with sqlite3.connect('gzccnewsdb5.sqlite') as db:
    newsdf.to_sql('gzccnewsdb5',db)
with sqlite3.connect('gzccnewsdb5.sqlite') as db:
    df2=pd.read_sql_query('SELECT * FROM gzccnewsdb5',con=db)
    df2[df2['newsClick']>300]

 运行结果：