【大数据】爬取全部的校园新闻

1.从新闻url获取新闻详情： 字典,anews

def anews(url):
    newsDetail={}
    res=requests.get(url)
    res.encoding='utf-8'
    soup=BeautifulSoup(res.text,'html.parser')
    newsDetail['newsTitle']=soup.select('.show-title')[0].text
    showinfo=soup.select('.show-info')[0].text
    newsDetail['newsDT']=newsdt(showinfo)
    newsDetail['newsClick']=click(url)
    return newsDetail

 

 

2.从列表页的url获取新闻url：列表append(字典) alist

listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/'
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']
            newsDesc=news.select('.news-list-description')[0].text
            newsDict=anews(newsUrl)
            newsDict['description']=newsDesc
            newsList.append(newsDict)
newsList

　　

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

allnews = []
for i in range(2,12):
    listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))
    
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

import time
import random
random.random()*3

　　

5.用pandas做简单的数据处理并保存

保存到csv或excel文件 

newsdf.to_csv(r'F:\duym\爬虫\gzccnews.csv')

newsdf=pd.DataFrame(allnews)
newsdf

#排序
newsdf.sort_index(by=['newsClick'],ascending=False)

#吧数据存到csv文件中
newsdf.to_csv(r'F:\hh\aa.csv')

　

保存到数据库

import pandas
with sqlite3.connect('gzccnewsdb.sqlite')as db:
    df2=pandas.read_sql_query('SELECT * FROM gzccnewsdb',con=db)

#输出点击数超过385的新闻
df2[df2['newsClick']>385]

完整代码：

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
import sqlite3
import pandas as pd
import time
import pandas
import random

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

#获取新闻时间
def newsdt(showinfo):
    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

#获取新闻信息
def anews(url):
    newsDetail={}
    res=requests.get(url)
    res.encoding='utf-8'
    soup=BeautifulSoup(res.text,'html.parser')
    newsDetail['newsTitle']=soup.select('.show-title')[0].text
    showinfo=soup.select('.show-info')[0].text
    newsDetail['newsDT']=newsdt(showinfo)
    newsDetail['newsClick']=click(url)
    return newsDetail

def alist(url):
    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']
            newsDest=news.select('.news-list-description')[0].text
            newsDict=anews(newsUrl)
            newsDict['description']=newsDest
            newsList.append(newsDict)
    return newsList


#url= 'http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0404/11155.html'
#anews(url)

url = 'http://news.gzcc.cn/html/xiaoyuanxinwen'
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:
        newsUrl=news.select('a')[0]['href']
       
allnews = []

#获取新闻第2-第12页的所有新闻
for i in range(2,12):
    listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))    
pd.Series(allnews)

#保存文件
newsdf=pd.DataFrame(allnews)
newsdf.sort_index(by=['newsClick'],ascending=False)
newsdf.to_csv(r'F:\hh\bb.csv')

#输出点击数大于385的新闻
with sqlite3.connect('gzccnewsdb.sqlite')as db:
    df2=pandas.read_sql_query('SELECT * FROM gzccnewsdb',con=db)
df2[df2['newsClick']>385]

结果如图：

                        输出到csv文件中的数据

　　

输出点击数超过385的新闻数据