爬取全部的校園新聞

作業要求來自：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE2/homework/2941

1.從新聞url擷取新聞詳情： 字典,anews

2.從清單頁的url擷取新聞url：清單append(字典) alist

3.生成所頁清單頁的url并擷取全部新聞 ：清單extend(清單) allnews

*每個同學爬學号尾數開始的10個清單頁

4.設定合理的爬取間隔

源代碼如下：

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

#從新聞url擷取新聞詳情： 字典,anews
def click(url):#擷取點選次數
    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):#轉換成datetime類型
    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):#擷取校園的點選次數，時間，标題
    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):#從清單頁的url擷取新聞url：清單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']#擷取連結
           #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(' 下一頁 '))#擷取校園新聞的頁數，去除多餘的東西

allnews=[]
for i in range(96,106):#擷取96~106頁數的校園新聞的各項資訊，生成所頁清單頁的url并擷取全部新聞 ：清單extend(清單) allnews
    listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))    
    
    for i in range(5):#設定合理的爬取間隔
        time.sleep(random.random()*3)
        
newsdf = pd.DataFrame(allnews)#轉化為二維的表格型資料結構
newsdf      

運作結果如下圖所示：

5.用pandas做簡單的資料處理并儲存

儲存到csv或excel檔案 

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

運作結果：

成功儲存到了F盤中的gzccnews5.csv中

儲存到資料庫

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]      

 運作結果：