爬取全部的校園新聞

1.從新聞url擷取新聞詳情：字典,anews

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
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
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
def anewsDate(url):
    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(newsUrl)
    return newsDetail
newsUrl='http://news.gzcc.cn/html/2005/xiaoyuanxinwen_0710/4.html'
anewsDate(newsUrl)
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']
        print(anews(newsUrl))

2.從清單頁的url擷取新聞url：清單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)

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

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

allnews=[]
for i in range(95,100):
    listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))
len(allnews)

4.設定合理的爬取間隔

import time

import random

time.sleep(random.random()*3)

5.用pandas做簡單的資料處理并儲存

儲存到csv或excel檔案

import pandas as pd
pd.DataFrame(data=newsList).to_csv('news.csv',encoding='utf_8_sig')

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

儲存到資料庫

import sqlite3

with sqlite3.connect('gzccnewsdb.sqlite') as db:

newsdf.to_sql('gzccnewsdb',db)