作业：爬取全部的校园新闻

这个作业的要求来自于：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE2/homework/2941。

---

1.从新闻url获取新闻详情： 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]
    newDT = newsDate+' '+newsTime
    dt = datetime.strptime(newDT,'%Y-%m-%d %H:%M:%S')
    return dt

def anews(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/2019/xiaoyuanxinwen_0404/11155.html'
anews(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.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)
print(newsList)

　　

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

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(77,87):
    listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))
len(allnews)
print(allnews)

 

4.设置合理的爬取间隔

 

allnews=[]
for i in range(77，87):
    listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))
len(allnews)

pd.Series(anews)
newsdf=pd.DataFrame(allnews)
for i in range(5):
    print(i)
    time.sleep(random.random()*3)        
    print(newsdf)

 

5.用pandas做简单的数据处理并保存

保存到csv或excel文件

保存到数据库

import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
    newsdf.to_sql('gzccnewsdb',db)