爬取全部的校园新闻

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

代码：

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 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_0403/11147.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))

效果:

2.从列表页的url获取新闻url：列表append(字典) alist

主要代码：

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)

效果:

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

主要代码：

 

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(101,111):
    listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    allnews.extend(alist(listUrl))
    len(allnews)

newsdf = pd.DataFrame(allnews)
print(newsdf)

运行效果：

4.设置合理的爬取间隔

import random
import time
for i in range(5):
    print(i)
    time.sleep(random.random()*3)

效果：

运行代码：

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csv或excel文件 

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

保存到数据库

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

具体代码：

import pandas as pd
s2 = pd.Series(anews(newsUrl))#一维数组对象
print(s2)
newsdf = pd.DataFrame(allnews)#表格型的数据结构
print(newsdf)
print(newsdf.sort_values(by=['newsDT'],ascending=False))#按更新时间降序排列
print(newsdf.sort_index(by=['newsClick'],ascending=False))#按点击量降序排列

newsdf.to_csv(r'gzccnews.csv')
import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
    newsdf.to_sql('gzccnewsdb',db)
with sqlite3.connect('gzccnewsdb.sqlite') as db:
    df2 = pandas.read_sql_query('SELECT * FROM gzccnewsdb',con=db)
print(df2[df2['newsClick']>385])

结果：
csv:

数据库：