【大数据作业七】爬取全部的校园新闻

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

1.从新闻url获取新闻详情：字典,anews

主要代码：

 1 import requests
 2 from bs4 import BeautifulSoup
 3 from datetime import datetime
 4 import re
 5 def click(url):
 6     id=re.findall('(\d{1,5})',url)[-1]
 7     clickUrl='http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id)
 8     resClick=requests.get(clickUrl)
 9     newsClick=int(resClick.text.split('.html')[-1].lstrip("('").rstrip("');"))
10     return newsClick
11 def newsdt(showinfo):
12     newsDate=showinfo.split()[0].split(":")[1]
13     newsTime=showinfo.split()[1]
14     newsDT=newsDate+' '+newsTime
15     dt=datetime.strptime(newsDT,'%Y-%m-%d %H:%M:%S')
16     return dt
17 def anews(url):
18     newsDetail={}
19     res=requests.get(url)
20     res.encoding='utf-8'
21     soup=BeautifulSoup(res.text,'html.parser')
22     newsDetail['nenewsTitle']=soup.select('.show-title')[0].text
23     showinfo=soup.select('.show-info')[0].text
24     newsDetail['newsDT']=newsdt(showinfo)
25     newsDetail['newsClick']=click(newsUrl)
26     return newsDetail
27 newsUrl='http://news.gzcc.cn/html/2005/xiaoyuanxinwen_0710/4.html'
28 anews(newsUrl)
29 res = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
30 res.encoding='utf-8'
31 soup = BeautifulSoup(res.text,'html.parser')
32 for news in soup.select('li'):
33     if len(news.select('.news-list-title'))>0:
34         newsUrl=news.select('a')[0]['href']
35         print(anews(newsUrl))

View Code

运行结果:

2.从列表页的url获取新闻url：列表append(字典) alist

主要代码：

 1 listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/'
 2 res=requests.get(listUrl)
 3 res.encoding='utf-8'
 4 soup = BeautifulSoup(res.text,'html.parser')
 5 newsList=[]
 6 for news in soup.select('li'):
 7     if len(news.select('.news-list-title'))>0:
 8         newsUrl=news.select('a')[0]['href']
 9         newsDesc=news.select('.news-list-description')[0].text
10         newsDict=anews(newsUrl)
11         newsDict['description']=newsDesc
12         newsList.append(newsDict)
13 newsList

View Code

运行结果：

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：

 1 def alist(url):
 2     res=requests.get(listUrl)
 3     res.encoding='utf-8'
 4     soup = BeautifulSoup(res.text,'html.parser')
 5     newsList=[]
 6     for news in soup.select('li'):
 7         if len(news.select('.news-list-title'))>0:
 8             newsUrl=news.select('a')[0]['href']
 9             newsDesc=news.select('.news-list-description')[0].text
10             newsDict=anews(newsUrl)
11             newsDict['description']=newsDesc
12             newsList.append(newsDict)
13     return newsList
14 listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/'
15 alist(listUrl)
16 
17 allnews=[]
18 for i in range(101,111):
19     listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
20     allnews.extend(alist(listUrl))
21 len(allnews)