1.选一个自己感兴趣的主题。网址为http://news.gzcc.cn/html/xiaoyuanxinwen/
2.网络上爬取相关的数据
import requests import re from bs4 import BeautifulSoup url='http://news.gzcc.cn/html/xiaoyuanxinwen/' res=requests.get(url) res.encoding='utf-8' soup=BeautifulSoup(res.text,'html.parser')#获取点击次数 def getclick(newurl):id=re.search('_(.*).html',newurl).group(1).split('/')[1]clickurl='http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id)click=int(requests.get(clickurl).text.split(".")[-1].lstrip("html('").rstrip("');"))return click#获取内容 def getonpages(listurl):res=requests.get(listurl)res.encoding='utf-8'soup=BeautifulSoup(res.text,'html.parser')for news in soup.select('li'):if len(news.select('.news-list-title'))>0:title=news.select('.news-list-title')[0].text #标题time=news.select('.news-list-info')[0].contents[0].text#时间url1=news.select('a')[0]['href'] #urlbumen=news.select('.news-list-info')[0].contents[1].text#部门description=news.select('.news-list-description')[0].text #描述resd=requests.get(url1)resd.encoding='utf-8'soupd=BeautifulSoup(resd.text,'html.parser')detail=soupd.select('.show-content')[0].textclick=getclick(url1) #调用点击次数print(title,click)count=int(soup.select('.a1')[0].text.rstrip("条")) pages=count//10+1 for i in range(2,4):pagesurl="http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i)getonpages(pagesurl)
3.进行文本分析,生成词云。
#coding:utf-8 import jieba from wordcloud import WordCloud import matplotlib.pyplot as plttext =open("D:\\cc.txt",'r',encoding='utf-8').read() print(text) wordlist = jieba.cut(text,cut_all=True) wl_split = "/".join(wordlist)mywc = WordCloud().generate(text) plt.imshow(mywc) plt.axis("off") plt.show()
4.结论,当前时间段主要新闻内容以新生入学和十九大的召开为主。