数据结构化与保存

 f=open(‘test.txt‘,‘w‘,encoding=‘utf-8‘)
 f.write(content)
 f.close()

import requests
from  bs4 import  BeautifulSoup
from datetime import datetime
import re
import pandas

#获取新闻点击次数
def getClickCount(newsUrl):
    newsId = re.findall(‘\_(.*).html‘, newsUrl)[0].split(‘/‘)[1]
    clickUrl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newsId)
    clickStr = requests.get(clickUrl).text
    count = re.search("hits‘\).html\(‘(.*)‘\);",clickStr).group(1)
    return count

def Writecontent(content)
    f=open(‘test.txt‘,‘w‘,encoding=‘utf-8‘)
    f.write(content)
    f.close()

# 获取新闻的信息
def getNewDetail(url):
    resd = requests.get(url)
    resd.encoding = ‘utf-8‘
    soupd = BeautifulSoup(resd.text, ‘html.parser‘)
    news={}
    news[‘title‘] = soupd.select(‘.show-title‘)[0].text
    info = soupd.select(‘.show-info‘)[0].text
    news[‘time‘] = info.lstrip(‘发布时间:‘)[0:19]
    
    dt = datetime.strptime(time, ‘%Y-%m-%d %H:%M:%S‘)

    if info.find(‘来源：‘) > 0:
        news[‘source‘] = info[info.find(‘来源：‘):].split()[0].lstrip(‘来源：‘)
    else:
        news[‘source‘] = ‘none‘

    if info.find(‘作者：‘) > 0:
        news[‘author‘] = info[info.find(‘作者：‘):].split()[0].lstrip(‘作者：‘)
    else:
       news[‘author‘] = ‘none‘

   news[‘clickcount‘]=getClickCount(url);
    content=soupd.select(‘.show-content‘)[0].text.strip()
    writeNewsContent(content)

    return news
   

def getListPage(listPageUrl):
    res = requests.get(listPageUrl)
    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:
            # 获取新闻模块链接
            a = news.a.attrs[‘href‘]
            newsList.append(getNewsDetail(a))
    return newsList




url=‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
resn = requests.get(url)
resn.encoding = ‘utf-8‘
soupn = BeautifulSoup(resn.text,‘html.parser‘)
n = int(soupn.select(‘.a1‘)[0].text.rstrip(‘条‘))


for i in range(n,n+1):
    pageUrl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    getListPage(pageUrl)
    newsTotal.extend(getListPage(pageUrl))
df=pandas.DataFrame(newsTotal)
df.to_excel(‘test.xlsx‘)

df=pandas.DataFrame(newsTotal)

df.to_excel(‘test.xlsx‘)

soulist = [‘国际学院‘, ‘学生工作处‘]
print(df[df[‘source‘].isin(soulist)])