数据结构化与保存

def writeNewsDatail(content):
    f=open(‘gzccnews1.txt‘,‘a‘,encoding=‘utf-8‘)
    f.write(content)
    f.close()

import pandas
import requests
import re
from bs4 import BeautifulSoup
from datetime import datetime
 
def writeNewsDatail(content):
    f=open(‘gzccnews1.txt‘,‘a‘,encoding=‘utf-8‘)
    f.write(content)
    f.close()#dui
 
# 获取新闻点击次数
def getNewsId(url):#dui
    newsId = re.findall(r‘\_(.*).html‘, url)[0][-4:]
    clickUrl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newsId)
    clickRes = requests.get(clickUrl)
    # 利用正则表达式获取新闻点击次数
    clickCount = int(re.search("hits‘\).html\(‘(.*)‘\);", clickRes.text).group(1))
    return clickCount
 
def getNewsDetail(newsUrl):#dui
    # 读取新闻细节
    resd = requests.get(newsUrl)
    resd.encoding = "utf-8"
    soupd = BeautifulSoup(resd.text, ‘html.parser‘)#打开详情页并解析
 
    news={}
    news[‘title‘]=soupd.select(‘.show-title‘)[0].text
    info = soupd.select(".show-info")[0].text  # info相关内容
    news[‘dt‘]=datetime.strptime(info.lstrip(‘发布时间:‘)[0:19],‘%Y-%m-%d %H:%M:%S‘)
    if info.find(‘来源：‘)>0:#作者：审核：来源：摄影：一样处理
        news[‘source‘]=info[info.find(‘来源：‘):].split()[0].lstrip(‘来源：‘)
    else:
        news[‘source‘]=‘none‘
 
    news[‘content‘] = soupd.select(".show-content")[0].text.strip()  # 正文
 
    news[‘count‘] = getNewsId(newsUrl)
    news[‘newsUrl‘]=newsUrl
    return(news)
   
def getListPage(pageUrl):#dui
    res=requests.get(pageUrl)
    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].attrs[‘href‘]  # 链接
            newsList.append(getNewsDetail(newsUrl)) #把详情的字典插进列表(一个新闻是字典 多个新闻是列表)
    return newsList
 
def getPageN(): #新闻列表页的总页数
    res=requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
    res.encoding=‘utf-8‘
    soup=BeautifulSoup(res.text,‘html.parser‘)
    n=int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘))
    return(n//10+1)
 
newsTotal=[]
n=getPageN()
p= [2, n]
for  i in p:
    listPageUrl = "http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i)
    print(listPageUrl)
    newsTotal.extend(getListPage(listPageUrl))
for news in newsTotal:
    print(news)

import pandas
df=pandas.DataFrame(newsTotal)

df.to_excel("0416.xlsx")

print(df[[‘count‘,‘title‘,‘source‘]][0:6])
print(df[(df[‘count‘]>3000)&(df[‘source‘]==‘学校综合办‘)])
print(df[(df[‘source‘]==‘国际学院‘)|(df[‘source‘]==‘学生处‘)])