数据结构化与保存

    f = open(“content.txt”, ‘a‘, encoding=‘utf-8‘)
    f.write(content)
    f.close()

# 获取新闻详情
def getNewDetail(url):
    resd = requests.get(url)
    resd.encoding = ‘utf-8‘
    soupd = BeautifulSoup(resd.text, ‘html.parser‘)

    #单条新闻的详情
    news = {}
    news[‘title‘] = soupd.select(‘.show-title‘)[0].text
    info = soupd.select(‘.show-info‘)[0].text
    t = soupd.select(‘.show-info‘)[0].text[0:24].lstrip(‘发布时间:‘)
    news[‘dt‘] = datetime.strptime(t, ‘%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[‘content‘] = soupd.select(‘.show-content‘)[0].text.strip()
    writeNewsDetail(news[‘content‘])

    news[‘click‘] = getClickCount(url)
    news[‘url‘] = url
    return (news)

def getListPage(PageUrl):
    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:
            # 获取每条新闻链接
            a = news.select(‘a‘)[0].attrs[‘href‘]
            # 调用函数获取新闻详情页的内容
            #一个列表页所有单条新闻汇总
            newsList.append(getNewDetail(a))
    print(newsList)
    return (newsList)

newsTotal = []

fristPage = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
#第一页新闻汇总列表
newsTotal.extend(getListPage(fristPage))

#获取每页新闻的链接
n = getPageN()
for i in range(2,n):
    pageUrl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    #所有列表页的所有新闻汇总列表
    newsTotal.extend(getListPage(pageUrl))

import pandas

df = pandas.DataFrame(newsTotal)

df.to_excel(‘gzccnews.xlsx‘)

print(df[[‘clicks‘, ‘title‘, ‘source‘]].head(6))

print(df[(df[‘clicks‘] > 3000) & (df[‘source‘] == ‘学校综合办‘)])

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