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

#獲取點擊次數
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 = int(re.search("hits‘\).html\(‘(.*)‘\);",clickStr).group(1))
    return count

# def writeNewsContent(content):
#     f = open(‘getNewsDetail.txt‘,‘a‘,encoding=‘utf-8‘)
#     f.write(content)
#     f.close()


# 獲取新聞詳情
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[‘dt‘] = datetime.strptime(info.lstrip(‘發布時間:‘)[0:19], ‘%Y-%m-%d %H:%M:%S‘)

    if info.find(‘來源：‘) > 0:
        news[‘source‘] = info[info.find(‘來源：‘):].split()[0].lstrip(‘來源：‘)
    else:
        news[‘source‘] = ‘none‘
    # if info.find(‘作者：‘) > 0:
    #     author = info[info.find(‘作者：‘):].split()[0].lstrip(‘作者：‘)
    # else:
    #     author = ‘none‘
    news[‘clickCount‘] = getClickCount(url)
    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:
            # 獲取新聞模塊鏈接
            a = news.a.attrs[‘href‘]
            # 調用函數獲取新聞正文
            newsList.append(getNewDetail(a))
    return newsList




# 首頁列表新聞
newsTotal = []
firstPageUrl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
newsTotal.extend(getListPage(firstPageUrl))


#計算總頁數
def getPageNum():
    resn = requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
    resn.encoding = ‘utf-8‘
    soupn = BeautifulSoup(resn.text, ‘html.parser‘)
    n = int(soupn.select(‘.a1‘)[0].text.rstrip(‘條‘))
    return (n // 10 + 1)

n = getPageNum()
for i in range(n,n+1):
    pageUrl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    newsTotal.extend(getListPage(pageUrl))
    # print(newsTotal)

df = pandas.DataFrame(newsTotal)
df.to_excel(‘gzccnews.xlsx‘)

#提取包含點擊次數、標題、來源的前6行數據
print(df.head(6))
#提取‘學校綜合辦’發布的，‘點擊次數’超過3000的新聞。
print(df[(df[‘clickCount‘]>3000)&(df[‘source‘]==‘學校綜合辦‘)])
#提取‘國際學院‘和‘學生工作處‘發布的全部新聞。
sour = [‘國際學院‘,‘學生工作處‘]
print(df[df[‘source‘].isin(sour)])

數據化結構與保存