使用正则表达式，取得点击次数，函数抽离

r=‘^(\w)+(\.\w+)*@(\w)+((\.\w{2,3}){1,3})$‘
e=‘67890222@qq.com‘
if re.match(r,e):
    print(re.match(r,e).group(0))
else:
    print(‘非邮箱格式！‘)

str=‘‘‘版权所有：广州商学院   地址：广州市黄埔区九龙大道206号
学校办公室：020-82876130   招生电话：020-82872773
粤公网安备 44011602000060号    粤ICP备15103669号‘‘‘
r = ‘\d{3}-\d{8}|\d{4}-\d{7}‘
n=re.findall(r,str)
for i in n:
    print(i)

str=‘‘‘Completely destroy information stored without your knowledge or approval: 
Internet history, Web pages and pictures from sites visited on the Internet, 
unwanted cookies, chatroom conversations, deleted e-mail messages, temporary files,
 the Windows swap file, the Recycle Bin, previously deleted files, valuable corporate 
 trade secrets, Business plans, personal files, photos or confidential letters, 
 etc.‘‘‘
n=re.split(r‘[ \t\n]+‘,str)
for i in n:
    print(i)

import  re
newurl=‘http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html‘
newid=re.search(‘\_(.*).html‘,newurl).group(1).split(‘/‘)[-1]
print(newid)

import  re
newurl=‘http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html‘
newid=re.search(‘\_(.*).html‘,newurl).group(1).split(‘/‘)[-1]
res=‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newid)
print(res)

import requests
import  re
newurl=‘http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html‘
newid=re.search(‘\_(.*).html‘,newurl).group(1).split(‘/‘)[-1]
res=requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newid))
r1=int(res.text.split(".html")[-1].lstrip("(‘").rstrip("‘);"))
print(r1)

import requests
import  re
def getClickCount(newsUrl):
    newid=re.search(‘\_(.*).html‘,newsUrl).group(1).split(‘/‘)[-1]
    res=requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newid))
    return int(res.text.split(".html")[-1].lstrip("(‘").rstrip("‘);"))

def getNewDetail(newsUrl):
    resd = requests.get(newsUrl)
    resd.encoding = ‘utf-8‘
    soupd = BeautifulSoup(resd.text, ‘html.parser‘)
    title = soupd.select(‘.show-title‘)[0].text
    info = soupd.select(‘.show-info‘)[0].text
    ti = datetime.strptime(info.lstrip(‘发布时间:‘)[0:19], ‘%Y-%m-%d %H:%M:%S‘)
    if info.find(‘来源：‘) > 0:
        source = info[info.find(‘来源：‘):].split()[0].lstrip(‘来源：‘)
    else:
        source = ‘none‘
    click = getClickCount(newsUrl)
    print(ti, title, source, click)

def getListPage(pageUrl):
    res = requests.get(pageUrl)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)
    for news in soup.select(‘li‘):
        if len(news.select(‘.news-list-title‘)) > 0:
            g = news.select(‘a‘)[0].attrs[‘href‘]
            print(g)
            getNewDetail(g)

def getPageN():
    res = requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)
    pagenumber=int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘))
    page = pagenumber//10+1
    return page

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