使用正则表达式，取得点击次数，函数抽离

import re
rule = ‘^\w+@\w+.\w+‘
mail = ‘820161175@qq.com‘
rec = re.match(rule, mail)
if(rec):
    print(rec.group(0))
else:
    print(‘error‘)

t = ‘‘‘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‘‘‘

rule = ‘\d{3}-\d{6,8}‘
rec = re.findall(rule, t)
if (rec):
    for i in rec:
        print(i)
else:
    print(‘error‘)

news=‘‘‘President Xi Jinping at the opening-ceremoy of?the Boao Forum for Asia Annual Conference 2018 on Tuseday ‘‘‘
print(re.split((‘[\s,.?\-]+‘),news))

newsUrl=‘http://news.gzcc.cn/html/2017/xiaoyuanxinwen_0925/8246.html‘
s=re.search(‘\_(.*).html‘,newsUrl).group(1).split(‘/‘)[1]
print(s)

 res = requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(s))

 r = ‘http://news.gzcc.cn/html/2017/xiaoyuanxinwen_0925/8246.html‘
    s = re.findall(‘\_(.*).html‘, r)[0].split(‘/‘)[-1]
    res = requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(s))
    return  int(res.text.split(‘.html‘)[-1].lstrip("(‘").rstrip("‘);"))

def getClickCount(r):
    s = re.findall(‘\_(.*).html‘, r)[0].split(‘/‘)[-1]
    res = requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(s))
    return  int(res.text.split(‘.html‘)[-1].lstrip("(‘").rstrip("‘);"))

def getNewsDetail(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):   #9. 取出一个新闻列表页的全部新闻 包装成函数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)
            getNewsDetail(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)