使用正则表达式，取得点击次数，函数抽离

e=‘974975677@qq.com‘
r=‘^(\w)+([\.\_\-]\w+)*@(\w)+((\.\w{2,3}){1,3})$‘
print(re.match(r,e))

tel=‘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‘
a=re.search(‘(\d{3,4})-(\d{6,8})‘,tel).group(2)
print(a)

str=‘‘‘Lee is on a five-day working visit to China starting Sunday, his second visit to China since September. During the visit, he will attend the Boao Forum for Asia‘s annual conference in Hainan. It will be his first time at the conference and he will deliver a speech at the opening session of the forum.‘‘‘
print(re.split("[\s,.?!]+",str))

q=‘http://news.gzcc.cn/html/2017/xiaoyuanxinwen_0925/8249.html‘
print(re.match(‘http://news.gzcc.cn/html/2017/xiaoyuanxinwen_(.*).html‘,q).group(1).split(‘/‘)[-1])
print(re.search(‘\_(.*).html‘,q).group(1).split(‘/‘)[-1])
print(re.findall(‘\_(.*).html‘,q)[-1].split(‘/‘)[-1])

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

def getClickCount(newUrl):
    newId=re.search(‘\_(.*).html‘,newUrl).group(1).split(‘/‘)[1]
    clickUrl=‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newId)
    return (int(requests.get(clickUrl).text.split(‘.html‘)[-1].lstrip("(‘").rstrip("‘);")))
def getNewDetail(url):
    res1 = requests.get(a)
    res1.encoding = ‘utf-8‘
    soup1 = BeautifulSoup(res1.text, ‘html.parser‘)

    soup1.select(‘#content‘)[0].text  # 正文
    info = soup1.select(‘.show-info‘)[0].text
    d = info.lstrip(‘发布时间:‘)[:19] #发布日期和时间

    dt=datetime.strptime(d,‘%Y-%m-%d %H:%M:%S‘)
    au=info[info.find(‘作者：‘):].split()[0].lstrip(‘作者：‘) #作者
    clickCount=getClickCount(a)

newUrl="http://news.gzcc.cn/html/2017/xiaoyuanxinwen_0925/8249.html"
newId = re.search(‘\_(.*).html‘, newUrl).group(1).split(‘/‘)[1]
clickUrl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newId)
print(clickUrl,‘\n‘,getClickCount(newUrl))

url=‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
res=requests.get(url)
res.encoding="utf-8"
soup=BeautifulSoup(res.text,"html.parser")
for news in soup.select("li"):
    if len(news.select(".news-list-title")) > 0:
        t=news.select(‘.news-list-title‘)[0].text
        a = news.select(‘a‘)[0].attrs[‘href‘]  # 新闻链接
        print(t,a,‘\n‘)
        getNewDetail(a)
        break