爬取校园新闻首页的新闻的详情，使用正则表达式，函数抽离

import requests
from bs4 import BeautifulSoup
res=requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
res.encoding= 'utf-8'
soup =BeautifulSoup(res.text,'html.parser')
import re

def getclick(link):
    newId = re.search('\_(.*).html', link).group(1).split('/')[1]
    click = requests.get('http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newId))
    return click.text.split('.html')[-1].lstrip("('").rstrip("');")

a=soup.select('li')

for news in a:
    if(len(news.select('.news-list-title'))>0):
        title=news.select('.news-list-title')[0].text
        description=news.select('.news-list-description')[0].text
        link=news.a.attrs['href']
        resd = requests.get(link)
        resd.encoding = 'utf-8'
        soupd = BeautifulSoup(resd.text, 'html.parser')

        content=soupd.select('.show-content')[0].text
        info=soupd.select('.show-info')[0].text
        divide=info.split()
        date= divide[0]+' '+ divide[1]
        author= divide[2]
        auditing= divide[3]
        source= divide[4]
        clickcount=getclick(link)

        print('新闻链接：' + link)
        print('新闻标题：' + title)
        print('新闻描述：' + description)
        print('新闻正文：' + content)
        print(date)
        print(author)
        print(auditing)
        print(source)
        print('点击次数：'+clickcount +'次')
        break


from datetime import datetime
now=datetime.now()
print(now)
time='2018-04-04 14:53:25 942204'
print(type(time))
date=datetime.strptime(time,'%Y-%m-%d %H:%M:%S %f')
print(date)
print(type(date))

截图：