#判断邮箱格式
import re
mail = '^(\w)+(\.\w+)*@(\w)+((\.\w{2,3}){1,3})$'
myMail = '45612563@qq.com'
if re.match(mail, myMail):
    print(re.match(mail, myMail).group(0))
else:
    print('error')

  

#用正则表达式识别出全部电话号码。
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
'''
print(re.findall('(\d{3,4}-(\d{6,8}))',str))

  

#用正则表达式进行英文分词。re.split('',news)
news = '''Let your friends underrate your advantage,while let your enemies overrate your disadvantage..'''
print(re.split('[\s,.?\-]+',news))

  

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

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

#获取点击次数
def getClickTime(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 = re.search("hits'\).html\('(.*)'\);",clickStr).group(1)
    return count


# 获取新闻详情
def getNewDetail(url):
    resd = requests.get(url)
    resd.encoding = 'utf-8'
    soupd = BeautifulSoup(resd.text, 'html.parser')
    info = soupd.select('.show-info')[0].text
    time = re.search('发布时间:(.*) \xa0\xa0 \xa0\xa0作者:', info).group(1)
    dtime = datetime.strptime(time, '%Y-%m-%d %H:%M:%S')

    print('链接:' + url)
    print('标题:' + title)
    print('发布时间:{}'.format(dtime))
    print('作者:' + re.search('作者:(.*)审核:', info).group(1))
    print('审核:' + re.search('审核:(.*)来源:', info).group(1))
    print('来源:' + re.search('来源:(.*)摄影:', info).group(1))
    print('摄影:' + re.search('摄影:(.*)点击', info).group(1))
    print('点击次数:' + getClickTime(a))


for news in soup.select('li'):
    if len(news.select('.news-list-title'))>0:
        title = news.select('.news-list-title')[0].text
        #获取新闻模块链接
        a = news.a.attrs['href']
        #调用函数获取新闻正文
        getNewDetail(a)
        break

        c = soupd.select('#content')[0].text#正文
        info=soupd.select('.show-info')[0].text
        dt = info.lstrip('发布时间:')[:19]#发布时间
        dati = datetime.strptime(dt,':%Y-%m-%d %H:%M:%S')
        sh = info[info.find('作者:'):].split()[0].lstrip('作者:')#作者

        print(dati,t,a,sh,c)
        break

  

 

 posted on 2018-04-10 17:41  Runka  阅读(200)  评论(0编辑  收藏  举报