使用正则表达式，取得点击次数，函数抽离

#判断邮箱电话格式
a = "1207384251@qq.com"
b = '020-12345678'
mail = re.search('\d{6,12}@[a-zA-Z0-9]+.[a-zA-Z0-9]+', a).group(0)
tele_num = re.search('\d{3,4}-\d{6,8}', b).group(0)
print(mail+'\n'+tele_num)

 

#识别全部电话号码
text="(021)88776543 010-55667890 02584533622 057184720483 837922740"
m=re.findall(r"\(?0\d{2,3}[) -]?\d{7,8}",text)
if m:
    print(m)
else:
    print ('not match')

 

#英文分词
#不保留匹配项
m = re.split('\d+' , '123abc321cba')
print (m)
print ("\n")
#保留匹配项
m = re.split('(\d+)' , '123abc321cba')
print (m)

 

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


# 获取新闻点击次数
def getNewsId(url):
    newsId = re.findall(r'\_(.*).html', url)[0][-4:]
    clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId)
    clickRes = requests.get(clickUrl)
    # 利用正则表达式获取新闻点击次数
    clickCount = int(re.search("hits'\).html\('(.*)'\);", clickRes.text).group(1))
    return clickCount



def getNewDetail(newsUrl):
    # 读取新闻细节
    resDescript = requests.get(newsUrl)
    resDescript.encoding = "utf-8"
    soupDescript = BeautifulSoup(resDescript.text, 'html.parser')

    content = soupDescript.select(".show-content")[0].text  # 正文
    info = soupDescript.select(".show-info")[0].text  # info相关内容
    # 第一种方法 分离 message = info.split()
    # 第二种方法 用正则表达式
    time = re.search("发布时间:(.*) \xa0\xa0 \xa0\xa0作者：", info).group(1)
    author = re.search("作者：(.*)\xa0\xa0审核：", info).group(1)
    right = re.search("审核：(.*)\xa0\xa0来源：", info).group(1)
    resource = re.search('来源：(.*)\xa0\xa0\xa0\xa0摄影：', info).group(1)
    video = re.search("摄影：(.*)\xa0\xa0\xa0\xa0点击：", info).group(1)
    count = getNewsId(newsUrl)
    dateTime = datetime.strptime(time, '%Y-%m-%d %H:%M:%S')

    print('标题' + ': ' + title)
    print('概要' + ': ' + description)
    print('链接' + ': ' + a)
    print('正文' + ' :' + content)
    print('发布时间：{0}\n作者：{1}\n审核：{2}\n来源：{3}\n摄影：{4}\n点击次数：{5}'.format(dateTime, author, right, resource, video,count))
    print("\n")



for s in soup.select("li"):
    if len(s.select(".news-list-title"))>0:
        title = s.select(".news-list-title")[0].text #新闻标题
        description = s.select(".news-list-description")[0].text #新闻描述
        a = s.a.attrs["href"] #观看新闻细节
        getNewDetail(a)
        break