使用正则表达式，取得点击次数，函数抽离

学会使用正则表达式

1. 用正则表达式判定邮箱是否输入正确。

2. 用正则表达式识别出全部电话号码。

3. 用正则表达式进行英文分词。re.split('',news)

import re
import requests
def checkEmail(Email):
    eroll='^([0-9a-zA-Z_]{0,16}@[0-9a-zA-Z]{0,8}(?:\.\w{2,3}){0,2})$'
    efindall = re.findall(eroll, Email)
    if len(efindall)>0:
        print('邮箱格式正确')
        print(efindall)
    else:
        print('邮箱格式错误')

Email = '123google@gmail.com'
checkEmail(Email)


def chenkPhonenum(phonenum):
    proll = '(\d{3,4}-\d{6,8})'
    pfindall = re.findall(proll, phonenum)
    print(pfindall)

def getClickCount(newUrl):
    re1 = re.search('\_(.*).html',newUrl)
    re2 = re.match('http://news.gzcc.cn/html/2018/xiaoyuanxinwen_(.*).html',newUrl)
    i = re1.group(1).split('/')[-1]
    return i

phonenum = '''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'''
chenkPhonenum(phonenum)


article = '''The constant presence of a mobile phone has a "brain drain" 
effect that significantly reduces people's intelligence and attention spans, 
a study has found. 
Researchers at the University of Texas discovered that people are worse at 
conducting tasks and remembering information if they have a smartphone within
eye shot. In two experiments they found phones sitting on a desk or even in
a pocket or handbag would distract users and lead to worse test scores even
when it was set up not to disturb test subjects. '''

print(re.split('[\s,.?!""]+',article))

　　

4. 使用正则表达式取得新闻编号

5. 生成点击次数的Request URL

6. 获取点击次数

7. 将456步骤定义成一个函数 def getClickCount(newsUrl):

8. 将获取新闻详情的代码定义成一个函数 def getNewDetail(newsUrl):

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

def getClickCount(newUrl):
    re1 = re.search('\_(.*).html',newUrl)
    re2 = re.match('http://news.gzcc.cn/html/2018/xiaoyuanxinwen_(.*).html',newUrl)
    i = re1.group(1).split('/')[-1]
    return i


def g(a1):
    res1 = requests.get(a1)
    res1.encoding = 'utf-8'
    soup1 = BeautifulSoup(res1.text, 'html.parser')
    title = soup1.select(".show-title")[0].text
    content = soup1.select("#content")[0].text
    about = soup1.select('.show-info')[0].text
    time = about.lstrip('发布时间:')[:19]
    time = datetime.strptime(time, '%Y-%m-%d %H:%M:%S')
    if about.find('来源：') > 0:
        origin = about[about.find('来源：'):].split()[0]
    if about.find('作者：') > 0:
        writer = about[about.find('作者：'):].split()[0]
    if about.find('审核：') > 0:
        audit = about[about.find('审核：'):].split()[0]
    photograph = 'null'
    if about.find('摄影：') > 0:
        photograph = about[about.find('摄影：'):].split()[0]
    newUrl = a1
    cUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(getClickCount(newUrl))
    res = requests.get(cUrl)
    print("标题：" + title, "发布时间：", time, origin, audit, writer, photograph,
          "点击次数:" + res.text.split(".html")[-1].lstrip("('").rstrip("');"))


url = "http://news.gzcc.cn/html/xiaoyuanxinwen/"
resurl = requests.get(url)
resurl.encoding = 'utf-8'
soup = BeautifulSoup(resurl.text, 'html.parser')
a = soup.select('li')

for news in a:
    if len(news.select('.news-list-title')) > 0:
        a1 = news.select('a')[0].attrs['href']
        g(a1)