使用正则表达式，取得点击次数，函数抽离

Posted 2020-10-30 086刘伟锋

1. 用正则表达式判定邮箱是否输入正确。

import re
import requests

def checkEmail(Email):
    if len(Email)>6:
        if re.match(‘^([0-9a-zA-Z_]{0,16}@[0-9a-zA-Z]{0,8}(?:\.\w{2,3}){0,2})$‘,Email)!=None:
            print(‘success‘)
        else:
            print(‘fail‘)
    else:
        print(‘fail‘)

Email = ‘[email protected]‘
checkEmail(Email)

2. 用正则表达式识别出全部电话号码。

import re

def checknumber(number):
    n=re.findall(r"\(?0\d{2,3}[) -]?\d{7,8}",number)
    if n:
        print (n)
    else:
        print (‘not match‘)
nb="[phone] 010-44767890"
checknumber(nb)

3. 用正则表达式进行英文分词。re.split(‘‘,news)

article=‘‘‘new233old fake help what ‘‘‘
print(re.split(‘[\d\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):

def getClickCount(newUrl):
    newId = re.search(‘\_(.*).html‘, newUrl).group(1).split(‘/‘)[-1]
    print(newId)
    clickUrl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newId)
    resc = requests.get(clickUrl)
    print(resc.text.split(‘.html‘)[-1].lstrip("(‘").rsplit("‘);"))
    return resc

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)