使用正则表达式

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

email =  input("请输入邮箱:")
result = re.match(‘^(\w)+(\.\w+)*@(\w)+((\.\w{2,3}){1,3})$‘,email)
if(result != None):
    print("正确")
else:
    print("错误")

import re
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))

string = "Today,we have a lot of homework"
print(re.split(‘,|\s‘,string))

newsurl = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html"
newID = re.match(‘http://news.gzcc.cn/html/2018/xiaoyuanxinwen(.*).html‘, newsurl).group(1).split("/")[1]
print(newID)

url = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newID)
print(url)

newsurl = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html"
newID = re.match(‘http://news.gzcc.cn/html/2018/xiaoyuanxinwen(.*).html‘, newsurl).group(1).split("/")[1]
url = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newID)
contact = requests.get(url)
count = contact.text.split(".html")[-1].lstrip("(‘").rstrip("‘);")
print(count)

import re
def getClickCount():
    newUrl = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html"
    newsId = re.findall("\_(.*).html",newUrl)[0].split("/")[-1];
    res = requests.get("http://oa.gzcc.cn/api.php?op=count&id= {}&modelid=80".format(newsId))
    return int(res.text.split(".html")[-1].lstrip("(‘").rsplit("‘);")[0])

def getNewDetail(newsUrl):
    detail_res = requests.get(newsUrl)
    detail_res.encoding = "utf-8"
    detail_soup = BeautifulSoup(detail_res.text, "html.parser")
    print(detail_soup.select("#content")[0].text)  # 正文
 
    print(time, title, description, newsUrl)
 
    content = detail_soup.select("#content")[0].text
    info = detail_soup.select(".show-info")[0].text
    date_time = info.lstrip(‘发布时间:‘)[:19]
    print(info)

def getlist(url):
   for news in soup.select("li"):
        if len(news.select(".news-list-title"))>0:  #排除为空的li
            time = news.select(".news-list-info")[0].contents[0].text
            title = news.select(".news-list-title")[0].text
            description = news.select(".news-list-description")[0].text
            detail_url = news.select(‘a‘)[0].attrs[‘href‘]
            print(time, title, description, detail_url)

def getPageN(url):
    res = requests.get(url)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)
    return int(soup.select(".a1")[0].text.rstrip("条"))//10+1

def getall(url):
   for num in range(2,getPageN(url)):
     listpageurl="http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(num)
     getlist(listpageurl)
     getNewDetail(listpageurl)