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。

import re
r ='^(\w)+(\.\w+)*@(\w)+((\.\w{2,3}){1,3})$'
e ='1546122489@qq.com'
if re.match(r,e):
    print(re.match(r,e).group(0))
else:
    print('error')

  

2. 用正则表达式识别出全部电话号码

import re
str ='''020-82876130 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
校外办公室0724-4263864 粤公网安备 44011602000060号    粤ICP备15103669号
'''
number=re.findall('(\d{3,4})-(\d{6,8})',str)
print(number)

  

3. 用正则表达式进行英文分词。re.split('',news)

import re
news = '''Failure is probably the fortification in your pole. It is like a peek your wallet as the thief, when you are thinking how to spend several hard-won lepta, when you are wondering whether new money, it has laid background.'''
word = re.split('[\s,.?\-]+',news)
print(word)

  

4. 使用正则表达式取得新闻编号

import re
newsUrl = 'http://news.gzcc.cn/html/2017/xiaoyuanxinwen_095/8249.html'
num=re.search('\_(.*).html',newsUrl).group(1)
print(num)

  

5. 生成点击次数的Request URL

import re
newsUrl = 'http://news.gzcc.cn/html/2017/xiaoyuanxinwen_095/8249.html'
newsId = re.search('\_(.*).html', newsUrl).group(1).split('/')[-1]
res = 'http://oa.gzcc.cn/api.php?op=count&id=8249&modelid=80'.format(newsId)
print(res)

  

6. 获取点击次数

import requests
import re
newsUrl = 'http://news.gzcc.cn/html/2017/xiaoyuanxinwen_095/8249.html'
newsId=re.search('\_(.*).html', newsUrl).group(1).split('/')[-1]
res = requests.get('http://oa.gzcc.cn/api.php?op=count&id=8249&modelid=80'.format(newsId))
ClickCount=(int(res.text.split('.html')[-1].lstrip("(')").rstrip("');")))
print(ClickCount)

  

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

def getClickCount(newsUrl):
    newsId=re.search('\_(.*).html', newsUrl).group(1).split('/')[-1]
    res = requests.get('http://oa.gzcc.cn/api.php?op=count&id=8249&modelid=80'.format(newsId))
    ClickCount = (int(res.text.split('.html')[-1].lstrip("(')").rstrip("');")))
    return ClickCount

  

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

def getNewsDetail(newsUrl):
    resd = requests.get(newsUrl)
    resd.encoding = 'utf-8'
    soupd = BeautifulSoup(resd.text, 'html.parser')  # 打开新闻详情页
    title = soupd.select('.show-title')[0].text
    info = soupd.select('.show-info')[0].text
   # c = soupd.select('#content')[0].text  # 正文
    dt = info.lstrip('发布时间:')[:19]  # 发布时间
    dati = datetime.strptime(dt, '%Y-%m-%d %H:%M:%S')
    if info.find('作者:') > 0:
        source = info[info.find('作者:'):].split()[0].lstrip('作者:')  # 作者
    else:
        source = 'none'
    content = soupd.select('.show-content')[0].text.strip()
    click = getClickCount(newsUrl)
    print(dati, title, newsUrl, source, click)

  

9. 取出一个新闻列表页的全部新闻 包装成函数def getListPage(pageUrl):

def getListPage(pageUrl):
    res = requests.get(pageUrl)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    for news in soup.select('li'):
        if len(news.select('.news-list-title')) > 0:
            newsUrl = news.select('a')[0].attrs['href']  # 链接
            getNewsDetail(newsUrl)

  

10. 获取总的新闻篇数,算出新闻总页数包装成函数def getPageN():

def getPageN():
    res = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text, 'html.parser')
    pagenumber=int(soup.select('.a1')[0].text.rstrip('条'))
    page = int(soup.select('.a1')[0].text.rstrip('条'))//10+1
    return page

  

11. 获取全部新闻列表页的全部新闻详情。

n=getPageN()
for i in range(1,n+1):
    pageUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
    getListPage(pageUrl)

  

posted @ 2018-04-10 22:19  235郑杰升  阅读(123)  评论(0编辑  收藏  举报