- 用正则表达式判定邮箱是否输入正确。
import re mail = '''11040aaAAs3@qq.com''' if re.match('^[0-9a-zA-Z]{0,20}@[[0-9a-zA-Z]{0,10}\.[a-zA-Z]{1,3}$', mail): print('right') else: print('wrong')
- 用正则表达式识别出全部电话号码。
import re str = '''学校办公室:020-82876130 招生电话:020-82872773''' a=re.findall('(\d{3,4})-(\d{6,8})', str) print(a)
3.用正则表达式进行英文分词。re.split('',news)
import re news = '''It's true that we don't know what we've got until we lose it, but it's also true that we don't know what we've been losing until it arrives. ''' new=re.split('[\s,.?!\-]+',news) print(new)
4 使用正则表达式取得新闻编号
import re Url = ' http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0401/8888.html' newsId = re.search('\_(.*).html', Url).group(1).split('/')[-1] print(newsId)
5. 生成点击次数的Request URL
import requests res = requests.get('http://oa.gzcc.cn/api.php?op=count&id=9122&modelid=80') res.encoding = 'utf-8' b=res.text.split('.html')[-1].lstrip("(')").rstrip("');") print(b)
6. 获取点击次数
import requests import re newsUrl = 'http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0329/9122.html' newsId=re.search('\_(.*).html',newsUrl).group(1).split('/')[-1] res = requests.get('http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId)) b=res.text.split('.html')[-1].lstrip("(')").rstrip("');") print(b)
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={}&modelid=80'.format(newsId)) b=res.text.split('.html')[-1].lstrip("(')").rstrip("');") print(b)
8. 将获取新闻详情的代码定义成一个函数 def getNewDetail(newsUrl):
def getNewsDetail(newsUrl): res = requests.get(newsUrl) res.encoding = 'utf-8' soupd = BeautifulSoup(res.text, 'html.parser') title=soupd.select('.show-title')[0].text info=soupd.select('.show-info')[0].text time=datetime.strptime(info.lstrip('发布时间:')[0:19], '%Y-%m-%d %H:%M:%S') if info.find('来源:')>0: zy=info[info.find('来源:'):].split()[0].lstrip('来源:') else: zy='none' click=getClickCount(newsUrl) print(time,title,zy,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: g = news.select('a')[0].attrs['href'] print(g) getNewsDetail(g)
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 = pagenumber//10+1 return page
11. 获取全部新闻列表页的全部新闻详情。
pageUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/' n=getPageN()for i in range(1,n+1): print(i) listPageUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) getListPage(listPageUrl)