import requests import re from bs4 import BeautifulSoup from datetime import datetime a = 'http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html' # 1. 用正则表达式判定邮箱是否输入正确。 r = '^(\w)+(\.\w+)*@(\w)+((\.\w{2,3}){1,3})$' e = '3947653@qq.com' if re.match(r,e): print('success') else: print('please input :') #2. 用正则表达式识别出全部电话号码。 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)) # 3. 用正则表达式进行英文分词。re.split('',news) news='''I like to read novel so much, especially the novels about how to find the murder. I want to be a detective when I grow up, because it means I am a smart person. I can catch the bad guys and help the good people. What’s more, people will respect me. It is so great to be a hero and save the world. ''' new = re.split("[\s+\n\.\,\']", news) print(new) # 4. 使用正则表达式取得新闻编号 a2 = re.search('\_(.*).html',a).group(1).split('/')[-1] print(a2) # 5. 生成点击次数的Request URL newsId = re.search('\_(.*).html',a).group(1).split('/')[-1] clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId) print(clickUrl) # 6. 获取点击次数 resc = requests.get(clickUrl).text.split('.html')[-1].lstrip("('").rstrip("');") print(resc) # 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] clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId) resc = requests.get(clickUrl).text.split('.html')[-1].lstrip("('").rstrip("');") print('编号:'+newsId) print(clickUrl) print('点击数:'+resc) return getClickCount('http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html') # 8. 将获取新闻详情的代码定义成一个函数 def getNewDetail(newsUrl): def getNewDetail(newsUrl): res = requests.get(newsUrl) res.encoding = 'utf-8' soupd = BeautifulSoup(res.text, "html.parser") info = soupd.select('.show-info')[0].text dt = info.lstrip('发布时间')[1:20] dt = datetime.strptime(dt, '%Y-%m-%d %H:%M:%S') print(dt) i = info.find('来源:') z = info.find('作者:') c = info.find('审核:') sy = info.find('摄影:') if i > 0: s = info[info.find('来源:'):].split()[0].lstrip('来源:') print('来源:'+s) if z > 0 : z = info[info.find('作者:'):].split()[0].lstrip('作者:') print( '作者:' + z) if c > 0 : c = info[info.find('审核:'):].split()[0].lstrip('审核:') print( '审核:' + c) if sy > 0: sy = info[info.find('摄影:'):].split()[0].lstrip('摄影:') print('摄影:'+ sy) # print('正文:' + soupd.select('.show-content')[0].text) # print(getClickCount(newsUrl)) return getNewDetail('http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0411/9203.html')