1. 用正则表达式判定邮箱是否输入正确。
import re def is_valid_email(addr): if re.match('\w+(\.\w+)*@\w+([-.]\w+)*\.\w+([-.]\w+)*', addr): return True return False tmail = 'www.694602156@qq.com' fmail = 'asdasdasdasdasd' t = is_valid_email(tmail) f = is_valid_email(fmail) print(t, f)
2. 用正则表达式识别出全部电话号码。
import re a='''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})',a))
3. 用正则表达式进行英文分词。re.split('',news)
import re a='''Once upon a time, a few mistakes ago I was in your sights, you got me alone You found me, you found me''' b=re.split('\W+',a) print(b)
4. 使用正则表达式取得新闻编号
import re url1 = 'http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html' id1 = re.search('\_(.*).html', url1).group(1).split('/')[-1] print(id1)
5. 生成点击次数的Request URL
import re url = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html" id1 = re.findall("\_(.*).html", url)[0].split("/")[-1]; req1 = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(id1) print(req1)
6. 获取点击次数
import re import requests url1 = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html" id1 = re.findall("\_(.*).html", url1)[0].split("/")[-1]; rurl = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(id1) res = requests.get(rurl); times=int(res.text.split('.html')[-1].lstrip("(')").rstrip("');")) print(times)
7. 将456步骤定义成一个函数 def getClickCount(newsUrl):
import requests import re def getClickCount(url1): id1 = re.findall("\_(.*).html", url1)[0].split("/")[-1]; rurl = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(id1) res = requests.get(rurl); times=int(res.text.split('.html')[-1].lstrip("(')").rstrip("');")) return times time=getClickCount("http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html") print(time)
8. 将获取新闻详情的代码定义成一个函数 def getNewDetail(newsUrl):
import requests from bs4 import BeautifulSoup def getNewDetail(newsUrl): res = requests.get(newsUrl) res.encoding = 'utf-8' soup = BeautifulSoup(res.text, 'html.parser') for news in soup.select('li'): if len(news.select('.news-list-title')) > 0: t = news.select('.news-list-title')[0].text d = news.select('.news-list-description')[0].text a = news.select('a')[0].attrs['href'] print('标题:', t) print('正文:', d) print('链接:', a) resd = requests.get(a) resd.encoding = 'utf-8' soupd = BeautifulSoup(resd.text, 'html.parser') info = soupd.select('.show-info')[0].text laiyuan = info[info.find('来源:'):].split()[0].lstrip('来源:') shenhe = info[info.find("审核"):].split()[0].lstrip('审核:') sheying = info[info.find('摄影:'):].split()[0].lstrip('点击:') print(info) time = info.lstrip('发布时间:')[:19] print('时间:', time) print(info[info.find('作者:'):info.find('审核:')]) print('来源:', laiyuan) print('审核:', shenhe) print(sheying) getNewDetail('http://news.gzcc.cn/html/xiaoyuanxinwen/')
9. 取出一个新闻列表页的全部新闻 包装成函数def getListPage(pageUrl):
import requests from bs4 import BeautifulSoup 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: time1 = news.select(".news-list-info")[0].contents[0].text title1 = news.select(".news-list-title")[0].text description1 = news.select(".news-list-description")[0].text url1 = news.select('a')[0].attrs['href'] print(time1, title1, description1,url1) getListPage('http://news.gzcc.cn/html/xiaoyuanxinwen/')
10. 获取总的新闻篇数,算出新闻总页数包装成函数def getPageN():
import requests from bs4 import BeautifulSoup def getPageN(): res = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/') res.encoding = "utf-8" soup = BeautifulSoup(res.text, 'html.parser') n = int(soup.select('#pages')[0].select('a')[0].text.rstrip('条')) return (n // 10 + 1) print(getPageN())
11. 获取全部新闻列表页的全部新闻详情。
n = getPageN(); def getallxinwen(): for i in range(1, n + 1): if (i == 1): newsurl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/' else: newsurl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) getListPage(newsurl); getallxinwen()
运行结果: