使用正则表达式,取得点击次数,函数抽离
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=input("请输入你的邮箱:"); if re.match(r,e): print("您的邮箱输入正确.") else: print("您的邮箱输入有误.")
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:0724-4263864 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)
import re string = "Youth is not a time of life; it is a state of mind; it is not a matter of rosy cheeks, red lips and supple knees; it is a matter of the will, a quality of the imagination, a vigor of the emotions; it is the freshness of the deep springs of life. " print(re.split('[\s,.;"?\-]+',string))
4. 使用正则表达式取得新闻编号
import re newUrl='http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html' newId = re.findall('\_(.*).html', newUrl)[0].split('/')[1]; print(newId)
5. 生成点击次数的Request URL
import re newUrl = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html" newsId = re.findall("\_(.*).html",newUrl)[0].split("/")[-1]; RequestUrl = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newsId) print(RequestUrl)
6. 获取点击次数
import re import requests newUrl = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html" newsId = re.findall("\_(.*).html",newUrl)[0].split("/")[-1]; RequestUrl = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newsId) res = requests.get(RequestUrl); 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 re import requests def getClickCount(newsUrl): newsId = re.findall("\_(.*).html",newsUrl)[0].split("/")[-1]; RequestUrl = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newsId) res = requests.get(RequestUrl); 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') print(soup.select("#content")[0].text) # 正文 info = soup.select(".show-info")[0].text time = info.lstrip('发布时间:')[:19] # 作者 if info.find('作者:') > 0: author = info[info.find('作者:'):info.find('审核:')].lstrip('作者:').split()[0] else: author = 'none'; print(author) getNewDetail('http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html')
9. 取出一个新闻列表页的全部新闻 包装成函数def getListPage(pageUrl):
import re 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: 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 url = news.select('a')[0].attrs['href'] print(time, title, description,url) 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 re 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)
11. 获取全部新闻列表页的全部新闻详情。
import re import requests from bs4 import BeautifulSoup #获取点击次数 def getClickCount(newsUrl): newsId = re.findall("\_(.*).html",newsUrl)[0].split("/")[-1]; RequestUrl = "http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newsId) res = requests.get(RequestUrl); times=int(res.text.split('.html')[-1].lstrip("(')").rstrip("');")) return times #获取新闻详细信息 def getNewDetail(newsUrl): res = requests.get(newsUrl) res.encoding = 'utf-8' soup = BeautifulSoup(res.text, 'html.parser') # print(soup.select("#content")[0].text) # 正文 info = soup.select(".show-info")[0].text time = info.lstrip('发布时间:')[:19] # 作者 if info.find('作者:') > 0: author = info[info.find('作者:'):info.find('审核:')].lstrip('作者:').split()[0] else: author= 'none'; print("作者:"+author+" "+"发布时间"+time) #获取该页新闻的信息 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: 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 url = news.select('a')[0].attrs['href'] print(time+" "+title+" "+description+" "+url) a=getClickCount(url); print("点击"+str(a)+"次") getNewDetail(url) #获取页数 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) n=getPageN(); 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);