使用正則表達式

1. 用正則表達式斷定郵箱是否輸入正確。

import re
r= '^(\w)+(\.\w)*@(\w)+((\.\w{2,3}){1,3})$'
e=input("請輸入你的郵箱:");
if re.match(r,e):
    print("您的郵箱輸入正確.")
else:
    print("您的郵箱輸入有誤.")

2. 用正則表達式識別出所有電話號碼。

import re
str='''020-82876130 版權全部：廣州商學院   地址：廣州市黃埔區九龍大道206號
學校辦公室：020-82876130   招生電話：020-82872773 校外：0724-4263864
粵公網安備 44011602000060號    粵ICP備15103669號'''
print(re.findall('(\d{3,4})-(\d{6,8})',str))

 

3. 用正則表達式進行英文分詞。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. 使用正則表達式取得新聞編號

import re
newUrl='http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html'
newId = re.findall('\_(.*).html', newUrl)[0].split('/')[1];
print(newId)

　　

5. 生成點擊次數的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. 獲取點擊次數

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. 將456步驟定義成一個函數 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. 將獲取新聞詳情的代碼定義成一個函數 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('發佈時間:')[:19]
    # 做者
    if info.find('做者：') > 0:
        author = info[info.find('做者：'):info.find('審覈：')].lstrip('做者：').split()[0]
    else:
        author = 'none';
    print(author)
getNewDetail('http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html')

 

9. 取出一個新聞列表頁的所有新聞 包裝成函數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. 獲取總的新聞篇數，算出新聞總頁數包裝成函數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('條'))
    return (n // 10 + 1)

 

11. 獲取所有新聞列表頁的所有新聞詳情。

import re
import requests
from bs4 import BeautifulSoup
 
#獲取點擊次數
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
 
#獲取新聞詳細信息
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('發佈時間:')[:19]
    # 做者
    if info.find('做者：') > 0:
       author = info[info.find('做者：'):info.find('審覈：')].lstrip('做者：').split()[0]
    else:
        author= 'none';
    print("做者："+author+" "+"發佈時間"+time)
 
#獲取該頁新聞的信息
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("點擊"+str(a)+"次")
            getNewDetail(url)
 
 
#獲取頁數
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('條'))
    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);