使用正则表达式，取得点击次数，函数抽离

Posted 2020-10-30 087林金龙

import requests
from bs4 import BeautifulSoup
import string
import time
import datetime
import re




#获取文章详情
def getNewDetail(newsrrl):
    #点击次数
    def getClickCount(newUrl):
            #获取新闻编号
            r2=re.findall(\'\\_\\d+\\/(.*?)\\.\',d,re.S)
            #print(r2)
            r1=\'http://oa.gzcc.cn/api.php?op=count&id=\'
            r3=\'&modelid=80\'
            r22="".join(r2)

            #生成点击次数的URL
            r_all=r1+r22+r3
            #print(r_all)
            rlink2=requests.get(r_all,headers=head)

            #获取点击次数
            hist=rlink2.text.split(\'.html\')[-1].lstrip("(\')").rstrip("\');")
            return hist
    soup=BeautifulSoup(r.text,\'html.parser\')
    for i in soup.select(\'li\'):
        if len(i.select(".news-list-title"))>0:
            a=i.select(".news-list-title")[0].text
            b=i.select(".news-list-info")[0].contents[0].text
            c=i.select(".news-list-info")[0].contents[1].text
            d=i.select("a")[0].attrs[\'href\']

            hist=getClickCount(d)



            print("标题："+a+\'\\n\'+"时间："+b+\'\\n\'+"来源："+c+\'\\n\'+"链接："+d+\'\\n\'+"点击："+hist+\'\\n\\n\')
            print()


            rlink=requests.get(d,headers=head)
            rlink.encoding=\'utf-8\'
            #print(rlink.text)
            soup=BeautifulSoup(rlink.text,\'html.parser\')
            e=soup.select(".show-info")[0].text
            f=e.split()
            for i in range(len(f)-1):
                print(f[i],end=\' \')
            print("点击："+hist+"次")
            print()
            print()



            #时间类型转换
            dt=e.lstrip(\'发布时间:\')[:19]
            dt = datetime.datetime.strptime(dt,\'%Y-%m-%d %H:%M:%S\')
            print("datetime类型时间：",end=\' \')
            print(dt)
            print()



            #作者
            i=e.find(\'作者：\')
            if i>0:
                s=e[e.find(\'作者：\'):].split()[0].lstrip(\'作者：\')
            print("作者：",end=\' \')
            print(s)
            print()



            #审核
            i=e.find(\'审核：\')
            if i>0:
                s=e[e.find(\'审核：\'):].split()[0].lstrip(\'审核：\')
            print("审核：",end=\' \')
            print(s)
            print()



            #来源
            i=e.find(\'来源：\')
            if i>0:
                s=e[e.find(\'来源：\'):].split()[0].lstrip(\'来源：\')
            print("来源：",end=\' \')
            print(s)
            print()
        
        
        
            #摄影
            i=e.find(\'摄影：\')
            if i>0:
                s=e[e.find(\'摄影：\'):].split()[0].lstrip(\'摄影：\')
            print("摄影：",end=\' \')
            print(s)
            print()



            #点击次数
            i=e.find(\'点击：\')
            if i>0:
                print("点击：",end=\' \')
            print(hist)

            for pn in range(5):
                print()




            print()
            #打印文章主体
            print(soup.select("#content")[0].text)
            print()
            print()
            print()

#爬虫伪装
head = {}
head[\'user-agent\']=\'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36\'

r=requests.get("http://news.gzcc.cn/html/xiaoyuanxinwen/",headers=head)
r.encoding=\'utf-8\'
soup=BeautifulSoup(r.text,\'html.parser\')
getNewDetail(r)



#电话
telephone=re.findall(\'(\\d{3,4})\\-(\\d{6,8})\',soup.text,re.S)
print(telephone)
print()

#邮箱
email=\'[e-mail]\'
eroll=\'^([0-9a-zA-Z_]{0,19}@[0-9a-zA-Z_]{0,19}(?:\\.\\w{2,3}){0,2})$\'
efinadll=re.findall(eroll,email)
print(efinadll)
print()

#英文分词
estr=\'\'\'Personal information such as names, birthdays, nicknames, pet\'s names, social security numbers, and the like 
should never, ever, ever be used because these are way too obvious and too easy to crack. The more you avoid using 
things like this as your passwords, the more secure your login areas will be.\'\'\'
print(re.split("[\\s,.?!]+",estr))