python爬取热搜制作词云

'''读取页面'''
def readhtml(self,catchUrl):
    catchUrl=self.catchUrl if not catchUrl else catchUrl
    response=urllib.request.urlopen(catchUrl)
    text=response.read().decode(self.bmcode)
    return text

'''生成时间'''
    def createTime(self):
        # 格式化成2016-03-20 11:45:39形式
        return time.strftime("%Y%m%d%H", time.localtime())
    '''写入文件'''
    def write2file(self,text):
        fileName=self.writePosition+self.createTime()+'.txt'
        self.fileName=fileName
        print(fileName)
        #判断路径，不存在生成
        if not os.path.exists(self.writePosition):
            os.mkdir(self.writePosition )
        if os.path.exists(fileName):
            uuid_tools().printlog('已经存在：{}'.format(fileName))
            return self.fileName
        mode='a' if os.path.exists(fileName) else 'w'
 
        with open(fileName,mode,encoding=self.bmcode) as f:
            f.write(text)
        print("写入{} 完成".format(fileName))
        return self.fileName

    '''打印日志'''
    def printlog(self,loginfo):
        logging.basicConfig(level=logging.INFO)
        logging.info(loginfo)

'''去掉标签'''
    def removeBq(self,content):
        pat=re.compile('>(.*?)<')
        str=''.join(pat.findall(content))
        str=str.replace(' 查看更多&gt; ','')
        return str
    '''输出内容'''
    def printContent(self, o,class_name):
        print(self.removeBq(str(o.find(class_=class_name))))

'''测试获取某个片段'''
    def readFilePd(self,fileName):
        #fileName='d:\\bdrs\\2021122010.txt'
        jt=open(fileName,'r',encoding=self.bmcode)
        try:
            content=jt.read()
            soup=BeautifulSoup(content,"html.parser")
            rs=RsBean()
            for k in soup.find_all('div',class_=rs.alldiv):
                print( str(k))
                # self.printContent(k,rs.sx)
                # self.printContent(k,rs.bt)
                # self.printContent(k,rs.ms)
                # self.printContent(k,rs.rszs)
        except  Exception as e:
            print('error:'+str(e))

'''打开连接'''
    def open(self):
        self.db=pymysql.connect(host=self.host,port=3306,user=self.user,passwd=self.passwd,db=self.database)
        #创建游标
        self.cursor=self.db.cursor()
        #print("打开连接成功")
    #关闭
    def close(self):
        self.cursor.close()
        self.db.close()
        #print("close连接成功")
def execute(self,sql,list=[]):
        try:
            self.open()
            self.cursor.execute(sql,list)
            self.db.commit()
            print("execute successfully!")
        except Exception as e:
            self.db.rollback()
            print("Execute failure!",str(e))
        self.close()

'''读取文件'''
    def readFile(self,fileName):
        #fileName='d:\\bdrs\\2021122010.txt'
        jt=open(fileName,'r',encoding=self.bmcode)
        try:
            content=jt.read()
            soup=BeautifulSoup(content,"html.parser")
            rs=RsBean()
            daoOper=OperateRsDao()
            rs_shijian=self.cutfilename(fileName)
            #先清空
            self.clearBefore(daoOper,rs_shijian)
            #读取文件
            for k in soup.find_all('div',class_=rs.alldiv):
                #插入数据
                rs.rs_shijian=rs_shijian
                self.insertData(daoOper,k,rs)
        except  Exception as e:
            print('error:'+str(e))

if __name__ == '__main__':
    a=db_connect()
    sql='select id,shun_xu,biao_ti,miao_shu,reshou_zhishu,insert_time,rs_shijian from bdrs_one order by rs_shijian desc,shun_xu asc '
    result=a.select(sql)
    jieguo=''
    for m in result:
        print(m)
        jieguo+=m[2]
    #根据title做词云
    CiYun().showImage(jieguo)