max_process = 16 #最大进程数 def read_SQL_write(r_host,r_port,r_user,r_passwd,r_db,r_charset,w_host,w_port,w_user,w_passwd,w_db,w_charset,cmd,index=None): #得到tem字典保存着信息 try: conn = pymysql.Connect(host=r_host, port=r_port, user=r_user, passwd =r_passwd, db =r_db, charset =r_charset) cursor = conn.cursor() cursor.execute(cmd) except Exception as e: error = "[-][-]%d fail to connect SQL for reading" % index log_error('error.log',error) return else: tem = cursor.fetchone() print('[+][+]%d succeed to connect SQL for reading' % index) finally: cursor.close() conn.close() try: conn = pymysql.Connect(host=w_host, port=w_port, user=w_user, passwd =w_passwd, db =w_db, charset =w_charset) cursor = conn.cursor() cursor.execute(cmd)except Exception as e: error = "[-][-]%d fail to connect SQL for writing" % index log_error('error.log',error) return else:print('[+][+]%d succeed to connect SQL for writing' % index) r_dict = dict() r_dict['id'] = tem[0] r_dict['content_id'] = tem[1] r_dict['pub_date'] = tem[2] r_dict['title'] = cht_to_chs(tem[3]) r_dict['title_score'] =tem[4] r_dict['news_content'] = cht_to_chs(tem[5]) r_dict['content_score'] = tem[6] for key in stock_dict.keys(): #能找到对应的股票 if stock_dict[key][1] and ( r_dict['title'].find(stock_dict[key][1])!=-1 or r_dict['news_content'].find(stock_dict[key][1])!=-1 ): w_dict=dict() w_dict['code'] = key w_dict['english_name'] = stock_dict[key][0] w_dict['cn_name'] = stock_dict[key][1] #得到分数 if r_dict['title_score']: w_dict['score']=r_dict['title_score'] else: w_dict['score']=r_dict['content_score'] #开始写入 try: global max_process cmd = "INSERT INTO dyx_stock_score%d VALUES ('%s', '%s' , %d , '%s' , '%s' , %.2f );" % (index%max_process ,r_dict['content_id'] ,r_dict['pub_date'] ,w_dict['code'] ,w_dict['english_name'] ,w_dict['cn_name'] ,w_dict['score']) cursor.execute(cmd) conn.commit() except Exception as e: error = " [-]%d fail to write to SQL" % index cursor.rollback() log_error('error.log',error) else: print(" [+]%d succeed to write to SQL" % index) cursor.close() conn.close() def main(): num = 238143#数据库查询拿到的总数 p = None for index in range(1,num+1): if index%max_process==1: if p: p.close() p.join() p = multiprocessing.Pool(max_process) r_cmd = ('select id,content_id,pub_date,title,title_score,news_content,content_score from dyx_emotion_analysis where id = %d;' % (index)) p.apply_async(func = read_SQL_write,args=(r_host,r_port,r_user,r_passwd,r_db,r_charset,w_host,w_port,w_user,w_passwd,w_db,w_charset,r_cmd,index,)) if p: p.close() p.join()