def getRecomSubjects(): #获取一个hive连接 connGetRecomSubject = HiveClient(HIVE_ONLINE_IP, HIVE_ONLINE_DB_NAME, HIVE_ONLINE_PORT) #获得数据 recomResult = connGetRecomSubject.query(SQL_RECALL_SOURCE_QUESTIONS) #清洗后写入新集合 listQuest = [] for recomQuest in recomResult: dictSubject = {} dictSubject['id'] = recomQuest[0] dictSubject['questno'] = recomQuest[1] dictSubject['txt_content'] = recomQuest[2] dictSubject['txt_content_url'] = recomQuest[3] dictSubject['txt_answer_url'] = recomQuest[4] dictSubject['txt_analysis_url'] = recomQuest[5] dictSubject['png_content_url'] = recomQuest[6] dictSubject['png_answer_url'] = recomQuest[7] dictSubject['png_analysis_url'] = recomQuest[8] dictSubject['html_content_url'] = recomQuest[9] dictSubject['html_answer_url'] = recomQuest[10] dictSubject['html_analysis_url'] = recomQuest[11] dictSubject['three_know_code'] = recomQuest[12] dictSubject['three_know_name'] = recomQuest[13] dictSubject['questtype_id'] = recomQuest[14] dictSubject['questtype_name'] = recomQuest[15] dictSubject['question_time'] = recomQuest[16] dictSubject['difficulty_val'] = recomQuest[17] dictSubject['recall_papername'] = recomQuest[18] dictSubject['quest_source'] = recomQuest[19] dictSubject['l_date'] = recomQuest[20] dictSubject['recall_label'] = recomQuest[21] listQuest.append(dictSubject) connGetRecomSubject.close() return listQuest
def getRecomSubjects(): #获取一个hive连接 connGetSubjects = HiveClient(HIVE_ONLINE_IP,HIVE_ONLINE_DB_NAME,HIVE_ONLINE_PORT) #获得数据 subjectResult = connGetSubjects.query(SQL_PAPER_RECALL_QUESTIONS) #重命名一下字段 listQuest = [] for lineSubject in subjectResult: dictSubject = {} dictSubject['y_id'] = lineSubject[0] dictSubject['t_id'] = lineSubject[1] dictSubject['y_know_code'] = lineSubject[2] dictSubject['y_know_name'] = lineSubject[3] dictSubject['y_content'] = lineSubject[4] dictSubject['t_content'] = lineSubject[5] listQuest.append(dictSubject) connGetSubjects.close() return listQuest
def getMatchSubjects(): #获取一个hive连接 connGetRecomSubject = HiveClient(HIVE_ONLINE_IP, HIVE_ONLINE_DB_NAME, HIVE_ONLINE_PORT) #获得数据 listSubjects = connGetRecomSubject.query(SQL_RECALL_SOURCE_QUESTIONS) #清洗后写入新集合 listSubjectsCol = [] for lineSubject in listSubjects: dictSubject = {} dictSubject['y_id'] = lineSubject[0] dictSubject['t_id'] = lineSubject[1] dictSubject['three_know_code'] = lineSubject[2] dictSubject['y_txt_content_par'] = lineSubject[3] dictSubject['t_txt_content_par'] = lineSubject[4] dictSubject['y_quest_source_id'] = lineSubject[5] dictSubject['t_quest_source_id'] = lineSubject[6] listSubjectsCol.append(dictSubject) connGetRecomSubject.close() return listSubjectsCol
def getRecomSubjects(): #获取一个hive连接 connGetRecomSubject = HiveClient(HIVE_ONLINE_IP, HIVE_ONLINE_DB_NAME, HIVE_ONLINE_PORT) #获得数据 recomResult = connGetRecomSubject.query(SQL_RECALL_SOURCE_QUESTIONS) #清洗后写入新集合 listQuest = [] for recomQuest in recomResult: dictSubject = {} dictSubject['grade_base_id'] = recomQuest[0] dictSubject['paper_question_id'] = recomQuest[1] dictSubject['data_center_id'] = recomQuest[2] dictSubject['vector'] = '' dictSubject['txt_content'] = recomQuest[4] dictSubject['txt_content_url'] = recomQuest[5] dictSubject['questtype_id'] = recomQuest[6] dictSubject['questtype_name'] = recomQuest[7] dictSubject['three_know_code'] = recomQuest[8] dictSubject['three_know_name'] = recomQuest[9] dictSubject['l_date'] = recomQuest[15] listQuest.append(dictSubject) connGetRecomSubject.close() return listQuest