def read_data(self, filepath): #0分组 1问题标签 2回答 3等价描述 4表情 5图片 6超时时间 book = xlrd.open_workbook(filepath) for sheet in book.sheets(): for i in range(1, sheet.nrows): row = sheet.row(i) if row[1].value != '' and row[2].value != '': d = [clean_str(x.value) for x in row] if d[4] == '': d[4] = 'null' if d[5] == '': d[5] = 'null' if len(d) > 6: if d[6] == '': timeout = 'null' else: timeout = d[6] else: timeout = 'null' data = {} data['group'] = d[0] data['label'] = d[1] data['answers'] = split_pro(d[2], '/') data['equal_questions'] = list(set(split_pro(d[1], '/') + \ split_pro(d[3], '/'))) data['equal_questions'] = \ list(set(questions_pro(data['equal_questions']))) data['emotion_name'] = d[4] data['emotion_url'] = Emotion[d[4]] data['media'] = d[5] data['timeout'] = timeout self.data.append(data)
def write_data2mongodb(self): for key in self.q2i.keys(): i = key.split('#') self.I.add(i[1]) dic = {} dic['equal_questions'] = list(set(questions_pro(list(set(self.q2i[key]))))) dic['business'] = i[0] dic['intention'] = i[1] dic['super_intention'] = i[2] dic['answers'] = self.i2a[i[1]][0] dic['emotion_name'] = self.i2a[i[1]][1] dic['emotion_url'] = Emotion[self.i2a[i[1]][1]] dic['media'] = self.i2a[i[1]][2] dic['timeout'] = self.i2a[i[1]][3] self.data.append(dic) self.db['dialogue'].drop() self.db['dialogue'].insert(self.data) self.db['dialogue'].create_index('intention')