Question

我认为这是错误的，因为我将fetchone（）更改为带有dict_factory函数的字典，而不是元组，但我希望它是一个字典我只想将值作为列表添加到键中

def dict_factory(cursor, row):
    d = {}
    for idx, col in enumerate(cursor.description):
        d[col[0]] = row[idx]
    return d

def open_sql(sql_folder, sql_name, sql_table):
    # databases are located at /work/jmjohnso1/db_project  
    path_name = os.path.join(sql_folder,sql_name).strip()
    con = lite.connect(path_name)
    con.row_factory = dict_factory
    cur = con.cursor()
    cur.execute('SELECT * FROM ' + sql_table) 

    dict_contents = defaultdict(list) 
    while cur.fetchone() != None:
        cur.fetchone()
        for k, v in cur.fetchone():
            dict_contents[k].append(v)
    con.close()
    pprint(dict_contents)
    return dict_contents

期望的输出：

    {'atime': [1141682141, 1141682142],
     'attr_id': [3, 2]
    }

我得到的错误：

        for k, v in cur.fetchone():
    ValueError: too many values to unpack (expected 2)

整个代码

    # python3.5
    # pymongo version 3.2.2
    # MongoDB shell version: 3.0.11


    import os
    import pymongo
    from pymongo import MongoClient
    import sqlite3 as lite
    import pyewf
    import hashlib
    from itertools import chain
    from collections import defaultdict
    import pprint

    def list_sql_db(folder):
        # need a list for multiprocessing so I made a file. 
        file_name = os.path.join(folder, 'sql_db')
        if not os.path.isfile(file_name):
            with open (file_name, 'w') as line:
                for (dirpath, dirs, files) in os.walk(folder):
                    for name in files:
                        line.write(name + '\n')
        return file_name    

    def dict_factory(cursor, row):
        d = {}
        for idx, col in enumerate(cursor.description):
            d[col[0]] = row[idx]
        return d

    def open_sql(sql_folder, sql_name, sql_table):
        # databases are located at /work/jmjohnso1/db_project  
        path_name = os.path.join(sql_folder,sql_name).strip()
        con = lite.connect(path_name)
        con.row_factory = dict_factory
        cur = con.cursor()
        cur.execute('SELECT * FROM ' + sql_table) 

        dict_contents = defaultdict(list) 
        while cur.fetchone() != None:
            cur.fetchone()
            for k, v in cur.fetchone():
                dict_contents[k].append(v)
        con.close()
        pprint(dict_contents)
        return dict_contents

    def insert_tsk_mongo(sql_folder, sql_name, sql_table):
        client = MongoClient() # connect to mongodb
        db = client.nus # make or use a db called nus
        contents = open_sql(sql_folder, sql_name, sql_table)
        collection = sql_name.strip().replace('-','_') # because mongo will write but not read a collection with -

        # document_id = db[collection].insert({ # sql_name is the hard drive name 
            # sql_table:
                # contents           
        # })


    ###############################################################################

    sql_folder = '/work/jmjohnso1/db_project'    
    # sql_tables = ['tsk_fs_info', 'tsk_image_info',
                  # 'tsk_db_info ', 'tsk_image_names',
                  # 'tsk_file_layout', 'tsk_objects',
                  # 'tsk_files', 'tsk_vs_info', 'tsk_vs_parts']

    sql_tables = ['tsk_files']              

    sql_folder_name = list_sql_db(sql_folder)

    with open (sql_folder_name, 'r') as read: 
        sql_names = read.readlines()

    for sql_name in sql_names:
        for sql_table in sql_tables:
            insert_tsk_mongo(sql_folder, sql_name, sql_table)
        break

Answer 1

请尝试使用以下代码替换代码中的光标取指令：

for k, v in cur.fetchone().items():

只要你的dict_factory返回一个dict，当获得对它的引用时，你必须迭代它包含的项，而不是它的引用。当它是一个元组时，cur.fetchone（）只是正确地完成了这项工作。

如何在循环中使用fetchone（）向值列表中添加值？

1 个答案: