我想在Ubuntu中PyMongo的帮助下使用Python将数据导入MongoDB。数据为安然邮件数据集。为了输入到数据库,我生成了以下Python代码。在import os
import datetime
from pymongo import MongoClient
__author__ = 'test'
MAIL_DIR_PATH = '/home/bigdata/Desktop/maildir'
PREFIX_TRIM_AMOUNT = len(MAIL_DIR_PATH) + 1
MAX_USER_RUN_LIMIT = 50
MAX_USER_EMAILS_PER_FOLDER_FILE_LIMIT = 2
counter = 1
def get_file_contents(file_to_open_name):
data_file = open(file_to_open_name)
file_contents = ""
try:
for data_line in data_file:
file_contents += data_line
finally:
data_file.close()
return file_contents.decode('cp1252')
def save_to_database(mailbox_owner_name, sub_folder, file_name, message_contents):
document = {"mailbox": mailbox_owner_name,
"subFolder&#