尝试打开.bson文件并读取给熊猫df，但是第一次使用.bson获取'bson.errors.InvalidBSON: objsize太大‘

link管理

链接快照平台

输入网页链接，自动生成快照
标签化管理网页链接

尝试打开.bson文件并读取给熊猫df，但是第一次使用.bson获取'bson.errors.InvalidBSON: objsize太大‘

import pandas as pd
import bson
FILE="users_(1).bson"
with open(FILE,'rb') as f:
    data = bson.decode_all(f.read())
main_df=pd.DataFrame(data)
main_df.describe()

[{'_id': ObjectId('999f24f260f653401b'),
    'isV2': False,
    'isBeingMigratedToV2': False,
    'firstName': 'Jezz',
    'lastName': 'Bezos',
    'subscription': {'_id': ObjectId('999f24f260f653401b'),
     'chargebeeId': 'AzZdd6T847kHQ',
     'currencyCode': 'EUR',
     'customerId': 'AzZdd6T847kHQ',
     'nextBillingAt': datetime.datetime(2022, 7, 7, 10, 14, 6),
     'numberOfMonthsPaid': 1,
     'planId': 'booster-v3-eur',
     'startedAt': datetime.datetime(2022, 6, 7, 10, 14, 6),
     'addons': [],
     'campaign': None,
     'maskedCardNumber': '************1234'},
    'email': '[email protected]',
    'groupName': None,
    'username': 'jeffbezy',
    'country': 'DE'},
   {'_id': ObjectId('999f242660f653401b'),
    'isV2': False,
    'isBeingMigratedToV2': False,
    'firstName': 'Caterina',
    'lastName': 'Fake',
    'subscription': {'_id': ObjectId('999f242660f653401b'),
     'chargebeeId': '16CGLYT846t99',
     'currencyCode': 'GBP',
     'customerId': '16CGLYT846t99',
     'nextBillingAt': datetime.datetime(2022, 7, 7, 10, 10, 41),
     'numberOfMonthsPaid': 1,
     'planId': 'personal-v3-gbp',
     'startedAt': datetime.datetime(2022, 6, 7, 10, 10, 41),
     'addons': [],
     'campaign': None,
     'maskedCardNumber': '************4311'},
    'email': '[email protected]',
    'groupName': None,
    'username': 'cfake',
    'country': 'GB'}]

'bson.errors.InvalidBSON: objsize too large'

import pandas as pd
from bson.json_util import loads
with open(filepath,'r') as f:
    data = f.read()
mapper = {
    '\'': '"',   # using double quotes
    'False': 'false',
    'None': '\"None\"',  # double quotes around None
    # modifying the ObjectIds and timestamps
    '("': '(', 
    '")': ')', 
    ')': ')"',
    'ObjectId': '"ObjectId',
    'datetime.datetime': '"datetime.datetime'

尝试打开.bson文件并读取给熊猫df，但是第一次使用.bson获取'bson.errors.InvalidBSON: objsize太大‘

1 个回答