使用Pandas0.20.3

import boto3
import pandas as pd
import sys

if sys.version_info[0] < 3: 
    from StringIO import StringIO # Python 2.x
else:
    from io import StringIO # Python 3.x

client = boto3.client('s3')

bucket_name = 'my_bucket'

object_key = 'my_file.csv'
csv_obj = client.get_object(Bucket=bucket_name, Key=object_key)
body = csv_obj['Body']
csv_string = body.read().decode('utf-8')

df = pd.read_csv(StringIO(csv_string))

基于建议使用smart_open从S3阅读的this answer，下面是我在Pandas中使用它的方式：

import os
import pandas as pd
from smart_open import smart_open

aws_key = os.environ['AWS_ACCESS_KEY']
aws_secret = os.environ['AWS_SECRET_ACCESS_KEY']

bucket_name = 'my_bucket'
object_key = 'my_file.csv'

path = 's3://{}:{}@{}/{}'.format(aws_key, aws_secret, bucket_name, object_key)

df = pd.read_csv(smart_open(path))

你不需要panda..你可以使用python的默认csv库

def read_file(bucket_name,region, remote_file_name, aws_access_key_id, aws_secret_access_key):
    # reads a csv from AWS

    # first you stablish connection with your passwords and region id

    conn = boto.s3.connect_to_region(
        region,
        aws_access_key_id=aws_access_key_id,
        aws_secret_access_key=aws_secret_access_key)

    # next you obtain the key of the csv you want to read
    # you will need the bucket name and the csv file name

    bucket = conn.get_bucket(bucket_name, validate=False)
    key = Key(bucket)
    key.key = remote_file_name
    data = key.get_contents_as_string()
    key.close()

    # you store it into a string, therefore you will need to split it
    # usually the split characters are '\r\n' if not just read the file normally 
    # and find out what they are 

    reader = csv.reader(data.split('\r\n'))
    data = []
    header = next(reader)
    for row in reader:
        data.append(row)

    return data

希望它解决了你的问题，祝你好运！：）

我最终意识到，您还需要设置bucket中每个单独对象的权限，以便使用以下代码提取它：

from boto.s3.key import Key
k = Key(bucket)
k.key = 'data_1.csv'
k.set_canned_acl('public-read')

我还必须修改www.example.com _csv命令中的存储桶地址pd.read，如下所示：

data = pd.read_csv('https://s3-ap-southeast-2.amazonaws.com/example_bucket/data_1.csv')

您可以使用AWS SDK for Pandas，这是一个扩展Pandas的库，可以与AWS数据存储（如S3）顺畅地工作。

import awswrangler as wr
df = wr.s3.read_csv("s3://bucket/file.csv")