将符合上次修改时间窗口的S3文件读入DataFrame

import boto3
import pandas as pd

# 配置AWS凭证
session = boto3.Session(
    aws_access_key_id='YOUR_ACCESS_KEY',
    aws_secret_access_key='YOUR_SECRET_KEY',
    region_name='YOUR_REGION'
)

# 创建S3客户端
s3_client = session.client('s3')

# 定义S3存储桶和文件路径
bucket_name = 'YOUR_BUCKET_NAME'
folder_path = 'YOUR_FOLDER_PATH'

# 获取S3存储桶中的所有对象
response = s3_client.list_objects_v2(Bucket=bucket_name, Prefix=folder_path)

# 遍历筛选符合上次修改时间窗口的文件
files = []
for obj in response['Contents']:
    last_modified = obj['LastModified']
    # 根据上次修改时间窗口进行筛选
    if last_modified >= start_time and last_modified <= end_time:
        file_key = obj['Key']
        files.append(file_key)

# 读取符合条件的S3文件到DataFrame
dataframes = []
for file_key in files:
    response = s3_client.get_object(Bucket=bucket_name, Key=file_key)
    content = response['Body'].read()
    dataframe = pd.read_csv(content)
    dataframes.append(dataframe)

# 合并所有DataFrame
merged_dataframe = pd.concat(dataframes)