在 Glue Catalog 中建立表格可以通过以下步骤来完成:

1. 导入 Glue 相关类:

import boto3
import botocore.exceptions
import pandas as pd
import awswrangler as wr

2. 创建 Glue 的客户端:

glue_client = boto3.client('glue')

3. 定义表格的 Schema:

table_columns = [
    {"Name": "id", "Type": "int"},
    {"Name": "name", "Type": "string"},
    {"Name": "age", "Type": "int"}
]

# 如果有分区，可以用以下方式定义分区 Schema:
# partition_keys = [{"Name": "date", "Type": "string"}]

4. 定义表格的属性:

database_name = 'your-database-name'
table_name = 'your-table-name'
path_to_data = 's3://bucket-name/path/to/data'

# 如果存在分区属性，可以使用以下方式定义:
# partition_keys = [{"Name": "date", "Type": "string"}]

5. 建立表格:

try:
    response = glue_client.create_table(
        DatabaseName=database_name,
        TableInput={
            "Name": table_name,
            "StorageDescriptor": {
                "Columns": table_columns,
                "Location": path_to_data,
                "InputFormat": "org.apache.hadoop.mapred.TextInputFormat",
                "OutputFormat": "org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat",
                "SerdeInfo": {
                    "SerializationLibrary": "org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe",
                    "Parameters": {
                        "serialization.format": ","
                    }
                },
                "BucketColumns": [],
                "SortColumns": [],
                "Parameters": {}
            }
        }
    )
    print("Table is successfully created")
except botocore.exceptions.ClientError as e:
    if e.response['Error']['Code'] == 'AlreadyExistsException':
        print(f"Table {table_name} already exists")
    else