dsProject/dsRag/ElasticSearch/T4_SelectAllData.py

import warnings

from elasticsearch import Elasticsearch

from Config import Config

# 抑制HTTPS相关警告
warnings.filterwarnings('ignore', message='Connecting to .* using TLS with verify_certs=False is insecure')
warnings.filterwarnings('ignore', message='Unverified HTTPS request is being made to host')


# 初始化Elasticsearch连接
es = Elasticsearch(
    hosts=Config.ES_CONFIG['hosts'],
    basic_auth=Config.ES_CONFIG['basic_auth'],
    verify_certs=False
)

# 查询所有数据
def select_all_data(index_name):
    try:
        # 构建查询条件 - 匹配所有文档
        # 修改查询条件为获取前10条数据
        query = {
            "query": {
                "match_all": {}
            },
            "size": 1000  # 仅获取10条数据
        }
        
        # 执行查询
        response = es.search(index=index_name, body=query)
        hits = response['hits']['hits']
        
        if not hits:
            print(f"索引 {index_name} 中没有数据")
        else:
            print(f"索引 {index_name} 中共有 {len(hits)} 条数据:")
            for i, hit in enumerate(hits, 1):
                print(f"{i}. ID: {hit['_id']}")
                print(f"   内容: {hit['_source'].get('user_input', '')}")
                print(f"   标签: {hit['_source'].get('tags', '')}")
                print(f"   时间戳: {hit['_source'].get('timestamp', '')}")
                # 在循环中添加打印完整数据结构的代码
                if i == 1:  # 只打印第一条数据的完整结构
                    print("完整数据结构:")
                    import pprint
                    pp = pprint.PrettyPrinter(indent=4)
                    pp.pprint(hit['_source'])
                print("-" * 50)
    except Exception as e:
        print(f"查询出错: {e}")

if __name__ == "__main__":
    select_all_data(Config.ES_CONFIG['index_name'])