zoukankan      html  css  js  c++  java
  • Elasticsearch分页查询

    global index
    global CLIENT
    index = "guajibao-ipused-2019.10.13"
    CLIENT = Elasticsearch(hosts=es_host,port=port,timeout=timeout)
    
    
    
    def load_all_data(scroll_id):
        if scroll_id:
            page = CLIENT.scroll(scroll_id=scroll_id, scroll='10m')
            scroll_id = page['_scroll_id']
        else:
            page = CLIENT.search(index=index, scroll='10m', size=100)
            scroll_id = page['_scroll_id']
        print(page)
        data = page["hits"]['hits']
        return {"data": data, "scroll_id": scroll_id, "length": len(data)}
    
    
    
    
    
    例子
    
    def load_all_data(scroll_id):
        if scroll_id:
            page = CLIENT.scroll(scroll_id=scroll_id, scroll='10m')
            scroll_id = page['_scroll_id']
        else:
            page = CLIENT.search(index=index, scroll='10m', size=100)
            scroll_id = page['_scroll_id']
        # print(page)
        data = page["hits"]['hits']
        total = page['hits']['total']['value']
        print(data)
        return  {"data": data, "scroll_id": scroll_id, "length": len(data), "total": total}
    
    
    
    
    if __name__ == "__main__":
        result = load_all_data(None)
        total =  result['total']
        scroll_id = result['scroll_id']
        for i in range(int(total/100)):
            scroll_id = load_all_data(scroll_id)['scroll_id']


    转至元数据结尾

     

    转至元数据起始

     

    global index
    global CLIENT
    index = "guajibao-ipused-2019.10.13"
    CLIENT = Elasticsearch(hosts=es_host,port=port,timeout=timeout)



    def load_all_data(scroll_id):
        if scroll_id:
            page = CLIENT.scroll(scroll_id=scroll_id, scroll='10m')
            scroll_id = page['_scroll_id']
        else:
            page = CLIENT.search(index=index, scroll='10m'size=100)
            scroll_id = page['_scroll_id']
        print(page)
        data = page["hits"]['hits']
        return {"data": data, "scroll_id": scroll_id, "length"len(data)}

     

     

    例子

    def load_all_data(scroll_id):
        if scroll_id:
            page = CLIENT.scroll(scroll_id=scroll_id, scroll='10m')
            scroll_id = page['_scroll_id']
        else:
            page = CLIENT.search(index=index, scroll='10m'size=100)
            scroll_id = page['_scroll_id']
        # print(page)
        data = page["hits"]['hits']
        total = page['hits']['total']['value']
        print(data)
        return  {"data": data, "scroll_id": scroll_id, "length"len(data), "total": total}




    if __name__ == "__main__":
        result = load_all_data(None)
        total =  result['total']
        scroll_id = result['scroll_id']
        for i in range(int(total/100)):
            scroll_id = load_all_data(scroll_id)['scroll_id']

  • 相关阅读:
    【POJ 3525】Most Distant Point from the Sea(直线平移、半平面交)
    【HDU 4940】Destroy Transportation system(无源无汇带上下界可行流)
    codevs 5962 [SDOI2017]数字表格
    【NOIP2016】天天爱跑步
    [2011WorldFinal]Chips Challenge[流量平衡]
    [Ahoi2014]支线剧情[无源汇有下界最小费用可行流]
    [NOI2008] 志愿者招募[流量平衡]
    [Wc2007]剪刀石头布[补集转化+拆边]
    poj3281 Dining[最大流]
    1458: 士兵占领[最大流]
  • 原文地址:https://www.cnblogs.com/xiao-xue-di/p/11692212.html
Copyright © 2011-2022 走看看