amazon-web-services - AWS CloudSearch 导出/下载数据

Question

我的 AWS CloudSearch 索引中有大约 150 万个文档。这让我付出了太多的代价，我希望放弃该服务。我无法看到如何从索引下载或导出我的文档。可能吗？

Answer 1

刚刚修复了一些问题，完全归功于@Nek 的回复 https://stackoverflow.com/a/32119407/1894553

<小时/>

先决条件，node + aws-sdk 插件

$ npm install aws-sdk

导出all.js

请注意，为了使用 return: "_all_fields" 参数获取完整转储，此字段必须在架构的索引选项中启用 return 标志。

var AWS = require('aws-sdk');
var fs = require('fs');

AWS.config.update({
        accessKeyId: 'xx',
        secretAccessKey: 'xx',
        region: 'xx',
        endpoint: 'xxx'
});

var batchSize = 10000;
var compteur = 0;
var result = [];
var resultMessage = [];

var params = {query:""};
var cloudsearchdomain = new AWS.CloudSearchDomain(params);

function launchSearch(theContext) {
    process.stdout.write('Launch AWS.CloudSearch ');

    if (theContext==null) {
        process.stdout.write('initial request ... ');
    } else {
        var current  = (theContext.start/batchSize) +2 ;
        var totalRun = (Math.ceil(theContext.found/batchSize  * 10) / 10) + 1;
        process.stdout.write('( ' + current + ' / ' + totalRun + ' )       ... ');
    }

// https://docs.aws.amazon.com/AWSJavaScriptSDK/latest/AWS/CloudSearchDomain.html#search-property
params = {
    query:"matchall",
    cursor: (theContext==null)?"initial":theContext.cursor,
    size:batchSize,
    queryParser: "structured",
    return: "_all_fields"
};
 
    var forCursor = new AWS.CloudSearchDomain(params);

    forCursor.search(params, function(err, data) {
        if (err) {
            console.log("Failed with params :" );
            console.log(err);
        } else {
            resultMessage = data;
            compteur = compteur + data.hits.hit.length;
            for(var i=0;i<data.hits.hit.length;i++){
                result.push(data.hits.hit[i]);
                };
            }


        process.stdout.write(resultMessage.hits.hit.length + ' hits found.');

        if (resultMessage.hits.hit.length==0) {
            process.stdout.write(' Done.\n\nLet\'s create thte file...\n');
            writeTheFile(result);
        } else {
            process.stdout.write('\n');
            var myContext = {};
            myContext.cursor = resultMessage.hits.cursor;
            myContext.start = resultMessage.hits.start;
            myContext.found = resultMessage.hits.found;
            myContext.retrived = resultMessage.hits.hit.length;
            launchSearch(myContext);
        }
    });
}

function writeTheFile(myResult) {

    fs.writeFile(process.argv[2], JSON.stringify(myResult), function(err) {
        if(err) {
            return console.log(err);
        }
    });
    process.stdout.write("DONE : File '"+ process.argv[2] + "' generated  ( " + compteur + " elements ).\n");
}



 /*Check parameters*/
if (!process.argv[2]) {
     //console.log(process.argv);
    process.stdout.write('ERROR : the output filename is expected as argument.\n');
    process.exit();
 } else {
    launchSearch();
}  

#执行

$ node export-all.js all-data.json