| |
| |
| <!-- |
| Javascript to render AIRFLOW-XXX and PR references in text |
| as HTML links. |
| |
| Overrides extrahead block from sphinx_rtd_theme |
| https://www.sphinx-doc.org/en/master/templating.html |
| --> |
| |
| |
| <!DOCTYPE html> |
| <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>airflow.contrib.operators.dynamodb_to_s3 — Airflow Documentation</title> |
| |
| |
| |
| |
| <link rel="shortcut icon" href="../../../../../_static/pin_32.png"/> |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../../../" src="../../../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../../../_static/language_data.js"></script> |
| <script type="text/javascript" src="../../../../../_static/jira-links.js"></script> |
| |
| <script type="text/javascript" src="../../../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../../_static/graphviz.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../../../_static/exampleinclude.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../../search.html" /> |
| <link rel="next" title="airflow.contrib.operators.ecs_operator" href="../ecs_operator/index.html" /> |
| <link rel="prev" title="airflow.contrib.operators.druid_operator" href="../druid_operator/index.html" /> |
| |
| <script> |
| </script> |
| <style> |
| |
| </style> |
| |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../../../index.html" class="icon icon-home"> Airflow |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 1.10.8 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../project.html">Project</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../license.html">License</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../start.html">Quick Start</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../installation.html">Installation</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../tutorial.html">Tutorial</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../howto/index.html">How-to Guides</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../ui.html">UI / Screenshots</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../concepts.html">Concepts</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../profiling.html">Data Profiling</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../cli.html">Command Line Interface Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../scheduler.html">Scheduling & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../executor/index.html">Executor</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../plugins.html">Plugins</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../security.html">Security</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../timezone.html">Time zones</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../api.html">REST API Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../integration.html">Integration</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../metrics.html">Metrics</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../errors.html">Error Tracking</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../dag-serialization.html">DAG Serialization</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../changelog.html">Changelog</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../best-practices.html">Best Practices</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../macros.html">Macros reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../privacy_notice.html">Privacy Notice</a></li> |
| </ul> |
| <p class="caption"><span class="caption-text">References</span></p> |
| <ul class="current"> |
| <li class="toctree-l1 current"><a class="reference internal" href="../../../../index.html">Python API</a><ul class="current"> |
| <li class="toctree-l2 current"><a class="reference internal" href="../../../../index.html#operators">Operators</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="../../../../index.html#baseoperator">BaseOperator</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../../../../index.html#basesensoroperator">BaseSensorOperator</a></li> |
| <li class="toctree-l3 current"><a class="reference internal" href="../../../../index.html#operators-packages">Operators packages</a><ul class="current"> |
| <li class="toctree-l4"><a class="reference internal" href="../../../operators/index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.operators</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../../sensors/index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.sensors</span></code></a></li> |
| <li class="toctree-l4 current"><a class="reference internal" href="../index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.operators</span></code></a></li> |
| <li class="toctree-l4"><a class="reference internal" href="../../sensors/index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.sensors</span></code></a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../../index.html#hooks">Hooks</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../../index.html#executors">Executors</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../../index.html#models">Models</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../../../index.html#core-and-community-package">Core and community package</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../../configurations-ref.html">Configurations</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../../../index.html">Airflow</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../../../index.html">Python API Reference</a> »</li> |
| |
| <li><a href="../index.html"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.operators</span></code></a> »</li> |
| |
| <li><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.operators.dynamodb_to_s3</span></code></li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="../../../../../_sources/_api/airflow/contrib/operators/dynamodb_to_s3/index.rst.txt" rel="nofollow"> View page source</a> |
| |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <div class="section" id="module-airflow.contrib.operators.dynamodb_to_s3"> |
| <span id="airflow-contrib-operators-dynamodb-to-s3"></span><h1><a class="reference internal" href="#module-airflow.contrib.operators.dynamodb_to_s3" title="airflow.contrib.operators.dynamodb_to_s3"><code class="xref py py-mod docutils literal notranslate"><span class="pre">airflow.contrib.operators.dynamodb_to_s3</span></code></a><a class="headerlink" href="#module-airflow.contrib.operators.dynamodb_to_s3" title="Permalink to this headline">¶</a></h1> |
| <p><p>This module contains operators to replicate records from |
| DynamoDB table to S3.</p> |
| </p> |
| <div class="section" id="module-contents"> |
| <h2>Module Contents<a class="headerlink" href="#module-contents" title="Permalink to this headline">¶</a></h2> |
| <dl class="function"> |
| <dt id="airflow.contrib.operators.dynamodb_to_s3._convert_item_to_json_bytes"> |
| <code class="sig-prename descclassname">airflow.contrib.operators.dynamodb_to_s3.</code><code class="sig-name descname">_convert_item_to_json_bytes</code><span class="sig-paren">(</span><em class="sig-param">item</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/operators/dynamodb_to_s3.html#_convert_item_to_json_bytes"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.operators.dynamodb_to_s3._convert_item_to_json_bytes" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="function"> |
| <dt id="airflow.contrib.operators.dynamodb_to_s3._upload_file_to_s3"> |
| <code class="sig-prename descclassname">airflow.contrib.operators.dynamodb_to_s3.</code><code class="sig-name descname">_upload_file_to_s3</code><span class="sig-paren">(</span><em class="sig-param">file_obj</em>, <em class="sig-param">bucket_name</em>, <em class="sig-param">s3_key_prefix</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/operators/dynamodb_to_s3.html#_upload_file_to_s3"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.operators.dynamodb_to_s3._upload_file_to_s3" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="class"> |
| <dt id="airflow.contrib.operators.dynamodb_to_s3.DynamoDBToS3Operator"> |
| <em class="property">class </em><code class="sig-prename descclassname">airflow.contrib.operators.dynamodb_to_s3.</code><code class="sig-name descname">DynamoDBToS3Operator</code><span class="sig-paren">(</span><em class="sig-param">dynamodb_table_name</em>, <em class="sig-param">s3_bucket_name</em>, <em class="sig-param">file_size</em>, <em class="sig-param">dynamodb_scan_kwargs=None</em>, <em class="sig-param">s3_key_prefix=''</em>, <em class="sig-param">process_func=_convert_item_to_json_bytes</em>, <em class="sig-param">*args</em>, <em class="sig-param">**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/operators/dynamodb_to_s3.html#DynamoDBToS3Operator"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.operators.dynamodb_to_s3.DynamoDBToS3Operator" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="../../../models/baseoperator/index.html#airflow.models.baseoperator.BaseOperator" title="airflow.models.baseoperator.BaseOperator"><code class="xref py py-class docutils literal notranslate"><span class="pre">airflow.models.baseoperator.BaseOperator</span></code></a></p> |
| <p>Replicates records from a DynamoDB table to S3. |
| It scans a DynamoDB table and write the received records to a file |
| on the local filesystem. It flushes the file to S3 once the file size |
| exceeds the file size limit specified by the user.</p> |
| <p>Users can also specify a filtering criteria using dynamodb_scan_kwargs |
| to only replicate records that satisfy the criteria.</p> |
| <p>To parallelize the replication, users can create multiple tasks of DynamoDBToS3Operator. |
| For instance to replicate with parallelism of 2, create two tasks like:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">op1</span> <span class="o">=</span> <span class="n">DynamoDBToS3Operator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s1">'replicator-1'</span><span class="p">,</span> |
| <span class="n">dynamodb_table_name</span><span class="o">=</span><span class="s1">'hello'</span><span class="p">,</span> |
| <span class="n">dynamodb_scan_kwargs</span><span class="o">=</span><span class="p">{</span> |
| <span class="s1">'TotalSegments'</span><span class="p">:</span> <span class="mi">2</span><span class="p">,</span> |
| <span class="s1">'Segment'</span><span class="p">:</span> <span class="mi">0</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="o">...</span> |
| <span class="p">)</span> |
| |
| <span class="n">op2</span> <span class="o">=</span> <span class="n">DynamoDBToS3Operator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s1">'replicator-2'</span><span class="p">,</span> |
| <span class="n">dynamodb_table_name</span><span class="o">=</span><span class="s1">'hello'</span><span class="p">,</span> |
| <span class="n">dynamodb_scan_kwargs</span><span class="o">=</span><span class="p">{</span> |
| <span class="s1">'TotalSegments'</span><span class="p">:</span> <span class="mi">2</span><span class="p">,</span> |
| <span class="s1">'Segment'</span><span class="p">:</span> <span class="mi">1</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="o">...</span> |
| <span class="p">)</span> |
| </pre></div> |
| </div> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters</dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>dynamodb_table_name</strong> – Dynamodb table to replicate data from</p></li> |
| <li><p><strong>s3_bucket_name</strong> – S3 bucket to replicate data to</p></li> |
| <li><p><strong>file_size</strong> – Flush file to s3 if file size >= file_size</p></li> |
| <li><p><strong>dynamodb_scan_kwargs</strong> – kwargs pass to <<a class="reference external" href="https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/dynamodb.html#DynamoDB.Table.scan">https://boto3.amazonaws.com/v1/documentation/api/latest/reference/services/dynamodb.html#DynamoDB.Table.scan</a>> # noqa: E501 pylint: disable=line-too-long</p></li> |
| <li><p><strong>s3_key_prefix</strong> – Prefix of s3 object key</p></li> |
| <li><p><strong>process_func</strong> – How we transforms a dynamodb item to bytes. By default we dump the json</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="method"> |
| <dt id="airflow.contrib.operators.dynamodb_to_s3.DynamoDBToS3Operator.execute"> |
| <code class="sig-name descname">execute</code><span class="sig-paren">(</span><em class="sig-param">self</em>, <em class="sig-param">context</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/operators/dynamodb_to_s3.html#DynamoDBToS3Operator.execute"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.operators.dynamodb_to_s3.DynamoDBToS3Operator.execute" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| <dl class="method"> |
| <dt id="airflow.contrib.operators.dynamodb_to_s3.DynamoDBToS3Operator._scan_dynamodb_and_upload_to_s3"> |
| <code class="sig-name descname">_scan_dynamodb_and_upload_to_s3</code><span class="sig-paren">(</span><em class="sig-param">self</em>, <em class="sig-param">temp_file</em>, <em class="sig-param">scan_kwargs</em>, <em class="sig-param">table</em><span class="sig-paren">)</span><a class="reference internal" href="../../../../../_modules/airflow/contrib/operators/dynamodb_to_s3.html#DynamoDBToS3Operator._scan_dynamodb_and_upload_to_s3"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#airflow.contrib.operators.dynamodb_to_s3.DynamoDBToS3Operator._scan_dynamodb_and_upload_to_s3" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| </div> |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| |
| |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <a href="../ecs_operator/index.html" class="btn btn-neutral float-right" title="airflow.contrib.operators.ecs_operator" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="../druid_operator/index.html" class="btn btn-neutral float-left" title="airflow.contrib.operators.druid_operator" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a> |
| |
| </div> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| <div class="footer">This page uses <a href="https://analytics.google.com/"> |
| Google Analytics</a> to collect statistics. You can disable it by blocking |
| the JavaScript coming from www.google-analytics.com. Check our |
| <a href="../../../../../privacy_notice.html">Privacy Policy</a> |
| for more details. |
| </div> |
| |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| <!-- Theme Analytics --> |
| <script> |
| (function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){ |
| (i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new Date();a=s.createElement(o), |
| m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m) |
| })(window,document,'script','https://www.google-analytics.com/analytics.js','ga'); |
| |
| ga('create', 'UA-140539454-1', 'auto'); |
| ga('send', 'pageview'); |
| </script> |
| |
| |
| |
| |
| </body> |
| </html> |
