| |
| |
| <!-- |
| 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>Google Cloud Storage to Google Drive Transfer Operators — 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="Google Cloud Natural Language Operators" href="natural_language.html" /> |
| <link rel="prev" title="Google Cloud Storage Operators" href="gcs.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 class="current"> |
| <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 current"><a class="reference internal" href="../../index.html">How-to Guides</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="../../set-config.html">Setting Configuration Options</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../initialize-database.html">Initializing a Database Backend</a></li> |
| <li class="toctree-l2 current"><a class="reference internal" href="../index.html">Using Operators</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="../bash.html">BashOperator</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../dingding.html">Dingding Operators</a></li> |
| <li class="toctree-l3 current"><a class="reference internal" href="index.html">Google Cloud Operators</a><ul class="current"> |
| <li class="toctree-l4"><a class="reference internal" href="bigtable.html">Google Cloud Bigtable Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="cloud_build.html">Google Cloud Build Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="compute.html">Google Compute Engine Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="function.html">Google Cloud Functions Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="gcs.html">Google Cloud Storage Operators</a></li> |
| <li class="toctree-l4 current"><a class="current reference internal" href="#">Google Cloud Storage to Google Drive Transfer Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="natural_language.html">Google Cloud Natural Language Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="spanner.html">Google Cloud Spanner Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="speech.html">Google Cloud Text to Speech Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="speech.html#google-cloud-speech-to-text-operators">Google Cloud Speech to Text Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="sql.html">Google Cloud Sql Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="transfer.html">Google Cloud Transfer Service Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="translate.html">Google Cloud Translate Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="translate-speech.html">Google Cloud Speech Translate Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="video.html">Google Cloud Video Intelligence Operators</a></li> |
| <li class="toctree-l4"><a class="reference internal" href="vision.html">Google Cloud Vision Operators</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="../papermill.html">Papermill</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../python.html">PythonOperator</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="../external.html">Cross-DAG Dependencies</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../../custom-operator.html">Creating a custom Operator</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../connection/index.html">Managing Connections</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../secure-connections.html">Securing Connections</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../secure-connections.html#rotating-encryption-keys">Rotating encryption keys</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../write-logs.html">Writing Logs</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../run-behind-proxy.html">Running Airflow behind a reverse proxy</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../run-with-systemd.html">Running Airflow with systemd</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../run-with-upstart.html">Running Airflow with upstart</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../use-test-config.html">Using the Test Mode Configuration</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../check-health.html">Checking Airflow Health Status</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../define_extra_link.html">Define an operator extra link</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../email-config.html">Email Configuration</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../tracking-user-activity.html">Tracking User Activity</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../../cli-completion.html">Using the Command Line Interface</a></li> |
| </ul> |
| </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> |
| <li class="toctree-l1"><a class="reference internal" href="../../../_api/index.html">Python API</a></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">How-to Guides</a> »</li> |
| |
| <li><a href="../index.html">Using Operators</a> »</li> |
| |
| <li><a href="index.html">Google Cloud Operators</a> »</li> |
| |
| <li>Google Cloud Storage to Google Drive Transfer Operators</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="../../../_sources/howto/operator/gcp/gcs_to_gdrive.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"> |
| |
| <blockquote> |
| <div></div></blockquote> |
| <div class="section" id="google-cloud-storage-to-google-drive-transfer-operators"> |
| <h1>Google Cloud Storage to Google Drive Transfer Operators<a class="headerlink" href="#google-cloud-storage-to-google-drive-transfer-operators" title="Permalink to this headline">¶</a></h1> |
| <p>Google has two services that store data. The <a class="reference external" href="https://cloud.google.com/storage/">Google Cloud Storage</a> is |
| used to store large data from various applications. The <a class="reference external" href="https://www.google.com/drive/">Google Drive</a> is |
| used to store daily use data, including documents and photos. Google Cloud Storage has strong integration |
| with Google Cloud Platform services. Google Drive has built-in mechanisms to facilitate group work e.g. |
| document editor, file sharing mechanisms.</p> |
| <div class="contents local topic" id="contents"> |
| <ul class="simple"> |
| <li><p><a class="reference internal" href="#prerequisite-tasks" id="id1">Prerequisite Tasks</a></p></li> |
| <li><p><a class="reference internal" href="#operator" id="id2">Operator</a></p></li> |
| <li><p><a class="reference internal" href="#reference" id="id3">Reference</a></p></li> |
| </ul> |
| </div> |
| <div class="section" id="prerequisite-tasks"> |
| <h2><a class="toc-backref" href="#id1">Prerequisite Tasks</a><a class="headerlink" href="#prerequisite-tasks" title="Permalink to this headline">¶</a></h2> |
| <blockquote> |
| <div></div></blockquote> |
| <p>To use these operators, you must do a few things:</p> |
| <blockquote> |
| <div><ul> |
| <li><p>Select or create a Cloud Platform project using <a class="reference external" href="https://console.cloud.google.com/project">Cloud Console</a>.</p></li> |
| <li><p>Enable billing for your project, as described in <a class="reference external" href="https://cloud.google.com/billing/docs/how-to/modify-project#enable_billing_for_a_project">Google Cloud documentation</a>.</p></li> |
| <li><p>Enable API, as described in <a class="reference external" href="https://cloud.google.com/apis/docs/enable-disable-apis">Cloud Console documentation</a>.</p></li> |
| <li><p>Install API libraries via <strong>pip</strong>.</p> |
| <div class="highlight-bash notranslate"><div class="highlight"><pre><span></span>pip install <span class="s1">'apache-airflow[gcp]'</span> |
| </pre></div> |
| </div> |
| <p>Detailed information is available <a class="reference internal" href="../../../installation.html"><span class="doc">Installation</span></a></p> |
| </li> |
| <li><p><a class="reference internal" href="../../connection/gcp.html"><span class="doc">Setup Connection</span></a>.</p></li> |
| </ul> |
| </div></blockquote> |
| </div> |
| <div class="section" id="operator"> |
| <span id="howto-operator-gcstogdriveoperator"></span><h2><a class="toc-backref" href="#id2">Operator</a><a class="headerlink" href="#operator" title="Permalink to this headline">¶</a></h2> |
| <p>Transfer files between Google Storage and Google Drive is performed with the |
| <a class="reference internal" href="../../../_api/airflow/contrib/operators/gcs_to_gdrive_operator/index.html#airflow.contrib.operators.gcs_to_gdrive_operator.GcsToGDriveOperator" title="airflow.contrib.operators.gcs_to_gdrive_operator.GcsToGDriveOperator"><code class="xref py py-class docutils literal notranslate"><span class="pre">GcsToGDriveOperator</span></code></a> operator.</p> |
| <p>You can use <a class="reference internal" href="../../../concepts.html#jinja-templating"><span class="std std-ref">Jinja templating</span></a> with |
| <span><code class="docutils literal notranslate"><span class="pre">source_bucket</span></code>, <code class="docutils literal notranslate"><span class="pre">source_object</span></code>, <code class="docutils literal notranslate"><span class="pre">destination_object</span></code></span> |
| parameters which allows you to dynamically determine values.</p> |
| <div class="section" id="copy-single-files"> |
| <h3>Copy single files<a class="headerlink" href="#copy-single-files" title="Permalink to this headline">¶</a></h3> |
| <p>The following Operator would copy a single file.</p> |
| <div class="example-block-wrapper docutils container"> |
| <p class="example-header example-header--with-button"><span class="example-title">airflow/contrib/example_dags/example_gcs_to_gdrive.py</span><a class="example-header-button viewcode-button reference internal" href="../../../_modules/airflow/contrib/example_dags/example_gcs_to_gdrive.html"><span>View Source</span></a></p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">copy_single_file</span> <span class="o">=</span> <span class="n">GcsToGDriveOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"copy_single_file"</span><span class="p">,</span> |
| <span class="n">source_bucket</span><span class="o">=</span><span class="n">GCS_TO_GDRIVE_BUCKET</span><span class="p">,</span> |
| <span class="n">source_object</span><span class="o">=</span><span class="s2">"sales/january.avro"</span><span class="p">,</span> |
| <span class="n">destination_object</span><span class="o">=</span><span class="s2">"copied_sales/january-backup.avro"</span><span class="p">,</span> |
| <span class="p">)</span> |
| </pre></div> |
| </div> |
| </div> |
| </div> |
| <div class="section" id="copy-multiple-files"> |
| <h3>Copy multiple files<a class="headerlink" href="#copy-multiple-files" title="Permalink to this headline">¶</a></h3> |
| <p>The following Operator would copy all the multiples files (i.e. using wildcard).</p> |
| <div class="example-block-wrapper docutils container"> |
| <p class="example-header example-header--with-button"><span class="example-title">airflow/contrib/example_dags/example_gcs_to_gdrive.py</span><a class="example-header-button viewcode-button reference internal" href="../../../_modules/airflow/contrib/example_dags/example_gcs_to_gdrive.html"><span>View Source</span></a></p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">copy_files</span> <span class="o">=</span> <span class="n">GcsToGDriveOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"copy_files"</span><span class="p">,</span> |
| <span class="n">source_bucket</span><span class="o">=</span><span class="n">GCS_TO_GDRIVE_BUCKET</span><span class="p">,</span> |
| <span class="n">source_object</span><span class="o">=</span><span class="s2">"sales/*"</span><span class="p">,</span> |
| <span class="n">destination_object</span><span class="o">=</span><span class="s2">"copied_sales/"</span><span class="p">,</span> |
| <span class="p">)</span> |
| </pre></div> |
| </div> |
| </div> |
| </div> |
| <div class="section" id="move-files"> |
| <h3>Move files<a class="headerlink" href="#move-files" title="Permalink to this headline">¶</a></h3> |
| <p>Using the <code class="docutils literal notranslate"><span class="pre">move_object</span></code> parameter allows you to move the files. After copying the file to Google Drive, |
| the original file from the bucket is deleted.</p> |
| <div class="example-block-wrapper docutils container"> |
| <p class="example-header example-header--with-button"><span class="example-title">airflow/contrib/example_dags/example_gcs_to_gdrive.py</span><a class="example-header-button viewcode-button reference internal" href="../../../_modules/airflow/contrib/example_dags/example_gcs_to_gdrive.html"><span>View Source</span></a></p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">move_files</span> <span class="o">=</span> <span class="n">GcsToGDriveOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"move_files"</span><span class="p">,</span> |
| <span class="n">source_bucket</span><span class="o">=</span><span class="n">GCS_TO_GDRIVE_BUCKET</span><span class="p">,</span> |
| <span class="n">source_object</span><span class="o">=</span><span class="s2">"sales/*.avro"</span><span class="p">,</span> |
| <span class="n">move_object</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> |
| <span class="p">)</span> |
| </pre></div> |
| </div> |
| </div> |
| </div> |
| </div> |
| <div class="section" id="reference"> |
| <h2><a class="toc-backref" href="#id3">Reference</a><a class="headerlink" href="#reference" title="Permalink to this headline">¶</a></h2> |
| <p>For further information, look at:</p> |
| <ul class="simple"> |
| <li><p><a class="reference external" href="https://developers.google.com/drive/api/v3/about-sdk">Google Drive API Documentation</a></p></li> |
| <li><p><a class="reference external" href="https://cloud.google.com/storage/">Google Cloud Storage Documentation</a></p></li> |
| </ul> |
| </div> |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| |
| |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <a href="natural_language.html" class="btn btn-neutral float-right" title="Google Cloud Natural Language Operators" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="gcs.html" class="btn btn-neutral float-left" title="Google Cloud Storage Operators" 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> |
