| |
| |
| |
| |
| |
| <!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.bigquery_get_data — Airflow Documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <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/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="index" title="Index" href="../../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../../search.html" /> |
| |
| <script> |
| document.addEventListener('DOMContentLoaded', function() { |
| var el = document.getElementById('changelog'); |
| if (el !== null ) { |
| // [AIRFLOW-...] |
| el.innerHTML = el.innerHTML.replace( |
| /\[(AIRFLOW-[\d]+)\]/g, |
| `<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>` |
| ); |
| // (#...) |
| el.innerHTML = el.innerHTML.replace( |
| /\(#([\d]+)\)/g, |
| `<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>` |
| ); |
| }; |
| }) |
| </script> |
| <!-- Matomo --> |
| <script> |
| var _paq = window._paq = window._paq || []; |
| _paq.push(['disableCookies']); |
| _paq.push(['trackPageView']); |
| _paq.push(['enableLinkTracking']); |
| (function() { |
| var u="https://analytics.apache.org/"; |
| _paq.push(['setTrackerUrl', u+'matomo.php']); |
| _paq.push(['setSiteId', '13']); |
| var d=document, g=d.createElement('script'), s=d.getElementsByTagName('script')[0]; |
| g.async=true; g.src=u+'matomo.js'; s.parentNode.insertBefore(g,s); |
| })(); |
| </script> |
| <!-- End Matomo --> |
| <style> |
| .example-header { |
| position: relative; |
| background: #9AAA7A; |
| padding: 8px 16px; |
| margin-bottom: 0; |
| } |
| .example-header--with-button { |
| padding-right: 166px; |
| } |
| .example-header:after{ |
| content: ''; |
| display: table; |
| clear: both; |
| } |
| .example-title { |
| display:block; |
| padding: 4px; |
| margin-right: 16px; |
| color: white; |
| overflow-x: auto; |
| } |
| .example-header-button { |
| top: 8px; |
| right: 16px; |
| position: absolute; |
| } |
| .example-header + .highlight-python { |
| margin-top: 0 !important; |
| } |
| .viewcode-button { |
| display: inline-block; |
| padding: 8px 16px; |
| border: 0; |
| margin: 0; |
| outline: 0; |
| border-radius: 2px; |
| -webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3); |
| box-shadow: 0 3px 6px 0 rgba(0,0,0,.3); |
| color: #404040; |
| background-color: #e7e7e7; |
| cursor: pointer; |
| font-size: 16px; |
| font-weight: 500; |
| line-height: 1; |
| text-decoration: none; |
| text-overflow: ellipsis; |
| overflow: hidden; |
| text-transform: uppercase; |
| -webkit-transition: background-color .2s; |
| transition: background-color .2s; |
| vertical-align: middle; |
| white-space: nowrap; |
| } |
| .viewcode-button:visited { |
| color: #404040; |
| } |
| .viewcode-button:hover, .viewcode-button:focus { |
| color: #404040; |
| background-color: #d6d6d6; |
| } |
| </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"> |
| 1.10.5 |
| </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="../../../../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="../../../../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="../../../../changelog.html">Changelog</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="../../../../_api/index.html">Python API Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../privacy_notice.html">Privacy Notice</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">Module code</a> »</li> |
| |
| <li><a href="../operators.html">airflow.contrib.operators</a> »</li> |
| |
| <li>airflow.contrib.operators.bigquery_get_data</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <h1>Source code for airflow.contrib.operators.bigquery_get_data</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># -*- coding: utf-8 -*-</span> |
| <span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="c1"># or more contributor license agreements. See the NOTICE file</span> |
| <span class="c1"># distributed with this work for additional information</span> |
| <span class="c1"># regarding copyright ownership. The ASF licenses this file</span> |
| <span class="c1"># to you under the Apache License, Version 2.0 (the</span> |
| <span class="c1"># "License"); you may not use this file except in compliance</span> |
| <span class="c1"># with the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing,</span> |
| <span class="c1"># software distributed under the License is distributed on an</span> |
| <span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span> |
| <span class="c1"># KIND, either express or implied. See the License for the</span> |
| <span class="c1"># specific language governing permissions and limitations</span> |
| <span class="c1"># under the License.</span> |
| |
| <span class="kn">from</span> <span class="nn">airflow.contrib.hooks.bigquery_hook</span> <span class="k">import</span> <span class="n">BigQueryHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.models</span> <span class="k">import</span> <span class="n">BaseOperator</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span> |
| |
| |
| <div class="viewcode-block" id="BigQueryGetDataOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/bigquery_get_data/index.html#airflow.contrib.operators.bigquery_get_data.BigQueryGetDataOperator">[docs]</a><span class="k">class</span> <span class="nc">BigQueryGetDataOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Fetches the data from a BigQuery table (alternatively fetch data for selected columns)</span> |
| <span class="sd"> and returns data in a python list. The number of elements in the returned list will</span> |
| <span class="sd"> be equal to the number of rows fetched. Each element in the list will again be a list</span> |
| <span class="sd"> where element would represent the columns values for that row.</span> |
| |
| <span class="sd"> **Example Result**: ``[['Tony', '10'], ['Mike', '20'], ['Steve', '15']]``</span> |
| |
| <span class="sd"> .. note::</span> |
| <span class="sd"> If you pass fields to ``selected_fields`` which are in different order than the</span> |
| <span class="sd"> order of columns already in</span> |
| <span class="sd"> BQ table, the data will still be in the order of BQ table.</span> |
| <span class="sd"> For example if the BQ table has 3 columns as</span> |
| <span class="sd"> ``[A,B,C]`` and you pass 'B,A' in the ``selected_fields``</span> |
| <span class="sd"> the data would still be of the form ``'A,B'``.</span> |
| |
| <span class="sd"> **Example**: ::</span> |
| |
| <span class="sd"> get_data = BigQueryGetDataOperator(</span> |
| <span class="sd"> task_id='get_data_from_bq',</span> |
| <span class="sd"> dataset_id='test_dataset',</span> |
| <span class="sd"> table_id='Transaction_partitions',</span> |
| <span class="sd"> max_results='100',</span> |
| <span class="sd"> selected_fields='DATE',</span> |
| <span class="sd"> bigquery_conn_id='airflow-service-account'</span> |
| <span class="sd"> )</span> |
| |
| <span class="sd"> :param dataset_id: The dataset ID of the requested table. (templated)</span> |
| <span class="sd"> :type dataset_id: str</span> |
| <span class="sd"> :param table_id: The table ID of the requested table. (templated)</span> |
| <span class="sd"> :type table_id: str</span> |
| <span class="sd"> :param max_results: The maximum number of records (rows) to be fetched</span> |
| <span class="sd"> from the table. (templated)</span> |
| <span class="sd"> :type max_results: str</span> |
| <span class="sd"> :param selected_fields: List of fields to return (comma-separated). If</span> |
| <span class="sd"> unspecified, all fields are returned.</span> |
| <span class="sd"> :type selected_fields: str</span> |
| <span class="sd"> :param bigquery_conn_id: reference to a specific BigQuery hook.</span> |
| <span class="sd"> :type bigquery_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have domain-wide</span> |
| <span class="sd"> delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> """</span> |
| <div class="viewcode-block" id="BigQueryGetDataOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/bigquery_get_data/index.html#airflow.contrib.operators.bigquery_get_data.BigQueryGetDataOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">(</span><span class="s1">'dataset_id'</span><span class="p">,</span> <span class="s1">'table_id'</span><span class="p">,</span> <span class="s1">'max_results'</span><span class="p">)</span></div> |
| <div class="viewcode-block" id="BigQueryGetDataOperator.ui_color"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/bigquery_get_data/index.html#airflow.contrib.operators.bigquery_get_data.BigQueryGetDataOperator.ui_color">[docs]</a> <span class="n">ui_color</span> <span class="o">=</span> <span class="s1">'#e4f0e8'</span></div> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">dataset_id</span><span class="p">,</span> |
| <span class="n">table_id</span><span class="p">,</span> |
| <span class="n">max_results</span><span class="o">=</span><span class="s1">'100'</span><span class="p">,</span> |
| <span class="n">selected_fields</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">bigquery_conn_id</span><span class="o">=</span><span class="s1">'bigquery_default'</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">BigQueryGetDataOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataset_id</span> <span class="o">=</span> <span class="n">dataset_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">table_id</span> <span class="o">=</span> <span class="n">table_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">max_results</span> <span class="o">=</span> <span class="n">max_results</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">selected_fields</span> <span class="o">=</span> <span class="n">selected_fields</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span> <span class="o">=</span> <span class="n">bigquery_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| |
| <div class="viewcode-block" id="BigQueryGetDataOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/bigquery_get_data/index.html#airflow.contrib.operators.bigquery_get_data.BigQueryGetDataOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Fetching Data from:'</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Dataset: </span><span class="si">%s</span><span class="s1"> ; Table: </span><span class="si">%s</span><span class="s1"> ; Max Results: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">dataset_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">table_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">max_results</span><span class="p">)</span> |
| |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">BigQueryHook</span><span class="p">(</span><span class="n">bigquery_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">bigquery_conn_id</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">delegate_to</span><span class="p">)</span> |
| |
| <span class="n">conn</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> |
| <span class="n">cursor</span> <span class="o">=</span> <span class="n">conn</span><span class="o">.</span><span class="n">cursor</span><span class="p">()</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="n">cursor</span><span class="o">.</span><span class="n">get_tabledata</span><span class="p">(</span><span class="n">dataset_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">dataset_id</span><span class="p">,</span> |
| <span class="n">table_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">table_id</span><span class="p">,</span> |
| <span class="n">max_results</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">max_results</span><span class="p">,</span> |
| <span class="n">selected_fields</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">selected_fields</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Total Extracted rows: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">response</span><span class="p">[</span><span class="s1">'totalRows'</span><span class="p">])</span> |
| <span class="n">rows</span> <span class="o">=</span> <span class="n">response</span><span class="p">[</span><span class="s1">'rows'</span><span class="p">]</span> |
| |
| <span class="n">table_data</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">dict_row</span> <span class="ow">in</span> <span class="n">rows</span><span class="p">:</span> |
| <span class="n">single_row</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">fields</span> <span class="ow">in</span> <span class="n">dict_row</span><span class="p">[</span><span class="s1">'f'</span><span class="p">]:</span> |
| <span class="n">single_row</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">fields</span><span class="p">[</span><span class="s1">'v'</span><span class="p">])</span> |
| <span class="n">table_data</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">single_row</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">table_data</span></div></div> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <footer> |
| |
| |
| <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>. |
| |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |