| |
| |
| |
| |
| |
| <!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.hooks.S3_hook — 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> |
| <script type="text/javascript"> |
| var _gaq = _gaq || []; |
| _gaq.push(['_setAccount', 'UA-140539454-1']); |
| _gaq.push(['_trackPageview']); |
| </script> |
| <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="../hooks.html">airflow.hooks</a> »</li> |
| |
| <li>airflow.hooks.S3_hook</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.hooks.S3_hook</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">botocore.exceptions</span> <span class="k">import</span> <span class="n">ClientError</span> |
| |
| <span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</span> |
| <span class="kn">from</span> <span class="nn">airflow.contrib.hooks.aws_hook</span> <span class="k">import</span> <span class="n">AwsHook</span> |
| |
| <span class="kn">from</span> <span class="nn">six</span> <span class="k">import</span> <span class="n">BytesIO</span> |
| <span class="kn">from</span> <span class="nn">urllib.parse</span> <span class="k">import</span> <span class="n">urlparse</span> |
| <span class="kn">import</span> <span class="nn">re</span> |
| <span class="kn">import</span> <span class="nn">fnmatch</span> |
| |
| |
| <div class="viewcode-block" id="S3Hook"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook">[docs]</a><span class="k">class</span> <span class="nc">S3Hook</span><span class="p">(</span><span class="n">AwsHook</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Interact with AWS S3, using the boto3 library.</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="S3Hook.get_conn"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.get_conn">[docs]</a> <span class="k">def</span> <span class="nf">get_conn</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_client_type</span><span class="p">(</span><span class="s1">'s3'</span><span class="p">)</span></div> |
| |
| <span class="nd">@staticmethod</span> |
| <div class="viewcode-block" id="S3Hook.parse_s3_url"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.parse_s3_url">[docs]</a> <span class="k">def</span> <span class="nf">parse_s3_url</span><span class="p">(</span><span class="n">s3url</span><span class="p">):</span> |
| <span class="n">parsed_url</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">s3url</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Please provide a bucket_name instead of "</span><span class="si">%s</span><span class="s1">"'</span> <span class="o">%</span> <span class="n">s3url</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">bucket_name</span> <span class="o">=</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span> |
| <span class="n">key</span> <span class="o">=</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">strip</span><span class="p">(</span><span class="s1">'/'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.check_for_bucket"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.check_for_bucket">[docs]</a> <span class="k">def</span> <span class="nf">check_for_bucket</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Check if bucket_name exists.</span> |
| |
| <span class="sd"> :param bucket_name: the name of the bucket</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> """</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">head_bucket</span><span class="p">(</span><span class="n">Bucket</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">)</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| <span class="k">except</span> <span class="n">ClientError</span> <span class="k">as</span> <span class="n">e</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="n">e</span><span class="o">.</span><span class="n">response</span><span class="p">[</span><span class="s2">"Error"</span><span class="p">][</span><span class="s2">"Message"</span><span class="p">])</span> |
| <span class="k">return</span> <span class="kc">False</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.get_bucket"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.get_bucket">[docs]</a> <span class="k">def</span> <span class="nf">get_bucket</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns a boto3.S3.Bucket object</span> |
| |
| <span class="sd"> :param bucket_name: the name of the bucket</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> """</span> |
| <span class="n">s3</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_resource_type</span><span class="p">(</span><span class="s1">'s3'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">s3</span><span class="o">.</span><span class="n">Bucket</span><span class="p">(</span><span class="n">bucket_name</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.create_bucket"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.create_bucket">[docs]</a> <span class="k">def</span> <span class="nf">create_bucket</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">,</span> <span class="n">region_name</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Creates an Amazon S3 bucket.</span> |
| |
| <span class="sd"> :param bucket_name: The name of the bucket</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param region_name: The name of the aws region in which to create the bucket.</span> |
| <span class="sd"> :type region_name: str</span> |
| <span class="sd"> """</span> |
| <span class="n">s3_conn</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">region_name</span><span class="p">:</span> |
| <span class="n">region_name</span> <span class="o">=</span> <span class="n">s3_conn</span><span class="o">.</span><span class="n">meta</span><span class="o">.</span><span class="n">region_name</span> |
| <span class="k">if</span> <span class="n">region_name</span> <span class="o">==</span> <span class="s1">'us-east-1'</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">create_bucket</span><span class="p">(</span><span class="n">Bucket</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">create_bucket</span><span class="p">(</span><span class="n">Bucket</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">,</span> |
| <span class="n">CreateBucketConfiguration</span><span class="o">=</span><span class="p">{</span> |
| <span class="s1">'LocationConstraint'</span><span class="p">:</span> <span class="n">region_name</span></div> |
| <span class="p">})</span> |
| |
| <div class="viewcode-block" id="S3Hook.check_for_prefix"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.check_for_prefix">[docs]</a> <span class="k">def</span> <span class="nf">check_for_prefix</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">,</span> <span class="n">prefix</span><span class="p">,</span> <span class="n">delimiter</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Checks that a prefix exists in a bucket</span> |
| |
| <span class="sd"> :param bucket_name: the name of the bucket</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param prefix: a key prefix</span> |
| <span class="sd"> :type prefix: str</span> |
| <span class="sd"> :param delimiter: the delimiter marks key hierarchy.</span> |
| <span class="sd"> :type delimiter: str</span> |
| <span class="sd"> """</span> |
| <span class="n">prefix</span> <span class="o">=</span> <span class="n">prefix</span> <span class="o">+</span> <span class="n">delimiter</span> <span class="k">if</span> <span class="n">prefix</span><span class="p">[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="o">!=</span> <span class="n">delimiter</span> <span class="k">else</span> <span class="n">prefix</span> |
| <span class="n">prefix_split</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="sa">r</span><span class="s1">'(\w+[</span><span class="si">{d}</span><span class="s1">])$'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">d</span><span class="o">=</span><span class="n">delimiter</span><span class="p">),</span> <span class="n">prefix</span><span class="p">,</span> <span class="mi">1</span><span class="p">)</span> |
| <span class="n">previous_level</span> <span class="o">=</span> <span class="n">prefix_split</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="n">plist</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">list_prefixes</span><span class="p">(</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">previous_level</span><span class="p">,</span> <span class="n">delimiter</span><span class="p">)</span> |
| <span class="k">return</span> <span class="kc">False</span> <span class="k">if</span> <span class="n">plist</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">prefix</span> <span class="ow">in</span> <span class="n">plist</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.list_prefixes"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.list_prefixes">[docs]</a> <span class="k">def</span> <span class="nf">list_prefixes</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="s1">''</span><span class="p">,</span> <span class="n">delimiter</span><span class="o">=</span><span class="s1">''</span><span class="p">,</span> |
| <span class="n">page_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">max_items</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Lists prefixes in a bucket under prefix</span> |
| |
| <span class="sd"> :param bucket_name: the name of the bucket</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param prefix: a key prefix</span> |
| <span class="sd"> :type prefix: str</span> |
| <span class="sd"> :param delimiter: the delimiter marks key hierarchy.</span> |
| <span class="sd"> :type delimiter: str</span> |
| <span class="sd"> :param page_size: pagination size</span> |
| <span class="sd"> :type page_size: int</span> |
| <span class="sd"> :param max_items: maximum items to return</span> |
| <span class="sd"> :type max_items: int</span> |
| <span class="sd"> """</span> |
| <span class="n">config</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'PageSize'</span><span class="p">:</span> <span class="n">page_size</span><span class="p">,</span> |
| <span class="s1">'MaxItems'</span><span class="p">:</span> <span class="n">max_items</span><span class="p">,</span> |
| <span class="p">}</span> |
| |
| <span class="n">paginator</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">get_paginator</span><span class="p">(</span><span class="s1">'list_objects_v2'</span><span class="p">)</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="n">paginator</span><span class="o">.</span><span class="n">paginate</span><span class="p">(</span><span class="n">Bucket</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">,</span> |
| <span class="n">Prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> |
| <span class="n">Delimiter</span><span class="o">=</span><span class="n">delimiter</span><span class="p">,</span> |
| <span class="n">PaginationConfig</span><span class="o">=</span><span class="n">config</span><span class="p">)</span> |
| |
| <span class="n">has_results</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="n">prefixes</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">page</span> <span class="ow">in</span> <span class="n">response</span><span class="p">:</span> |
| <span class="k">if</span> <span class="s1">'CommonPrefixes'</span> <span class="ow">in</span> <span class="n">page</span><span class="p">:</span> |
| <span class="n">has_results</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">page</span><span class="p">[</span><span class="s1">'CommonPrefixes'</span><span class="p">]:</span> |
| <span class="n">prefixes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">p</span><span class="p">[</span><span class="s1">'Prefix'</span><span class="p">])</span> |
| |
| <span class="k">if</span> <span class="n">has_results</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">prefixes</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.list_keys"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.list_keys">[docs]</a> <span class="k">def</span> <span class="nf">list_keys</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="s1">''</span><span class="p">,</span> <span class="n">delimiter</span><span class="o">=</span><span class="s1">''</span><span class="p">,</span> |
| <span class="n">page_size</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">max_items</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Lists keys in a bucket under prefix and not containing delimiter</span> |
| |
| <span class="sd"> :param bucket_name: the name of the bucket</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param prefix: a key prefix</span> |
| <span class="sd"> :type prefix: str</span> |
| <span class="sd"> :param delimiter: the delimiter marks key hierarchy.</span> |
| <span class="sd"> :type delimiter: str</span> |
| <span class="sd"> :param page_size: pagination size</span> |
| <span class="sd"> :type page_size: int</span> |
| <span class="sd"> :param max_items: maximum items to return</span> |
| <span class="sd"> :type max_items: int</span> |
| <span class="sd"> """</span> |
| <span class="n">config</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'PageSize'</span><span class="p">:</span> <span class="n">page_size</span><span class="p">,</span> |
| <span class="s1">'MaxItems'</span><span class="p">:</span> <span class="n">max_items</span><span class="p">,</span> |
| <span class="p">}</span> |
| |
| <span class="n">paginator</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">get_paginator</span><span class="p">(</span><span class="s1">'list_objects_v2'</span><span class="p">)</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="n">paginator</span><span class="o">.</span><span class="n">paginate</span><span class="p">(</span><span class="n">Bucket</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">,</span> |
| <span class="n">Prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> |
| <span class="n">Delimiter</span><span class="o">=</span><span class="n">delimiter</span><span class="p">,</span> |
| <span class="n">PaginationConfig</span><span class="o">=</span><span class="n">config</span><span class="p">)</span> |
| |
| <span class="n">has_results</span> <span class="o">=</span> <span class="kc">False</span> |
| <span class="n">keys</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="k">for</span> <span class="n">page</span> <span class="ow">in</span> <span class="n">response</span><span class="p">:</span> |
| <span class="k">if</span> <span class="s1">'Contents'</span> <span class="ow">in</span> <span class="n">page</span><span class="p">:</span> |
| <span class="n">has_results</span> <span class="o">=</span> <span class="kc">True</span> |
| <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">page</span><span class="p">[</span><span class="s1">'Contents'</span><span class="p">]:</span> |
| <span class="n">keys</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">k</span><span class="p">[</span><span class="s1">'Key'</span><span class="p">])</span> |
| |
| <span class="k">if</span> <span class="n">has_results</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">keys</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.check_for_key"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.check_for_key">[docs]</a> <span class="k">def</span> <span class="nf">check_for_key</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Checks if a key exists in a bucket</span> |
| |
| <span class="sd"> :param key: S3 key that will point to the file</span> |
| <span class="sd"> :type key: str</span> |
| <span class="sd"> :param bucket_name: Name of the bucket in which the file is stored</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">bucket_name</span><span class="p">:</span> |
| <span class="p">(</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span><span class="p">)</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">parse_s3_url</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">head_object</span><span class="p">(</span><span class="n">Bucket</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">Key</span><span class="o">=</span><span class="n">key</span><span class="p">)</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| <span class="k">except</span> <span class="n">ClientError</span> <span class="k">as</span> <span class="n">e</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="n">e</span><span class="o">.</span><span class="n">response</span><span class="p">[</span><span class="s2">"Error"</span><span class="p">][</span><span class="s2">"Message"</span><span class="p">])</span> |
| <span class="k">return</span> <span class="kc">False</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.get_key"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.get_key">[docs]</a> <span class="k">def</span> <span class="nf">get_key</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns a boto3.s3.Object</span> |
| |
| <span class="sd"> :param key: the path to the key</span> |
| <span class="sd"> :type key: str</span> |
| <span class="sd"> :param bucket_name: the name of the bucket</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">bucket_name</span><span class="p">:</span> |
| <span class="p">(</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span><span class="p">)</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">parse_s3_url</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| |
| <span class="n">obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_resource_type</span><span class="p">(</span><span class="s1">'s3'</span><span class="p">)</span><span class="o">.</span><span class="n">Object</span><span class="p">(</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span><span class="p">)</span> |
| <span class="n">obj</span><span class="o">.</span><span class="n">load</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">obj</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.read_key"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.read_key">[docs]</a> <span class="k">def</span> <span class="nf">read_key</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Reads a key from S3</span> |
| |
| <span class="sd"> :param key: S3 key that will point to the file</span> |
| <span class="sd"> :type key: str</span> |
| <span class="sd"> :param bucket_name: Name of the bucket in which the file is stored</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">obj</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_key</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">obj</span><span class="o">.</span><span class="n">get</span><span class="p">()[</span><span class="s1">'Body'</span><span class="p">]</span><span class="o">.</span><span class="n">read</span><span class="p">()</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.select_key"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.select_key">[docs]</a> <span class="k">def</span> <span class="nf">select_key</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">expression</span><span class="o">=</span><span class="s1">'SELECT * FROM S3Object'</span><span class="p">,</span> |
| <span class="n">expression_type</span><span class="o">=</span><span class="s1">'SQL'</span><span class="p">,</span> |
| <span class="n">input_serialization</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">output_serialization</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Reads a key with S3 Select.</span> |
| |
| <span class="sd"> :param key: S3 key that will point to the file</span> |
| <span class="sd"> :type key: str</span> |
| <span class="sd"> :param bucket_name: Name of the bucket in which the file is stored</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param expression: S3 Select expression</span> |
| <span class="sd"> :type expression: str</span> |
| <span class="sd"> :param expression_type: S3 Select expression type</span> |
| <span class="sd"> :type expression_type: str</span> |
| <span class="sd"> :param input_serialization: S3 Select input data serialization format</span> |
| <span class="sd"> :type input_serialization: dict</span> |
| <span class="sd"> :param output_serialization: S3 Select output data serialization format</span> |
| <span class="sd"> :type output_serialization: dict</span> |
| <span class="sd"> :return: retrieved subset of original data by S3 Select</span> |
| <span class="sd"> :rtype: str</span> |
| |
| <span class="sd"> .. seealso::</span> |
| <span class="sd"> For more details about S3 Select parameters:</span> |
| <span class="sd"> http://boto3.readthedocs.io/en/latest/reference/services/s3.html#S3.Client.select_object_content</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">input_serialization</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">input_serialization</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'CSV'</span><span class="p">:</span> <span class="p">{}}</span> |
| <span class="k">if</span> <span class="n">output_serialization</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">output_serialization</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'CSV'</span><span class="p">:</span> <span class="p">{}}</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">bucket_name</span><span class="p">:</span> |
| <span class="p">(</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span><span class="p">)</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">parse_s3_url</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| |
| <span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">select_object_content</span><span class="p">(</span> |
| <span class="n">Bucket</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">,</span> |
| <span class="n">Key</span><span class="o">=</span><span class="n">key</span><span class="p">,</span> |
| <span class="n">Expression</span><span class="o">=</span><span class="n">expression</span><span class="p">,</span> |
| <span class="n">ExpressionType</span><span class="o">=</span><span class="n">expression_type</span><span class="p">,</span> |
| <span class="n">InputSerialization</span><span class="o">=</span><span class="n">input_serialization</span><span class="p">,</span> |
| <span class="n">OutputSerialization</span><span class="o">=</span><span class="n">output_serialization</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="s1">''</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">event</span><span class="p">[</span><span class="s1">'Records'</span><span class="p">][</span><span class="s1">'Payload'</span><span class="p">]</span><span class="o">.</span><span class="n">decode</span><span class="p">(</span><span class="s1">'utf-8'</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">event</span> <span class="ow">in</span> <span class="n">response</span><span class="p">[</span><span class="s1">'Payload'</span><span class="p">]</span> |
| <span class="k">if</span> <span class="s1">'Records'</span> <span class="ow">in</span> <span class="n">event</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.check_for_wildcard_key"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.check_for_wildcard_key">[docs]</a> <span class="k">def</span> <span class="nf">check_for_wildcard_key</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">wildcard_key</span><span class="p">,</span> <span class="n">bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">delimiter</span><span class="o">=</span><span class="s1">''</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Checks that a key matching a wildcard expression exists in a bucket</span> |
| |
| <span class="sd"> :param wildcard_key: the path to the key</span> |
| <span class="sd"> :type wildcard_key: str</span> |
| <span class="sd"> :param bucket_name: the name of the bucket</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param delimiter: the delimiter marks key hierarchy</span> |
| <span class="sd"> :type delimiter: str</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_wildcard_key</span><span class="p">(</span><span class="n">wildcard_key</span><span class="o">=</span><span class="n">wildcard_key</span><span class="p">,</span> |
| <span class="n">bucket_name</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">,</span> |
| <span class="n">delimiter</span><span class="o">=</span><span class="n">delimiter</span><span class="p">)</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.get_wildcard_key"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.get_wildcard_key">[docs]</a> <span class="k">def</span> <span class="nf">get_wildcard_key</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">wildcard_key</span><span class="p">,</span> <span class="n">bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">delimiter</span><span class="o">=</span><span class="s1">''</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Returns a boto3.s3.Object object matching the wildcard expression</span> |
| |
| <span class="sd"> :param wildcard_key: the path to the key</span> |
| <span class="sd"> :type wildcard_key: str</span> |
| <span class="sd"> :param bucket_name: the name of the bucket</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param delimiter: the delimiter marks key hierarchy</span> |
| <span class="sd"> :type delimiter: str</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">bucket_name</span><span class="p">:</span> |
| <span class="p">(</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">wildcard_key</span><span class="p">)</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">parse_s3_url</span><span class="p">(</span><span class="n">wildcard_key</span><span class="p">)</span> |
| |
| <span class="n">prefix</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="sa">r</span><span class="s1">'[*]'</span><span class="p">,</span> <span class="n">wildcard_key</span><span class="p">,</span> <span class="mi">1</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> |
| <span class="n">klist</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">list_keys</span><span class="p">(</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">prefix</span><span class="o">=</span><span class="n">prefix</span><span class="p">,</span> <span class="n">delimiter</span><span class="o">=</span><span class="n">delimiter</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">klist</span><span class="p">:</span> |
| <span class="n">key_matches</span> <span class="o">=</span> <span class="p">[</span><span class="n">k</span> <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">klist</span> <span class="k">if</span> <span class="n">fnmatch</span><span class="o">.</span><span class="n">fnmatch</span><span class="p">(</span><span class="n">k</span><span class="p">,</span> <span class="n">wildcard_key</span><span class="p">)]</span> |
| <span class="k">if</span> <span class="n">key_matches</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_key</span><span class="p">(</span><span class="n">key_matches</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">bucket_name</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.load_file"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.load_file">[docs]</a> <span class="k">def</span> <span class="nf">load_file</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">filename</span><span class="p">,</span> |
| <span class="n">key</span><span class="p">,</span> |
| <span class="n">bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">replace</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">encrypt</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Loads a local file to S3</span> |
| |
| <span class="sd"> :param filename: name of the file to load.</span> |
| <span class="sd"> :type filename: str</span> |
| <span class="sd"> :param key: S3 key that will point to the file</span> |
| <span class="sd"> :type key: str</span> |
| <span class="sd"> :param bucket_name: Name of the bucket in which to store the file</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param replace: A flag to decide whether or not to overwrite the key</span> |
| <span class="sd"> if it already exists. If replace is False and the key exists, an</span> |
| <span class="sd"> error will be raised.</span> |
| <span class="sd"> :type replace: bool</span> |
| <span class="sd"> :param encrypt: If True, the file will be encrypted on the server-side</span> |
| <span class="sd"> by S3 and will be stored in an encrypted form while at rest in S3.</span> |
| <span class="sd"> :type encrypt: bool</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">bucket_name</span><span class="p">:</span> |
| <span class="p">(</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span><span class="p">)</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">parse_s3_url</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">replace</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">check_for_key</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"The key </span><span class="si">{key}</span><span class="s2"> already exists."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="n">key</span><span class="p">))</span> |
| |
| <span class="n">extra_args</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="n">encrypt</span><span class="p">:</span> |
| <span class="n">extra_args</span><span class="p">[</span><span class="s1">'ServerSideEncryption'</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"AES256"</span> |
| |
| <span class="n">client</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> |
| <span class="n">client</span><span class="o">.</span><span class="n">upload_file</span><span class="p">(</span><span class="n">filename</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">ExtraArgs</span><span class="o">=</span><span class="n">extra_args</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.load_string"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.load_string">[docs]</a> <span class="k">def</span> <span class="nf">load_string</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">string_data</span><span class="p">,</span> |
| <span class="n">key</span><span class="p">,</span> |
| <span class="n">bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">replace</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">encrypt</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">encoding</span><span class="o">=</span><span class="s1">'utf-8'</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Loads a string to S3</span> |
| |
| <span class="sd"> This is provided as a convenience to drop a string in S3. It uses the</span> |
| <span class="sd"> boto infrastructure to ship a file to s3.</span> |
| |
| <span class="sd"> :param string_data: str to set as content for the key.</span> |
| <span class="sd"> :type string_data: str</span> |
| <span class="sd"> :param key: S3 key that will point to the file</span> |
| <span class="sd"> :type key: str</span> |
| <span class="sd"> :param bucket_name: Name of the bucket in which to store the file</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param replace: A flag to decide whether or not to overwrite the key</span> |
| <span class="sd"> if it already exists</span> |
| <span class="sd"> :type replace: bool</span> |
| <span class="sd"> :param encrypt: If True, the file will be encrypted on the server-side</span> |
| <span class="sd"> by S3 and will be stored in an encrypted form while at rest in S3.</span> |
| <span class="sd"> :type encrypt: bool</span> |
| <span class="sd"> """</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">load_bytes</span><span class="p">(</span><span class="n">string_data</span><span class="o">.</span><span class="n">encode</span><span class="p">(</span><span class="n">encoding</span><span class="p">),</span> |
| <span class="n">key</span><span class="o">=</span><span class="n">key</span><span class="p">,</span> |
| <span class="n">bucket_name</span><span class="o">=</span><span class="n">bucket_name</span><span class="p">,</span> |
| <span class="n">replace</span><span class="o">=</span><span class="n">replace</span><span class="p">,</span> |
| <span class="n">encrypt</span><span class="o">=</span><span class="n">encrypt</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.load_bytes"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.load_bytes">[docs]</a> <span class="k">def</span> <span class="nf">load_bytes</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">bytes_data</span><span class="p">,</span> |
| <span class="n">key</span><span class="p">,</span> |
| <span class="n">bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">replace</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">encrypt</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Loads bytes to S3</span> |
| |
| <span class="sd"> This is provided as a convenience to drop a string in S3. It uses the</span> |
| <span class="sd"> boto infrastructure to ship a file to s3.</span> |
| |
| <span class="sd"> :param bytes_data: bytes to set as content for the key.</span> |
| <span class="sd"> :type bytes_data: bytes</span> |
| <span class="sd"> :param key: S3 key that will point to the file</span> |
| <span class="sd"> :type key: str</span> |
| <span class="sd"> :param bucket_name: Name of the bucket in which to store the file</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param replace: A flag to decide whether or not to overwrite the key</span> |
| <span class="sd"> if it already exists</span> |
| <span class="sd"> :type replace: bool</span> |
| <span class="sd"> :param encrypt: If True, the file will be encrypted on the server-side</span> |
| <span class="sd"> by S3 and will be stored in an encrypted form while at rest in S3.</span> |
| <span class="sd"> :type encrypt: bool</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">bucket_name</span><span class="p">:</span> |
| <span class="p">(</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span><span class="p">)</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">parse_s3_url</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">replace</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">check_for_key</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"The key </span><span class="si">{key}</span><span class="s2"> already exists."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="n">key</span><span class="p">))</span> |
| |
| <span class="n">extra_args</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="n">encrypt</span><span class="p">:</span> |
| <span class="n">extra_args</span><span class="p">[</span><span class="s1">'ServerSideEncryption'</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"AES256"</span> |
| |
| <span class="n">filelike_buffer</span> <span class="o">=</span> <span class="n">BytesIO</span><span class="p">(</span><span class="n">bytes_data</span><span class="p">)</span> |
| |
| <span class="n">client</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> |
| <span class="n">client</span><span class="o">.</span><span class="n">upload_fileobj</span><span class="p">(</span><span class="n">filelike_buffer</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">ExtraArgs</span><span class="o">=</span><span class="n">extra_args</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.load_file_obj"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.load_file_obj">[docs]</a> <span class="k">def</span> <span class="nf">load_file_obj</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">file_obj</span><span class="p">,</span> |
| <span class="n">key</span><span class="p">,</span> |
| <span class="n">bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">replace</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">encrypt</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Loads a file object to S3</span> |
| |
| <span class="sd"> :param file_obj: The file-like object to set as the content for the S3 key.</span> |
| <span class="sd"> :type file_obj: file-like object</span> |
| <span class="sd"> :param key: S3 key that will point to the file</span> |
| <span class="sd"> :type key: str</span> |
| <span class="sd"> :param bucket_name: Name of the bucket in which to store the file</span> |
| <span class="sd"> :type bucket_name: str</span> |
| <span class="sd"> :param replace: A flag that indicates whether to overwrite the key</span> |
| <span class="sd"> if it already exists.</span> |
| <span class="sd"> :type replace: bool</span> |
| <span class="sd"> :param encrypt: If True, S3 encrypts the file on the server,</span> |
| <span class="sd"> and the file is stored in encrypted form at rest in S3.</span> |
| <span class="sd"> :type encrypt: bool</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">bucket_name</span><span class="p">:</span> |
| <span class="p">(</span><span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span><span class="p">)</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">parse_s3_url</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">replace</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">check_for_key</span><span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"The key </span><span class="si">{key}</span><span class="s2"> already exists."</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="n">key</span><span class="p">))</span> |
| |
| <span class="n">extra_args</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="k">if</span> <span class="n">encrypt</span><span class="p">:</span> |
| <span class="n">extra_args</span><span class="p">[</span><span class="s1">'ServerSideEncryption'</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"AES256"</span> |
| |
| <span class="n">client</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span> |
| <span class="n">client</span><span class="o">.</span><span class="n">upload_fileobj</span><span class="p">(</span><span class="n">file_obj</span><span class="p">,</span> <span class="n">bucket_name</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">ExtraArgs</span><span class="o">=</span><span class="n">extra_args</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.copy_object"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.copy_object">[docs]</a> <span class="k">def</span> <span class="nf">copy_object</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">source_bucket_key</span><span class="p">,</span> |
| <span class="n">dest_bucket_key</span><span class="p">,</span> |
| <span class="n">source_bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">dest_bucket_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">source_version_id</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Creates a copy of an object that is already stored in S3.</span> |
| |
| <span class="sd"> Note: the S3 connection used here needs to have access to both</span> |
| <span class="sd"> source and destination bucket/key.</span> |
| |
| <span class="sd"> :param source_bucket_key: The key of the source object.</span> |
| |
| <span class="sd"> It can be either full s3:// style url or relative path from root level.</span> |
| |
| <span class="sd"> When it's specified as a full s3:// url, please omit source_bucket_name.</span> |
| <span class="sd"> :type source_bucket_key: str</span> |
| <span class="sd"> :param dest_bucket_key: The key of the object to copy to.</span> |
| |
| <span class="sd"> The convention to specify `dest_bucket_key` is the same</span> |
| <span class="sd"> as `source_bucket_key`.</span> |
| <span class="sd"> :type dest_bucket_key: str</span> |
| <span class="sd"> :param source_bucket_name: Name of the S3 bucket where the source object is in.</span> |
| |
| <span class="sd"> It should be omitted when `source_bucket_key` is provided as a full s3:// url.</span> |
| <span class="sd"> :type source_bucket_name: str</span> |
| <span class="sd"> :param dest_bucket_name: Name of the S3 bucket to where the object is copied.</span> |
| |
| <span class="sd"> It should be omitted when `dest_bucket_key` is provided as a full s3:// url.</span> |
| <span class="sd"> :type dest_bucket_name: str</span> |
| <span class="sd"> :param source_version_id: Version ID of the source object (OPTIONAL)</span> |
| <span class="sd"> :type source_version_id: str</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">if</span> <span class="n">dest_bucket_name</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">dest_bucket_name</span><span class="p">,</span> <span class="n">dest_bucket_key</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">parse_s3_url</span><span class="p">(</span><span class="n">dest_bucket_key</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">parsed_url</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">dest_bucket_key</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">scheme</span> <span class="o">!=</span> <span class="s1">''</span> <span class="ow">or</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span> <span class="o">!=</span> <span class="s1">''</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'If dest_bucket_name is provided, '</span> <span class="o">+</span> |
| <span class="s1">'dest_bucket_key should be relative path '</span> <span class="o">+</span> |
| <span class="s1">'from root level, rather than a full s3:// url'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">source_bucket_name</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">source_bucket_name</span><span class="p">,</span> <span class="n">source_bucket_key</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">parse_s3_url</span><span class="p">(</span><span class="n">source_bucket_key</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">parsed_url</span> <span class="o">=</span> <span class="n">urlparse</span><span class="p">(</span><span class="n">source_bucket_key</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">scheme</span> <span class="o">!=</span> <span class="s1">''</span> <span class="ow">or</span> <span class="n">parsed_url</span><span class="o">.</span><span class="n">netloc</span> <span class="o">!=</span> <span class="s1">''</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'If source_bucket_name is provided, '</span> <span class="o">+</span> |
| <span class="s1">'source_bucket_key should be relative path '</span> <span class="o">+</span> |
| <span class="s1">'from root level, rather than a full s3:// url'</span><span class="p">)</span> |
| |
| <span class="n">CopySource</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'Bucket'</span><span class="p">:</span> <span class="n">source_bucket_name</span><span class="p">,</span> |
| <span class="s1">'Key'</span><span class="p">:</span> <span class="n">source_bucket_key</span><span class="p">,</span> |
| <span class="s1">'VersionId'</span><span class="p">:</span> <span class="n">source_version_id</span><span class="p">}</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">copy_object</span><span class="p">(</span><span class="n">Bucket</span><span class="o">=</span><span class="n">dest_bucket_name</span><span class="p">,</span> |
| <span class="n">Key</span><span class="o">=</span><span class="n">dest_bucket_key</span><span class="p">,</span> |
| <span class="n">CopySource</span><span class="o">=</span><span class="n">CopySource</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">response</span></div> |
| |
| <div class="viewcode-block" id="S3Hook.delete_objects"><a class="viewcode-back" href="../../../_api/airflow/hooks/S3_hook/index.html#airflow.hooks.S3_hook.S3Hook.delete_objects">[docs]</a> <span class="k">def</span> <span class="nf">delete_objects</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">bucket</span><span class="p">,</span> |
| <span class="n">keys</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> :param bucket: Name of the bucket in which you are going to delete object(s)</span> |
| <span class="sd"> :type bucket: str</span> |
| <span class="sd"> :param keys: The key(s) to delete from S3 bucket.</span> |
| |
| <span class="sd"> When ``keys`` is a string, it's supposed to be the key name of</span> |
| <span class="sd"> the single object to delete.</span> |
| |
| <span class="sd"> When ``keys`` is a list, it's supposed to be the list of the</span> |
| <span class="sd"> keys to delete.</span> |
| <span class="sd"> :type keys: str or list</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">keys</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="n">keys</span> <span class="o">=</span> <span class="n">keys</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">keys</span> <span class="o">=</span> <span class="p">[</span><span class="n">keys</span><span class="p">]</span> |
| |
| <span class="n">delete_dict</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"Objects"</span><span class="p">:</span> <span class="p">[{</span><span class="s2">"Key"</span><span class="p">:</span> <span class="n">k</span><span class="p">}</span> <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">keys</span><span class="p">]}</span> |
| <span class="n">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">get_conn</span><span class="p">()</span><span class="o">.</span><span class="n">delete_objects</span><span class="p">(</span><span class="n">Bucket</span><span class="o">=</span><span class="n">bucket</span><span class="p">,</span> |
| <span class="n">Delete</span><span class="o">=</span><span class="n">delete_dict</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">response</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>. |
| <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. |
| <script type="text/javascript"> |
| (function() { |
| var ga = document.createElement('script'); |
| ga.src = ('https:' == document.location.protocol ? |
| 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; |
| ga.setAttribute('async', 'true'); |
| var nodes = document.documentElement.childNodes; |
| var i = -1; |
| var node; |
| do { |
| i++; |
| node = nodes[i] |
| } while(node.nodeType !== Node.ELEMENT_NODE); |
| node.appendChild(ga); |
| })(); |
| </script> |
| </div> |
| |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |