769 lines
54 KiB
HTML
769 lines
54 KiB
HTML
|
||
|
||
<!DOCTYPE html>
|
||
<html class="writer-html5" lang="en" >
|
||
<head>
|
||
<meta charset="utf-8">
|
||
|
||
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
||
|
||
<title>Chapter 1 - Essential Scripts — Python Forensics Handbook 0.1.2 documentation</title>
|
||
|
||
|
||
|
||
<link rel="stylesheet" href="_static/css/theme.css" type="text/css" />
|
||
<link rel="stylesheet" href="_static/pygments.css" type="text/css" />
|
||
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<!--[if lt IE 9]>
|
||
<script src="_static/js/html5shiv.min.js"></script>
|
||
<![endif]-->
|
||
|
||
|
||
<script type="text/javascript" id="documentation_options" data-url_root="./" src="_static/documentation_options.js"></script>
|
||
<script src="_static/jquery.js"></script>
|
||
<script src="_static/underscore.js"></script>
|
||
<script src="_static/doctools.js"></script>
|
||
<script src="_static/language_data.js"></script>
|
||
|
||
<script type="text/javascript" src="_static/js/theme.js"></script>
|
||
|
||
|
||
<link rel="index" title="Index" href="genindex.html" />
|
||
<link rel="search" title="Search" href="search.html" />
|
||
<link rel="next" title="Chapter 2 - Registry Parsing" href="ch02_registry.html" />
|
||
<link rel="prev" title="The Python Forensics Handbook" href="index.html" />
|
||
|
||
<!-- Global site tag (gtag.js) - Google Analytics -->
|
||
<script async src="https://www.googletagmanager.com/gtag/js?id=UA-17386833-12"></script>
|
||
<script>
|
||
window.dataLayer = window.dataLayer || [];
|
||
function gtag(){dataLayer.push(arguments);}
|
||
gtag('js', new Date());
|
||
|
||
gtag('config', 'UA-17386833-12');
|
||
</script>
|
||
|
||
</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" alt="Documentation Home"> Python Forensics Handbook
|
||
|
||
|
||
|
||
</a>
|
||
|
||
|
||
|
||
|
||
<div class="version">
|
||
0.1.2
|
||
</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">
|
||
|
||
|
||
|
||
|
||
|
||
|
||
<p class="caption"><span class="caption-text">Table of Contents:</span></p>
|
||
<ul class="current">
|
||
<li class="toctree-l1 current"><a class="current reference internal" href="#">Chapter 1 - Essential Scripts</a><ul>
|
||
<li class="toctree-l2"><a class="reference internal" href="#module-pyforhandbook.ch01_essentials.argparse_example">Section 1.1 - Argparse Example</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#argparse-configuration">Argparse configuration</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#module-pyforhandbook.ch01_essentials.logging_example">Section 1.2 - Logging Example</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#logging-configuration">Logging configuration</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#docstring-references">Docstring References</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#module-pyforhandbook.ch01_essentials.open_files">Section 1.3 - Open Files</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#open-files-with-proper-encoding">Open files with proper encoding</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#id1">Docstring References</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#module-pyforhandbook.ch01_essentials.csv_example">Section 1.4 - CSV Example</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#list-of-dictionaries-to-csv">List of dictionaries to CSV</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#list-of-ordered-lists-to-csv">List of ordered lists to CSV</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#id2">Docstring References</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#module-pyforhandbook.ch01_essentials.recursion_example">Section 1.5 - Directory Recursion</a><ul>
|
||
<li class="toctree-l3"><a class="reference internal" href="#list-a-directory">List a directory</a></li>
|
||
<li class="toctree-l3"><a class="reference internal" href="#list-a-directory-recursively">List a directory recursively</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l2"><a class="reference internal" href="#indices-and-tables">Indices and tables</a></li>
|
||
</ul>
|
||
</li>
|
||
<li class="toctree-l1"><a class="reference internal" href="ch02_registry.html">Chapter 2 - Registry Parsing</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="ch03_event_logs.html">Chapter 3 - Windows Event Log Parsing</a></li>
|
||
<li class="toctree-l1"><a class="reference internal" href="ch06_databases.html">Chapter 6 - Sqlite & MacOS/Mobile/Browsers</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">Python Forensics Handbook</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" class="icon icon-home"></a> »</li>
|
||
|
||
<li>Chapter 1 - Essential Scripts</li>
|
||
|
||
|
||
<li class="wy-breadcrumbs-aside">
|
||
|
||
|
||
<a href="_sources/ch01_essentials.rst.txt" rel="nofollow"> View page source</a>
|
||
|
||
|
||
</li>
|
||
|
||
</ul>
|
||
|
||
|
||
<hr/>
|
||
</div>
|
||
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
|
||
<div itemprop="articleBody">
|
||
|
||
<div class="section" id="chapter-1-essential-scripts">
|
||
<h1>Chapter 1 - Essential Scripts<a class="headerlink" href="#chapter-1-essential-scripts" title="Permalink to this headline">¶</a></h1>
|
||
<div class="toctree-wrapper compound">
|
||
</div>
|
||
<div class="section" id="module-pyforhandbook.ch01_essentials.argparse_example">
|
||
<span id="section-1-1-argparse-example"></span><h2>Section 1.1 - Argparse Example<a class="headerlink" href="#module-pyforhandbook.ch01_essentials.argparse_example" title="Permalink to this headline">¶</a></h2>
|
||
<p>Example for setting up arguments for your command line utility.</p>
|
||
<p>Example Usage:</p>
|
||
<blockquote>
|
||
<div><p><code class="docutils literal notranslate"><span class="pre">$</span> <span class="pre">python</span> <span class="pre">argparse.py</span></code></p>
|
||
</div></blockquote>
|
||
<p>References:</p>
|
||
<ul class="simple">
|
||
<li><p><a class="reference external" href="https://docs.python.org/3/library/argparse.html">https://docs.python.org/3/library/argparse.html</a></p></li>
|
||
<li><p><a class="reference external" href="https://docs.python.org/3/library/os.html">https://docs.python.org/3/library/os.html</a></p></li>
|
||
<li><p><a class="reference external" href="https://docs.python.org/3/library/pathlib.html">https://docs.python.org/3/library/pathlib.html</a></p></li>
|
||
</ul>
|
||
<div class="section" id="argparse-configuration">
|
||
<h3>Argparse configuration<a class="headerlink" href="#argparse-configuration" title="Permalink to this headline">¶</a></h3>
|
||
<p>This function shows an example of creating an argparse instance
|
||
with required and optional parameters. Further, it demonstrates
|
||
how to set default values and boolean arguments. the <code class="docutils literal notranslate"><span class="pre">argparse</span></code>
|
||
module has many more features documented at
|
||
<a class="reference external" href="https://docs.python.org/3/library/argparse.html">https://docs.python.org/3/library/argparse.html</a></p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">setup_argparse</span><span class="p">():</span>
|
||
<span class="c1"># Setup a parser instance with common fields including a</span>
|
||
<span class="c1"># description and epilog. The `formatter_class` instructs</span>
|
||
<span class="c1"># argparse to show default values set for parameters.</span>
|
||
<span class="n">parser</span> <span class="o">=</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">(</span>
|
||
<span class="n">description</span><span class="o">=</span><span class="s2">"Sample Argparse"</span><span class="p">,</span>
|
||
<span class="n">formatter_class</span><span class="o">=</span><span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentDefaultsHelpFormatter</span><span class="p">,</span>
|
||
<span class="n">epilog</span><span class="o">=</span><span class="sa">f</span><span class="s2">"Built by </span><span class="si">{</span><span class="n">__author__</span><span class="si">}</span><span class="s2">, v.</span><span class="si">{</span><span class="n">__date__</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span>
|
||
<span class="p">)</span>
|
||
|
||
<span class="c1"># The simplest form of adding an argument, the name of the</span>
|
||
<span class="c1"># parameter and a description of its form.</span>
|
||
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"INPUT_FILE"</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Input file to parse"</span><span class="p">)</span>
|
||
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s2">"OUTPUT_FOLDER"</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Folder to store output"</span><span class="p">)</span>
|
||
|
||
<span class="c1"># An optional argument with multiple methods of specifying</span>
|
||
<span class="c1"># the parameter. Includes a default value</span>
|
||
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
|
||
<span class="s2">"-l"</span><span class="p">,</span>
|
||
<span class="s2">"--log"</span><span class="p">,</span>
|
||
<span class="n">help</span><span class="o">=</span><span class="s2">"Path to log file"</span><span class="p">,</span>
|
||
<span class="n">default</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">abspath</span><span class="p">(</span>
|
||
<span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span>
|
||
<span class="n">PurePath</span><span class="p">(</span><span class="vm">__file__</span><span class="p">)</span><span class="o">.</span><span class="n">parent</span><span class="p">,</span>
|
||
<span class="n">PurePath</span><span class="p">(</span><span class="vm">__file__</span><span class="p">)</span><span class="o">.</span><span class="n">name</span><span class="o">.</span><span class="n">rsplit</span><span class="p">(</span><span class="s2">"."</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="o">+</span> <span class="s2">".log"</span><span class="p">,</span>
|
||
<span class="p">)</span>
|
||
<span class="p">),</span>
|
||
<span class="p">)</span>
|
||
|
||
<span class="c1"># An optional argument which does not accept a value, instead</span>
|
||
<span class="c1"># just modifies functionality.</span>
|
||
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
|
||
<span class="s2">"-v"</span><span class="p">,</span> <span class="s2">"--verbose"</span><span class="p">,</span> <span class="n">action</span><span class="o">=</span><span class="s2">"store_true"</span><span class="p">,</span> <span class="n">help</span><span class="o">=</span><span class="s2">"Include debug log messages"</span>
|
||
<span class="p">)</span>
|
||
|
||
<span class="c1"># Once we've specified our arguments we can parse them for</span>
|
||
<span class="c1"># reference</span>
|
||
<span class="n">args</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse_args</span><span class="p">()</span>
|
||
|
||
<span class="c1"># Returning our parsed arguments for further use.</span>
|
||
<span class="k">return</span> <span class="n">args</span>
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
</div>
|
||
<div class="section" id="module-pyforhandbook.ch01_essentials.logging_example">
|
||
<span id="section-1-2-logging-example"></span><h2>Section 1.2 - Logging Example<a class="headerlink" href="#module-pyforhandbook.ch01_essentials.logging_example" title="Permalink to this headline">¶</a></h2>
|
||
<p>Example for writing logging information to the console and a
|
||
log file.</p>
|
||
<p>Example Usage:</p>
|
||
<blockquote>
|
||
<div><p><code class="docutils literal notranslate"><span class="pre">$</span> <span class="pre">python</span> <span class="pre">logging_example.py</span></code></p>
|
||
</div></blockquote>
|
||
<p>References:</p>
|
||
<ul class="simple">
|
||
<li><p><a class="reference external" href="https://docs.python.org/3/library/logging.html">https://docs.python.org/3/library/logging.html</a></p></li>
|
||
<li><p><a class="reference external" href="https://docs.python.org/3/library/os.html">https://docs.python.org/3/library/os.html</a></p></li>
|
||
</ul>
|
||
<div class="section" id="logging-configuration">
|
||
<h3>Logging configuration<a class="headerlink" href="#logging-configuration" title="Permalink to this headline">¶</a></h3>
|
||
<p>This function shows an example of creating a logging instance that
|
||
writes messages to both STDERR and a file, allowing your script
|
||
to write content to STDOUT uninterrupted. Additionally, you can
|
||
set different logging levels for the two handlers - generally you
|
||
keep debugging information in the log file while writing more
|
||
critical messages to the console in STDERR.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">setup_logging</span><span class="p">(</span><span class="n">logging_obj</span><span class="p">,</span> <span class="n">log_file</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span>
|
||
<span class="sd">"""Function to setup logging configuration and test it.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> logging_obj: A logging instance, returned from logging.getLogger().</span>
|
||
<span class="sd"> log_file: File path to write log messages to.</span>
|
||
<span class="sd"> verbose: Whether or not to enable the debug level in STDERR output.</span>
|
||
|
||
<span class="sd"> Examples:</span>
|
||
<span class="sd"> >>> sample_logger = logging.getLogger(name=__name__)</span>
|
||
<span class="sd"> >>> log_path = "sample.log"</span>
|
||
<span class="sd"> >>> setup_logging(sample_logger, log_path, verbose=True)</span>
|
||
<span class="sd"> >>> sample_logger.debug("This is a debug message")</span>
|
||
<span class="sd"> >>> sample_logger.info("This is an info message")</span>
|
||
<span class="sd"> >>> sample_logger.warning("This is a warning message")</span>
|
||
<span class="sd"> >>> sample_logger.error("This is a error message")</span>
|
||
<span class="sd"> >>> sample_logger.critical("This is a critical message")</span>
|
||
<span class="sd"> """</span>
|
||
<span class="n">logging_obj</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">DEBUG</span><span class="p">)</span>
|
||
|
||
<span class="c1"># Logging formatter. Best to keep consistent for most use cases</span>
|
||
<span class="n">log_format</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">Formatter</span><span class="p">(</span>
|
||
<span class="s2">"</span><span class="si">%(asctime)s</span><span class="s2"> </span><span class="si">%(filename)s</span><span class="s2"> </span><span class="si">%(levelname)s</span><span class="s2"> </span><span class="si">%(module)s</span><span class="s2"> "</span>
|
||
<span class="s2">"</span><span class="si">%(funcName)s</span><span class="s2"> </span><span class="si">%(lineno)d</span><span class="s2"> </span><span class="si">%(message)s</span><span class="s2">"</span>
|
||
<span class="p">)</span>
|
||
|
||
<span class="c1"># Setup STDERR logging, allowing you uninterrupted</span>
|
||
<span class="c1"># STDOUT redirection</span>
|
||
<span class="n">stderr_handle</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">StreamHandler</span><span class="p">(</span><span class="n">stream</span><span class="o">=</span><span class="n">sys</span><span class="o">.</span><span class="n">stderr</span><span class="p">)</span>
|
||
<span class="k">if</span> <span class="n">verbose</span><span class="p">:</span>
|
||
<span class="n">stderr_handle</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">DEBUG</span><span class="p">)</span>
|
||
<span class="k">else</span><span class="p">:</span>
|
||
<span class="n">stderr_handle</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">INFO</span><span class="p">)</span>
|
||
<span class="n">stderr_handle</span><span class="o">.</span><span class="n">setFormatter</span><span class="p">(</span><span class="n">log_format</span><span class="p">)</span>
|
||
|
||
<span class="c1"># Setup file logging</span>
|
||
<span class="n">file_handle</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">FileHandler</span><span class="p">(</span><span class="n">log_file</span><span class="p">,</span> <span class="s2">"a"</span><span class="p">)</span>
|
||
<span class="n">file_handle</span><span class="o">.</span><span class="n">setLevel</span><span class="p">(</span><span class="n">logging</span><span class="o">.</span><span class="n">DEBUG</span><span class="p">)</span>
|
||
<span class="n">file_handle</span><span class="o">.</span><span class="n">setFormatter</span><span class="p">(</span><span class="n">log_format</span><span class="p">)</span>
|
||
|
||
<span class="c1"># Add handles</span>
|
||
<span class="n">logging_obj</span><span class="o">.</span><span class="n">addHandler</span><span class="p">(</span><span class="n">stderr_handle</span><span class="p">)</span>
|
||
<span class="n">logging_obj</span><span class="o">.</span><span class="n">addHandler</span><span class="p">(</span><span class="n">file_handle</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
<div class="section" id="docstring-references">
|
||
<h3>Docstring References<a class="headerlink" href="#docstring-references" title="Permalink to this headline">¶</a></h3>
|
||
<dl class="py function">
|
||
<dt id="pyforhandbook.ch01_essentials.logging_example.setup_logging">
|
||
<code class="sig-name descname">setup_logging</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">logging_obj</span></em>, <em class="sig-param"><span class="n">log_file</span></em>, <em class="sig-param"><span class="n">verbose</span><span class="o">=</span><span class="default_value">False</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyforhandbook.ch01_essentials.logging_example.setup_logging" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Function to setup logging configuration and test it.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters</dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>logging_obj</strong> – A logging instance, returned from logging.getLogger().</p></li>
|
||
<li><p><strong>log_file</strong> – File path to write log messages to.</p></li>
|
||
<li><p><strong>verbose</strong> – Whether or not to enable the debug level in STDERR output.</p></li>
|
||
</ul>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Examples</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">sample_logger</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="n">name</span><span class="o">=</span><span class="vm">__name__</span><span class="p">)</span>
|
||
<span class="gp">>>> </span><span class="n">log_path</span> <span class="o">=</span> <span class="s2">"sample.log"</span>
|
||
<span class="gp">>>> </span><span class="n">setup_logging</span><span class="p">(</span><span class="n">sample_logger</span><span class="p">,</span> <span class="n">log_path</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
|
||
<span class="gp">>>> </span><span class="n">sample_logger</span><span class="o">.</span><span class="n">debug</span><span class="p">(</span><span class="s2">"This is a debug message"</span><span class="p">)</span>
|
||
<span class="gp">>>> </span><span class="n">sample_logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">"This is an info message"</span><span class="p">)</span>
|
||
<span class="gp">>>> </span><span class="n">sample_logger</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s2">"This is a warning message"</span><span class="p">)</span>
|
||
<span class="gp">>>> </span><span class="n">sample_logger</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s2">"This is a error message"</span><span class="p">)</span>
|
||
<span class="gp">>>> </span><span class="n">sample_logger</span><span class="o">.</span><span class="n">critical</span><span class="p">(</span><span class="s2">"This is a critical message"</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
</div>
|
||
<div class="section" id="module-pyforhandbook.ch01_essentials.open_files">
|
||
<span id="section-1-3-open-files"></span><h2>Section 1.3 - Open Files<a class="headerlink" href="#module-pyforhandbook.ch01_essentials.open_files" title="Permalink to this headline">¶</a></h2>
|
||
<p>Example for reading data from encoded text files.</p>
|
||
<p>Demonstrates how to handle setting the proper encoding for
|
||
UTF-8, UTF-16-LE, and UTF-16-BE with the ability to easily
|
||
expand to support checking other file magic values/signatures.</p>
|
||
<p>Example Usage:</p>
|
||
<blockquote>
|
||
<div><p><code class="docutils literal notranslate"><span class="pre">$</span> <span class="pre">python</span> <span class="pre">open_files.py</span></code></p>
|
||
</div></blockquote>
|
||
<p>References:</p>
|
||
<ul class="simple">
|
||
<li><p><a class="reference external" href="https://docs.python.org/3/library/io.html">https://docs.python.org/3/library/io.html</a></p></li>
|
||
</ul>
|
||
<div class="section" id="open-files-with-proper-encoding">
|
||
<h3>Open files with proper encoding<a class="headerlink" href="#open-files-with-proper-encoding" title="Permalink to this headline">¶</a></h3>
|
||
<p>This first function shows an example of opening a file after checking for a
|
||
byte-order mark (BOM). While this method could be expanded to check for a file’s
|
||
magic value/file signature, this low-tech method will help with parsing a
|
||
collection of files that may be UTF-8, UTF-16-LE, and UTF-16-BE, three very
|
||
common text file encodings. Feel free to build and share on this.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">open_file</span><span class="p">(</span><span class="n">input_file</span><span class="p">):</span>
|
||
<span class="sd">"""Opens an encoded text file and prints the contents</span>
|
||
|
||
<span class="sd"> Arguments:</span>
|
||
<span class="sd"> input_file (str): Path to file to open</span>
|
||
<span class="sd"> """</span>
|
||
|
||
<span class="n">test_encoding</span> <span class="o">=</span> <span class="nb">open</span><span class="p">(</span><span class="n">input_file</span><span class="p">,</span> <span class="s2">"rb"</span><span class="p">)</span>
|
||
<span class="n">bom</span> <span class="o">=</span> <span class="n">test_encoding</span><span class="o">.</span><span class="n">read</span><span class="p">(</span><span class="mi">2</span><span class="p">)</span>
|
||
<span class="n">file_encoding</span> <span class="o">=</span> <span class="s2">"utf-8"</span>
|
||
<span class="k">if</span> <span class="n">bom</span> <span class="o">==</span> <span class="sa">b</span><span class="s2">"FEFF"</span><span class="p">:</span>
|
||
<span class="n">file_encoding</span> <span class="o">=</span> <span class="s2">"utf-16-le"</span>
|
||
<span class="k">elif</span> <span class="n">bom</span> <span class="o">==</span> <span class="sa">b</span><span class="s2">"FFFE"</span><span class="p">:</span>
|
||
<span class="n">file_encoding</span> <span class="o">=</span> <span class="s2">"utf-16-be"</span>
|
||
|
||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">input_file</span><span class="p">,</span> <span class="s2">"r"</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="n">file_encoding</span><span class="p">)</span> <span class="k">as</span> <span class="n">open_input_file</span><span class="p">:</span>
|
||
<span class="k">for</span> <span class="n">raw_line</span> <span class="ow">in</span> <span class="n">open_input_file</span><span class="p">:</span>
|
||
<span class="n">line</span> <span class="o">=</span> <span class="n">raw_line</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="n">line</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
<div class="section" id="id1">
|
||
<h3>Docstring References<a class="headerlink" href="#id1" title="Permalink to this headline">¶</a></h3>
|
||
<dl class="py function">
|
||
<dt id="pyforhandbook.ch01_essentials.open_files.open_file">
|
||
<code class="sig-name descname">open_file</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">input_file</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyforhandbook.ch01_essentials.open_files.open_file" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Opens an encoded text file and prints the contents</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters</dt>
|
||
<dd class="field-odd"><p><strong>input_file</strong> (<em>str</em>) – Path to file to open</p>
|
||
</dd>
|
||
</dl>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
</div>
|
||
<div class="section" id="module-pyforhandbook.ch01_essentials.csv_example">
|
||
<span id="section-1-4-csv-example"></span><h2>Section 1.4 - CSV Example<a class="headerlink" href="#module-pyforhandbook.ch01_essentials.csv_example" title="Permalink to this headline">¶</a></h2>
|
||
<p>Example for writing datasets into CSV files.</p>
|
||
<p>Demonstrates source datasets comprised of lists of dictionaries
|
||
and lists of lists as separate functions. Example data is
|
||
provided in line and will generate two identical CSVs as output.</p>
|
||
<p>Example Usage:</p>
|
||
<blockquote>
|
||
<div><p><code class="docutils literal notranslate"><span class="pre">$</span> <span class="pre">python</span> <span class="pre">csv_example.py</span></code></p>
|
||
</div></blockquote>
|
||
<p>References:</p>
|
||
<ul class="simple">
|
||
<li><p><a class="reference external" href="https://docs.python.org/3/library/csv.html">https://docs.python.org/3/library/csv.html</a></p></li>
|
||
<li><p><a class="reference external" href="https://docs.python.org/3/library/os.html">https://docs.python.org/3/library/os.html</a></p></li>
|
||
</ul>
|
||
<div class="section" id="list-of-dictionaries-to-csv">
|
||
<h3>List of dictionaries to CSV<a class="headerlink" href="#list-of-dictionaries-to-csv" title="Permalink to this headline">¶</a></h3>
|
||
<p>Example <code class="docutils literal notranslate"><span class="pre">data</span></code> variable:</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="p">[</span>
|
||
<span class="p">{</span><span class="s1">'name'</span><span class="p">:</span> <span class="s1">'apple'</span><span class="p">,</span> <span class="s1">'quantity'</span><span class="p">:</span> <span class="mi">10</span><span class="p">,</span> <span class="s1">'location'</span><span class="p">:</span> <span class="s1">'VT'</span><span class="p">},</span>
|
||
<span class="p">{</span><span class="s1">'name'</span><span class="p">:</span> <span class="s1">'orange'</span><span class="p">,</span> <span class="s1">'quantity'</span><span class="p">:</span> <span class="mi">5</span><span class="p">,</span> <span class="s1">'location'</span><span class="p">:</span> <span class="s1">'FL'</span><span class="p">}</span>
|
||
<span class="p">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>This first function shows an example of writing a list containing
|
||
multiple dictionaries to a CSV file. You can optionally provide
|
||
an ordered list of headers to filter what rows to show, or let the
|
||
function use the keys of the first dictionary in the list to
|
||
generate the header information. The latter option may produce
|
||
a new order each iteration and is not preferred if you can
|
||
determine the headers in advance.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">write_csv_dicts</span><span class="p">(</span><span class="n">outfile</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">headers</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||
<span class="sd">"""Writes a list of dictionaries to a CSV file.</span>
|
||
|
||
<span class="sd"> Arguments:</span>
|
||
<span class="sd"> outfile (str): Path to output file</span>
|
||
<span class="sd"> data (list): List of dictionaries to write to file</span>
|
||
<span class="sd"> headers (list): Header row to use. If empty, will use the</span>
|
||
<span class="sd"> first dictionary in the `data` list.</span>
|
||
|
||
<span class="sd"> Example:</span>
|
||
<span class="sd"> >>> list_of_dicts = [</span>
|
||
<span class="sd"> >>> {'name': 'apple', 'quantity': 10, 'location': 'VT'},</span>
|
||
<span class="sd"> >>> {'name': 'orange', 'quantity': 5, 'location': 'FL'}</span>
|
||
<span class="sd"> >>> ]</span>
|
||
<span class="sd"> >>> write_csv_dicts('dict_test.csv', list_of_dicts)</span>
|
||
<span class="sd"> """</span>
|
||
|
||
<span class="k">if</span> <span class="ow">not</span> <span class="n">headers</span><span class="p">:</span>
|
||
<span class="c1"># Use the first line of data</span>
|
||
<span class="n">headers</span> <span class="o">=</span> <span class="p">[</span><span class="nb">str</span><span class="p">(</span><span class="n">x</span><span class="p">)</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">data</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">keys</span><span class="p">()]</span>
|
||
|
||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">outfile</span><span class="p">,</span> <span class="s2">"w"</span><span class="p">,</span> <span class="n">newline</span><span class="o">=</span><span class="s2">""</span><span class="p">)</span> <span class="k">as</span> <span class="n">open_file</span><span class="p">:</span>
|
||
<span class="c1"># Write only provided headers, ignore others</span>
|
||
<span class="n">csv_file</span> <span class="o">=</span> <span class="n">csv</span><span class="o">.</span><span class="n">DictWriter</span><span class="p">(</span><span class="n">open_file</span><span class="p">,</span> <span class="n">headers</span><span class="p">,</span> <span class="n">extrasaction</span><span class="o">=</span><span class="s2">"ignore"</span><span class="p">)</span>
|
||
<span class="n">csv_file</span><span class="o">.</span><span class="n">writeheader</span><span class="p">()</span>
|
||
<span class="n">csv_file</span><span class="o">.</span><span class="n">writerows</span><span class="p">(</span><span class="n">data</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
<div class="section" id="list-of-ordered-lists-to-csv">
|
||
<h3>List of ordered lists to CSV<a class="headerlink" href="#list-of-ordered-lists-to-csv" title="Permalink to this headline">¶</a></h3>
|
||
<p>Example <code class="docutils literal notranslate"><span class="pre">data</span></code> variable:</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="p">[</span>
|
||
<span class="p">[</span><span class="s1">'name'</span><span class="p">,</span> <span class="s1">'quantity'</span><span class="p">,</span> <span class="s1">'location'</span><span class="p">],</span>
|
||
<span class="p">[</span><span class="s1">'apple'</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="s1">'VT'</span><span class="p">],</span>
|
||
<span class="p">[</span><span class="s1">'orange'</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="s1">'FL'</span><span class="p">]</span>
|
||
<span class="p">]</span>
|
||
</pre></div>
|
||
</div>
|
||
<p>This function shows an example of writing a list containing
|
||
multiple lists to a CSV file. You can optionally provide
|
||
an ordered list of headers, or let the function use the values
|
||
of the first element in the list to generate the header
|
||
information. Unlike the dictionary option, you cannot filter
|
||
column data by adjusting the provided headers, you must write all
|
||
columns to the CSV.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">write_csv_lists</span><span class="p">(</span><span class="n">outfile</span><span class="p">,</span> <span class="n">data</span><span class="p">,</span> <span class="n">headers</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
|
||
<span class="sd">"""Writes a list of lists to a CSV file.</span>
|
||
|
||
<span class="sd"> Arguments:</span>
|
||
<span class="sd"> outfile (str): Path to output file</span>
|
||
<span class="sd"> data (list): List of lists to write to file</span>
|
||
<span class="sd"> headers (list): Header row to use. If empty, will use the</span>
|
||
<span class="sd"> first list in the `data` list.</span>
|
||
|
||
<span class="sd"> Examples:</span>
|
||
<span class="sd"> >>> fields = ['name', 'quantity', 'location']</span>
|
||
<span class="sd"> >>> list_of_lists = [</span>
|
||
<span class="sd"> >>> ['apple', 10, 'VT'],</span>
|
||
<span class="sd"> >>> ['orange', 5, 'FL']</span>
|
||
<span class="sd"> >>> ]</span>
|
||
<span class="sd"> >>> write_csv_lists('list_test.csv', list_of_lists, headers=fields)</span>
|
||
<span class="sd"> """</span>
|
||
|
||
<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">outfile</span><span class="p">,</span> <span class="s2">"w"</span><span class="p">,</span> <span class="n">newline</span><span class="o">=</span><span class="s2">""</span><span class="p">)</span> <span class="k">as</span> <span class="n">open_file</span><span class="p">:</span>
|
||
<span class="c1"># Write only provided headers, ignore others</span>
|
||
<span class="n">csv_file</span> <span class="o">=</span> <span class="n">csv</span><span class="o">.</span><span class="n">writer</span><span class="p">(</span><span class="n">open_file</span><span class="p">)</span>
|
||
<span class="k">for</span> <span class="n">count</span><span class="p">,</span> <span class="n">entry</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">data</span><span class="p">):</span>
|
||
<span class="k">if</span> <span class="n">count</span> <span class="o">==</span> <span class="mi">0</span> <span class="ow">and</span> <span class="n">headers</span><span class="p">:</span>
|
||
<span class="c1"># If headers are defined, write them, otherwise</span>
|
||
<span class="c1"># continue as they will be written anyways</span>
|
||
<span class="n">csv_file</span><span class="o">.</span><span class="n">writerow</span><span class="p">(</span><span class="n">headers</span><span class="p">)</span>
|
||
<span class="n">csv_file</span><span class="o">.</span><span class="n">writerow</span><span class="p">(</span><span class="n">entry</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
<div class="section" id="id2">
|
||
<h3>Docstring References<a class="headerlink" href="#id2" title="Permalink to this headline">¶</a></h3>
|
||
<dl class="py function">
|
||
<dt id="pyforhandbook.ch01_essentials.csv_example.write_csv_dicts">
|
||
<code class="sig-name descname">write_csv_dicts</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">outfile</span></em>, <em class="sig-param"><span class="n">data</span></em>, <em class="sig-param"><span class="n">headers</span><span class="o">=</span><span class="default_value">None</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyforhandbook.ch01_essentials.csv_example.write_csv_dicts" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Writes a list of dictionaries to a CSV file.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters</dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>outfile</strong> (<em>str</em>) – Path to output file</p></li>
|
||
<li><p><strong>data</strong> (<em>list</em>) – List of dictionaries to write to file</p></li>
|
||
<li><p><strong>headers</strong> (<em>list</em>) – Header row to use. If empty, will use the
|
||
first dictionary in the <cite>data</cite> list.</p></li>
|
||
</ul>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Example</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">list_of_dicts</span> <span class="o">=</span> <span class="p">[</span>
|
||
<span class="gp">>>> </span> <span class="p">{</span><span class="s1">'name'</span><span class="p">:</span> <span class="s1">'apple'</span><span class="p">,</span> <span class="s1">'quantity'</span><span class="p">:</span> <span class="mi">10</span><span class="p">,</span> <span class="s1">'location'</span><span class="p">:</span> <span class="s1">'VT'</span><span class="p">},</span>
|
||
<span class="gp">>>> </span> <span class="p">{</span><span class="s1">'name'</span><span class="p">:</span> <span class="s1">'orange'</span><span class="p">,</span> <span class="s1">'quantity'</span><span class="p">:</span> <span class="mi">5</span><span class="p">,</span> <span class="s1">'location'</span><span class="p">:</span> <span class="s1">'FL'</span><span class="p">}</span>
|
||
<span class="gp">>>> </span><span class="p">]</span>
|
||
<span class="gp">>>> </span><span class="n">write_csv_dicts</span><span class="p">(</span><span class="s1">'dict_test.csv'</span><span class="p">,</span> <span class="n">list_of_dicts</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="py function">
|
||
<dt id="pyforhandbook.ch01_essentials.csv_example.write_csv_lists">
|
||
<code class="sig-name descname">write_csv_lists</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">outfile</span></em>, <em class="sig-param"><span class="n">data</span></em>, <em class="sig-param"><span class="n">headers</span><span class="o">=</span><span class="default_value">None</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyforhandbook.ch01_essentials.csv_example.write_csv_lists" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Writes a list of lists to a CSV file.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters</dt>
|
||
<dd class="field-odd"><ul class="simple">
|
||
<li><p><strong>outfile</strong> (<em>str</em>) – Path to output file</p></li>
|
||
<li><p><strong>data</strong> (<em>list</em>) – List of lists to write to file</p></li>
|
||
<li><p><strong>headers</strong> (<em>list</em>) – Header row to use. If empty, will use the
|
||
first list in the <cite>data</cite> list.</p></li>
|
||
</ul>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Examples</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">fields</span> <span class="o">=</span> <span class="p">[</span><span class="s1">'name'</span><span class="p">,</span> <span class="s1">'quantity'</span><span class="p">,</span> <span class="s1">'location'</span><span class="p">]</span>
|
||
<span class="gp">>>> </span><span class="n">list_of_lists</span> <span class="o">=</span> <span class="p">[</span>
|
||
<span class="gp">>>> </span> <span class="p">[</span><span class="s1">'apple'</span><span class="p">,</span> <span class="mi">10</span><span class="p">,</span> <span class="s1">'VT'</span><span class="p">],</span>
|
||
<span class="gp">>>> </span> <span class="p">[</span><span class="s1">'orange'</span><span class="p">,</span> <span class="mi">5</span><span class="p">,</span> <span class="s1">'FL'</span><span class="p">]</span>
|
||
<span class="gp">>>> </span><span class="p">]</span>
|
||
<span class="gp">>>> </span><span class="n">write_csv_lists</span><span class="p">(</span><span class="s1">'list_test.csv'</span><span class="p">,</span> <span class="n">list_of_lists</span><span class="p">,</span> <span class="n">headers</span><span class="o">=</span><span class="n">fields</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
</div>
|
||
<div class="section" id="module-pyforhandbook.ch01_essentials.recursion_example">
|
||
<span id="section-1-5-directory-recursion"></span><h2>Section 1.5 - Directory Recursion<a class="headerlink" href="#module-pyforhandbook.ch01_essentials.recursion_example" title="Permalink to this headline">¶</a></h2>
|
||
<p>File recursion example.</p>
|
||
<p>Demonstration of iterating through a directory to interact with
|
||
files.</p>
|
||
<p>Example Usage:</p>
|
||
<blockquote>
|
||
<div><p><code class="docutils literal notranslate"><span class="pre">$</span> <span class="pre">python</span> <span class="pre">recursion_example.py</span></code></p>
|
||
</div></blockquote>
|
||
<p>References:</p>
|
||
<ul class="simple">
|
||
<li><p><a class="reference external" href="https://docs.python.org/3/library/os.html">https://docs.python.org/3/library/os.html</a></p></li>
|
||
</ul>
|
||
<div class="section" id="list-a-directory">
|
||
<h3>List a directory<a class="headerlink" href="#list-a-directory" title="Permalink to this headline">¶</a></h3>
|
||
<p>This function shows an example of displaying all files and
|
||
folders within a single directory. From here you can further
|
||
interact with individual files and folders or iterate recursively
|
||
by calling the function on identified subdirectories.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">list_directory</span><span class="p">(</span><span class="n">path</span><span class="p">):</span>
|
||
<span class="sd">"""List all file and folder entries in `path`.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> path (str): A directory within a mounted file system. May be relative or</span>
|
||
<span class="sd"> absolute.</span>
|
||
|
||
<span class="sd"> Examples:</span>
|
||
<span class="sd"> >>> list_directory('.')</span>
|
||
|
||
<span class="sd"> """</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"Files and folders in '</span><span class="si">{</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">abspath</span><span class="p">(</span><span class="n">path</span><span class="p">)</span><span class="si">}</span><span class="s2">':"</span><span class="p">)</span>
|
||
<span class="c1"># Quick and easy method for listing items within a single</span>
|
||
<span class="c1"># folder.</span>
|
||
<span class="k">for</span> <span class="n">entry</span> <span class="ow">in</span> <span class="n">os</span><span class="o">.</span><span class="n">listdir</span><span class="p">(</span><span class="n">path</span><span class="p">):</span>
|
||
<span class="c1"># Print all entry names</span>
|
||
<span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">"</span><span class="se">\t</span><span class="si">{</span><span class="n">entry</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</div>
|
||
<div class="section" id="list-a-directory-recursively">
|
||
<h3>List a directory recursively<a class="headerlink" href="#list-a-directory-recursively" title="Permalink to this headline">¶</a></h3>
|
||
<p>This function shows an example of displaying all files and
|
||
folders within a all directories. You don’t need to worry about
|
||
additional function calls as the <code class="docutils literal notranslate"><span class="pre">os.walk()</span></code> method handles
|
||
the recursion on subdirectories and your logic can focus on
|
||
handling the processing of files. This sample shows a method of
|
||
counting the number of files, subdirectories, and files ending in
|
||
“.py” as an example.</p>
|
||
<div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="k">def</span> <span class="nf">iterate_files</span><span class="p">(</span><span class="n">path</span><span class="p">):</span>
|
||
<span class="sd">"""Recursively iterate over a path, findings all files within the folder</span>
|
||
<span class="sd"> and its subdirectories.</span>
|
||
|
||
<span class="sd"> Args:</span>
|
||
<span class="sd"> path (str): A directory within a mounted file system. May be relative or</span>
|
||
<span class="sd"> absolute.</span>
|
||
|
||
<span class="sd"> Examples:</span>
|
||
<span class="sd"> >>> number_of_py_files = 0</span>
|
||
<span class="sd"> >>> for f in iterate_files('../'):</span>
|
||
<span class="sd"> ... if f.endswith('.py'):</span>
|
||
<span class="sd"> ... number_of_py_files += 1</span>
|
||
<span class="sd"> >>> print(f"\t{number_of_py_files} python files found "</span>
|
||
<span class="sd"> ... f"in {os.path.abspath('../')}")</span>
|
||
<span class="sd"> """</span>
|
||
<span class="c1"># Though `os.walk()` exposes a list of directories in the</span>
|
||
<span class="c1"># current `root`, it is rarely used since we are generally</span>
|
||
<span class="c1"># interested in the files found within the subdirectories.</span>
|
||
<span class="c1"># For this reason, it is common to see `dirs` named `_`.</span>
|
||
<span class="c1"># DO NOT NAME `dirs` as `dir` since `dir` is a reserved word!</span>
|
||
<span class="k">for</span> <span class="n">root</span><span class="p">,</span> <span class="n">dirs</span><span class="p">,</span> <span class="n">files</span> <span class="ow">in</span> <span class="n">os</span><span class="o">.</span><span class="n">walk</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">abspath</span><span class="p">(</span><span class="n">path</span><span class="p">)):</span>
|
||
<span class="c1"># Both `dirs` and `files` are lists containing all entries</span>
|
||
<span class="c1"># at the current `root`.</span>
|
||
<span class="k">for</span> <span class="n">file_name</span> <span class="ow">in</span> <span class="n">files</span><span class="p">:</span>
|
||
<span class="c1"># To effectively reference a file, you should include</span>
|
||
<span class="c1"># the below line which creates a full path reference</span>
|
||
<span class="c1"># to the specific file, regardless of how nested it is</span>
|
||
<span class="c1"># We can then hand `file_entry` off to other functions.</span>
|
||
<span class="k">yield</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">root</span><span class="p">,</span> <span class="n">file_name</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
<dl class="py function">
|
||
<dt id="pyforhandbook.ch01_essentials.recursion_example.iterate_files">
|
||
<code class="sig-name descname">iterate_files</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">path</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyforhandbook.ch01_essentials.recursion_example.iterate_files" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>Recursively iterate over a path, findings all files within the folder
|
||
and its subdirectories.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters</dt>
|
||
<dd class="field-odd"><p><strong>path</strong> (<em>str</em>) – A directory within a mounted file system. May be relative or
|
||
absolute.</p>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Examples</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">number_of_py_files</span> <span class="o">=</span> <span class="mi">0</span>
|
||
<span class="gp">>>> </span><span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">iterate_files</span><span class="p">(</span><span class="s1">'../'</span><span class="p">):</span>
|
||
<span class="gp">... </span> <span class="k">if</span> <span class="n">f</span><span class="o">.</span><span class="n">endswith</span><span class="p">(</span><span class="s1">'.py'</span><span class="p">):</span>
|
||
<span class="gp">... </span> <span class="n">number_of_py_files</span> <span class="o">+=</span> <span class="mi">1</span>
|
||
<span class="gp">>>> </span><span class="nb">print</span><span class="p">(</span><span class="sa">f</span><span class="s2">" </span><span class="si">{</span><span class="n">number_of_py_files</span><span class="si">}</span><span class="s2"> python files found "</span>
|
||
<span class="gp">... </span> <span class="sa">f</span><span class="s2">"in </span><span class="si">{</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">abspath</span><span class="p">(</span><span class="s1">'../'</span><span class="p">)</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
<dl class="py function">
|
||
<dt id="pyforhandbook.ch01_essentials.recursion_example.list_directory">
|
||
<code class="sig-name descname">list_directory</code><span class="sig-paren">(</span><em class="sig-param"><span class="n">path</span></em><span class="sig-paren">)</span><a class="headerlink" href="#pyforhandbook.ch01_essentials.recursion_example.list_directory" title="Permalink to this definition">¶</a></dt>
|
||
<dd><p>List all file and folder entries in <cite>path</cite>.</p>
|
||
<dl class="field-list simple">
|
||
<dt class="field-odd">Parameters</dt>
|
||
<dd class="field-odd"><p><strong>path</strong> (<em>str</em>) – A directory within a mounted file system. May be relative or
|
||
absolute.</p>
|
||
</dd>
|
||
</dl>
|
||
<p class="rubric">Examples</p>
|
||
<div class="doctest highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">list_directory</span><span class="p">(</span><span class="s1">'.'</span><span class="p">)</span>
|
||
</pre></div>
|
||
</div>
|
||
</dd></dl>
|
||
|
||
</div>
|
||
</div>
|
||
<div class="section" id="indices-and-tables">
|
||
<h2>Indices and tables<a class="headerlink" href="#indices-and-tables" title="Permalink to this headline">¶</a></h2>
|
||
<ul class="simple">
|
||
<li><p><a class="reference internal" href="genindex.html"><span class="std std-ref">Index</span></a></p></li>
|
||
<li><p><a class="reference internal" href="py-modindex.html"><span class="std std-ref">Module Index</span></a></p></li>
|
||
<li><p><a class="reference internal" href="search.html"><span class="std std-ref">Search Page</span></a></p></li>
|
||
</ul>
|
||
</div>
|
||
</div>
|
||
|
||
|
||
</div>
|
||
|
||
</div>
|
||
<footer>
|
||
|
||
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
|
||
|
||
<a href="ch02_registry.html" class="btn btn-neutral float-right" title="Chapter 2 - Registry Parsing" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a>
|
||
|
||
|
||
<a href="index.html" class="btn btn-neutral float-left" title="The Python Forensics Handbook" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a>
|
||
|
||
</div>
|
||
|
||
|
||
<hr/>
|
||
|
||
<div role="contentinfo">
|
||
<p>
|
||
|
||
© Copyright 2020, Chapin Bryce
|
||
|
||
</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> |