309 lines
462 KiB
HTML
309 lines
462 KiB
HTML
|
<!DOCTYPE html>
|
|||
|
<html><head><title>文件和IO操作</title><meta charSet="utf-8"/><meta name="viewport" content="width=device-width, initial-scale=1.0"/><meta property="og:title" content="文件和IO操作"/><meta property="og:description" content="Python 文件和IO操作,主要涉及基础的文件操作和拓展库,以及文件系统的操作。."/><meta property="og:image" content="https://wiki.7wate.com/static/og-image.png"/><meta property="og:width" content="1200"/><meta property="og:height" content="675"/><link rel="icon" href="../../../../static/icon.png"/><meta name="description" content="Python 文件和IO操作,主要涉及基础的文件操作和拓展库,以及文件系统的操作。."/><meta name="generator" content="Quartz"/><link rel="preconnect" href="https://fonts.googleapis.com"/><link rel="preconnect" href="https://fonts.gstatic.com"/><script async src="https://umami.7wate.com/script.js" data-website-id="c061efdc-95dd-4d21-9d04-a1ffda0a85b9"></script><script>
|
|||
|
var _hmt = _hmt || [];
|
|||
|
(function() {
|
|||
|
var hm = document.createElement("script");
|
|||
|
hm.src = "https://hm.baidu.com/hm.js?94d8ccb156eb7c65abf317e6e01cdba9";
|
|||
|
var s = document.getElementsByTagName("script")[0];
|
|||
|
s.parentNode.insertBefore(hm, s);
|
|||
|
})();
|
|||
|
</script><script async src="https://www.googletagmanager.com/gtag/js?id=G-MHMEL0F832"></script><script>
|
|||
|
(function() {
|
|||
|
window.dataLayer = window.dataLayer || [];
|
|||
|
function gtag() {
|
|||
|
window.dataLayer.push(arguments);
|
|||
|
}
|
|||
|
gtag('js', new Date());
|
|||
|
gtag('config', 'G-MHMEL0F832');
|
|||
|
})();
|
|||
|
</script><link href="../../../../index.css" rel="stylesheet" type="text/css" spa-preserve/><link href="https://cdn.jsdelivr.net/npm/katex@0.16.0/dist/katex.min.css" rel="stylesheet" type="text/css" spa-preserve/><link href="https://fonts.googleapis.com/css2?family=IBM Plex Mono&family=Schibsted Grotesk:wght@400;700&family=Source Sans Pro:ital,wght@0,400;0,600;1,400;1,600&display=swap" rel="stylesheet" type="text/css" spa-preserve/><script src="../../../../prescript.js" type="application/javascript" spa-preserve></script><script type="application/javascript" spa-preserve>const fetchData = fetch(`../../../../static/contentIndex.json`).then(data => data.json())</script></head><body data-slug="Tech/programming-language/Python/进阶/文件和IO操作"><div id="quartz-root" class="page"><div id="quartz-body"><div class="left sidebar"><h1 class="page-title "><a href="../../../..">📚 X·Eden</a></h1><div class="spacer mobile-only"></div><div class="search "><div id="search-icon"><p>Search</p><div></div><svg tabIndex="0" aria-labelledby="title desc" role="img" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 19.9 19.7"><title id="title">Search</title><desc id="desc">Search</desc><g class="search-path" fill="none"><path stroke-linecap="square" d="M18.5 18.3l-5.4-5.4"></path><circle cx="8" cy="8" r="7"></circle></g></svg></div><div id="search-container"><div id="search-space"><input autocomplete="off" id="search-bar" name="search" type="text" aria-label="Search for something" placeholder="Search for something"/><div id="results-container"></div></div></div></div><div class="darkmode "><input class="toggle" id="darkmode-toggle" type="checkbox" tabIndex="-1"/><label id="toggle-label-light" for="darkmode-toggle" tabIndex="-1"><svg xmlns="http://www.w3.org/2000/svg" xmlnsXlink="http://www.w3.org/1999/xlink" version="1.1" id="dayIcon" x="0px" y="0px" viewBox="0 0 35 35" style="enable-background:new 0 0 35 35;" xmlSpace="preserve"><title>Light mode</title><path d="M6,17.5C6,16.672,5.328,16,4.5,16h-3C0.672,16,0,16.672,0,17.5 S0.672,19,1.5,19h3C5.328,19,6,18.328,6,17.5z M7.5,26c-0.414,0-0.789,0.168-1.061,0.439l-2,2C4.168,28.711,4,29.086,4,29.5 C4,30.328,4.671,31,5.5,31c0.414,0,0.789-0.168,1.06-0.44l2-2C8.832,28.289,9,27.914,9,27.5C9,26.672,8.329,26,7.5,26z M17.5,6 C18.329,6,19,5.328,19,4.5v-3C19,0.672,18.329,0,17.5,0S16,0.672,16,1.5v3C16,5.328,16.671,6,17.5,6z M27.5,9 c0.414,0,0.789-0.168,1.06-0.439l2-2C30.832,6.289,31,5.914,31,5.5C31,4.672,30.329,4,29.5,4c-0.414,0-0.789,0.168-1.061,0.44 l-2,2C26.168,6.711,26,7.086,26,7.5C26,8.328,26.671,9,27.5,9z M6.439,8.561C6.711,8.832,7.086,9,7.5,9C8.328,9,9,8.328,9,7.5 c0-0.414-0.168-0.789-0.439-1.061l-2-2C6.289,4.168,5.914,4,5.5,4C4.672,4,4,4.672,4,5.5c0,0.414,0.168,0.789,0.439,1.06 L6.439,8.561z M33.5,16h-3c-0.828,0-1.5,0.672-1.5,1.5s0.672,1.5,1.5,1.5h3c0.828,0,1.5-0.672,1.5-1.5S34.328,16,33.5,16z M28.561,26.439C28.289,26.168,27.914,26,27.5,26c-0.828,0-1.5,0.672-1.5,1.5c0,0.414,0.168,0.789,0.439,1.06l2,2 C28.711,30.832,29.086,31,29.5,31c0.828,0,1.5-0.672,1.5-1.5c0-0.414-0.168-0.789-0.439-1.061L28.561,26.439z M17.5,29 c-0.829,0-1.5,0.672-1.5,1.5v3c0,0.828,0.671,1.5,1.5,1.5s1.5-0.672,1.5-1.5v-3C19,29.672,18.329,29,17.5,29z M17.5,7 C11.71,7,7,11.71,7,17.5S11.71,28,17.5,28S28,23.29,28,17.5S23.29,7,17.5,7z M17.5,25c-4.136,0-7.5-3.364-7.5-7.5 c0-4.136,3.364-7.5,7.5-7.5c4.136,0,7.5,3.364,7.5,7.5C25,21.636,21.636,25,17.5,25z"></path></svg></label><label id="toggle-label-dark" for="darkmode-toggle" tabIndex="-1"><svg xmlns="http://www.w3.org/2000/svg" xmlnsXlink="http://www.w3.org/1999/xlink" version="1.1" id="nightIcon" x="0px" y="0px" viewBox="0 0 100 100" style="enable-background='new 0 0 100 100'" xmlSpace="preserve"><title>Dark mode</title><path d="M96.76,66.458c-0.853-0.852-2.15-1.064-3.23-0.534c-6.063,2.991-12.858,4.571-19.655,4.571 C62.022,70.495,50.88,65.88,42.5,57.5C29.043,44.043,25.658,23.536,34.076,6.47c0.532-1.08,0.318-2.379-0.534-3.23 c-0.851-0.852-2.15-1.064-3.23-0.534c-4.918,2.427-9.375,5.619-13.246,9.491c-9.447,9.447-14.65,22.008-
|
|||
|
<h3 id="文件和-io-的基本概念">文件和 IO 的基本概念<a aria-hidden="true" tabindex="-1" href="#文件和-io-的基本概念" class="internal"> §</a></h3>
|
|||
|
<p>在编程领域,文件和输入/输出(IO)操作是基本的组成部分。文件是存储在磁盘上的数据集合,可以包含文本、图片、音频等多种格式的数据。IO 操作则涉及到数据的读取(输入)和写入(输出)。在 Python 中,对文件的操作简单而强大,涵盖了从文本文件到复杂数据格式的处理。</p>
|
|||
|
<p>理解文件的操作对于数据处理、日志记录、配置文件的读写等都至关重要。Python 提供了丰富的库来处理各种类型的文件,使得文件读写变得既简单又安全。</p>
|
|||
|
<h3 id="文件打开与关闭">文件打开与关闭<a aria-hidden="true" tabindex="-1" href="#文件打开与关闭" class="internal"> §</a></h3>
|
|||
|
<p>文件在使用前必须先打开,并在操作完成后关闭。Python 通过内置的 <code>open()</code> 函数来打开文件,这个函数返回一个文件对象,然后可以对其进行读取或写入操作。文件操作完成后,应该使用 <code>close()</code> 方法关闭文件以释放系统资源。但更推荐的做法是使用 <code>with</code> 语句(<a href="../../../../Tech/programming-language/Python/进阶/资源管理" class="internal" data-slug="Tech/programming-language/Python/进阶/资源管理">上下文管理器</a>),它会在代码块执行完毕后自动关闭文件,即使在代码块中发生了异常。</p>
|
|||
|
<h3 id="文件读写操作">文件读写操作<a aria-hidden="true" tabindex="-1" href="#文件读写操作" class="internal"> §</a></h3>
|
|||
|
<p>读取和写入是文件操作中最基础的部分。Python 提供了多种方法来读取文件(如 <code>read()</code>,<code>readline()</code>,<code>readlines()</code>)和写入文件(如 <code>write()</code>,<code>writelines()</code>)。这些方法可以灵活应用于不同的场景,如逐字符、逐行读取或写入整个文件。</p>
|
|||
|
<h3 id="文件模式">文件模式<a aria-hidden="true" tabindex="-1" href="#文件模式" class="internal"> §</a></h3>
|
|||
|
<p>在打开文件时,可以指定不同的模式:</p>
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
|
|||
|
<table><thead><tr><th>模式</th><th>描述</th></tr></thead><tbody><tr><td><code>'r'</code></td><td>只读模式。如果文件不存在,抛出异常。</td></tr><tr><td><code>'w'</code></td><td>写入模式。如果文件存在,覆盖原有内容;如果文件不存在,创建新文件。</td></tr><tr><td><code>'a'</code></td><td>附加模式。如果文件存在,将数据添加到文件末尾;如果文件不存在,创建新文件。</td></tr><tr><td><code>'r+'</code></td><td>读写模式。可以读取和写入文件,如果文件不存在,抛出异常。</td></tr><tr><td><code>'w+'</code></td><td>写读模式。打开文件进行读写,覆盖原有内容;如果文件不存在,则创建新文件。</td></tr><tr><td><code>'a+'</code></td><td>附加和读取模式。可以读取和在文件末尾附加内容;如果文件不存在,则创建新文件。</td></tr><tr><td><code>'rb'</code></td><td>以二进制格式打开文件进行只读。</td></tr><tr><td><code>'wb'</code></td><td>以二进制格式打开文件进行写入,覆盖原有内容;如果文件不存在,则创建新文件。</td></tr><tr><td><code>'ab'</code></td><td>以二进制格式打开文件进行附加,如果文件不存在,则创建新文件。</td></tr><tr><td><code>'rb+'</code></td><td>以二进制格式打开文件进行读写。</td></tr><tr><td><code>'wb+'</code></td><td>以二进制格式打开文件进行写读,覆盖原有内容;如果文件不存在,则创建新文件。</td></tr><tr><td><code>'ab+'</code></td><td>以二进制格式打开文件进行附加和读取。</td></tr></tbody></table>
|
|||
|
<h2 id="文件类型和数据格式处理">文件类型和数据格式处理<a aria-hidden="true" tabindex="-1" href="#文件类型和数据格式处理" class="internal"> §</a></h2>
|
|||
|
<h3 id="处理文本文件">处理文本文件<a aria-hidden="true" tabindex="-1" href="#处理文本文件" class="internal"> §</a></h3>
|
|||
|
<p>文本文件存储的是可读字符,如 <code>.txt</code> 文件。Python 中处理文本文件非常直接,可以使用字符串方法对内容进行操作。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-comment);"># 读取文本文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'example.txt'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'r'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> content </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">read</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(content)</span></span></code></pre></div>
|
|||
|
<h3 id="处理二进制文件">处理二进制文件<a aria-hidden="true" tabindex="-1" href="#处理二进制文件" class="internal"> §</a></h3>
|
|||
|
<p>二进制文件存储的是字节数据,如图片、音频等。在 Python 中,通过在 <code>open()</code> 函数中使用 <code>'rb'</code> 或 <code>'wb'</code> 模式来读取或写入二进制文件。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-comment);"># 读取二进制文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'image.png'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'rb'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> content </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">read</span><span style="color:var(--shiki-token-punctuation);">()</span></span></code></pre></div>
|
|||
|
<h3 id="csv-文件处理">CSV 文件处理<a aria-hidden="true" tabindex="-1" href="#csv-文件处理" class="internal"> §</a></h3>
|
|||
|
<p>CSV(逗号分隔值)是一种常见的数据交换格式。Python 的 <a href="../../../../Tech/programming-language/Python/模块/数据处理/csv-文件读写" class="internal" data-slug="Tech/programming-language/Python/模块/数据处理/csv-文件读写"> csv 模块</a> 提供了读取和写入 CSV 文件的功能。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> csv</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 读取 CSV 文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'data.csv'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'r'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> csv_reader </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> csv</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">reader</span><span style="color:var(--shiki-token-punctuation);">(file)</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">for</span><span style="color:var(--shiki-color-text);"> row </span><span style="color:var(--shiki-token-keyword);">in</span><span style="color:var(--shiki-color-text);"> csv_reader</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(row)</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 写入 CSV 文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'output.csv'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'w'</span><span style="color:var(--shiki-token-punctuation);">, newline</span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-token-string-expression);">''</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> csv_writer </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> csv</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">writer</span><span style="color:var(--shiki-token-punctuation);">(file)</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> csv_writer</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">writerow</span><span style="color:var(--shiki-token-punctuation);">([</span><span style="color:var(--shiki-token-string-expression);">'name'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'age'</span><span style="color:var(--shiki-token-punctuation);">])</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> csv_writer</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">writerow</span><span style="color:var(--shiki-token-punctuation);">([</span><span style="color:var(--shiki-token-string-expression);">'Alice'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-constant);">30</span><span style="color:var(--shiki-token-punctuation);">])</span></span></code></pre></div>
|
|||
|
<h3 id="json-文件处理">JSON 文件处理<a aria-hidden="true" tabindex="-1" href="#json-文件处理" class="internal"> §</a></h3>
|
|||
|
<p>JSON(JavaScript Object Notation)是一种轻量级的数据交换格式。Python 的 <a href="../../../../Tech/programming-language/Python/模块/数据处理/json-编码和解码器" class="internal" data-slug="Tech/programming-language/Python/模块/数据处理/json-编码和解码器">json 模块</a> 可以轻松处理 JSON 数据。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> json</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 读取 JSON 文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'data.json'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'r'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> data </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> json</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">load</span><span style="color:var(--shiki-token-punctuation);">(file)</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(data)</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 写入 JSON 文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'output.json'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'w'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> json</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">dump</span><span style="color:var(--shiki-token-punctuation);">({</span><span style="color:var(--shiki-token-string-expression);">'name'</span><span style="color:var(--shiki-token-punctuation);">: </span><span style="color:var(--shiki-token-string-expression);">'Alice'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'age'</span><span style="color:var(--shiki-token-punctuation);">: </span><span style="color:var(--shiki-token-constant);">30</span><span style="color:var(--shiki-token-punctuation);">}, file, indent</span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-token-constant);">4</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line> </span></code></pre></div>
|
|||
|
<h2 id="文件系统操作">文件系统操作<a aria-hidden="true" tabindex="-1" href="#文件系统操作" class="internal"> §</a></h2>
|
|||
|
<h3 id="文件和目录的基本操作">文件和目录的基本操作<a aria-hidden="true" tabindex="-1" href="#文件和目录的基本操作" class="internal"> §</a></h3>
|
|||
|
<p>Python 的 <code>os</code> 和 <code>shutil</code> 模块提供了丰富的文件和目录管理功能,包括创建、删除、移动、复制等。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> os</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> shutil</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 创建目录</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);">os</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">mkdir</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'new_directory'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 移动文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);">shutil</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">move</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'example.txt'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'new_directory/example.txt'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 复制文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);">shutil</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">copy</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'new_directory/example.txt'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'example_copy.txt'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 删除文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);">os</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">remove</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'example_copy.txt'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line> </span></code></pre></div>
|
|||
|
<h3 id="路径操作">路径操作<a aria-hidden="true" tabindex="-1" href="#路径操作" class="internal"> §</a></h3>
|
|||
|
<p>Python 提供了 <code>os.path</code> 和 <code>pathlib</code> 模块来处理文件路径的各种需求。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">from</span><span style="color:var(--shiki-color-text);"> pathlib </span><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> Path</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 创建 Path 对象</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);">path </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">Path</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'example.txt'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 检查文件是否存在</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(path.</span><span style="color:var(--shiki-token-function);">exists</span><span style="color:var(--shiki-token-punctuation);">())</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 获取文件扩展名</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(path.suffix)</span></span>
|
|||
|
<span data-line> </span></code></pre></div>
|
|||
|
<h3 id="使用临时文件">使用临时文件<a aria-hidden="true" tabindex="-1" href="#使用临时文件" class="internal"> §</a></h3>
|
|||
|
<p><code>tempfile</code> 模块用于创建临时文件和目录,这在需要临时存储数据时非常有用。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> tempfile</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 创建临时文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);">temp_file </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> tempfile</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">TemporaryFile</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 写入临时文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);">temp_file</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">write</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-keyword);">b</span><span style="color:var(--shiki-token-string-expression);">'Temporary data'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);">temp_file</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">seek</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-constant);">0</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 读取临时文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(temp_file.</span><span style="color:var(--shiki-token-function);">read</span><span style="color:var(--shiki-token-punctuation);">())</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 关闭临时文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);">temp_file</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">close</span><span style="color:var(--shiki-token-punctuation);">()</span></span></code></pre></div>
|
|||
|
<h2 id="高级文件操作技巧">高级文件操作技巧<a aria-hidden="true" tabindex="-1" href="#高级文件操作技巧" class="internal"> §</a></h2>
|
|||
|
<h3 id="文件迭代与遍历">文件迭代与遍历<a aria-hidden="true" tabindex="-1" href="#文件迭代与遍历" class="internal"> §</a></h3>
|
|||
|
<p>文件内容可以逐行或按特定条件迭代,这对于处理大型文件尤为重要。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-comment);"># 逐行读取文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'large_file.txt'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'r'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">for</span><span style="color:var(--shiki-color-text);"> line </span><span style="color:var(--shiki-token-keyword);">in</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">process</span><span style="color:var(--shiki-token-punctuation);">(line)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-comment);"># 自定义的处理函数</span></span>
|
|||
|
<span data-line> </span></code></pre></div>
|
|||
|
<h3 id="内存映射文件操作">内存映射文件操作<a aria-hidden="true" tabindex="-1" href="#内存映射文件操作" class="internal"> §</a></h3>
|
|||
|
<p>使用 <code>mmap</code> 模块可以将文件内容映射到内存,这样可以提高读写大文件的效率。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> mmap</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 内存映射一个大文件</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'large_file.txt'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'r+b'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> f</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> mm </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> mmap</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">mmap</span><span style="color:var(--shiki-token-punctuation);">(f.</span><span style="color:var(--shiki-token-function);">fileno</span><span style="color:var(--shiki-token-punctuation);">(), </span><span style="color:var(--shiki-token-constant);">0</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(mm.</span><span style="color:var(--shiki-token-function);">readline</span><span style="color:var(--shiki-token-punctuation);">())</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-comment);"># 读取一行内容</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> mm</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">close</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
|
|||
|
<span data-line> </span></code></pre></div>
|
|||
|
<h3 id="异步-io-操作">异步 IO 操作<a aria-hidden="true" tabindex="-1" href="#异步-io-操作" class="internal"> §</a></h3>
|
|||
|
<p>Python 的 <code>asyncio</code> 库允许进行异步 IO 操作,这对于提高 IO 密集型应用的性能很有帮助。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> asyncio</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">async</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">def</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">read_file_async</span><span style="color:var(--shiki-color-text);">(</span><span style="color:var(--shiki-token-parameter);">file_name</span><span style="color:var(--shiki-color-text);">):</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(file_name, </span><span style="color:var(--shiki-token-string-expression);">'r'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">return</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">await</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">read</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-comment);"># 在异步函数中调用</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">async</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">def</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">main</span><span style="color:var(--shiki-color-text);">():</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> content </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">await</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">read_file_async</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'example.txt'</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(content)</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);">asyncio</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">run</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-function);">main</span><span style="color:var(--shiki-token-punctuation);">())</span></span>
|
|||
|
<span data-line> </span></code></pre></div>
|
|||
|
<h2 id="编码和错误处理">编码和错误处理<a aria-hidden="true" tabindex="-1" href="#编码和错误处理" class="internal"> §</a></h2>
|
|||
|
<h3 id="字符编码">字符编码<a aria-hidden="true" tabindex="-1" href="#字符编码" class="internal"> §</a></h3>
|
|||
|
<p>理解字符编码(如 UTF-8, ASCII)对于正确处理文本文件至关重要,特别是在处理国际化内容时。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-comment);"># 指定文件的编码</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'example.txt'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'r'</span><span style="color:var(--shiki-token-punctuation);">, encoding</span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-token-string-expression);">'utf-8'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> content </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">read</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
|
|||
|
<span data-line> </span></code></pre></div>
|
|||
|
<h3 id="文件操作中的错误处理">文件操作中的错误处理<a aria-hidden="true" tabindex="-1" href="#文件操作中的错误处理" class="internal"> §</a></h3>
|
|||
|
<p>文件操作可能会引发各种 <a href="../../../../Tech/programming-language/Python/进阶/异常处理" class="internal" data-slug="Tech/programming-language/Python/进阶/异常处理">异常</a>,例如 <code>FileNotFoundError</code> 或 <code>PermissionError</code>。正确处理这些异常是编写健壮代码的关键。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">try</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'nonexistent_file.txt'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'r'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> content </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">read</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">except</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-constant);">FileNotFoundError</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">print</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">"文件不存在"</span><span style="color:var(--shiki-token-punctuation);">)</span></span></code></pre></div>
|
|||
|
<h2 id="性能优化和最佳实践">性能优化和最佳实践<a aria-hidden="true" tabindex="-1" href="#性能优化和最佳实践" class="internal"> §</a></h2>
|
|||
|
<p>处理文件和 IO 操作时,性能优化和资源管理是两个关键的方面。正确处理这些问题不仅可以提高程序的效率,还能避免常见的资源泄露和同步问题。</p>
|
|||
|
<h3 id="性能优化">性能优化<a aria-hidden="true" tabindex="-1" href="#性能优化" class="internal"> §</a></h3>
|
|||
|
<p>在处理大型文件时,性能成为一个重要的考虑因素。以下是一些优化文件操作性能的策略:</p>
|
|||
|
<h4 id="逐行处理而非一次性读取整个文件">逐行处理而非一次性读取整个文件<a aria-hidden="true" tabindex="-1" href="#逐行处理而非一次性读取整个文件" class="internal"> §</a></h4>
|
|||
|
<p>对于非常大的文件,一次性读取整个文件到内存中可能会导致内存溢出。逐行读取文件是一个更好的选择。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'large_file.txt'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'r'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">for</span><span style="color:var(--shiki-color-text);"> line </span><span style="color:var(--shiki-token-keyword);">in</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">process</span><span style="color:var(--shiki-token-punctuation);">(line)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-comment);"># 对每行进行处理</span></span></code></pre></div>
|
|||
|
<h4 id="使用生成器进行延迟计算">使用生成器进行延迟计算<a aria-hidden="true" tabindex="-1" href="#使用生成器进行延迟计算" class="internal"> §</a></h4>
|
|||
|
<p>如果处理文件的过程涉及到复杂的数据处理,可以<strong>使用生成器来进行延迟计算</strong>,这样可以避免不必要的内存使用。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">def</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">read_large_file</span><span style="color:var(--shiki-color-text);">(</span><span style="color:var(--shiki-token-parameter);">file_obj</span><span style="color:var(--shiki-color-text);">):</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-comment);">"""逐行读取大文件的生成器"""</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">for</span><span style="color:var(--shiki-color-text);"> line </span><span style="color:var(--shiki-token-keyword);">in</span><span style="color:var(--shiki-color-text);"> file_obj</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">yield</span><span style="color:var(--shiki-color-text);"> line</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">strip</span><span style="color:var(--shiki-token-punctuation);">()</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'large_file.txt'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'r'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> file</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">for</span><span style="color:var(--shiki-color-text);"> line </span><span style="color:var(--shiki-token-keyword);">in</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">read_large_file</span><span style="color:var(--shiki-token-punctuation);">(file):</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">process</span><span style="color:var(--shiki-token-punctuation);">(line)</span></span></code></pre></div>
|
|||
|
<h4 id="内存映射文件">内存映射文件<a aria-hidden="true" tabindex="-1" href="#内存映射文件" class="internal"> §</a></h4>
|
|||
|
<p>对于非常大的文件,使用内存映射的方式可以提高读写效率。这种方法适用于二进制文件,可以让你像访问数组一样访问文件内容。</p>
|
|||
|
<div data-rehype-pretty-code-fragment><pre style="background-color:var(--shiki-color-background);" tabindex="0" data-language="python" data-theme="default"><code data-language="python" data-theme="default"><span data-line><span style="color:var(--shiki-token-keyword);">import</span><span style="color:var(--shiki-color-text);"> mmap</span></span>
|
|||
|
<span data-line> </span>
|
|||
|
<span data-line><span style="color:var(--shiki-token-keyword);">with</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-function);">open</span><span style="color:var(--shiki-token-punctuation);">(</span><span style="color:var(--shiki-token-string-expression);">'large_file.bin'</span><span style="color:var(--shiki-token-punctuation);">, </span><span style="color:var(--shiki-token-string-expression);">'r+b'</span><span style="color:var(--shiki-token-punctuation);">)</span><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-keyword);">as</span><span style="color:var(--shiki-color-text);"> f</span><span style="color:var(--shiki-token-punctuation);">:</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> mm </span><span style="color:var(--shiki-token-keyword);">=</span><span style="color:var(--shiki-color-text);"> mmap</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">mmap</span><span style="color:var(--shiki-token-punctuation);">(f.</span><span style="color:var(--shiki-token-function);">fileno</span><span style="color:var(--shiki-token-punctuation);">(), </span><span style="color:var(--shiki-token-constant);">0</span><span style="color:var(--shiki-token-punctuation);">)</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> </span><span style="color:var(--shiki-token-comment);"># 访问文件内容</span></span>
|
|||
|
<span data-line><span style="color:var(--shiki-color-text);"> mm</span><span style="color:var(--shiki-token-punctuation);">.</span><span style="color:var(--shiki-token-function);">close</span><span style="color:var(--shiki-token-punctuation);">()</span></span></code></pre></div>
|
|||
|
<h3 id="资源管理最佳实践">资源管理最佳实践<a aria-hidden="true" tabindex="-1" href="#资源管理最佳实践" class="internal"> §</a></h3>
|
|||
|
<p>在文件和 IO 操作中,正确的资源管理至关重要。以下是一些资源管理的最佳实践:<a href="../../../../Tech/programming-language/Python/进阶/资源管理" class="internal" data-slug="Tech/programming-language/Python/进阶/资源管理">资源管理</a>。</p></article></div><div class="right sidebar"><div class="graph "><h3>Graph View</h3><div class="graph-outer"><div id="graph-container" data-cfg="{"drag":true,"zoom":true,"depth":1,"scale":1.1,"repelForce":0.5,"centerForce":0.3,"linkDistance":30,"fontSize":0.6,"opacityScale":1,"showTags":true,"removeTags":[]}"></div><svg version="1.1" id="global-graph-icon" xmlns="http://www.w3.org/2000/svg" xmlnsXlink="http://www.w3.org/1999/xlink" x="0px" y="0px" viewBox="0 0 55 55" fill="currentColor" xmlSpace="preserve"><path d="M49,0c-3.309,0-6,2.691-6,6c0,1.035,0.263,2.009,0.726,2.86l-9.829,9.829C32.542,17.634,30.846,17,29,17
|
|||
|
s-3.542,0.634-4.898,1.688l-7.669-7.669C16.785,10.424,17,9.74,17,9c0-2.206-1.794-4-4-4S9,6.794,9,9s1.794,4,4,4
|
|||
|
c0.74,0,1.424-0.215,2.019-0.567l7.669,7.669C21.634,21.458,21,23.154,21,25s0.634,3.542,1.688,4.897L10.024,42.562
|
|||
|
C8.958,41.595,7.549,41,6,41c-3.309,0-6,2.691-6,6s2.691,6,6,6s6-2.691,6-6c0-1.035-0.263-2.009-0.726-2.86l12.829-12.829
|
|||
|
c1.106,0.86,2.44,1.436,3.898,1.619v10.16c-2.833,0.478-5,2.942-5,5.91c0,3.309,2.691,6,6,6s6-2.691,6-6c0-2.967-2.167-5.431-5-5.91
|
|||
|
v-10.16c1.458-0.183,2.792-0.759,3.898-1.619l7.669,7.669C41.215,39.576,41,40.26,41,41c0,2.206,1.794,4,4,4s4-1.794,4-4
|
|||
|
s-1.794-4-4-4c-0.74,0-1.424,0.215-2.019,0.567l-7.669-7.669C36.366,28.542,37,26.846,37,25s-0.634-3.542-1.688-4.897l9.665-9.665
|
|||
|
C46.042,11.405,47.451,12,49,12c3.309,0,6-2.691,6-6S52.309,0,49,0z M11,9c0-1.103,0.897-2,2-2s2,0.897,2,2s-0.897,2-2,2
|
|||
|
S11,10.103,11,9z M6,51c-2.206,0-4-1.794-4-4s1.794-4,4-4s4,1.794,4,4S8.206,51,6,51z M33,49c0,2.206-1.794,4-4,4s-4-1.794-4-4
|
|||
|
s1.794-4,4-4S33,46.794,33,49z M29,31c-3.309,0-6-2.691-6-6s2.691-6,6-6s6,2.691,6,6S32.309,31,29,31z M47,41c0,1.103-0.897,2-2,2
|
|||
|
s-2-0.897-2-2s0.897-2,2-2S47,39.897,47,41z M49,10c-2.206,0-4-1.794-4-4s1.794-4,4-4s4,1.794,4,4S51.206,10,49,10z"></path></svg></div><div id="global-graph-outer"><div id="global-graph-container" data-cfg="{"drag":true,"zoom":true,"depth":-1,"scale":0.9,"repelForce":0.5,"centerForce":0.3,"linkDistance":30,"fontSize":0.6,"opacityScale":1,"showTags":true,"removeTags":[]}"></div></div></div><div class="toc desktop-only"><button type="button" id="toc" class><h3>Table of Contents</h3><svg xmlns="http://www.w3.org/2000/svg" width="24" height="24" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" class="fold"><polyline points="6 9 12 15 18 9"></polyline></svg></button><div id="toc-content"><ul class="overflow"><li class="depth-0"><a href="#python-文件操作基础" data-for="python-文件操作基础">Python 文件操作基础</a></li><li class="depth-1"><a href="#文件和-io-的基本概念" data-for="文件和-io-的基本概念">文件和 IO 的基本概念</a></li><li class="depth-1"><a href="#文件打开与关闭" data-for="文件打开与关闭">文件打开与关闭</a></li><li class="depth-1"><a href="#文件读写操作" data-for="文件读写操作">文件读写操作</a></li><li class="depth-1"><a href="#文件模式" data-for="文件模式">文件模式</a></li><li class="depth-0"><a href="#文件类型和数据格式处理" data-for="文件类型和数据格式处理">文件类型和数据格式处理</a></li><li class="depth-1"><a href="#处理文本文件" data-for="处理文本文件">处理文本文件</a></li><li class="depth-1"><a href="#处理二进制文件" data-for="处理二进制文件">处理二进制文件</a></li><li class="depth-1"><a href="#csv-文件处理" data-for="csv-文件处理">CSV 文件处理</a></li><li class="depth-1"><a href="#json-文件处理" data-for="json-文件处理">JSON 文件处理</a></li><li class="depth-0"><a href="#文件系统操作" data-for="文件系统操作">文件系统操作</a></li><li class="depth-1"><a href="#文件和目录的基本操作" data-for="文件和目录的基本操作">文件和目录的基本操作</a></li><li class="depth-1"><a href="#路径操作" data-for="路径操作">路径操作</a></li><li class="depth-1"><a href="#使用临时文件" data-for="使用临时文件">使用临时文件</a></li><li class="depth-0"><a href="#高级文件操作技巧" data-for="高级文件操作技巧">高级文件操作技巧</a></li><li class="depth-1"><a href="#文件迭代与遍历" data-for="文件迭代与遍历">文件迭代与遍历</a></li><li class="depth-1"><a href="#内存映射文件操作" data-for="内存映射文件操作">内存映射文件操作</a></li><li class="depth-1"><a href="#异步-io-操作" data-for="异步-io-操作">异步 IO 操作</a></li><li class="depth-0"><a href="#编码和错误处理" data-for="编码和错误处理">编码和错误处理</a></li><li class="depth-1"><a href="#字符编码" data-for="字符编码">字符编码</a></li><li class="depth-1"><a href="#文件操作中的错误处理" data-for="文件操作中的错误处理">文件操作中的错误处理</a></li><li class="depth-0"><a href="#性能优化和最佳实践" data-for="性能优化和最佳实践">性能优化和最佳实践</a></li><li class="depth-1"><a href="#性能优化" data-for="性能优化">性能优化</a></li><li class="depth-1"><a href="#资源管理最佳实践" data-for="资源管理最佳实践">资源管理最佳实践</a></li></ul></div></div><div class="backlinks "><h3>Backlinks</h3><ul class="overflow"><li>No backlinks found</li></ul></div><div class="explorer mobile-only"><button type="button" id="explorer" data-behavior="collapse" data-collapsed="collapsed" data-savestate="true" data-tree="[{"path":"Basics","collapsed":true},{"path":"Basics/english","collapsed":true},{"path":"Blo
|
|||
|
function toggleCallout() {
|
|||
|
const outerBlock = this.parentElement;
|
|||
|
outerBlock.classList.toggle(`is-collapsed`);
|
|||
|
const collapsed = outerBlock.classList.contains(`is-collapsed`);
|
|||
|
const height = collapsed ? this.scrollHeight : outerBlock.scrollHeight;
|
|||
|
outerBlock.style.maxHeight = height + `px`;
|
|||
|
let current = outerBlock;
|
|||
|
let parent = outerBlock.parentElement;
|
|||
|
while (parent) {
|
|||
|
if (!parent.classList.contains(`callout`)) {
|
|||
|
return;
|
|||
|
}
|
|||
|
const collapsed2 = parent.classList.contains(`is-collapsed`);
|
|||
|
const height2 = collapsed2 ? parent.scrollHeight : parent.scrollHeight + current.scrollHeight;
|
|||
|
parent.style.maxHeight = height2 + `px`;
|
|||
|
current = parent;
|
|||
|
parent = parent.parentElement;
|
|||
|
}
|
|||
|
}
|
|||
|
function setupCallout() {
|
|||
|
const collapsible = document.getElementsByClassName(
|
|||
|
`callout is-collapsible`
|
|||
|
);
|
|||
|
for (const div of collapsible) {
|
|||
|
const title = div.firstElementChild;
|
|||
|
if (title) {
|
|||
|
title.removeEventListener(`click`, toggleCallout);
|
|||
|
title.addEventListener(`click`, toggleCallout);
|
|||
|
const collapsed = div.classList.contains(`is-collapsed`);
|
|||
|
const height = collapsed ? title.scrollHeight : div.scrollHeight;
|
|||
|
div.style.maxHeight = height + `px`;
|
|||
|
}
|
|||
|
}
|
|||
|
}
|
|||
|
document.addEventListener(`nav`, setupCallout);
|
|||
|
window.addEventListener(`resize`, setupCallout);
|
|||
|
</script><script type="module">
|
|||
|
import mermaid from 'https://cdn.jsdelivr.net/npm/mermaid/dist/mermaid.esm.min.mjs';
|
|||
|
const darkMode = document.documentElement.getAttribute('saved-theme') === 'dark'
|
|||
|
mermaid.initialize({
|
|||
|
startOnLoad: false,
|
|||
|
securityLevel: 'loose',
|
|||
|
theme: darkMode ? 'dark' : 'default'
|
|||
|
});
|
|||
|
document.addEventListener('nav', async () => {
|
|||
|
await mermaid.run({
|
|||
|
querySelector: '.mermaid'
|
|||
|
})
|
|||
|
});
|
|||
|
</script><script src="https://cdn.jsdelivr.net/npm/katex@0.16.7/dist/contrib/copy-tex.min.js" type="application/javascript"></script><script src="../../../../postscript.js" type="module"></script></html>
|