Files
docs/omniread/wiki/03_extending/index.html
Vishesh 'ironeagle' Bangotra aedd2061e1 feat: collect omniread wiki; register wiki kind; refresh lib and mcp artifacts
Adds the omniread wiki to the hub alongside lib and mcp and completes the
library nav with csv/xlsx groups, picking up regenerated MCP modules.
2026-09-16 19:59:00 +05:30

714 lines
30 KiB
HTML

<!doctype html>
<html lang="en" class="no-js">
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width,initial-scale=1">
<link rel="prev" href="../02_how_to_use/">
<link rel="next" href="../04_development/">
<link rel="icon" href="../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
<title>Extending OmniRead - OmniRead Documentation</title>
<link rel="stylesheet" href="../assets/stylesheets/main.84d31ad4.min.css">
<link rel="stylesheet" href="../assets/stylesheets/palette.06af60db.min.css">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CJetBrains+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Roboto";--md-code-font:"JetBrains Mono"}</style>
<link rel="stylesheet" href="https://unpkg.com/dracula-prism/dist/css/dracula-prism.css">
<script>__md_scope=new URL("..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
</head>
<body dir="ltr" data-md-color-scheme="slate" data-md-color-primary="blue-grey" data-md-color-accent="teal">
<input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off">
<input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off">
<label class="md-overlay" for="__drawer"></label>
<div data-md-component="skip">
<a href="#extending-omniread" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href=".." title="OmniRead Documentation" class="md-header__button md-logo" aria-label="OmniRead Documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m19 2-5 4.5v11l5-4.5zM6.5 5C4.55 5 2.45 5.4 1 6.5v14.66c0 .25.25.5.5.5.1 0 .15-.07.25-.07 1.35-.65 3.3-1.09 4.75-1.09 1.95 0 4.05.4 5.5 1.5 1.35-.85 3.8-1.5 5.5-1.5 1.65 0 3.35.31 4.75 1.06.1.05.15.03.25.03.25 0 .5-.25.5-.5V6.5c-.6-.45-1.25-.75-2-1V19c-1.1-.35-2.3-.5-3.5-.5-1.7 0-4.15.65-5.5 1.5V6.5C10.55 5.4 8.45 5 6.5 5"/></svg>
</a>
<label class="md-header__button md-icon" for="__drawer">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg>
</label>
<div class="md-header__title" data-md-component="header-title">
<div class="md-header__ellipsis">
<div class="md-header__topic">
<span class="md-ellipsis">
OmniRead Documentation
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Extending OmniRead
</span>
</div>
</div>
</div>
<label class="md-header__button md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
</label>
<div class="md-search" data-md-component="search" role="dialog">
<label class="md-search__overlay" for="__search"></label>
<div class="md-search__inner" role="search">
<form class="md-search__form" name="search">
<input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required>
<label class="md-search__icon md-icon" for="__search">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg>
</label>
<nav class="md-search__options" aria-label="Search">
<a href="javascript:void(0)" class="md-search__icon md-icon" title="Share" aria-label="Share" data-clipboard data-clipboard-text="" data-md-component="search-share" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M18 16.08c-.76 0-1.44.3-1.96.77L8.91 12.7c.05-.23.09-.46.09-.7s-.04-.47-.09-.7l7.05-4.11c.54.5 1.25.81 2.04.81a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3c0 .24.04.47.09.7L8.04 9.81C7.5 9.31 6.79 9 6 9a3 3 0 0 0-3 3 3 3 0 0 0 3 3c.79 0 1.5-.31 2.04-.81l7.12 4.15c-.05.21-.08.43-.08.66 0 1.61 1.31 2.91 2.92 2.91s2.92-1.3 2.92-2.91A2.92 2.92 0 0 0 18 16.08"/></svg>
</a>
<button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg>
</button>
</nav>
<div class="md-search__suggest" data-md-component="search-suggest"></div>
</form>
<div class="md-search__output">
<div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix>
<div class="md-search-result" data-md-component="search-result">
<div class="md-search-result__meta">
Initializing search
</div>
<ol class="md-search-result__list" role="presentation"></ol>
</div>
</div>
</div>
</div>
</div>
</nav>
</header>
<div class="md-container" data-md-component="container">
<nav class="md-tabs" aria-label="Tabs" data-md-component="tabs">
<div class="md-grid">
<ul class="md-tabs__list">
<li class="md-tabs__item">
<a href=".." class="md-tabs__link">
Home
</a>
</li>
<li class="md-tabs__item">
<a href="../01_overview/" class="md-tabs__link">
Overview
</a>
</li>
<li class="md-tabs__item">
<a href="../02_how_to_use/" class="md-tabs__link">
How to Use
</a>
</li>
<li class="md-tabs__item md-tabs__item--active">
<a href="./" class="md-tabs__link">
Extending OmniRead
</a>
</li>
<li class="md-tabs__item">
<a href="../04_development/" class="md-tabs__link">
Development
</a>
</li>
</ul>
</div>
</nav>
<main class="md-main" data-md-component="main">
<div class="md-main__inner md-grid">
<div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<nav class="md-nav md-nav--primary md-nav--lifted md-nav--integrated" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href=".." title="OmniRead Documentation" class="md-nav__button md-logo" aria-label="OmniRead Documentation" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="m19 2-5 4.5v11l5-4.5zM6.5 5C4.55 5 2.45 5.4 1 6.5v14.66c0 .25.25.5.5.5.1 0 .15-.07.25-.07 1.35-.65 3.3-1.09 4.75-1.09 1.95 0 4.05.4 5.5 1.5 1.35-.85 3.8-1.5 5.5-1.5 1.65 0 3.35.31 4.75 1.06.1.05.15.03.25.03.25 0 .5-.25.5-.5V6.5c-.6-.45-1.25-.75-2-1V19c-1.1-.35-2.3-.5-3.5-.5-1.7 0-4.15.65-5.5 1.5V6.5C10.55 5.4 8.45 5 6.5 5"/></svg>
</a>
OmniRead Documentation
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href=".." class="md-nav__link">
<span class="md-ellipsis">
Home
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../01_overview/" class="md-nav__link">
<span class="md-ellipsis">
Overview
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../02_how_to_use/" class="md-nav__link">
<span class="md-ellipsis">
How to Use
</span>
</a>
</li>
<li class="md-nav__item md-nav__item--active">
<input class="md-nav__toggle md-toggle" type="checkbox" id="__toc">
<label class="md-nav__link md-nav__link--active" for="__toc">
<span class="md-ellipsis">
Extending OmniRead
</span>
<span class="md-nav__icon md-icon"></span>
</label>
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Extending OmniRead
</span>
</a>
<nav class="md-nav md-nav--secondary" aria-label="Table of contents">
<label class="md-nav__title" for="__toc">
<span class="md-nav__icon md-icon"></span>
Table of contents
</label>
<ul class="md-nav__list" data-md-component="toc" data-md-scrollfix>
<li class="md-nav__item">
<a href="#custom-parsers" class="md-nav__link">
<span class="md-ellipsis">
🧬 Custom parsers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#custom-pdf-parsers" class="md-nav__link">
<span class="md-ellipsis">
🧬 Custom PDF parsers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#custom-clients" class="md-nav__link">
<span class="md-ellipsis">
🧬 Custom clients
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#custom-scrapers" class="md-nav__link">
<span class="md-ellipsis">
🚀 Custom scrapers
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#extension-checklist" class="md-nav__link">
<span class="md-ellipsis">
✅ Extension checklist
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#read-next" class="md-nav__link">
<span class="md-ellipsis">
📚 Read Next
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="../04_development/" class="md-nav__link">
<span class="md-ellipsis">
Development
</span>
</a>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="extending-omniread">🧩 Extending OmniRead</h1>
<p>OmniRead is meant to be extended by subclassing. All public extension points
are generic over their result type, so your parser returns exactly the shape
you need.</p>
<hr />
<h2 id="custom-parsers">🧬 Custom parsers</h2>
<p>Subclass <code>BaseParser[T]</code> (or a format parser) and implement <code>parse()</code>:</p>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-0-1"> 1</a></span>
<span class="normal"><a href="#__codelineno-0-2"> 2</a></span>
<span class="normal"><a href="#__codelineno-0-3"> 3</a></span>
<span class="normal"><a href="#__codelineno-0-4"> 4</a></span>
<span class="normal"><a href="#__codelineno-0-5"> 5</a></span>
<span class="normal"><a href="#__codelineno-0-6"> 6</a></span>
<span class="normal"><a href="#__codelineno-0-7"> 7</a></span>
<span class="normal"><a href="#__codelineno-0-8"> 8</a></span>
<span class="normal"><a href="#__codelineno-0-9"> 9</a></span>
<span class="normal"><a href="#__codelineno-0-10">10</a></span>
<span class="normal"><a href="#__codelineno-0-11">11</a></span>
<span class="normal"><a href="#__codelineno-0-12">12</a></span>
<span class="normal"><a href="#__codelineno-0-13">13</a></span>
<span class="normal"><a href="#__codelineno-0-14">14</a></span>
<span class="normal"><a href="#__codelineno-0-15">15</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-0-1"><a id="__codelineno-0-1" name="__codelineno-0-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">pydantic</span><span class="w"> </span><span class="kn">import</span> <span class="n">BaseModel</span>
</span><span id="__span-0-2"><a id="__codelineno-0-2" name="__codelineno-0-2"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">HTMLParser</span>
</span><span id="__span-0-3"><a id="__codelineno-0-3" name="__codelineno-0-3"></a>
</span><span id="__span-0-4"><a id="__codelineno-0-4" name="__codelineno-0-4"></a><span class="k">class</span><span class="w"> </span><span class="nc">Page</span><span class="p">(</span><span class="n">BaseModel</span><span class="p">):</span>
</span><span id="__span-0-5"><a id="__codelineno-0-5" name="__codelineno-0-5"></a> <span class="n">title</span><span class="p">:</span> <span class="nb">str</span>
</span><span id="__span-0-6"><a id="__codelineno-0-6" name="__codelineno-0-6"></a> <span class="n">content</span><span class="p">:</span> <span class="nb">str</span> <span class="o">|</span> <span class="kc">None</span>
</span><span id="__span-0-7"><a id="__codelineno-0-7" name="__codelineno-0-7"></a>
</span><span id="__span-0-8"><a id="__codelineno-0-8" name="__codelineno-0-8"></a><span class="k">class</span><span class="w"> </span><span class="nc">PageParser</span><span class="p">(</span><span class="n">HTMLParser</span><span class="p">[</span><span class="n">Page</span><span class="p">]):</span>
</span><span id="__span-0-9"><a id="__codelineno-0-9" name="__codelineno-0-9"></a> <span class="k">def</span><span class="w"> </span><span class="nf">parse</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Page</span><span class="p">:</span>
</span><span id="__span-0-10"><a id="__codelineno-0-10" name="__codelineno-0-10"></a> <span class="n">soup</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_soup</span>
</span><span id="__span-0-11"><a id="__codelineno-0-11" name="__codelineno-0-11"></a> <span class="n">div</span> <span class="o">=</span> <span class="n">soup</span><span class="o">.</span><span class="n">find</span><span class="p">(</span><span class="s2">&quot;div&quot;</span><span class="p">,</span> <span class="nb">id</span><span class="o">=</span><span class="s2">&quot;content&quot;</span><span class="p">)</span>
</span><span id="__span-0-12"><a id="__codelineno-0-12" name="__codelineno-0-12"></a> <span class="k">return</span> <span class="n">Page</span><span class="p">(</span>
</span><span id="__span-0-13"><a id="__codelineno-0-13" name="__codelineno-0-13"></a> <span class="n">title</span><span class="o">=</span><span class="n">soup</span><span class="o">.</span><span class="n">title</span><span class="o">.</span><span class="n">string</span><span class="p">,</span>
</span><span id="__span-0-14"><a id="__codelineno-0-14" name="__codelineno-0-14"></a> <span class="n">content</span><span class="o">=</span><span class="n">div</span><span class="o">.</span><span class="n">get_text</span><span class="p">()</span> <span class="k">if</span> <span class="n">div</span> <span class="k">else</span> <span class="kc">None</span><span class="p">,</span>
</span><span id="__span-0-15"><a id="__codelineno-0-15" name="__codelineno-0-15"></a> <span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
<p>The parsed page is validated by Pydantic on construction — no manual
assertions required.</p>
<hr />
<h2 id="custom-pdf-parsers">🧬 Custom PDF parsers</h2>
<p>PDF binary layout is format-specific, so parsers return your own model:</p>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-1-1"> 1</a></span>
<span class="normal"><a href="#__codelineno-1-2"> 2</a></span>
<span class="normal"><a href="#__codelineno-1-3"> 3</a></span>
<span class="normal"><a href="#__codelineno-1-4"> 4</a></span>
<span class="normal"><a href="#__codelineno-1-5"> 5</a></span>
<span class="normal"><a href="#__codelineno-1-6"> 6</a></span>
<span class="normal"><a href="#__codelineno-1-7"> 7</a></span>
<span class="normal"><a href="#__codelineno-1-8"> 8</a></span>
<span class="normal"><a href="#__codelineno-1-9"> 9</a></span>
<span class="normal"><a href="#__codelineno-1-10">10</a></span>
<span class="normal"><a href="#__codelineno-1-11">11</a></span>
<span class="normal"><a href="#__codelineno-1-12">12</a></span>
<span class="normal"><a href="#__codelineno-1-13">13</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-1-1"><a id="__codelineno-1-1" name="__codelineno-1-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">typing</span><span class="w"> </span><span class="kn">import</span> <span class="n">Literal</span>
</span><span id="__span-1-2"><a id="__codelineno-1-2" name="__codelineno-1-2"></a><span class="kn">from</span><span class="w"> </span><span class="nn">pydantic</span><span class="w"> </span><span class="kn">import</span> <span class="n">BaseModel</span>
</span><span id="__span-1-3"><a id="__codelineno-1-3" name="__codelineno-1-3"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">PDFParser</span>
</span><span id="__span-1-4"><a id="__codelineno-1-4" name="__codelineno-1-4"></a>
</span><span id="__span-1-5"><a id="__codelineno-1-5" name="__codelineno-1-5"></a><span class="k">class</span><span class="w"> </span><span class="nc">ParsedPDF</span><span class="p">(</span><span class="n">BaseModel</span><span class="p">):</span>
</span><span id="__span-1-6"><a id="__codelineno-1-6" name="__codelineno-1-6"></a> <span class="n">size_bytes</span><span class="p">:</span> <span class="nb">int</span>
</span><span id="__span-1-7"><a id="__codelineno-1-7" name="__codelineno-1-7"></a> <span class="n">magic</span><span class="p">:</span> <span class="n">Literal</span><span class="p">[</span><span class="sa">b</span><span class="s2">&quot;%PDF&quot;</span><span class="p">]</span>
</span><span id="__span-1-8"><a id="__codelineno-1-8" name="__codelineno-1-8"></a>
</span><span id="__span-1-9"><a id="__codelineno-1-9" name="__codelineno-1-9"></a><span class="k">class</span><span class="w"> </span><span class="nc">SimplePDFParser</span><span class="p">(</span><span class="n">PDFParser</span><span class="p">[</span><span class="n">ParsedPDF</span><span class="p">]):</span>
</span><span id="__span-1-10"><a id="__codelineno-1-10" name="__codelineno-1-10"></a> <span class="k">def</span><span class="w"> </span><span class="nf">parse</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">ParsedPDF</span><span class="p">:</span>
</span><span id="__span-1-11"><a id="__codelineno-1-11" name="__codelineno-1-11"></a> <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">content</span><span class="o">.</span><span class="n">raw</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="sa">b</span><span class="s2">&quot;%PDF&quot;</span><span class="p">):</span>
</span><span id="__span-1-12"><a id="__codelineno-1-12" name="__codelineno-1-12"></a> <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">&quot;Not a valid PDF&quot;</span><span class="p">)</span>
</span><span id="__span-1-13"><a id="__codelineno-1-13" name="__codelineno-1-13"></a> <span class="k">return</span> <span class="n">ParsedPDF</span><span class="p">(</span><span class="n">size_bytes</span><span class="o">=</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">content</span><span class="o">.</span><span class="n">raw</span><span class="p">),</span> <span class="n">magic</span><span class="o">=</span><span class="sa">b</span><span class="s2">&quot;%PDF&quot;</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
<hr />
<h2 id="custom-clients">🧬 Custom clients</h2>
<p>Clients supply raw bytes to a scraper. For PDFs, subclass
<code>BasePDFClient</code> (or <code>FileSystemPDFClient</code>) and implement
<code>fetch(source) -&gt; bytes</code>:</p>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-2-1">1</a></span>
<span class="normal"><a href="#__codelineno-2-2">2</a></span>
<span class="normal"><a href="#__codelineno-2-3">3</a></span>
<span class="normal"><a href="#__codelineno-2-4">4</a></span>
<span class="normal"><a href="#__codelineno-2-5">5</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-2-1"><a id="__codelineno-2-1" name="__codelineno-2-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread.pdf.client</span><span class="w"> </span><span class="kn">import</span> <span class="n">BasePDFClient</span>
</span><span id="__span-2-2"><a id="__codelineno-2-2" name="__codelineno-2-2"></a>
</span><span id="__span-2-3"><a id="__codelineno-2-3" name="__codelineno-2-3"></a><span class="k">class</span><span class="w"> </span><span class="nc">MockPDFClient</span><span class="p">(</span><span class="n">BasePDFClient</span><span class="p">):</span>
</span><span id="__span-2-4"><a id="__codelineno-2-4" name="__codelineno-2-4"></a> <span class="k">def</span><span class="w"> </span><span class="nf">fetch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source</span><span class="p">):</span>
</span><span id="__span-2-5"><a id="__codelineno-2-5" name="__codelineno-2-5"></a> <span class="k">return</span> <span class="sa">b</span><span class="s2">&quot;%PDF ...&quot;</span> <span class="c1"># bytes for the logical identifier</span>
</span></code></pre></div></td></tr></table></div>
<p>The same pattern applies to <code>BaseCsvClient</code> and <code>BaseXlsxClient</code>.</p>
<hr />
<h2 id="custom-scrapers">🚀 Custom scrapers</h2>
<p>Festch something that a built-in scraper does not cover by extending
<code>BaseScraper</code>:</p>
<div class="language-python highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal"><a href="#__codelineno-3-1">1</a></span>
<span class="normal"><a href="#__codelineno-3-2">2</a></span>
<span class="normal"><a href="#__codelineno-3-3">3</a></span>
<span class="normal"><a href="#__codelineno-3-4">4</a></span>
<span class="normal"><a href="#__codelineno-3-5">5</a></span>
<span class="normal"><a href="#__codelineno-3-6">6</a></span></pre></div></td><td class="code"><div><pre><span></span><code><span id="__span-3-1"><a id="__codelineno-3-1" name="__codelineno-3-1"></a><span class="kn">from</span><span class="w"> </span><span class="nn">omniread</span><span class="w"> </span><span class="kn">import</span> <span class="n">BaseScraper</span><span class="p">,</span> <span class="n">Content</span><span class="p">,</span> <span class="n">ContentType</span>
</span><span id="__span-3-2"><a id="__codelineno-3-2" name="__codelineno-3-2"></a>
</span><span id="__span-3-3"><a id="__codelineno-3-3" name="__codelineno-3-3"></a><span class="k">class</span><span class="w"> </span><span class="nc">StorageScraper</span><span class="p">(</span><span class="n">BaseScraper</span><span class="p">):</span>
</span><span id="__span-3-4"><a id="__codelineno-3-4" name="__codelineno-3-4"></a> <span class="k">def</span><span class="w"> </span><span class="nf">fetch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">source</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
</span><span id="__span-3-5"><a id="__codelineno-3-5" name="__codelineno-3-5"></a> <span class="n">raw</span> <span class="o">=</span> <span class="n">my_object_storage</span><span class="o">.</span><span class="n">download</span><span class="p">(</span><span class="n">source</span><span class="p">)</span> <span class="c1"># your I/O</span>
</span><span id="__span-3-6"><a id="__codelineno-3-6" name="__codelineno-3-6"></a> <span class="k">return</span> <span class="n">Content</span><span class="p">(</span><span class="n">raw</span><span class="o">=</span><span class="n">raw</span><span class="p">,</span> <span class="n">source</span><span class="o">=</span><span class="n">source</span><span class="p">,</span> <span class="n">content_type</span><span class="o">=</span><span class="n">ContentType</span><span class="o">.</span><span class="n">JSON</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
<hr />
<h2 id="extension-checklist">✅ Extension checklist</h2>
<ol>
<li>Keep <strong>scraper</strong> and <strong>parser</strong> separate — never mix I/O into <code>parse()</code>.</li>
<li>Return <code>Content</code> from any scraper/client so downstream stays uniform.</li>
<li>Return a <em>typed</em> result from your parser (Pydantic model, dataclass, str).</li>
<li>Test your custom layers with a mock client, not a live network.</li>
</ol>
<hr />
<h2 id="read-next">📚 Read Next</h2>
<ul>
<li><a href="../02_how_to_use/">How to Use</a> — built-in example flows.</li>
<li><a href="../04_development/">Development</a> — running tests and docs.</li>
</ul>
</article>
</div>
<script>var tabs=__md_get("__tabs");if(Array.isArray(tabs))e:for(var set of document.querySelectorAll(".tabbed-set")){var labels=set.querySelector(".tabbed-labels");for(var tab of tabs)for(var label of labels.getElementsByTagName("label"))if(label.innerText.trim()===tab){var input=document.getElementById(label.htmlFor);input.checked=!0;continue e}}</script>
<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
</div>
<button type="button" class="md-top md-icon" data-md-component="top" hidden>
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M13 20h-2V8l-5.5 5.5-1.42-1.42L12 4.16l7.92 7.92-1.42 1.42L13 8z"/></svg>
Back to top
</button>
</main>
<footer class="md-footer">
<div class="md-footer-meta md-typeset">
<div class="md-footer-meta__inner md-grid">
<div class="md-copyright">
Made with
<a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener">
Material for MkDocs
</a>
</div>
</div>
</div>
</footer>
</div>
<div class="md-dialog" data-md-component="dialog">
<div class="md-dialog__inner md-typeset"></div>
</div>
<script id="__config" type="application/json">{"base": "..", "features": ["navigation.sections", "navigation.expand", "navigation.top", "navigation.instant", "navigation.tracking", "navigation.indexes", "content.code.copy", "content.code.annotate", "content.tabs.link", "content.action.edit", "search.highlight", "search.share", "search.suggest", "navigation.tabs", "toc.integrate", "header.autohide", "announce.dismiss", "footer.social", "content.code.select", "content.code.line_numbers", "content.tooltips"], "search": "../assets/javascripts/workers/search.973d3a69.min.js", "tags": null, "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}, "version": null}</script>
<script src="../assets/javascripts/bundle.f55a23d4.min.js"></script>
</body>
</html>