Files
docs/libs/omniread/site/core/index.html
Vishesh 'ironeagle' Bangotra 9191de9dff
All checks were successful
continuous-integration/drone/push Build is passing
Build: 0.1.8
2026-03-08 01:01:39 +05:30

1810 lines
53 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="..">
<link rel="next" href="content/">
<link rel="icon" href="../assets/images/favicon.png">
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
<title>Core - omniread</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=Inter:300,300i,400,400i,700,700i%7CJetBrains+Mono:400,400i,700,700i&display=fallback">
<style>:root{--md-text-font:"Inter";--md-code-font:"JetBrains Mono"}</style>
<link rel="stylesheet" href="../assets/_mkdocstrings.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="deep-purple" data-md-color-accent="cyan">
<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="#core" class="md-skip">
Skip to content
</a>
</div>
<div data-md-component="announce">
</div>
<header class="md-header md-header--shadow" data-md-component="header">
<nav class="md-header__inner md-grid" aria-label="Header">
<a href=".." title="omniread" class="md-header__button md-logo" aria-label="omniread" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></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
</span>
</div>
<div class="md-header__topic" data-md-component="header-topic">
<span class="md-ellipsis">
Core
</span>
</div>
</div>
</div>
<form class="md-header__option" data-md-component="palette">
<input class="md-option" data-md-color-media="" data-md-color-scheme="slate" data-md-color-primary="deep-purple" data-md-color-accent="cyan" aria-hidden="true" type="radio" name="__palette" id="__palette_0">
</form>
<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
<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">
<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" aria-label="Navigation" data-md-level="0">
<label class="md-nav__title" for="__drawer">
<a href=".." title="omniread" class="md-nav__button md-logo" aria-label="omniread" data-md-component="logo">
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg>
</a>
omniread
</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 md-nav__item--active md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_2" checked>
<div class="md-nav__link md-nav__container">
<a href="./" class="md-nav__link md-nav__link--active">
<span class="md-ellipsis">
Core API
</span>
</a>
<label class="md-nav__link md-nav__link--active" for="__nav_2" id="__nav_2_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="true">
<label class="md-nav__title" for="__nav_2">
<span class="md-nav__icon md-icon"></span>
Core API
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="content/" class="md-nav__link">
<span class="md-ellipsis">
Content
</span>
</a>
</li>
<li class="md-nav__item">
<a href="parser/" class="md-nav__link">
<span class="md-ellipsis">
Parser
</span>
</a>
</li>
<li class="md-nav__item">
<a href="scraper/" class="md-nav__link">
<span class="md-ellipsis">
Scraper
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_3" >
<div class="md-nav__link md-nav__container">
<a href="../html/" class="md-nav__link ">
<span class="md-ellipsis">
HTML Handling
</span>
</a>
<label class="md-nav__link " for="__nav_3" id="__nav_3_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_3">
<span class="md-nav__icon md-icon"></span>
HTML Handling
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../html/parser/" class="md-nav__link">
<span class="md-ellipsis">
Parser
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../html/scraper/" class="md-nav__link">
<span class="md-ellipsis">
Scraper
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item md-nav__item--section md-nav__item--nested">
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4" >
<div class="md-nav__link md-nav__container">
<a href="../pdf/" class="md-nav__link ">
<span class="md-ellipsis">
PDF Handling
</span>
</a>
<label class="md-nav__link " for="__nav_4" id="__nav_4_label" tabindex="">
<span class="md-nav__icon md-icon"></span>
</label>
</div>
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false">
<label class="md-nav__title" for="__nav_4">
<span class="md-nav__icon md-icon"></span>
PDF Handling
</label>
<ul class="md-nav__list" data-md-scrollfix>
<li class="md-nav__item">
<a href="../pdf/client/" class="md-nav__link">
<span class="md-ellipsis">
Client
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../pdf/parser/" class="md-nav__link">
<span class="md-ellipsis">
Parser
</span>
</a>
</li>
<li class="md-nav__item">
<a href="../pdf/scraper/" class="md-nav__link">
<span class="md-ellipsis">
Scraper
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" >
<div class="md-sidebar__scrollwrap">
<div class="md-sidebar__inner">
<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="#omniread.core" class="md-nav__link">
<span class="md-ellipsis">
core
</span>
</a>
<nav class="md-nav" aria-label="core">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core--summary" class="md-nav__link">
<span class="md-ellipsis">
Summary
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.core--public-api" class="md-nav__link">
<span class="md-ellipsis">
Public API
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.core-classes" class="md-nav__link">
<span class="md-ellipsis">
Classes
</span>
</a>
<nav class="md-nav" aria-label="Classes">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core.BaseParser" class="md-nav__link">
<span class="md-ellipsis">
BaseParser
</span>
</a>
<nav class="md-nav" aria-label="BaseParser">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core.BaseParser-attributes" class="md-nav__link">
<span class="md-ellipsis">
Attributes
</span>
</a>
<nav class="md-nav" aria-label="Attributes">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core.BaseParser.supported_types" class="md-nav__link">
<span class="md-ellipsis">
supported_types
</span>
</a>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#omniread.core.BaseParser-functions" class="md-nav__link">
<span class="md-ellipsis">
Functions
</span>
</a>
<nav class="md-nav" aria-label="Functions">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core.BaseParser.parse" class="md-nav__link">
<span class="md-ellipsis">
parse
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.core.BaseParser.supports" class="md-nav__link">
<span class="md-ellipsis">
supports
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#omniread.core.BaseScraper" class="md-nav__link">
<span class="md-ellipsis">
BaseScraper
</span>
</a>
<nav class="md-nav" aria-label="BaseScraper">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core.BaseScraper-functions" class="md-nav__link">
<span class="md-ellipsis">
Functions
</span>
</a>
<nav class="md-nav" aria-label="Functions">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core.BaseScraper.fetch" class="md-nav__link">
<span class="md-ellipsis">
fetch
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#omniread.core.Content" class="md-nav__link">
<span class="md-ellipsis">
Content
</span>
</a>
<nav class="md-nav" aria-label="Content">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core.Content-attributes" class="md-nav__link">
<span class="md-ellipsis">
Attributes
</span>
</a>
<nav class="md-nav" aria-label="Attributes">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core.Content.content_type" class="md-nav__link">
<span class="md-ellipsis">
content_type
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.core.Content.metadata" class="md-nav__link">
<span class="md-ellipsis">
metadata
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.core.Content.raw" class="md-nav__link">
<span class="md-ellipsis">
raw
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.core.Content.source" class="md-nav__link">
<span class="md-ellipsis">
source
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
<li class="md-nav__item">
<a href="#omniread.core.ContentType" class="md-nav__link">
<span class="md-ellipsis">
ContentType
</span>
</a>
<nav class="md-nav" aria-label="ContentType">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core.ContentType-attributes" class="md-nav__link">
<span class="md-ellipsis">
Attributes
</span>
</a>
<nav class="md-nav" aria-label="Attributes">
<ul class="md-nav__list">
<li class="md-nav__item">
<a href="#omniread.core.ContentType.HTML" class="md-nav__link">
<span class="md-ellipsis">
HTML
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.core.ContentType.JSON" class="md-nav__link">
<span class="md-ellipsis">
JSON
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.core.ContentType.PDF" class="md-nav__link">
<span class="md-ellipsis">
PDF
</span>
</a>
</li>
<li class="md-nav__item">
<a href="#omniread.core.ContentType.XML" class="md-nav__link">
<span class="md-ellipsis">
XML
</span>
</a>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</li>
</ul>
</nav>
</div>
</div>
</div>
<div class="md-content" data-md-component="content">
<article class="md-content__inner md-typeset">
<h1 id="core">Core</h1>
<div class="doc doc-object doc-module">
<h2 id="omniread.core" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-module"></code> <span class="doc doc-object-name doc-module-name">omniread.core</span>
</h2>
<div class="doc doc-contents first">
<p>Core domain contracts for OmniRead.</p>
<hr />
<h4 id="omniread.core--summary">Summary</h4>
<p>This package defines the <strong>format-agnostic domain layer</strong> of OmniRead.
It exposes canonical content models and abstract interfaces that are
implemented by format-specific modules (HTML, PDF, etc.).</p>
<p>Public exports from this package are considered <strong>stable contracts</strong> and
are safe for downstream consumers to depend on.</p>
<p>Submodules:
- content: Canonical content models and enums
- parser: Abstract parsing contracts
- scraper: Abstract scraping contracts</p>
<p>Format-specific behavior must not be introduced at this layer.</p>
<hr />
<h4 id="omniread.core--public-api">Public API</h4>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span></pre></div></td><td class="code"><div><pre><span></span><code>Content
ContentType
</code></pre></div></td></tr></table></div>
<hr />
<div class="doc doc-children">
<h3 id="omniread.core-classes">Classes</h3>
<div class="doc doc-object doc-class">
<h4 id="omniread.core.BaseParser" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-class"></code> <span class="doc doc-object-name doc-class-name">BaseParser</span>
</h4>
<div class="language-python doc-signature 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></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="nf">BaseParser</span><span class="p">(</span><span class="n">content</span><span class="p">:</span> <span class="n">Content</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p class="doc doc-class-bases">
Bases: <code><span title="abc.ABC">ABC</span></code>, <code><span title="typing.Generic">Generic</span>[<span title="omniread.core.parser.T">T</span>]</code></p>
<p>Base interface for all parsers.</p>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Guarantees:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span></pre></div></td><td class="code"><div><pre><span></span><code>- A parser is a self-contained object that owns the Content it is responsible for interpreting
- Consumers may rely on early validation of content compatibility and type-stable return values from `parse()`
</code></pre></div></td></tr></table></div>
<p><strong>Responsibilities:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span>
<span class="normal">3</span></pre></div></td><td class="code"><div><pre><span></span><code>- Implementations must declare supported content types via `supported_types`
- Implementations must raise parsing-specific exceptions from `parse()`
- Implementations must remain deterministic for a given input
</code></pre></div></td></tr></table></div>
</details>
<p>Initialize the parser with content to be parsed.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>content</code></td>
<td>
<code><a class="autorefs autorefs-internal" title="omniread.core.content.Content" href="../omniread/core/content/#omniread.core.content.Content">Content</a></code>
</td>
<td>
<div class="doc-md-description">
<p>Content instance to be parsed.</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Raises:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>ValueError</code>
</td>
<td>
<div class="doc-md-description">
<p>If the content type is not supported by this parser.</p>
</div>
</td>
</tr>
</tbody>
</table>
<div class="doc doc-children">
<h5 id="omniread.core.BaseParser-attributes">Attributes</h5>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.core.BaseParser.supported_types" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">supported_types</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="n">supported_types</span><span class="p">:</span> <span class="n">Set</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Set of content types supported by this parser. An empty set indicates that the parser is content-type agnostic.</p>
</div>
</div>
<h5 id="omniread.core.BaseParser-functions">Functions</h5>
<div class="doc doc-object doc-function">
<h6 id="omniread.core.BaseParser.parse" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">parse</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-abstractmethod"><code>abstractmethod</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="nf">parse</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="n">T</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Parse the owned content into structured output.</p>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Name</th> <th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>T</code></td> <td>
<code><span title="omniread.core.parser.T">T</span></code>
</td>
<td>
<div class="doc-md-description">
<p>Parsed, structured representation.</p>
</div>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Raises:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>Exception</code>
</td>
<td>
<div class="doc-md-description">
<p>Parsing-specific errors as defined by the implementation.</p>
</div>
</td>
</tr>
</tbody>
</table>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Responsibilities:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span></pre></div></td><td class="code"><div><pre><span></span><code>- Implementations must fully consume the provided content and return a deterministic, structured output
</code></pre></div></td></tr></table></div>
</details>
</div>
</div>
<div class="doc doc-object doc-function">
<h6 id="omniread.core.BaseParser.supports" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">supports</span>
</h6>
<div class="language-python doc-signature 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></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="nf">supports</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="nb">bool</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Check whether this parser supports the content's type.</p>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Name</th> <th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>bool</code></td> <td>
<code>bool</code>
</td>
<td>
<div class="doc-md-description">
<p>True if the content type is supported; False otherwise.</p>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
</div>
</div>
</div>
<div class="doc doc-object doc-class">
<h4 id="omniread.core.BaseScraper" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-class"></code> <span class="doc doc-object-name doc-class-name">BaseScraper</span>
</h4>
<div class="doc doc-contents ">
<p class="doc doc-class-bases">
Bases: <code><span title="abc.ABC">ABC</span></code></p>
<p>Base interface for all scrapers.</p>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Responsibilities:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span>
<span class="normal">3</span>
<span class="normal">4</span></pre></div></td><td class="code"><div><pre><span></span><code>- A scraper is responsible ONLY for fetching raw content (bytes) from a source. It must not interpret or parse it
- A scraper is a stateless acquisition component that retrieves raw content from a source and returns it as a `Content` object
- Scrapers define how content is obtained, not what the content means
- Implementations may vary in transport mechanism, authentication strategy, retry and backoff behavior
</code></pre></div></td></tr></table></div>
<p><strong>Constraints:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span></pre></div></td><td class="code"><div><pre><span></span><code>- Implementations must not parse content, modify content semantics, or couple scraping logic to a specific parser
</code></pre></div></td></tr></table></div>
</details>
<div class="doc doc-children">
<h5 id="omniread.core.BaseScraper-functions">Functions</h5>
<div class="doc doc-object doc-function">
<h6 id="omniread.core.BaseScraper.fetch" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-method"></code> <span class="doc doc-object-name doc-function-name">fetch</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-abstractmethod"><code>abstractmethod</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="nf">fetch</span><span class="p">(</span><span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Content</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Fetch raw content from the given source.</p>
<p><span class="doc-section-title">Parameters:</span></p>
<table>
<thead>
<tr>
<th>Name</th>
<th>Type</th>
<th>Description</th>
<th>Default</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>source</code></td>
<td>
<code>str</code>
</td>
<td>
<div class="doc-md-description">
<p>Location identifier (URL, file path, S3 URI, etc.)</p>
</div>
</td>
<td>
<em>required</em>
</td>
</tr>
<tr class="doc-section-item">
<td><code>metadata</code></td>
<td>
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, <span title="typing.Any">Any</span>]]</code>
</td>
<td>
<div class="doc-md-description">
<p>Optional hints for the scraper (headers, auth, etc.)</p>
</div>
</td>
<td>
<code>None</code>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Returns:</span></p>
<table>
<thead>
<tr>
<th>Name</th> <th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td><code>Content</code></td> <td>
<code><a class="autorefs autorefs-internal" title="omniread.core.content.Content" href="../omniread/core/content/#omniread.core.content.Content">Content</a></code>
</td>
<td>
<div class="doc-md-description">
<p>Content object containing raw bytes and metadata.</p>
</div>
</td>
</tr>
</tbody>
</table>
<p><span class="doc-section-title">Raises:</span></p>
<table>
<thead>
<tr>
<th>Type</th>
<th>Description</th>
</tr>
</thead>
<tbody>
<tr class="doc-section-item">
<td>
<code>Exception</code>
</td>
<td>
<div class="doc-md-description">
<p>Retrieval-specific errors as defined by the implementation.</p>
</div>
</td>
</tr>
</tbody>
</table>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Responsibilities:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span></pre></div></td><td class="code"><div><pre><span></span><code>- Implementations must retrieve the content referenced by `source` and return it as raw bytes wrapped in a `Content` object
</code></pre></div></td></tr></table></div>
</details>
</div>
</div>
</div>
</div>
</div>
<div class="doc doc-object doc-class">
<h4 id="omniread.core.Content" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-class"></code> <span class="doc doc-object-name doc-class-name">Content</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-dataclass"><code>dataclass</code></small>
</span>
</h4>
<div class="language-python doc-signature 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></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="nf">Content</span><span class="p">(</span><span class="n">raw</span><span class="p">:</span> <span class="nb">bytes</span><span class="p">,</span> <span class="n">source</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">content_type</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="o">...</span><span class="p">,</span> <span class="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="o">...</span><span class="p">)</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Normalized representation of extracted content.</p>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Responsibilities:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span></pre></div></td><td class="code"><div><pre><span></span><code>- A `Content` instance represents a raw content payload along with minimal contextual metadata describing its origin and type
- This class is the primary exchange format between Scrapers, Parsers, and Downstream consumers
</code></pre></div></td></tr></table></div>
</details>
<div class="doc doc-children">
<h5 id="omniread.core.Content-attributes">Attributes</h5>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.core.Content.content_type" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">content_type</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="n">content_type</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Optional MIME type of the content, if known.</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.core.Content.metadata" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">metadata</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="n">metadata</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Mapping</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Optional, implementation-defined metadata associated with the content (e.g., headers, encoding hints, extraction notes).</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.core.Content.raw" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">raw</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="n">raw</span><span class="p">:</span> <span class="nb">bytes</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Raw content bytes as retrieved from the source.</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.core.Content.source" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">source</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="n">source</span><span class="p">:</span> <span class="nb">str</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>Identifier of the content origin (URL, file path, or logical name).</p>
</div>
</div>
</div>
</div>
</div>
<div class="doc doc-object doc-class">
<h4 id="omniread.core.ContentType" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-class"></code> <span class="doc doc-object-name doc-class-name">ContentType</span>
</h4>
<div class="doc doc-contents ">
<p class="doc doc-class-bases">
Bases: <code>str</code>, <code><span title="enum.Enum">Enum</span></code></p>
<p>Supported MIME types for extracted content.</p>
<details class="notes" open>
<summary>Notes</summary>
<p><strong>Guarantees:</strong></p>
<div class="language-text highlight"><table class="highlighttable"><tr><td class="linenos"><div class="linenodiv"><pre><span></span><span class="normal">1</span>
<span class="normal">2</span></pre></div></td><td class="code"><div><pre><span></span><code>- This enum represents the declared or inferred media type of the content source
- It is primarily used for routing content to the appropriate parser or downstream consumer
</code></pre></div></td></tr></table></div>
</details>
<div class="doc doc-children">
<h5 id="omniread.core.ContentType-attributes">Attributes</h5>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.core.ContentType.HTML" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">HTML</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="n">HTML</span> <span class="o">=</span> <span class="s1">&#39;text/html&#39;</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>HTML document content.</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.core.ContentType.JSON" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">JSON</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="n">JSON</span> <span class="o">=</span> <span class="s1">&#39;application/json&#39;</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>JSON document content.</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.core.ContentType.PDF" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">PDF</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="n">PDF</span> <span class="o">=</span> <span class="s1">&#39;application/pdf&#39;</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>PDF document content.</p>
</div>
</div>
<div class="doc doc-object doc-attribute">
<h6 id="omniread.core.ContentType.XML" class="doc doc-heading">
<code class="doc-symbol doc-symbol-heading doc-symbol-attribute"></code> <span class="doc doc-object-name doc-attribute-name">XML</span>
<span class="doc doc-labels">
<small class="doc doc-label doc-label-class-attribute"><code>class-attribute</code></small>
<small class="doc doc-label doc-label-instance-attribute"><code>instance-attribute</code></small>
</span>
</h6>
<div class="language-python doc-signature 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></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="n">XML</span> <span class="o">=</span> <span class="s1">&#39;application/xml&#39;</span>
</span></code></pre></div></td></tr></table></div>
<div class="doc doc-contents ">
<p>XML document content.</p>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</div>
</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"], "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>