All checks were successful
continuous-integration/drone/push Build is passing
2057 lines
50 KiB
HTML
2057 lines
50 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="../core/scraper/">
|
|
|
|
|
|
<link rel="next" href="parser/">
|
|
|
|
|
|
<link rel="icon" href="../assets/images/favicon.png">
|
|
<meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.6.23">
|
|
|
|
|
|
|
|
<title>Html - 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="#html" 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" 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">
|
|
|
|
Html
|
|
|
|
</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">
|
|
|
|
<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>
|
|
|
|
</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="../core/" class="md-tabs__link">
|
|
|
|
|
|
|
|
Core API
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-tabs__item md-tabs__item--active">
|
|
<a href="./" class="md-tabs__link">
|
|
|
|
|
|
|
|
HTML Handling
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-tabs__item">
|
|
<a href="../pdf/" class="md-tabs__link">
|
|
|
|
|
|
|
|
PDF Handling
|
|
|
|
</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" 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--nested">
|
|
|
|
|
|
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_2" >
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_2" id="__nav_2_label" tabindex="0">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Core API
|
|
|
|
</span>
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_2_label" aria-expanded="false">
|
|
<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="../core/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Core
|
|
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../core/content/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Content
|
|
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../core/parser/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Parser
|
|
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<li class="md-nav__item">
|
|
<a href="../core/scraper/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Scraper
|
|
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</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_3" checked>
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_3" id="__nav_3_label" tabindex="">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
HTML Handling
|
|
|
|
</span>
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<nav class="md-nav" data-md-level="1" aria-labelledby="__nav_3_label" aria-expanded="true">
|
|
<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 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">
|
|
Html
|
|
|
|
</span>
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<a href="./" class="md-nav__link md-nav__link--active">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Html
|
|
|
|
</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="#omniread.html" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
html
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="html">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
HTMLParser
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="HTMLParser">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.supported_types" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
supported_types
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.parse" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
parse
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.parse_div" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
parse_div
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.parse_link" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
parse_link
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.parse_meta" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
parse_meta
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.parse_table" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
parse_table
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.supports" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
supports
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLScraper" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
HTMLScraper
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="HTMLScraper">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLScraper.fetch" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
fetch
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLScraper.validate_content_type" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
validate_content_type
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
|
|
</nav>
|
|
|
|
</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--nested">
|
|
|
|
|
|
|
|
|
|
|
|
<input class="md-nav__toggle md-toggle md-toggle--indeterminate" type="checkbox" id="__nav_4" >
|
|
|
|
|
|
<label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
PDF Handling
|
|
|
|
</span>
|
|
|
|
|
|
<span class="md-nav__icon md-icon"></span>
|
|
</label>
|
|
|
|
<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/" class="md-nav__link">
|
|
|
|
|
|
|
|
<span class="md-ellipsis">
|
|
Pdf
|
|
|
|
</span>
|
|
|
|
|
|
</a>
|
|
</li>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<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.html" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
html
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="html">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
HTMLParser
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="HTMLParser">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.supported_types" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
supported_types
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.parse" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
parse
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.parse_div" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
parse_div
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.parse_link" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
parse_link
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.parse_meta" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
parse_meta
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.parse_table" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
parse_table
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLParser.supports" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
supports
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
</ul>
|
|
</nav>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLScraper" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
HTMLScraper
|
|
</span>
|
|
</a>
|
|
|
|
<nav class="md-nav" aria-label="HTMLScraper">
|
|
<ul class="md-nav__list">
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLScraper.fetch" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
fetch
|
|
</span>
|
|
</a>
|
|
|
|
</li>
|
|
|
|
<li class="md-nav__item">
|
|
<a href="#omniread.html.HTMLScraper.validate_content_type" class="md-nav__link">
|
|
<span class="md-ellipsis">
|
|
validate_content_type
|
|
</span>
|
|
</a>
|
|
|
|
</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="html">Html</h1>
|
|
|
|
|
|
<div class="doc doc-object doc-module">
|
|
|
|
|
|
|
|
<h2 id="omniread.html" class="doc doc-heading">
|
|
<span class="doc doc-object-name doc-module-name">omniread.html</span>
|
|
|
|
|
|
</h2>
|
|
|
|
<div class="doc doc-contents first">
|
|
|
|
<p>HTML format implementation for OmniRead.</p>
|
|
<p>This package provides <strong>HTML-specific implementations</strong> of the core OmniRead
|
|
contracts defined in <code>omniread.core</code>.</p>
|
|
<p>It includes:
|
|
- HTML parsers that interpret HTML content
|
|
- HTML scrapers that retrieve HTML documents</p>
|
|
<p>This package:
|
|
- Implements, but does not redefine, core contracts
|
|
- May contain HTML-specific behavior and edge-case handling
|
|
- Produces canonical content models defined in <code>omniread.core.content</code></p>
|
|
<p>Consumers should depend on <code>omniread.core</code> interfaces wherever possible and
|
|
use this package only when HTML-specific behavior is required.</p>
|
|
|
|
|
|
|
|
<div class="doc doc-children">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div class="doc doc-object doc-class">
|
|
|
|
|
|
|
|
<h3 id="omniread.html.HTMLParser" class="doc doc-heading">
|
|
<span class="doc doc-object-name doc-class-name">HTMLParser</span>
|
|
|
|
|
|
</h3>
|
|
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">HTMLParser</span><span class="p">(</span><span class="n">content</span><span class="p">:</span> <span class="n">Content</span><span class="p">,</span> <span class="n">features</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s1">'html.parser'</span><span class="p">)</span>
|
|
</code></pre></div>
|
|
|
|
<div class="doc doc-contents ">
|
|
<p class="doc doc-class-bases">
|
|
Bases: <code><a class="autorefs autorefs-internal" title="omniread.core.parser.BaseParser" href="../core/parser/#omniread.core.parser.BaseParser">BaseParser</a>[<span title="omniread.html.parser.T">T</span>]</code>, <code><span title="typing.Generic">Generic</span>[<span title="omniread.html.parser.T">T</span>]</code></p>
|
|
|
|
|
|
<p>Base HTML parser.</p>
|
|
<p>This class extends the core <code>BaseParser</code> with HTML-specific behavior,
|
|
including DOM parsing via BeautifulSoup and reusable extraction helpers.</p>
|
|
<p>Provides reusable helpers for HTML extraction.
|
|
Concrete parsers must explicitly define the return type.</p>
|
|
<p>Characteristics:
|
|
- Accepts only HTML content
|
|
- Owns a parsed BeautifulSoup DOM tree
|
|
- Provides pure helper utilities for common HTML structures</p>
|
|
<p>Concrete subclasses must:
|
|
- Define the output type <code>T</code>
|
|
- Implement the <code>parse()</code> method</p>
|
|
|
|
<p>Initialize the HTML parser.</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="../core/content/#omniread.core.content.Content">Content</a></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>HTML content to be parsed.</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<em>required</em>
|
|
</td>
|
|
</tr>
|
|
<tr class="doc-section-item">
|
|
<td><code>features</code></td>
|
|
<td>
|
|
<code>str</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>BeautifulSoup parser backend to use
|
|
(e.g., 'html.parser', 'lxml').</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<code>'html.parser'</code>
|
|
</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 is empty or not valid HTML.</p>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
|
|
|
|
|
|
<div class="doc doc-children">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div class="doc doc-object doc-attribute">
|
|
|
|
|
|
|
|
<h4 id="omniread.html.HTMLParser.supported_types" class="doc doc-heading">
|
|
<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>
|
|
|
|
</h4>
|
|
<div class="doc-signature highlight"><pre><span></span><code><span class="n">supported_types</span><span class="p">:</span> <span class="nb">set</span><span class="p">[</span><span class="n">ContentType</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span><span class="n">HTML</span><span class="p">}</span>
|
|
</code></pre></div>
|
|
|
|
<div class="doc doc-contents ">
|
|
|
|
<p>Set of content types supported by this parser (HTML only).</p>
|
|
</div>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<div class="doc doc-object doc-function">
|
|
|
|
|
|
<h4 id="omniread.html.HTMLParser.parse" class="doc doc-heading">
|
|
<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>
|
|
|
|
</h4>
|
|
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">parse</span><span class="p">()</span> <span class="o">-></span> <span class="n">T</span>
|
|
</code></pre></div>
|
|
|
|
<div class="doc doc-contents ">
|
|
|
|
<p>Fully parse the HTML content into structured output.</p>
|
|
<p>Implementations must fully interpret the HTML DOM and return
|
|
a deterministic, structured output.</p>
|
|
|
|
|
|
<p><span class="doc-section-title">Returns:</span></p>
|
|
<table>
|
|
<thead>
|
|
<tr>
|
|
<th>Type</th>
|
|
<th>Description</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code><span title="omniread.html.parser.T">T</span></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>Parsed representation of type <code>T</code>.</p>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<div class="doc doc-object doc-function">
|
|
|
|
|
|
<h4 id="omniread.html.HTMLParser.parse_div" class="doc doc-heading">
|
|
<span class="doc doc-object-name doc-function-name">parse_div</span>
|
|
|
|
|
|
<span class="doc doc-labels">
|
|
<small class="doc doc-label doc-label-staticmethod"><code>staticmethod</code></small>
|
|
</span>
|
|
|
|
</h4>
|
|
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">parse_div</span><span class="p">(</span><span class="n">div</span><span class="p">:</span> <span class="n">Tag</span><span class="p">,</span> <span class="o">*</span><span class="p">,</span> <span class="n">separator</span><span class="p">:</span> <span class="nb">str</span> <span class="o">=</span> <span class="s1">' '</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span>
|
|
</code></pre></div>
|
|
|
|
<div class="doc doc-contents ">
|
|
|
|
<p>Extract normalized text from a <code><div></code> element.</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>div</code></td>
|
|
<td>
|
|
<code><span title="bs4.Tag">Tag</span></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>BeautifulSoup tag representing a <code><div></code>.</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<em>required</em>
|
|
</td>
|
|
</tr>
|
|
<tr class="doc-section-item">
|
|
<td><code>separator</code></td>
|
|
<td>
|
|
<code>str</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>String used to separate text nodes.</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<code>' '</code>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
|
|
<p><span class="doc-section-title">Returns:</span></p>
|
|
<table>
|
|
<thead>
|
|
<tr>
|
|
<th>Type</th>
|
|
<th>Description</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code>str</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>Flattened, whitespace-normalized text content.</p>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<div class="doc doc-object doc-function">
|
|
|
|
|
|
<h4 id="omniread.html.HTMLParser.parse_link" class="doc doc-heading">
|
|
<span class="doc doc-object-name doc-function-name">parse_link</span>
|
|
|
|
|
|
<span class="doc doc-labels">
|
|
<small class="doc doc-label doc-label-staticmethod"><code>staticmethod</code></small>
|
|
</span>
|
|
|
|
</h4>
|
|
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">parse_link</span><span class="p">(</span><span class="n">a</span><span class="p">:</span> <span class="n">Tag</span><span class="p">)</span> <span class="o">-></span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span>
|
|
</code></pre></div>
|
|
|
|
<div class="doc doc-contents ">
|
|
|
|
<p>Extract the hyperlink reference from an <code><a></code> element.</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>a</code></td>
|
|
<td>
|
|
<code><span title="bs4.Tag">Tag</span></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>BeautifulSoup tag representing an anchor.</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<em>required</em>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
|
|
<p><span class="doc-section-title">Returns:</span></p>
|
|
<table>
|
|
<thead>
|
|
<tr>
|
|
<th>Type</th>
|
|
<th>Description</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code><span title="typing.Optional">Optional</span>[str]</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>The value of the <code>href</code> attribute, or None if absent.</p>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<div class="doc doc-object doc-function">
|
|
|
|
|
|
<h4 id="omniread.html.HTMLParser.parse_meta" class="doc doc-heading">
|
|
<span class="doc doc-object-name doc-function-name">parse_meta</span>
|
|
|
|
|
|
</h4>
|
|
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">parse_meta</span><span class="p">()</span> <span class="o">-></span> <span class="nb">dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span>
|
|
</code></pre></div>
|
|
|
|
<div class="doc doc-contents ">
|
|
|
|
<p>Extract high-level metadata from the HTML document.</p>
|
|
<p>This includes:
|
|
- Document title
|
|
- <code><meta></code> tag name/property → content mappings</p>
|
|
|
|
|
|
<p><span class="doc-section-title">Returns:</span></p>
|
|
<table>
|
|
<thead>
|
|
<tr>
|
|
<th>Type</th>
|
|
<th>Description</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code><span title="typing.dict">dict</span>[str, <span title="typing.Any">Any</span>]</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>Dictionary containing extracted metadata.</p>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<div class="doc doc-object doc-function">
|
|
|
|
|
|
<h4 id="omniread.html.HTMLParser.parse_table" class="doc doc-heading">
|
|
<span class="doc doc-object-name doc-function-name">parse_table</span>
|
|
|
|
|
|
<span class="doc doc-labels">
|
|
<small class="doc doc-label doc-label-staticmethod"><code>staticmethod</code></small>
|
|
</span>
|
|
|
|
</h4>
|
|
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">parse_table</span><span class="p">(</span><span class="n">table</span><span class="p">:</span> <span class="n">Tag</span><span class="p">)</span> <span class="o">-></span> <span class="nb">list</span><span class="p">[</span><span class="nb">list</span><span class="p">[</span><span class="nb">str</span><span class="p">]]</span>
|
|
</code></pre></div>
|
|
|
|
<div class="doc doc-contents ">
|
|
|
|
<p>Parse an HTML table into a 2D list of strings.</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>table</code></td>
|
|
<td>
|
|
<code><span title="bs4.Tag">Tag</span></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>BeautifulSoup tag representing a <code><table></code>.</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<em>required</em>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
|
|
<p><span class="doc-section-title">Returns:</span></p>
|
|
<table>
|
|
<thead>
|
|
<tr>
|
|
<th>Type</th>
|
|
<th>Description</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code><span title="typing.list">list</span>[<span title="typing.list">list</span>[str]]</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>A list of rows, where each row is a list of cell text values.</p>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<div class="doc doc-object doc-function">
|
|
|
|
|
|
<h4 id="omniread.html.HTMLParser.supports" class="doc doc-heading">
|
|
<span class="doc doc-object-name doc-function-name">supports</span>
|
|
|
|
|
|
</h4>
|
|
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">supports</span><span class="p">()</span> <span class="o">-></span> <span class="nb">bool</span>
|
|
</code></pre></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>Type</th>
|
|
<th>Description</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr class="doc-section-item">
|
|
<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">
|
|
|
|
|
|
|
|
<h3 id="omniread.html.HTMLScraper" class="doc doc-heading">
|
|
<span class="doc doc-object-name doc-class-name">HTMLScraper</span>
|
|
|
|
|
|
</h3>
|
|
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">HTMLScraper</span><span class="p">(</span><span class="o">*</span><span class="p">,</span> <span class="n">client</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">httpx</span><span class="o">.</span><span class="n">Client</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">timeout</span><span class="p">:</span> <span class="nb">float</span> <span class="o">=</span> <span class="mf">15.0</span><span class="p">,</span> <span class="n">headers</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="nb">str</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span> <span class="n">follow_redirects</span><span class="p">:</span> <span class="nb">bool</span> <span class="o">=</span> <span class="kc">True</span><span class="p">)</span>
|
|
</code></pre></div>
|
|
|
|
<div class="doc doc-contents ">
|
|
<p class="doc doc-class-bases">
|
|
Bases: <code><a class="autorefs autorefs-internal" title="omniread.core.scraper.BaseScraper" href="../core/scraper/#omniread.core.scraper.BaseScraper">BaseScraper</a></code></p>
|
|
|
|
|
|
<p>Base HTML scraper using httpx.</p>
|
|
<p>This scraper retrieves HTML documents over HTTP(S) and returns them
|
|
as raw content wrapped in a <code>Content</code> object.</p>
|
|
<p>Fetches raw bytes and metadata only.
|
|
The scraper:
|
|
- Uses <code>httpx.Client</code> for HTTP requests
|
|
- Enforces an HTML content type
|
|
- Preserves HTTP response metadata</p>
|
|
<p>The scraper does not:
|
|
- Parse HTML
|
|
- Perform retries or backoff
|
|
- Handle non-HTML responses</p>
|
|
|
|
<p>Initialize the HTML scraper.</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>client</code></td>
|
|
<td>
|
|
<code><span title="typing.Optional">Optional</span>[<span title="httpx.Client">Client</span>]</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>Optional pre-configured <code>httpx.Client</code>. If omitted,
|
|
a client is created internally.</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<code>None</code>
|
|
</td>
|
|
</tr>
|
|
<tr class="doc-section-item">
|
|
<td><code>timeout</code></td>
|
|
<td>
|
|
<code>float</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>Request timeout in seconds.</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<code>15.0</code>
|
|
</td>
|
|
</tr>
|
|
<tr class="doc-section-item">
|
|
<td><code>headers</code></td>
|
|
<td>
|
|
<code><span title="typing.Optional">Optional</span>[<span title="typing.Mapping">Mapping</span>[str, str]]</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>Optional default HTTP headers.</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<code>None</code>
|
|
</td>
|
|
</tr>
|
|
<tr class="doc-section-item">
|
|
<td><code>follow_redirects</code></td>
|
|
<td>
|
|
<code>bool</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>Whether to follow HTTP redirects.</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<code>True</code>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
|
|
|
|
|
|
<div class="doc doc-children">
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div class="doc doc-object doc-function">
|
|
|
|
|
|
<h4 id="omniread.html.HTMLScraper.fetch" class="doc doc-heading">
|
|
<span class="doc doc-object-name doc-function-name">fetch</span>
|
|
|
|
|
|
</h4>
|
|
<div class="doc-signature highlight"><pre><span></span><code><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">-></span> <span class="n">Content</span>
|
|
</code></pre></div>
|
|
|
|
<div class="doc doc-contents ">
|
|
|
|
<p>Fetch an HTML document 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>URL of the HTML document.</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 metadata to be merged into the returned content.</p>
|
|
</div>
|
|
</td>
|
|
<td>
|
|
<code>None</code>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
|
|
<p><span class="doc-section-title">Returns:</span></p>
|
|
<table>
|
|
<thead>
|
|
<tr>
|
|
<th>Type</th>
|
|
<th>Description</th>
|
|
</tr>
|
|
</thead>
|
|
<tbody>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code><a class="autorefs autorefs-internal" title="omniread.core.content.Content" href="../core/content/#omniread.core.content.Content">Content</a></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>A <code>Content</code> instance containing:</p>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code><a class="autorefs autorefs-internal" title="omniread.core.content.Content" href="../core/content/#omniread.core.content.Content">Content</a></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<ul>
|
|
<li>Raw HTML bytes</li>
|
|
</ul>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code><a class="autorefs autorefs-internal" title="omniread.core.content.Content" href="../core/content/#omniread.core.content.Content">Content</a></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<ul>
|
|
<li>Source URL</li>
|
|
</ul>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code><a class="autorefs autorefs-internal" title="omniread.core.content.Content" href="../core/content/#omniread.core.content.Content">Content</a></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<ul>
|
|
<li>HTML content type</li>
|
|
</ul>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code><a class="autorefs autorefs-internal" title="omniread.core.content.Content" href="../core/content/#omniread.core.content.Content">Content</a></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<ul>
|
|
<li>HTTP response metadata</li>
|
|
</ul>
|
|
</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><span title="httpx.HTTPError">HTTPError</span></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>If the HTTP request fails.</p>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
<tr class="doc-section-item">
|
|
<td>
|
|
<code>ValueError</code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>If the response is not valid HTML.</p>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
<div class="doc doc-object doc-function">
|
|
|
|
|
|
<h4 id="omniread.html.HTMLScraper.validate_content_type" class="doc doc-heading">
|
|
<span class="doc doc-object-name doc-function-name">validate_content_type</span>
|
|
|
|
|
|
</h4>
|
|
<div class="doc-signature highlight"><pre><span></span><code><span class="nf">validate_content_type</span><span class="p">(</span><span class="n">response</span><span class="p">:</span> <span class="n">httpx</span><span class="o">.</span><span class="n">Response</span><span class="p">)</span> <span class="o">-></span> <span class="kc">None</span>
|
|
</code></pre></div>
|
|
|
|
<div class="doc doc-contents ">
|
|
|
|
<p>Validate that the HTTP response contains HTML content.</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>response</code></td>
|
|
<td>
|
|
<code><span title="httpx.Response">Response</span></code>
|
|
</td>
|
|
<td>
|
|
<div class="doc-md-description">
|
|
<p>HTTP response returned by <code>httpx</code>.</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 <code>Content-Type</code> header is missing or does not
|
|
indicate HTML content.</p>
|
|
</div>
|
|
</td>
|
|
</tr>
|
|
</tbody>
|
|
</table>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
</div>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</article>
|
|
</div>
|
|
|
|
|
|
<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.tabs", "navigation.expand", "navigation.top", "navigation.instant", "content.code.copy", "content.code.annotate"], "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> |