jcbowyer's picture
Deploy: Consolidated gold tables, fixed nginx docs routing
3d16fe6 verified
<!doctype html><html lang=en dir=ltr class="docs-wrapper plugin-docs plugin-id-default docs-version-current docs-doc-page docs-doc-id-data-sources/overview" data-has-hydrated=false><head><meta charset=UTF-8><meta name=generator content="Docusaurus v3.10.0"><title data-rh=true>Data Sources Overview | Open Navigator</title><meta data-rh=true name=viewport content="width=device-width, initial-scale=1.0"/><meta data-rh=true property=og:image content=https://www.communityone.com/img/docusaurus-social-card.jpg /><meta data-rh=true name=twitter:image content=https://www.communityone.com/img/docusaurus-social-card.jpg /><meta data-rh=true property=og:url content=https://www.communityone.com/docs/data-sources/overview /><meta data-rh=true property=og:locale content=en /><meta data-rh=true name=docusaurus_locale content=en /><meta data-rh=true name=docsearch:language content=en /><meta data-rh=true name=keywords content="civic engagement, policy tracking, meeting minutes, nonprofit tracking, municipal government, advocacy, open data, local government"/><meta data-rh=true property=og:type content=website /><meta data-rh=true property=og:site_name content="Open Navigator"/><meta data-rh=true name=twitter:card content=summary_large_image /><meta data-rh=true name=docusaurus_version content=current /><meta data-rh=true name=docusaurus_tag content=docs-default-current /><meta data-rh=true name=docsearch:version content=current /><meta data-rh=true name=docsearch:docusaurus_tag content=docs-default-current /><meta data-rh=true property=og:title content="Data Sources Overview | Open Navigator"/><meta data-rh=true name=description content="This document covers the official, free, public datasets used by Open Navigator."/><meta data-rh=true property=og:description content="This document covers the official, free, public datasets used by Open Navigator."/><link data-rh=true rel=icon href=/img/favicon.ico /><link data-rh=true rel=canonical href=https://www.communityone.com/docs/data-sources/overview /><link data-rh=true rel=alternate href=https://www.communityone.com/docs/data-sources/overview hreflang=en /><link data-rh=true rel=alternate href=https://www.communityone.com/docs/data-sources/overview hreflang=x-default /><script data-rh=true type=application/ld+json>{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","item":"https://www.communityone.com/docs/data-sources/overview","name":"Data Sources Overview","position":1}]}</script><link rel=alternate type=application/rss+xml href=/blog/rss.xml title="Open Navigator RSS Feed"><link rel=alternate type=application/atom+xml href=/blog/atom.xml title="Open Navigator Atom Feed"><link rel=preconnect href=https://www.google-analytics.com><link rel=preconnect href=https://www.googletagmanager.com><script async src="https://www.googletagmanager.com/gtag/js?id=G-5EQV815915"></script><script>function gtag(){dataLayer.push(arguments)}window.dataLayer=window.dataLayer||[],gtag("js",new Date),gtag("config","G-5EQV815915",{anonymize_ip:!0})</script><link rel=stylesheet href=/assets/css/styles.c89d6b2d.css /><script src=/assets/js/runtime~main.c8fa085e.js defer></script><script src=/assets/js/main.6e24e536.js defer></script></head><body><svg style="display: none;"><defs>
<symbol id=theme-svg-external-link viewBox="0 0 24 24"><path fill=currentColor d="M21 13v10h-21v-19h12v2h-10v15h17v-8h2zm3-12h-10.988l4.035 4-6.977 7.07 2.828 2.828 6.977-7.07 4.125 4.172v-11z"/></symbol>
</defs></svg>
<script>!function(){var t=function(){try{return new URLSearchParams(window.location.search).get("docusaurus-theme")}catch(t){}}()||function(){try{return window.localStorage.getItem("theme-7e9")}catch(t){}}();document.documentElement.setAttribute("data-theme",t||(window.matchMedia("(prefers-color-scheme: dark)").matches?"dark":"light")),document.documentElement.setAttribute("data-theme-choice",t||"system")}(),function(){try{for(var[t,e]of new URLSearchParams(window.location.search).entries())if(t.startsWith("docusaurus-data-")){var a=t.replace("docusaurus-data-","data-");document.documentElement.setAttribute(a,e)}}catch(t){}}()</script><div id=__docusaurus><link rel=preload as=image href=/img/communityone_logo.svg /><script type=application/ld+json>{"@context":"https://schema.org","@type":"Organization","address":{"@type":"PostalAddress","addressCountry":"US","addressLocality":"Tuscaloosa","addressRegion":"AL","postalCode":"35406","streetAddress":"5617 Lakeridge Court"},"contactPoint":{"@type":"ContactPoint","availableLanguage":["English"],"contactType":"Customer Service","email":"johnbowyer@communityone.com"},"description":"Track 90,000+ jurisdictions, 1.8M nonprofits, and analyze meeting minutes with AI. The open path to everything local.","email":"johnbowyer@communityone.com","legalName":"CommunityOne","logo":"https://www.communityone.com/img/communityone_logo.svg","name":"CommunityOne","sameAs":["https://www.facebook.com/communityone","https://www.instagram.com/communityone","https://twitter.com/communityone","https://www.linkedin.com/company/communityone","https://www.youtube.com/@communityone","https://discord.gg/communityone","https://github.com/getcommunityone/open-navigator"],"url":"https://www.communityone.com"}</script><script type=application/ld+json>{"@context":"https://schema.org","@type":"WebSite","alternateName":"CommunityOne Open Navigator","description":"AI-powered civic engagement platform tracking jurisdictions, nonprofits, and government meetings","name":"Open Navigator","potentialAction":{"@type":"SearchAction","query-input":"required name=search_term_string","target":{"@type":"EntryPoint","urlTemplate":"https://www.communityone.com/search?q={search_term_string}"}},"url":"https://www.communityone.com"}</script><script type=application/ld+json>{"@context":"https://schema.org","@type":"SoftwareApplication","aggregateRating":{"@type":"AggregateRating","ratingCount":"1","ratingValue":"5"},"applicationCategory":"BusinessApplication","description":"Track 90,000+ jurisdictions, 1.8M nonprofits, and analyze meeting minutes with AI","featureList":["Track 90,000+ jurisdictions","Monitor 1.8M nonprofits","Analyze meeting minutes","Legislative bill tracking","Campaign finance data"],"name":"Open Navigator","offers":{"@type":"Offer","price":"0","priceCurrency":"USD"},"operatingSystem":"Web","screenshot":"https://www.communityone.com/img/docusaurus-social-card.jpg","softwareVersion":"1.0.0"}</script><div role=region aria-label="Skip to main content"><a class=skipToContent_fXgn href=#__docusaurus_skipToContent_fallback>Skip to main content</a></div><nav aria-label=Main class="theme-layout-navbar navbar navbar--fixed-top"><div class=navbar__inner><div class="theme-layout-navbar-left navbar__items"><button aria-label="Toggle navigation bar" aria-expanded=false class="navbar__toggle clean-btn" type=button><svg width=30 height=30 viewBox="0 0 30 30" aria-hidden=true><path stroke=currentColor stroke-linecap=round stroke-miterlimit=10 stroke-width=2 d="M4 7h22M4 15h22M4 23h22"/></svg></button><a href=https://www.communityone.com target=_self rel="noopener noreferrer" class=navbar__brand><div class=navbar__logo><img src=/img/communityone_logo.svg alt="CommunityOne Logo" class="themedComponent_mlkZ themedComponent--light_NVdE"/><img src=/img/communityone_logo.svg alt="CommunityOne Logo" class="themedComponent_mlkZ themedComponent--dark_xIcU"/></div><b class="navbar__title text--truncate">Open Navigator Home</b></a><a class="navbar__item navbar__link" href=/docs/intro>Getting Started</a><a class="navbar__item navbar__link" href=/docs/for-families>Families & Individuals</a><a aria-current=page class="navbar__item navbar__link navbar__link--active" href=/docs/for-advocates>Policy Makers</a><a class="navbar__item navbar__link" href=/docs/for-developers>Developers</a><a class="navbar__item navbar__link" href=/docs/data-sources/citations>Data and Terms</a><a class="navbar__item navbar__link" href=/blog>Blog</a></div><div class="theme-layout-navbar-right navbar__items navbar__items--right"><a href=https://github.com/getcommunityone/open-navigator-for-engagement target=_blank rel="noopener noreferrer" class="navbar__item navbar__link">GitHub<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a><div class="toggle_vylO colorModeToggle_DEke"><button class="clean-btn toggleButton_gllP toggleButtonDisabled_aARS" type=button disabled title="system mode" aria-label="Switch between dark and light mode (currently system mode)"><svg viewBox="0 0 24 24" width=24 height=24 aria-hidden=true class="toggleIcon_g3eP lightToggleIcon_pyhR"><path fill=currentColor d="M12,9c1.65,0,3,1.35,3,3s-1.35,3-3,3s-3-1.35-3-3S10.35,9,12,9 M12,7c-2.76,0-5,2.24-5,5s2.24,5,5,5s5-2.24,5-5 S14.76,7,12,7L12,7z M2,13l2,0c0.55,0,1-0.45,1-1s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S1.45,13,2,13z M20,13l2,0c0.55,0,1-0.45,1-1 s-0.45-1-1-1l-2,0c-0.55,0-1,0.45-1,1S19.45,13,20,13z M11,2v2c0,0.55,0.45,1,1,1s1-0.45,1-1V2c0-0.55-0.45-1-1-1S11,1.45,11,2z M11,20v2c0,0.55,0.45,1,1,1s1-0.45,1-1v-2c0-0.55-0.45-1-1-1C11.45,19,11,19.45,11,20z M5.99,4.58c-0.39-0.39-1.03-0.39-1.41,0 c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0s0.39-1.03,0-1.41L5.99,4.58z M18.36,16.95 c-0.39-0.39-1.03-0.39-1.41,0c-0.39,0.39-0.39,1.03,0,1.41l1.06,1.06c0.39,0.39,1.03,0.39,1.41,0c0.39-0.39,0.39-1.03,0-1.41 L18.36,16.95z M19.42,5.99c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06c-0.39,0.39-0.39,1.03,0,1.41 s1.03,0.39,1.41,0L19.42,5.99z M7.05,18.36c0.39-0.39,0.39-1.03,0-1.41c-0.39-0.39-1.03-0.39-1.41,0l-1.06,1.06 c-0.39,0.39-0.39,1.03,0,1.41s1.03,0.39,1.41,0L7.05,18.36z"/></svg><svg viewBox="0 0 24 24" width=24 height=24 aria-hidden=true class="toggleIcon_g3eP darkToggleIcon_wfgR"><path fill=currentColor d="M9.37,5.51C9.19,6.15,9.1,6.82,9.1,7.5c0,4.08,3.32,7.4,7.4,7.4c0.68,0,1.35-0.09,1.99-0.27C17.45,17.19,14.93,19,12,19 c-3.86,0-7-3.14-7-7C5,9.07,6.81,6.55,9.37,5.51z M12,3c-4.97,0-9,4.03-9,9s4.03,9,9,9s9-4.03,9-9c0-0.46-0.04-0.92-0.1-1.36 c-0.98,1.37-2.58,2.26-4.4,2.26c-2.98,0-5.4-2.42-5.4-5.4c0-1.81,0.89-3.42,2.26-4.4C12.92,3.04,12.46,3,12,3L12,3z"/></svg><svg viewBox="0 0 24 24" width=24 height=24 aria-hidden=true class="toggleIcon_g3eP systemToggleIcon_QzmC"><path fill=currentColor d="m12 21c4.971 0 9-4.029 9-9s-4.029-9-9-9-9 4.029-9 9 4.029 9 9 9zm4.95-13.95c1.313 1.313 2.05 3.093 2.05 4.95s-0.738 3.637-2.05 4.95c-1.313 1.313-3.093 2.05-4.95 2.05v-14c1.857 0 3.637 0.737 4.95 2.05z"/></svg></button></div><div class=navbarSearchContainer_Bca1></div></div></div><div role=presentation class=navbar-sidebar__backdrop></div></nav><div id=__docusaurus_skipToContent_fallback class="theme-layout-main main-wrapper mainWrapper_z2l0"><div class=docsWrapper_hBAB><button aria-label="Scroll back to top" class="clean-btn theme-back-to-top-button backToTopButton_sjWU" type=button></button><div class=docRoot_UBD9><aside class="theme-doc-sidebar-container docSidebarContainer_YfHR"><div class=sidebarViewport_aRkj><div class=sidebar_njMd><nav aria-label="Docs sidebar" class="menu thin-scrollbar menu_SIkG"><ul class="theme-doc-sidebar-menu menu__list"><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-1 menu__list-item"><div class=menu__list-item-collapsible><a class="categoryLink_byQd menu__link menu__link--sublist menu__link--sublist-caret menu__link--active" role=button aria-expanded=true href=/docs/for-advocates><span title="Policy Makers & Advocates" class=categoryLinkLabel_W154>Policy Makers & Advocates</span></a></div><ul class=menu__list><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-2 menu__list-item"><a class=menu__link tabindex=0 href=/docs/for-advocates><span title="For Policy Makers & Advocates" class=linkLabel_WmDU>For Policy Makers & Advocates</span></a><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item"><div class=menu__list-item-collapsible><a class="categoryLink_byQd menu__link menu__link--sublist menu__link--sublist-caret menu__link--active" role=button aria-expanded=true tabindex=0 href=/docs/data-sources/overview><span title="Understanding the Data" class=categoryLinkLabel_W154>Understanding the Data</span></a></div><ul class=menu__list><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item"><a class="menu__link menu__link--active" aria-current=page tabindex=0 href=/docs/data-sources/overview><span title="Data Sources Overview" class=linkLabel_WmDU>Data Sources Overview</span></a><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item"><a class=menu__link tabindex=0 href=/docs/data-sources/citations><span title="Data and Citations" class=linkLabel_WmDU>Data and Citations</span></a><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item"><a class=menu__link tabindex=0 href=/docs/data-sources/nonprofit-sources><span title="Nonprofit Data Sources & Reference Sites" class=linkLabel_WmDU>Nonprofit Data Sources & Reference Sites</span></a><li class="theme-doc-sidebar-item-link theme-doc-sidebar-item-link-level-3 menu__list-item"><a class=menu__link tabindex=0 href=/docs/data-sources/video-sources><span title="Complete Video Channel Discovery Sources" class=linkLabel_WmDU>Complete Video Channel Discovery Sources</span></a></ul><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class=menu__list-item-collapsible><a class="categoryLink_byQd menu__link menu__link--sublist menu__link--sublist-caret" role=button aria-expanded=false tabindex=0 href=/docs/guides/political-economy><span title="Analysis & Strategy" class=categoryLinkLabel_W154>Analysis & Strategy</span></a></div><li class="theme-doc-sidebar-item-category theme-doc-sidebar-item-category-level-2 menu__list-item menu__list-item--collapsed"><div class=menu__list-item-collapsible><a class="categoryLink_byQd menu__link menu__link--sublist menu__link--sublist-caret" role=button aria-expanded=false tabindex=0 href=/docs/case-studies/tuscaloosa-complete><span title="Real-World Examples" class=categoryLinkLabel_W154>Real-World Examples</span></a></div></ul></ul></nav></div></div></aside><main class=docMainContainer_TBSr><div class="container padding-top--md padding-bottom--lg"><div class=row><div class="col docItemCol_VOVn"><div class=docItemContainer_Djhp><article><nav class="theme-doc-breadcrumbs breadcrumbsContainer_Z_bl" aria-label=Breadcrumbs><ul class=breadcrumbs><li class=breadcrumbs__item><a aria-label="Home page" class=breadcrumbs__link href=/><svg viewBox="0 0 24 24" class=breadcrumbHomeIcon_YNFT><path d="M10 19v-5h4v5c0 .55.45 1 1 1h3c.55 0 1-.45 1-1v-7h1.7c.46 0 .68-.57.33-.87L12.67 3.6c-.38-.34-.96-.34-1.34 0l-8.36 7.53c-.34.3-.13.87.33.87H5v7c0 .55.45 1 1 1h3c.55 0 1-.45 1-1z" fill=currentColor /></svg></a><li class=breadcrumbs__item><span class=breadcrumbs__link>Policy Makers & Advocates</span><li class=breadcrumbs__item><span class=breadcrumbs__link>Understanding the Data</span><li class="breadcrumbs__item breadcrumbs__item--active"><span class=breadcrumbs__link>Data Sources Overview</span></ul></nav><div class="tocCollapsible_ETCw theme-doc-toc-mobile tocMobile_ITEo"><button type=button class="clean-btn tocCollapsibleButton_TO0P">On this page</button></div><div class="theme-doc-markdown markdown"><header><h1>Data Sources Overview</h1></header>
<p>This document covers the <strong>official, free, public datasets</strong> used by Open Navigator.</p>
<div class="theme-admonition theme-admonition-tip admonition_xJq3 alert alert--success"><div class=admonitionHeading_Gvgb><span class=admonitionIcon_Rf37><svg viewBox="0 0 12 16"><path fill-rule=evenodd d="M6.5 0C3.48 0 1 2.19 1 5c0 .92.55 2.25 1 3 1.34 2.25 1.78 2.78 2 4v1h5v-1c.22-1.22.66-1.75 2-4 .45-.75 1-2.08 1-3 0-2.81-2.48-5-5.5-5zm3.64 7.48c-.25.44-.47.8-.67 1.11-.86 1.41-1.25 2.06-1.45 3.23-.02.05-.02.11-.02.17H5c0-.06 0-.13-.02-.17-.2-1.17-.59-1.83-1.45-3.23-.2-.31-.42-.67-.67-1.11C2.44 6.78 2 5.65 2 5c0-2.2 2.02-4 4.5-4 1.22 0 2.36.42 3.22 1.19C10.55 2.94 11 3.94 11 5c0 .66-.44 1.78-.86 2.48zM4 14h5c-.23 1.14-1.3 2-2.5 2s-2.27-.86-2.5-2z"/></svg></span>πŸ“š Full Citations & Academic References</div><div class=admonitionContent_BuS1><p>For complete citations, licenses, and attribution for all data sources, see:<p>πŸ‘‰ <strong><a class="" href=/docs/data-sources/citations>Citations & Data Sources</a></strong> β€” Includes BibTeX citations, license information, coverage details, and links to original sources.</div></div>
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id=-data-scale--coverage>πŸ“Š Data Scale & Coverage<a href=#-data-scale--coverage class=hash-link aria-label="Direct link to πŸ“Š Data Scale & Coverage" title="Direct link to πŸ“Š Data Scale & Coverage" translate=no>​</a></h2>
<p>Open Navigator provides comprehensive coverage across the United States:</p>
<table><thead><tr><th>Data Type<th>Count<th>Coverage<tbody><tr><td><strong>Government Jurisdictions</strong><td>90,000+<td>All U.S. local governments<tr><td><strong>Counties</strong><td>3,144<td>100% of U.S. counties<tr><td><strong>Municipalities</strong><td>19,500+<td>Cities, towns, villages<tr><td><strong>Townships</strong><td>36,000+<td>County subdivisions<tr><td><strong>School Districts</strong><td>13,000+<td>Complete NCES coverage<tr><td><strong>Nonprofit Organizations</strong><td>3,000,000+<td>All IRS-registered 501(c) orgs<tr><td><strong>Official .gov Domains</strong><td>15,000+<td>CISA validated domains<tr><td><strong>States</strong><td>50<td>All U.S. states + DC<tr><td><strong>Meeting Video Sources</strong><td>1,000+<td>Cities with full transcripts</table>
<p><strong>Key Insight:</strong> All data sources are <strong>100% free and public</strong> - no subscriptions, no API fees, no paywalls.</p>
<hr/>
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id=-data-source-categories>πŸ“‚ Data Source Categories<a href=#-data-source-categories class=hash-link aria-label="Direct link to πŸ“‚ Data Source Categories" title="Direct link to πŸ“‚ Data Source Categories" translate=no>​</a></h2>
<p>Open Navigator integrates data from six main categories:</p>
<ol>
<li class=""><strong><a href=#government-jurisdiction-data class="">Government Jurisdictions</a></strong> - Cities, counties, school districts (this page)</li>
<li class=""><strong><a class="" href=/docs/data-sources/nonprofit-sources>Nonprofit Organizations</a></strong> - IRS Form 990s, charity ratings, transparency data</li>
<li class=""><strong><a class="" href=/docs/data-sources/ballot-election-sources>Ballot Measures & Elections</a></strong> - Propositions, referendums, election results</li>
<li class=""><strong><a class="" href=/docs/data-sources/polling-survey-sources>Public Opinion & Surveys</a></strong> - Scientifically validated survey questions, polling data</li>
<li class=""><strong><a class="" href=/docs/data-sources/factcheck-sources>Fact-Checking & Verification</a></strong> - Google Fact Check API, FactCheck.org, PolitiFact claim verification</li>
<li class=""><strong><a class="" href=/docs/data-sources/open-source-repositories>Open Source Projects</a></strong> - Civic tech repositories, community tools, digital public goods</li>
</ol>
<hr/>
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id=️-government-jurisdiction-data>πŸ›οΈ Government Jurisdiction Data<a href=#️-government-jurisdiction-data class=hash-link aria-label="Direct link to πŸ›οΈ Government Jurisdiction Data" title="Direct link to πŸ›οΈ Government Jurisdiction Data" translate=no>​</a></h2>
<h3 class="anchor anchorTargetStickyNavbar_Vzrq" id=1-cisa-gov-domain-master-list--most-authoritative>1. CISA .gov Domain Master List ⭐ <strong>Most Authoritative</strong><a href=#1-cisa-gov-domain-master-list--most-authoritative class=hash-link aria-label="Direct link to 1-cisa-gov-domain-master-list--most-authoritative" title="Direct link to 1-cisa-gov-domain-master-list--most-authoritative" translate=no>​</a></h3>
<p><strong>Source:</strong> Cybersecurity and Infrastructure Security Agency (CISA)<br/>
<strong>URL:</strong> <a href=https://github.com/cisagov/dotgov-data target=_blank rel="noopener noreferrer" class="">https://github.com/cisagov/dotgov-data</a><br/>
<strong>File:</strong> <code>current-full.csv</code> (updated daily!)</p>
<p><strong>What It Contains:</strong></p>
<ul>
<li class=""><strong>15,000+ registered .gov domains</strong></li>
<li class="">Domain Type: City, County, State, Tribal, School District</li>
<li class="">Organization names and locations</li>
<li class="">Security contacts and registration dates</li>
</ul>
<p><strong>Why We Use It:</strong></p>
<blockquote>
<p>"The most authoritative source for government URLs is CISA. They maintain a daily-updated repository of every registered .gov domain."</p>
</blockquote>
<p><strong>How We Use It:</strong></p>
<div class="language-python codeBlockContainer_Ckt0 theme-code-block" style=--prism-color:#393A34;--prism-background-color:#f6f8fa><div class=codeBlockContent_QJqH><pre tabindex=0 class="prism-code language-python codeBlock_bY9V thin-scrollbar" style=color:#393A34;background-color:#f6f8fa><code class=codeBlockLines_e6Vv><div class=token-line style=color:#393A34><span class="token comment" style=color:#999988;font-style:italic># Direct download from GitHub</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain"></span><span class="token keyword" style=color:#00009f>from</span><span class="token plain"> discovery</span><span class="token punctuation" style=color:#393A34>.</span><span class="token plain">gsa_domains </span><span class="token keyword" style=color:#00009f>import</span><span class="token plain"> GSADomainList</span><br/></div><div class=token-line style=color:#393A34><span class="token plain" style=display:inline-block></span><br/></div><div class=token-line style=color:#393A34><span class="token plain">gsa </span><span class="token operator" style=color:#393A34>=</span><span class="token plain"> GSADomainList</span><span class="token punctuation" style=color:#393A34>(</span><span class="token punctuation" style=color:#393A34>)</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain">domains_df </span><span class="token operator" style=color:#393A34>=</span><span class="token plain"> </span><span class="token keyword" style=color:#00009f>await</span><span class="token plain"> gsa</span><span class="token punctuation" style=color:#393A34>.</span><span class="token plain">download_domain_list</span><span class="token punctuation" style=color:#393A34>(</span><span class="token punctuation" style=color:#393A34>)</span><br/></div></code></pre></div></div>
<p><strong>Lakehouse Strategy:</strong></p>
<ol>
<li class="">Ingest to <strong>Bronze Layer</strong> (<code>bronze/gov_domains</code>)</li>
<li class="">Filter by <code>Domain Type</code> for targeted scraping (City, County)</li>
<li class="">Use for <strong>exact matching</strong> (confidence: 0.95-1.0)</li>
<li class="">Use for <strong>fuzzy matching</strong> with 75%+ similarity</li>
</ol>
<hr/>
<h3 class="anchor anchorTargetStickyNavbar_Vzrq" id=2-us-census-bureau---government-integrated-directory-gid>2. U.S. Census Bureau - Government Integrated Directory (GID)<a href=#2-us-census-bureau---government-integrated-directory-gid class=hash-link aria-label="Direct link to 2. U.S. Census Bureau - Government Integrated Directory (GID)" title="Direct link to 2. U.S. Census Bureau - Government Integrated Directory (GID)" translate=no>​</a></h3>
<p><strong>Source:</strong> U.S. Census Bureau, Government Statistics<br/>
<strong>URL:</strong> <a href=https://www.census.gov/programs-surveys/gus.html target=_blank rel="noopener noreferrer" class="">https://www.census.gov/programs-surveys/gus.html</a><br/>
<strong>Dataset:</strong> 2022 Census of Governments</p>
<p><strong>What It Contains:</strong></p>
<ul>
<li class=""><strong>90,735 total government units</strong>
<ul>
<li class="">3,143 counties</li>
<li class="">19,495 municipalities (cities/towns)</li>
<li class="">16,504 townships</li>
<li class="">13,051 school districts</li>
<li class="">38,542 special districts</li>
</ul>
</li>
<li class="">FIPS codes (standardized IDs)</li>
<li class="">Population data</li>
<li class="">Geographic hierarchy (state, county, place)</li>
</ul>
<p><strong>Why We Use It:</strong></p>
<blockquote>
<p>"The Census Bureau GID provides a list of all 90,000+ legal government units. You can join this against the CISA list to find 'missing' URLs that your agent needs to hunt for."</p>
</blockquote>
<p><strong>How We Use It:</strong></p>
<div class="language-python codeBlockContainer_Ckt0 theme-code-block" style=--prism-color:#393A34;--prism-background-color:#f6f8fa><div class=codeBlockContent_QJqH><pre tabindex=0 class="prism-code language-python codeBlock_bY9V thin-scrollbar" style=color:#393A34;background-color:#f6f8fa><code class=codeBlockLines_e6Vv><div class=token-line style=color:#393A34><span class="token keyword" style=color:#00009f>from</span><span class="token plain"> discovery</span><span class="token punctuation" style=color:#393A34>.</span><span class="token plain">census_ingestion </span><span class="token keyword" style=color:#00009f>import</span><span class="token plain"> CensusGovernmentIngestion</span><br/></div><div class=token-line style=color:#393A34><span class="token plain" style=display:inline-block></span><br/></div><div class=token-line style=color:#393A34><span class="token plain">census </span><span class="token operator" style=color:#393A34>=</span><span class="token plain"> CensusGovernmentIngestion</span><span class="token punctuation" style=color:#393A34>(</span><span class="token punctuation" style=color:#393A34>)</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain">dfs </span><span class="token operator" style=color:#393A34>=</span><span class="token plain"> </span><span class="token keyword" style=color:#00009f>await</span><span class="token plain"> census</span><span class="token punctuation" style=color:#393A34>.</span><span class="token plain">ingest_all_jurisdictions</span><span class="token punctuation" style=color:#393A34>(</span><span class="token punctuation" style=color:#393A34>)</span><br/></div></code></pre></div></div>
<p><strong>Lakehouse Strategy:</strong></p>
<ol>
<li class="">Ingest to <strong>Bronze Layer</strong> (<code>bronze/jurisdictions/{{type}}</code>)</li>
<li class="">Create <strong>unified view</strong> with all jurisdiction types</li>
<li class=""><strong>Join with CISA</strong> to identify missing URLs</li>
<li class="">Prioritize by population for scraping</li>
</ol>
<hr/>
<h3 class="anchor anchorTargetStickyNavbar_Vzrq" id=3-nces-common-core-of-data-ccd>3. NCES Common Core of Data (CCD)<a href=#3-nces-common-core-of-data-ccd class=hash-link aria-label="Direct link to 3. NCES Common Core of Data (CCD)" title="Direct link to 3. NCES Common Core of Data (CCD)" translate=no>​</a></h3>
<p><strong>Source:</strong> National Center for Education Statistics (NCES)<br/>
<strong>URL:</strong> <a href=https://nces.ed.gov/ccd/ target=_blank rel="noopener noreferrer" class="">https://nces.ed.gov/ccd/</a><br/>
<strong>Dataset:</strong> Local Education Agency (LEA) Universe Survey</p>
<p><strong>What It Contains:</strong></p>
<ul>
<li class=""><strong>13,000+ school districts</strong></li>
<li class="">Official district names and NCES IDs</li>
<li class="">Physical addresses and phone numbers</li>
<li class=""><strong>Website URLs</strong> (when available)</li>
<li class="">Enrollment and demographic data</li>
<li class="">District type (Regular, Charter, etc.)</li>
</ul>
<p><strong>Why We Use It:</strong></p>
<blockquote>
<p>"Since one of your goals is tracking school dental screenings, you need a dedicated list of school board domains, as these are often separate from city governments."</p>
</blockquote>
<p><strong>How We Use It:</strong></p>
<div class="language-python codeBlockContainer_Ckt0 theme-code-block" style=--prism-color:#393A34;--prism-background-color:#f6f8fa><div class=codeBlockContent_QJqH><pre tabindex=0 class="prism-code language-python codeBlock_bY9V thin-scrollbar" style=color:#393A34;background-color:#f6f8fa><code class=codeBlockLines_e6Vv><div class=token-line style=color:#393A34><span class="token keyword" style=color:#00009f>from</span><span class="token plain"> discovery</span><span class="token punctuation" style=color:#393A34>.</span><span class="token plain">nces_ingestion </span><span class="token keyword" style=color:#00009f>import</span><span class="token plain"> NCESSchoolDistrictIngestion</span><br/></div><div class=token-line style=color:#393A34><span class="token plain" style=display:inline-block></span><br/></div><div class=token-line style=color:#393A34><span class="token plain">nces </span><span class="token operator" style=color:#393A34>=</span><span class="token plain"> NCESSchoolDistrictIngestion</span><span class="token punctuation" style=color:#393A34>(</span><span class="token punctuation" style=color:#393A34>)</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain">districts_df </span><span class="token operator" style=color:#393A34>=</span><span class="token plain"> </span><span class="token keyword" style=color:#00009f>await</span><span class="token plain"> nces</span><span class="token punctuation" style=color:#393A34>.</span><span class="token plain">ingest_school_districts</span><span class="token punctuation" style=color:#393A34>(</span><span class="token punctuation" style=color:#393A34>)</span><br/></div></code></pre></div></div>
<p><strong>Lakehouse Strategy:</strong></p>
<ol>
<li class="">Ingest to <strong>Bronze Layer</strong> (<code>bronze/nces_school_districts</code>)</li>
<li class="">Extract <strong>provided URLs</strong> (many NCES records include website field!)</li>
<li class="">Use district names to <strong>generate URL patterns</strong> for missing sites</li>
<li class="">Common pattern: <code>{{district}}.k12.{{state}}.us</code></li>
</ol>
<hr/>
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id=-summary-table-where-to-pull-the-lists>πŸ“‹ Summary Table: Where to Pull the Lists<a href=#-summary-table-where-to-pull-the-lists class=hash-link aria-label="Direct link to πŸ“‹ Summary Table: Where to Pull the Lists" title="Direct link to πŸ“‹ Summary Table: Where to Pull the Lists" translate=no>​</a></h2>
<table><thead><tr><th>Jurisdiction Type<th>Primary Free Source<th>Format<th>Coverage<tbody><tr><td><strong>All Official .gov</strong><td>CISA dotgov-data<td>CSV / GitHub<td>15,000+ domains<tr><td><strong>School Districts</strong><td>NCES CCD Data<td>CSV<td>13,000+ districts<tr><td><strong>Counties/Cities</strong><td>Census Bureau GID<td>CSV<td>22,638 jurisdictions<tr><td><strong>Townships</strong><td>Census Bureau GID<td>CSV<td>16,504 townships<tr><td><strong>Special Districts</strong><td>Census Bureau GID<td>CSV<td>38,542 districts<tr><td><strong>State Legislatures</strong><td>LegiScan API<td>JSON / API<td>50 states</table>
<hr/>
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id=-scraping-strategy-based-on-your-guidance>πŸ” Scraping Strategy (Based on Your Guidance)<a href=#-scraping-strategy-based-on-your-guidance class=hash-link aria-label="Direct link to πŸ” Scraping Strategy (Based on Your Guidance)" title="Direct link to πŸ” Scraping Strategy (Based on Your Guidance)" translate=no>​</a></h2>
<h3 class="anchor anchorTargetStickyNavbar_Vzrq" id=step-1-ingest>Step 1: Ingest<a href=#step-1-ingest class=hash-link aria-label="Direct link to Step 1: Ingest" title="Direct link to Step 1: Ingest" translate=no>​</a></h3>
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style=--prism-color:#393A34;--prism-background-color:#f6f8fa><div class=codeBlockContent_QJqH><pre tabindex=0 class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style=color:#393A34;background-color:#f6f8fa><code class=codeBlockLines_e6Vv><div class=token-line style=color:#393A34><span class="token plain">python main.py init # Initialize Delta Lake</span><br/></div><div class=token-line style=color:#393A34><span class="token plain">python main.py discover-jurisdictions --limit 100 # Test run</span><br/></div></code></pre></div></div>
<p><strong>Pulls:</strong></p>
<ul>
<li class="">βœ… <code>current-full.csv</code> from CISA β†’ Bronze layer</li>
<li class="">βœ… Census GID CSVs β†’ Bronze layer</li>
<li class="">βœ… NCES CCD data β†’ Bronze layer</li>
</ul>
<h3 class="anchor anchorTargetStickyNavbar_Vzrq" id=step-2-filter>Step 2: Filter<a href=#step-2-filter class=hash-link aria-label="Direct link to Step 2: Filter" title="Direct link to Step 2: Filter" translate=no>​</a></h3>
<div class="language-python codeBlockContainer_Ckt0 theme-code-block" style=--prism-color:#393A34;--prism-background-color:#f6f8fa><div class=codeBlockContent_QJqH><pre tabindex=0 class="prism-code language-python codeBlock_bY9V thin-scrollbar" style=color:#393A34;background-color:#f6f8fa><code class=codeBlockLines_e6Vv><div class=token-line style=color:#393A34><span class="token comment" style=color:#999988;font-style:italic># Create Silver layer table</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain">df </span><span class="token operator" style=color:#393A34>=</span><span class="token plain"> spark</span><span class="token punctuation" style=color:#393A34>.</span><span class="token plain">read</span><span class="token punctuation" style=color:#393A34>.</span><span class="token builtin">format</span><span class="token punctuation" style=color:#393A34>(</span><span class="token string" style=color:#e3116c>"delta"</span><span class="token punctuation" style=color:#393A34>)</span><span class="token punctuation" style=color:#393A34>.</span><span class="token plain">load</span><span class="token punctuation" style=color:#393A34>(</span><span class="token string" style=color:#e3116c>"bronze/gov_domains"</span><span class="token punctuation" style=color:#393A34>)</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain" style=display:inline-block></span><br/></div><div class=token-line style=color:#393A34><span class="token plain"></span><span class="token comment" style=color:#999988;font-style:italic># Filter for local governments</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain">local_govs </span><span class="token operator" style=color:#393A34>=</span><span class="token plain"> df</span><span class="token punctuation" style=color:#393A34>.</span><span class="token builtin">filter</span><span class="token punctuation" style=color:#393A34>(</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain"> col</span><span class="token punctuation" style=color:#393A34>(</span><span class="token string" style=color:#e3116c>"Domain Type"</span><span class="token punctuation" style=color:#393A34>)</span><span class="token punctuation" style=color:#393A34>.</span><span class="token plain">isin</span><span class="token punctuation" style=color:#393A34>(</span><span class="token punctuation" style=color:#393A34>[</span><span class="token string" style=color:#e3116c>"City"</span><span class="token punctuation" style=color:#393A34>,</span><span class="token plain"> </span><span class="token string" style=color:#e3116c>"County"</span><span class="token punctuation" style=color:#393A34>,</span><span class="token plain"> </span><span class="token string" style=color:#e3116c>"School District"</span><span class="token punctuation" style=color:#393A34>]</span><span class="token punctuation" style=color:#393A34>)</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain"></span><span class="token punctuation" style=color:#393A34>)</span><br/></div></code></pre></div></div>
<p><strong>Result:</strong> ~8,000-10,000 high-priority targets</p>
<h3 class="anchor anchorTargetStickyNavbar_Vzrq" id=step-3-crawl>Step 3: Crawl<a href=#step-3-crawl class=hash-link aria-label="Direct link to Step 3: Crawl" title="Direct link to Step 3: Crawl" translate=no>​</a></h3>
<div class="language-bash codeBlockContainer_Ckt0 theme-code-block" style=--prism-color:#393A34;--prism-background-color:#f6f8fa><div class=codeBlockContent_QJqH><pre tabindex=0 class="prism-code language-bash codeBlock_bY9V thin-scrollbar" style=color:#393A34;background-color:#f6f8fa><code class=codeBlockLines_e6Vv><div class=token-line style=color:#393A34><span class="token plain">python main.py scrape-batch --source discovered --limit 50</span><br/></div></code></pre></div></div>
<p><strong>Points Scrapy agents at discovered URLs:</strong></p>
<ul>
<li class="">Homepage URLs from CISA + pattern matching</li>
<li class="">Verified with HTTP HEAD/GET requests</li>
<li class="">Prioritized by population and domain type</li>
</ul>
<h3 class="anchor anchorTargetStickyNavbar_Vzrq" id=step-4-keyword-hunt>Step 4: Keyword Hunt<a href=#step-4-keyword-hunt class=hash-link aria-label="Direct link to Step 4: Keyword Hunt" title="Direct link to Step 4: Keyword Hunt" translate=no>​</a></h3>
<p><strong>Agent searches for:</strong></p>
<ul>
<li class="">"Minutes" pages</li>
<li class="">"Agendas" pages</li>
<li class="">"Meetings" pages</li>
<li class="">"Water" + "Fluoride" content</li>
</ul>
<p><strong>CMS Detection:</strong></p>
<ul>
<li class="">Granicus</li>
<li class="">CivicClerk</li>
<li class="">Municode</li>
<li class="">Legistar</li>
</ul>
<hr/>
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id=-non-gov-coverage>πŸš€ Non-.gov Coverage<a href=#-non-gov-coverage class=hash-link aria-label="Direct link to πŸš€ Non-.gov Coverage" title="Direct link to πŸš€ Non-.gov Coverage" translate=no>​</a></h2>
<p><strong>Many smaller municipalities use non-.gov domains:</strong></p>
<ul>
<li class=""><code>.org</code> (e.g., <code>cityofsomewhere.org</code>)</li>
<li class=""><code>.us</code> (e.g., <code>somewhere.ca.us</code>)</li>
<li class=""><code>.net</code> (e.g., <code>districschools.net</code>)</li>
</ul>
<p><strong>Our URL patterns cover these:</strong></p>
<div class="language-python codeBlockContainer_Ckt0 theme-code-block" style=--prism-color:#393A34;--prism-background-color:#f6f8fa><div class=codeBlockContent_QJqH><pre tabindex=0 class="prism-code language-python codeBlock_bY9V thin-scrollbar" style=color:#393A34;background-color:#f6f8fa><code class=codeBlockLines_e6Vv><div class=token-line style=color:#393A34><span class="token comment" style=color:#999988;font-style:italic># Pattern generation includes:</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain">patterns </span><span class="token operator" style=color:#393A34>=</span><span class="token plain"> </span><span class="token punctuation" style=color:#393A34>[</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain"> </span><span class="token string" style=color:#e3116c>"https://cityname.gov"</span><span class="token punctuation" style=color:#393A34>,</span><span class="token plain"> </span><span class="token comment" style=color:#999988;font-style:italic># Primary</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain"> </span><span class="token string" style=color:#e3116c>"https://cityname.us"</span><span class="token punctuation" style=color:#393A34>,</span><span class="token plain"> </span><span class="token comment" style=color:#999988;font-style:italic># Alternative</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain"> </span><span class="token string" style=color:#e3116c>"https://cityname.org"</span><span class="token punctuation" style=color:#393A34>,</span><span class="token plain"> </span><span class="token comment" style=color:#999988;font-style:italic># Non-profit</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain"> </span><span class="token string" style=color:#e3116c>"https://cityname.net"</span><span class="token punctuation" style=color:#393A34>,</span><span class="token plain"> </span><span class="token comment" style=color:#999988;font-style:italic># Legacy</span><span class="token plain"></span><br/></div><div class=token-line style=color:#393A34><span class="token plain"></span><span class="token punctuation" style=color:#393A34>]</span><br/></div></code></pre></div></div>
<p><strong>Future Enhancement:</strong></p>
<ul>
<li class=""><a href=https://www.statelocalgov.net/ target=_blank rel="noopener noreferrer" class="">State and Local Government on the Net</a></li>
<li class="">Could scrape this directory as fallback for missing URLs</li>
<li class="">Manually curated list of non-.gov government sites</li>
</ul>
<hr/>
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id=-cost-0>πŸ’° Cost: $0<a href=#-cost-0 class=hash-link aria-label="Direct link to πŸ’° Cost: $0" title="Direct link to πŸ’° Cost: $0" translate=no>​</a></h2>
<p>All data sources are <strong>free and publicly available</strong>:</p>
<table><thead><tr><th>Source<th>Cost<th>Update Frequency<tbody><tr><td>CISA dotgov-data<td><strong>$0</strong><td>Daily<tr><td>Census Bureau GID<td><strong>$0</strong><td>Annual<tr><td>NCES CCD<td><strong>$0</strong><td>Annual<tr><td>Pattern Matching<td><strong>$0</strong><td>On-demand</table>
<p><strong>Total API costs:</strong> <strong>$0</strong> πŸŽ‰</p>
<p>Compare to deprecated approach:</p>
<ul>
<li class=""><del>Google Custom Search API: $5/1000 queries = ~$150</del></li>
<li class=""><del>Bing Search API: $7/1000 queries = ~$90</del></li>
</ul>
<p><strong>Savings: $240+ per discovery run</strong> βœ…</p>
<hr/>
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id=-references>πŸ“š References<a href=#-references class=hash-link aria-label="Direct link to πŸ“š References" title="Direct link to πŸ“š References" translate=no>​</a></h2>
<p><strong>Government Jurisdiction Data:</strong></p>
<ul>
<li class=""><strong>CISA .gov Domains:</strong> <a href=https://github.com/cisagov/dotgov-data target=_blank rel="noopener noreferrer" class="">https://github.com/cisagov/dotgov-data</a></li>
<li class=""><strong>Census Bureau GID:</strong> <a href=https://www.census.gov/programs-surveys/gus.html target=_blank rel="noopener noreferrer" class="">https://www.census.gov/programs-surveys/gus.html</a></li>
<li class=""><strong>NCES CCD:</strong> <a href=https://nces.ed.gov/ccd/ target=_blank rel="noopener noreferrer" class="">https://nces.ed.gov/ccd/</a></li>
<li class=""><strong>State/Local Gov Directory:</strong> <a href=https://www.statelocalgov.net/ target=_blank rel="noopener noreferrer" class="">https://www.statelocalgov.net/</a></li>
<li class=""><strong>LegiScan API:</strong> <a href=https://legiscan.com/legiscan target=_blank rel="noopener noreferrer" class="">https://legiscan.com/legiscan</a></li>
</ul>
<p><strong>Nonprofit Data:</strong>
<strong>Nonprofit Data:</strong></p>
<ul>
<li class="">See <a class="" href=/docs/data-sources/nonprofit-sources>Nonprofit Data Sources</a> for ProPublica, Charity Navigator, Candid/GuideStar, and GiveWell</li>
</ul>
<p><strong>Open Source Projects:</strong></p>
<ul>
<li class="">See <a class="" href=/docs/data-sources/open-source-repositories>Open Source Repositories</a> for civic tech projects, GitHub data, and community tools</li>
</ul>
<hr/>
<h2 class="anchor anchorTargetStickyNavbar_Vzrq" id=-credits>βœ… Credits<a href=#-credits class=hash-link aria-label="Direct link to βœ… Credits" title="Direct link to βœ… Credits" translate=no>​</a></h2>
<p><strong>System Architecture:</strong> Medallion Architecture (Bronze β†’ Silver β†’ Gold)<br/>
<strong>Data Engineering Pattern:</strong> Delta Lake + PySpark<br/>
<strong>Sustainable Approach:</strong> No deprecated search APIs<br/>
<strong>Guidance Source:</strong> Professional data engineering best practices</p>
<p><strong>Thank you for the excellent guidance on official data sources!</strong> πŸ™</p>
<p>This system now uses <strong>the exact sources recommended by data engineers</strong> to map the U.S. government landscape. 🦷✨</div><footer class="theme-doc-footer docusaurus-mt-lg"><div class="row margin-top--sm theme-doc-footer-edit-meta-row"><div class="col noPrint_WFHX"><a href=https://github.com/getcommunityone/open-navigator-for-engagement/tree/main/website/docs/data-sources/overview.md target=_blank rel="noopener noreferrer" class=theme-edit-this-page><svg fill=currentColor height=20 width=20 viewBox="0 0 40 40" class=iconEdit_Z9Sw aria-hidden=true><g><path d="m34.5 11.7l-3 3.1-6.3-6.3 3.1-3q0.5-0.5 1.2-0.5t1.1 0.5l3.9 3.9q0.5 0.4 0.5 1.1t-0.5 1.2z m-29.5 17.1l18.4-18.5 6.3 6.3-18.4 18.4h-6.3v-6.2z"/></g></svg>Edit this page</a></div><div class="col lastUpdated_JAkA"></div></div></footer></article><nav class="docusaurus-mt-lg pagination-nav" aria-label="Docs pages"><a class="pagination-nav__link pagination-nav__link--prev" href=/docs/for-advocates><div class=pagination-nav__sublabel>Previous</div><div class=pagination-nav__label>For Policy Makers & Advocates</div></a><a class="pagination-nav__link pagination-nav__link--next" href=/docs/data-sources/citations><div class=pagination-nav__sublabel>Next</div><div class=pagination-nav__label>Data and Citations</div></a></nav></div></div><div class="col col--3"><div class="tableOfContents_bqdL thin-scrollbar theme-doc-toc-desktop"><ul class="table-of-contents table-of-contents__left-border"><li><a href=#-data-scale--coverage class="table-of-contents__link toc-highlight">πŸ“Š Data Scale & Coverage</a><li><a href=#-data-source-categories class="table-of-contents__link toc-highlight">πŸ“‚ Data Source Categories</a><li><a href=#️-government-jurisdiction-data class="table-of-contents__link toc-highlight">πŸ›οΈ Government Jurisdiction Data</a><ul><li><a href=#1-cisa-gov-domain-master-list--most-authoritative class="table-of-contents__link toc-highlight">1. CISA .gov Domain Master List ⭐ <strong>Most Authoritative</strong></a><li><a href=#2-us-census-bureau---government-integrated-directory-gid class="table-of-contents__link toc-highlight">2. U.S. Census Bureau - Government Integrated Directory (GID)</a><li><a href=#3-nces-common-core-of-data-ccd class="table-of-contents__link toc-highlight">3. NCES Common Core of Data (CCD)</a></ul><li><a href=#-summary-table-where-to-pull-the-lists class="table-of-contents__link toc-highlight">πŸ“‹ Summary Table: Where to Pull the Lists</a><li><a href=#-scraping-strategy-based-on-your-guidance class="table-of-contents__link toc-highlight">πŸ” Scraping Strategy (Based on Your Guidance)</a><ul><li><a href=#step-1-ingest class="table-of-contents__link toc-highlight">Step 1: Ingest</a><li><a href=#step-2-filter class="table-of-contents__link toc-highlight">Step 2: Filter</a><li><a href=#step-3-crawl class="table-of-contents__link toc-highlight">Step 3: Crawl</a><li><a href=#step-4-keyword-hunt class="table-of-contents__link toc-highlight">Step 4: Keyword Hunt</a></ul><li><a href=#-non-gov-coverage class="table-of-contents__link toc-highlight">πŸš€ Non-.gov Coverage</a><li><a href=#-cost-0 class="table-of-contents__link toc-highlight">πŸ’° Cost: $0</a><li><a href=#-references class="table-of-contents__link toc-highlight">πŸ“š References</a><li><a href=#-credits class="table-of-contents__link toc-highlight">βœ… Credits</a></ul></div></div></div></div></main></div></div></div><footer class="theme-layout-footer footer footer--dark"><div class="container container-fluid"><div class="row footer__links"><div class="theme-layout-footer-column col footer__col"><div class=footer__title>Documentation</div><ul class="footer__items clean-list"><li class=footer__item><a class=footer__link-item href=/docs/intro>Getting Started</a><li class=footer__item><a class=footer__link-item href=/docs/data-sources/citations>Citations & Data Sources</a><li class=footer__item><a class=footer__link-item href=/docs/data-sources/overview>Data Sources</a><li class=footer__item><a class=footer__link-item href=/docs/for-developers>For Developers</a></ul></div><div class="theme-layout-footer-column col footer__col"><div class=footer__title>Resources</div><ul class="footer__items clean-list"><li class=footer__item><a href=https://www.communityone.com target=_blank rel="noopener noreferrer" class=footer__link-item>Launch Open Navigator<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a><li class=footer__item><a href=https://github.com/getcommunityone/open-navigator-for-engagement target=_blank rel="noopener noreferrer" class=footer__link-item>GitHub<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a><li class=footer__item><a href=https://www.groundvue.org/ target=_blank rel="noopener noreferrer" class=footer__link-item>GroundVue (Partner)<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a></ul></div><div class="theme-layout-footer-column col footer__col"><div class=footer__title>Community</div><ul class="footer__items clean-list"><li class=footer__item><a href=https://www.instagram.com/getcommunityone/ target=_blank rel="noopener noreferrer" class=footer__link-item>Instagram<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a><li class=footer__item><a href=https://www.facebook.com/getcommunityone target=_blank rel="noopener noreferrer" class=footer__link-item>Facebook<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a><li class=footer__item><a href=https://x.com/getcommunityone/ target=_blank rel="noopener noreferrer" class=footer__link-item>X (Twitter)<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a><li class=footer__item><a href=https://www.linkedin.com/company/getcommunityone target=_blank rel="noopener noreferrer" class=footer__link-item>LinkedIn<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a><li class=footer__item><a href=https://www.youtube.com/@getcommunityone target=_blank rel="noopener noreferrer" class=footer__link-item>YouTube<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a><li class=footer__item><a href=https://discord.gg/uH6Dytek target=_blank rel="noopener noreferrer" class=footer__link-item>Discord<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a></ul></div><div class="theme-layout-footer-column col footer__col"><div class=footer__title>Legal</div><ul class="footer__items clean-list"><li class=footer__item><a class=footer__link-item href=/docs/legal/privacy-policy>Privacy Policy</a><li class=footer__item><a class=footer__link-item href=/docs/legal/terms-of-service>Terms of Service</a><li class=footer__item><a class=footer__link-item href=/docs/legal/data-provider-terms>Data Provider Terms</a></ul></div><div class="theme-layout-footer-column col footer__col"><div class=footer__title>More</div><ul class="footer__items clean-list"><li class=footer__item><a class=footer__link-item href=/blog>Blog</a><li class=footer__item><a href=https://github.com/getcommunityone/open-navigator-for-engagement/blob/main/LICENSE target=_blank rel="noopener noreferrer" class=footer__link-item>License (MIT)<svg width=13.5 height=13.5 aria-label="(opens in new tab)" class=iconExternalLink_nPIU><use href=#theme-svg-external-link /></svg></a></ul></div></div><div class="footer__bottom text--center"><div class=footer__copyright>Copyright Β© 2026 Community One. Built with Docusaurus.</div></div></div></footer></div></body>