Enrich Search Engines tools batch 3/4 (THE-153)

Populated enrichment metadata for 25 tools across Academic/Publication
Search, News Search, Other Search, and Search Tools subsections.

Status breakdown: 17 live, 5 down/deprecated, 3 freemium.
Deprecated: YouGotTheNews, NewsBrief (EMM), Hubii, EntityCube,
FindTheData (acquired by Amazon/Graphiq).

Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
s0lray
2026-03-28 21:09:26 -04:00
co-authored by Paperclip
parent 8cd1259c13
commit 982c602df9
+400 -25
View File
@@ -14350,17 +14350,62 @@
{
"name": "The Open Syllabus Project",
"type": "url",
"url": "https://www.opensyllabus.org/"
"url": "https://www.opensyllabus.org/",
"description": "Searchable database of 7 million+ university course syllabi revealing what texts, authors, and topics are assigned across institutions worldwide.",
"status": "live",
"pricing": "free",
"bestFor": "Identifying commonly used academic texts and tracking curricula connections between subjects",
"input": "Keywords, author names, or book titles",
"output": "Syllabus records showing courses, institutions, co-assignment frequency, and publication details",
"opsec": "passive",
"opsecNote": "Queries a public database of aggregated syllabus data; no contact with individuals or institutions.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": true,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "Science Publications",
"type": "url",
"url": "https://www.thescipub.com/"
"url": "https://www.thescipub.com/",
"description": "Open-access scientific journal publisher offering peer-reviewed articles across science, technology, engineering, and social science disciplines.",
"status": "live",
"pricing": "free",
"bestFor": "Finding open-access academic publications across scientific disciplines",
"input": "Keywords, journal names, or author names",
"output": "Full-text articles, journal listings, and academic bibliographic metadata",
"opsec": "passive",
"opsecNote": "Accesses publicly available open-access publications without exposing investigator identity.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": true,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "arXiv.org",
"type": "url",
"url": "https://arxiv.org/"
"url": "https://arxiv.org/",
"description": "Open-access preprint repository hosting 2.4+ million academic papers in physics, mathematics, computer science, and related fields before formal publication.",
"status": "live",
"pricing": "free",
"bestFor": "Finding preprint and early-release academic papers in technical fields",
"input": "Keywords, author names, subject categories, or arXiv IDs",
"output": "Full-text preprints with metadata, version history, and cross-linked related works",
"opsec": "passive",
"opsecNote": "Searches a public database of submitted preprints; queries are logged by arXiv.",
"localInstall": false,
"googleDork": true,
"registration": false,
"editUrl": true,
"api": true,
"invitationOnly": false,
"deprecated": false
}
]
},
@@ -14371,67 +14416,262 @@
{
"name": "Google News Search",
"type": "url",
"url": "https://news.google.com/news/advanced_news_search?"
"url": "https://news.google.com/news/advanced_news_search?",
"description": "Google's aggregated news service indexing articles from thousands of publishers globally with topic-based organization and real-time search.",
"status": "live",
"pricing": "free",
"bestFor": "Real-time and recent news discovery by topic, entity, or keyword across thousands of publishers",
"input": "Keywords, names, organizations, or topics",
"output": "Grouped news articles with source attribution, timestamp, and snippet",
"opsec": "passive",
"opsecNote": "Searches a public news index; queries are logged by Google and tied to account if signed in.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": true,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "Flipboard",
"type": "url",
"url": "https://flipboard.com/"
"url": "https://flipboard.com/",
"description": "Content curation platform aggregating news and articles from publishers and social sources into personalized topic-based digital magazines.",
"status": "live",
"pricing": "freemium",
"bestFor": "Discovering curated topic collections and tracking how stories spread across multiple sources",
"input": "Topics, keywords, publisher names, or people",
"output": "Curated article collections with source attribution and publication metadata",
"opsec": "passive",
"opsecNote": "Browses publicly indexed content; account creation reveals interests to Flipboard.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "YouGotTheNews",
"type": "url",
"url": "https://yougotthenews.com/"
"url": "https://yougotthenews.com/",
"description": "Real-time social news discovery service that aggregated trending news based on social sharing activity. The service is no longer operational.",
"status": "down",
"pricing": "free",
"bestFor": "Social news trend discovery (service discontinued)",
"input": "N/A",
"output": "N/A",
"opsec": "passive",
"opsecNote": "Service is no longer operational.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": true
},
{
"name": "NewspaperARCHIVE.com",
"type": "url",
"url": "https://newspaperarchive.com/"
"url": "https://newspaperarchive.com/",
"description": "Historical newspaper archive with 760 million+ pages of digitized newspapers spanning over 400 years from the US and internationally.",
"status": "live",
"pricing": "freemium",
"bestFor": "Historical records research, obituaries, legal notices, and archived news content verification",
"input": "Names, keywords, dates, location, and publication filters",
"output": "Scanned newspaper pages with OCR-indexed text, metadata, and clipping tools",
"opsec": "passive",
"opsecNote": "Accesses historical newspaper archives; limited free access requires account creation for full results.",
"localInstall": false,
"googleDork": false,
"registration": true,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "PressReader.com",
"type": "url",
"url": "https://www.pressreader.com/"
"url": "https://www.pressreader.com/",
"description": "Digital newsstand providing access to 7,000+ newspapers and magazines in full-layout format from 100+ countries and multiple languages.",
"status": "live",
"pricing": "freemium",
"bestFor": "Accessing full-format digital editions of international newspapers and magazines for OSINT research",
"input": "Publication name, country, or language",
"output": "Full-layout digital newspaper and magazine issues with integrated text search",
"opsec": "passive",
"opsecNote": "Requires account; many public library cards provide free full access. Direct subscription is paid.",
"localInstall": false,
"googleDork": false,
"registration": true,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "Newspaper Map",
"type": "url",
"url": "https://newspapermap.com/"
"url": "https://newspapermap.com/",
"description": "Interactive geographic map displaying newspapers by location, enabling discovery of regional and local publications worldwide with links to their archives.",
"status": "live",
"pricing": "free",
"bestFor": "Discovering regional and local newspapers by geographic location for place-specific research",
"input": "Geographic location on map or place name search",
"output": "Newspaper listings with publication details, language, and links to digitized archives",
"opsec": "passive",
"opsecNote": "Navigates a public geographic newspaper directory; no contact with target publications.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "NewsBrief",
"type": "url",
"url": "https://emm.newsbrief.eu/NewsBrief/clusteredition/en/latest.html"
"url": "https://emm.newsbrief.eu/NewsBrief/clusteredition/en/latest.html",
"description": "European Commission media monitoring service that tracked and clustered multilingual news articles from thousands of sources. The service has been discontinued.",
"status": "down",
"pricing": "free",
"bestFor": "Multilingual European news monitoring and event clustering (service discontinued)",
"input": "N/A",
"output": "N/A",
"opsec": "passive",
"opsecNote": "Service is no longer operational.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": true
},
{
"name": "AllYouCanRead.com",
"type": "url",
"url": "https://www.allyoucanread.com/"
"url": "https://www.allyoucanread.com/",
"description": "Directory of 25,000+ online newspapers, magazines, and news publications from 200+ countries, organized by region, language, and category.",
"status": "live",
"pricing": "free",
"bestFor": "Discovering international news publications by country, language, or media type",
"input": "Country, region, language, or publication category",
"output": "Directory listings with publication names, language, and direct links",
"opsec": "passive",
"opsecNote": "Navigates a public publication directory; no contact with individual news organizations.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "World News",
"type": "url",
"url": "https://wn.com/#/search"
"url": "https://wn.com/#/search",
"description": "Multilingual global news aggregator indexing articles from thousands of sources across 200+ countries with real-time search.",
"status": "live",
"pricing": "free",
"bestFor": "Searching global news coverage across multiple languages and geographic regions",
"input": "Keywords, names, or topics",
"output": "Aggregated news articles with source, language, and publication date",
"opsec": "passive",
"opsecNote": "Searches a public global news index; queries are logged by the service.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": true,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "NewsNow.co.uk",
"type": "url",
"url": "https://www.newsnow.co.uk/h/"
"url": "https://www.newsnow.co.uk/h/",
"description": "UK-based independent news aggregator providing real-time headlines from thousands of publishers, organized by topic and region.",
"status": "live",
"pricing": "free",
"bestFor": "Real-time news monitoring by topic with broad international publication coverage",
"input": "Keywords or topic categories",
"output": "Aggregated headlines with source, timestamp, and article links",
"opsec": "passive",
"opsecNote": "Searches a public news aggregation index; queries are logged by the service.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": true,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "Hubii",
"type": "url",
"url": "https://hubii.com/"
"url": "https://hubii.com/",
"description": "Norwegian content distribution and monetization platform connecting publishers and creators. OSINT utility is limited; service appears inactive.",
"status": "down",
"pricing": "freemium",
"bestFor": "Content publisher discovery (limited OSINT applicability)",
"input": "N/A",
"output": "N/A",
"opsec": "passive",
"opsecNote": "Service appears to be inactive or repurposed.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": true
},
{
"name": "Inshorts",
"type": "url",
"url": "https://inshorts.com/en/read"
"url": "https://inshorts.com/en/read",
"description": "Indian news aggregator delivering 60-word summaries of major news stories covering politics, business, sports, and entertainment.",
"status": "live",
"pricing": "free",
"bestFor": "Quick news digest and tracking coverage of Indian and international events in brief format",
"input": "Topic categories or keyword search",
"output": "60-word news summaries with source attribution and link to full article",
"opsec": "passive",
"opsecNote": "Accesses publicly summarized news content; no investigator identity is exposed to target sources.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "NewsBot",
"type": "url",
"url": "https://getnewsbot.com/"
"url": "https://getnewsbot.com/",
"description": "Automated news delivery service providing personalized news briefings and alerts via messaging platforms and bot integrations.",
"status": "live",
"pricing": "free",
"bestFor": "Automated news monitoring and delivery through messaging platform integrations",
"input": "Topics, keywords, or source selections",
"output": "Scheduled news briefings delivered to messaging platforms",
"opsec": "passive",
"opsecNote": "Queries news sources on behalf of the user; account and topic preferences are logged by the service.",
"localInstall": false,
"googleDork": false,
"registration": true,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
}
]
},
@@ -14442,22 +14682,82 @@
{
"name": "Colossus International Engine List",
"type": "url",
"url": "https://www.searchenginecolossus.com/"
"url": "https://www.searchenginecolossus.com/",
"description": "Comprehensive directory of 2,100+ search engines organized by country, language, and specialty for discovering regional and niche search tools.",
"status": "live",
"pricing": "free",
"bestFor": "Discovering country-specific and niche search engines for targeted regional intelligence gathering",
"input": "Country filter, language selection, or category browsing",
"output": "Directory of search engines with brief descriptions and direct links",
"opsec": "passive",
"opsecNote": "Navigates a public search engine directory; no queries are made to listed engines.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "Zenodo",
"type": "url",
"url": "https://zenodo.org/"
"url": "https://zenodo.org/",
"description": "Open research repository hosted by CERN and OpenAIRE accepting research outputs across all disciplines including papers, datasets, software, and presentations.",
"status": "live",
"pricing": "free",
"bestFor": "Finding research datasets, preprints, and supplementary materials not indexed by traditional academic databases",
"input": "Keywords, author names, DOI, or research community",
"output": "Research records with metadata, file downloads, and citation information",
"opsec": "passive",
"opsecNote": "Searches a public open-access repository; queries are logged by Zenodo/CERN.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": true,
"api": true,
"invitationOnly": false,
"deprecated": false
},
{
"name": "EntityCube",
"type": "url",
"url": "https://entitycube.research.microsoft.com/"
"url": "https://entitycube.research.microsoft.com/",
"description": "Microsoft Research entity-based search engine that aggregated facts about people and organizations from web sources. The service has been discontinued.",
"status": "down",
"pricing": "free",
"bestFor": "Entity-centric person and organization research (service discontinued)",
"input": "N/A",
"output": "N/A",
"opsec": "passive",
"opsecNote": "Service is no longer operational.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": true
},
{
"name": "FindTheData A Research Engine",
"type": "url",
"url": "https://www.findthedata.com/"
"url": "https://www.findthedata.com/",
"description": "Structured data search engine that enabled comparison and discovery across datasets in categories including people, places, and statistics. Service acquired and no longer operational.",
"status": "down",
"pricing": "free",
"bestFor": "Structured data search and comparison (service discontinued)",
"input": "N/A",
"output": "N/A",
"opsec": "passive",
"opsecNote": "Service was acquired by Amazon/Graphiq and is no longer operational.",
"localInstall": false,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": true
}
]
},
@@ -14468,27 +14768,102 @@
{
"name": "wayparam",
"type": "url",
"url": "https://github.com/aleff-github/wayparam"
"url": "https://github.com/aleff-github/wayparam",
"description": "Python tool that extracts historical URL parameters for a target domain using the Wayback Machine CDX API to reveal hidden endpoints and parameter patterns.",
"status": "live",
"pricing": "free",
"bestFor": "Discovering historical URL parameters and endpoint patterns for web application OSINT",
"input": "Target domain name",
"output": "List of URL parameters extracted from archived Wayback Machine snapshots of the target domain",
"opsec": "passive",
"opsecNote": "Queries the Wayback Machine archive rather than the live target; target does not see the requests.",
"localInstall": true,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "SearchDiggity (T)",
"type": "url",
"url": "https://bishopfox.com/resources"
"url": "https://bishopfox.com/resources",
"description": "Bishop Fox's Windows GUI tool for automating search engine dorking across Google, Bing, and other engines using custom dork lists against multiple targets.",
"status": "live",
"pricing": "free",
"bestFor": "Automated mass search engine dorking against multiple targets using custom vulnerability dork databases",
"input": "Target domains or IP ranges with dork templates",
"output": "Search results matching vulnerability patterns, exposed files, and configuration data",
"opsec": "passive",
"opsecNote": "Uses search engines as proxies; queries appear as normal search traffic but are logged by the engine.",
"localInstall": true,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "Scanner-inurlbr (T)",
"type": "url",
"url": "https://github.com/googleinurl/SCANNER-INURLBR"
"url": "https://github.com/googleinurl/SCANNER-INURLBR",
"description": "PHP-based scanner automating Google and Bing dork searches to discover vulnerabilities, CMS fingerprints, and sensitive data exposed in URLs.",
"status": "live",
"pricing": "free",
"bestFor": "Automated vulnerability discovery and OSINT reconnaissance through search engine dorking",
"input": "Dork query templates and target URL patterns",
"output": "Matching URLs with vulnerability indicators, server information, and HTTP response data",
"opsec": "active",
"opsecNote": "Sends automated search requests that may trigger rate limiting; also makes direct requests to discovered target URLs.",
"localInstall": true,
"googleDork": false,
"registration": false,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "Google Alerts",
"type": "url",
"url": "https://www.google.com/alerts"
"url": "https://www.google.com/alerts",
"description": "Google's web monitoring service that sends email notifications when new content matching specified search terms is indexed by Google.",
"status": "live",
"pricing": "free",
"bestFor": "Passive long-term monitoring of web mentions for names, organizations, or topics over time",
"input": "Search terms, keywords, names, or phrases",
"output": "Email digests with matching article URLs, snippets, and source publication dates",
"opsec": "passive",
"opsecNote": "Alert configuration requires a Google account; monitored terms and alert history are stored by Google.",
"localInstall": false,
"googleDork": false,
"registration": true,
"editUrl": false,
"api": false,
"invitationOnly": false,
"deprecated": false
},
{
"name": "Google Custom Search Engine",
"type": "url",
"url": "https://cse.google.com/cse/"
"url": "https://cse.google.com/cse/",
"description": "Google's programmable search API enabling custom search engines scoped to specified domains, with JSON API access and free and paid tiers.",
"status": "live",
"pricing": "freemium",
"bestFor": "Building targeted search engines over specific site lists or topic domains for structured OSINT research",
"input": "Search queries scoped to selected domain lists or the full web",
"output": "Structured JSON search results or hosted search interface with source URLs and snippets",
"opsec": "passive",
"opsecNote": "API calls are logged by Google; free tier allows 100 queries/day.",
"localInstall": false,
"googleDork": false,
"registration": true,
"editUrl": false,
"api": true,
"invitationOnly": false,
"deprecated": false
},
{
"name": "pagodo - Passive Google Dork (T)",