# Website / Domain Categorization API for Node.js Website / Domain Categorization API is a Node.js module that uses machine learning model to classify arbitrary blocks of input texts or URLs into content categories. We return categorizations of URLS for the following taxonomies: IAB, version 3, with 4 Tiers (taxonomy from Internet Advertising Bureau - IAB, with members including top global companies - Ford, IBM, Unilever, etc.) (703 categories) IAB, version 2, with 4 Tiers (taxonomy from Internet Advertising Bureau - IAB, with members including top global companies - Procter & Gamble, General Motors, etc.) (698 categories) IPTC NewsCodes, especially suitable for News Categorization (used by the world's largest news agencies, such as Associated Press, Reuters, BBC, News York Times) (1124 categories) Web Content Filtering Taxonomy (44 categories) Google Shopping Taxonomy, used by millions of online retailers (5474 categories) Shopify Taxonomy, used by millions of online stores (10560 categories) Amazon Taxonomy (39004 categories) We also return the following classifications / enriched data about each URL: Detection of Malware/Social Engineering/Mailicious Software Web Technologies used Likely Buyer Personas Topics Key Entities Named Sentiment Analysis Similar companies / Competitors Similar domains Tags Keywords # Installation ``` npm i @websitecategorization/websitecategorization ``` # Usage example ``` var myHeaders = new Headers(); myHeaders.append("Content-Type", "application/x-www-form-urlencoded"); var urlencoded = new URLSearchParams(); urlencoded.append("query", "www.alpha-quantum.com"); urlencoded.append("api_key", "your_api_key"); urlencoded.append("data_type", "url"); var requestOptions = { method: 'POST', headers: myHeaders, body: urlencoded, redirect: 'follow' }; fetch("https://www.websitecategorizationapi.com/api/iab/iab_web_content_filtering.php", requestOptions) .then(response => response.text()) .then(result => console.log(result)) .catch(error => console.log('error', error)); ``` # Use cases Web Categorization API is used by a wide variety of companies for many different use cases. It is suitable for Ad Exchanges, Demand Side Platforms (DSPs), Supply Side Platforms (SSPs) and Ad Networks. SSP (Supply Side Platform) companies can e.g. use it to identify the advertiser’s category to check its eligibility for real-time bidding. Other use cases include Web Content Filtering where a company can employ it to filter out non-work related websites, such as social media networks, shopping platforms and similar. [Website / Domain categorization API](https://www.websitecategorizationapi.com) is based on a machine learning model that has been extensively tested and used both in small and large scale classification projects, including on a project with 30+ million texts. It is continuously developed and regularly updated (in terms of training data set) to reflect and include new verticals arising each year. ## Our other services Schools, libraries, and enterprises subject to CIPA or acceptable-use regulations need a reliable way to classify domains before traffic reaches end users. A [enterprise web filtering](https://www.webfilteringdatabase.com) database lets IT teams load 100 million pre-categorized domains directly into DNS resolvers, firewalls, or proxy servers without relying on external API calls at query time. The database ships with 59 content categories covering adult content, malware, gambling, social media, streaming, and other policy-relevant verticals. Bulk updates are published regularly so filtering rules stay current as new domains appear. We also provide an [Anonymization API](https://www.anonymizationapi.com) for privacy-preserving media and data workflows. For K-12 environments where web categorization feeds directly into student-safety workflows, the Children's Internet Protection Act (CIPA) requires schools and libraries receiving E-Rate funding to filter harmful online content — the [FCC's CIPA compliance guide](https://www.fcc.gov/consumers/guides/childrens-internet-protection-act) details the federal requirements, and the [American Library Association's CIPA resource page](https://www.ala.org/advocacy/advleg/federallegislation/cipa) provides implementation guidance for institutions navigating the law. Our [web filtering for schools](https://www.cipawebfiltering.com) database delivers 120 million domains classified across 57+ categories specifically aligned to these CIPA requirements — covering obscene content, child exploitation material, and content harmful to minors as defined in the statute, plus granular AI-tool categories that generic taxonomies miss. The database integrates directly with DNS resolvers, proxy servers, and firewall appliances used in school and library networks, enabling IT administrators to enforce internet safety policies without routing traffic through external services. Security teams can further harden their filtering stack with a [phishing threat intelligence feed](https://www.phishingdetectionapi.com) that tracks 390,000+ DNS-verified active phishing sites and exposes them through a single REST endpoint. The [Anti-Phishing Working Group (APWG)](https://apwg.org/trendsreports/) reports that phishing attacks continue to reach record volumes, and [CISA's phishing guidance](https://www.cisa.gov/secure-our-world/recognize-and-report-phishing) recommends layered defenses including domain-level blocking as a frontline measure. Our phishing detection service makes it straightforward to block credential-harvesting pages at the DNS or proxy layer, with every domain in the dataset DNS-verified to confirm it is actively serving malicious content. Combining content classification with phishing intelligence ensures that both policy enforcement and threat prevention operate from the same up-to-date domain data. # Machine Learning Models for Website Classification Text classification is usually automated as it is often used on use cases where the number of texts needed to be classified number in millions. For this reason, we use machine learning models for text classifications. In early period of machine learning, the most common models used for text classification were ranging from simpler ones, like Naive Bayes to more complex ones like Random Forests, Support Vector Machines and Logistic Regression. Support Vector Machines are especially good in terms of accuracy and f1 scores achieved on text classification tasks, they however have a downside in that the complexity of training a SVM model rapidly increases with number of texts in training dataset. In last decade, with the rise of neural networks, more text classification models are based on the latter. Earlier deep neural networks for text classification were often based on LSTM neural net. In recent times there have been other neural network architectures successfuly used for general text and product classification models. Authors in this highly cited paper: [https://arxiv.org/pdf/1803.01271.pdf](https://arxiv.org/pdf/1803.01271.pdf) researched convolutional neural networks for text classification and came to conclusion that even a simple convolutional architecture outperforms canonical recurrent networks such as the previously mentioned LSTMs, across different classification tasks. The NN model from the paper can be accessed here: [https://github.com/locuslab/TCN](https://github.com/philipperemy/keras-tcn), with keras implementation available at [https://github.com/philipperemy/keras-tcn](https://github.com/philipperemy/keras-tcn). # Product categorization AI In addition to our website categorization, we also provide Product categorization AI, which returns categories from around 10k Shopify categories and attributes for products. You can see the new Shopify categories here: [https://github.com/Shopify/product-taxonomy/blob/main/dist/en/categories.txt](https://github.com/Shopify/product-taxonomy/blob/main/dist/en/categories.txt) Also very interesting are the attributes of products which are returned with [ Product categorization AI](https://www.productcategorization.com) . # Feature engineering When using texts as input to machine learning models, we need to convert them in a numerical format. This is part of the feature engineering process, which can also include other steps, e.g. lemmatization, removal of stop words, removal of punctuations, etc. Once these pre-processing is done, we can use different approaches in converting texts to numerical representation. One of the simplest one is Bag of Words, where we simply count the number of times a word has occured in text. A more complex, "count" method is TF-IDF or term frequence-inverse document frequency. In this case we count the number of times a token,word, term has occured in a document but "correct" this for its frequency in the whole corpus. In this way, common words like "the" are discounted because they occur commonly in the whole corpus, whereas words that are specific to some document but are not often found elsewhere are not corrected by much of a factor. A more advanced form of feature engineering includes using shallow neural nets for representation of texts. One approach from this group is Word2Vec where we represent each word with fixed-dimensional vector. Vectors of words are "learned" by training the shallow neural network of Word2Vec on a large corpus of documents with the main idea being that words that are semantically similar should be located near in the hyperspace of words vectors. A well known example is that arithmetic operation of vector("King") - vector("Queen") should be a very similar vector to the vector obtained with vector("Man") - vector("Woman"). The most well known Word2Vec model is the one trained on Google News corpus and can be accessed at [https://huggingface.co/fse/word2vec-google-news-300](https://huggingface.co/fse/word2vec-google-news-300). There also implementation available in many NLP libraries, e.g. in spacy: [https://spacy.io/usage/embeddings-transformers](https://spacy.io/usage/embeddings-transformers). These word embedding and sentence embedding approaches can be especially useful when developing text and product classification models. # Other services URL categorization is a foundational task in Natural Language Processing (NLP), often leveraged to improve content filtering and security; see this [Stanford NLP lecture](https://web.stanford.edu/class/cs224n/) for further reading. A comprehensive [list of categorized domains](https://www.urlcategorizationdatabase.com) is essential for training and evaluating models in real-world web data scenarios. AI-powered tools are revolutionizing contract analysis, automating risk detection and clause extraction—learn more in this [MIT CSAIL legal AI overview](https://www.csail.mit.edu/research/artificial-intelligence-law). Accessing reliable business information is easier with APIs; Harvard’s [OpenCorporates API research](https://dataverse.harvard.edu/dataset.xhtml?persistentId=doi:10.7910/DVN/EUS6OY) demonstrates the impact on data-driven applications. By combining these tools, organizations can automate due diligence processes while reducing manual workloads—see the [Carnegie Mellon NLP Group](https://lti.cs.cmu.edu/) for recent research. These innovations highlight the intersection of NLP, legal technology, and business intelligence, paving the way for smarter enterprise solutions. An important part of feature engineering is the use of article extractors. You can read more about them in this article on [how to do website categorization](https://medium.com/website-categorization/website-categorization-api-ca6c3e0f6c4d). # Machine learning interpretability / explainability (XAI) Machine learning models are increasingly influencing decisions in our everyday lives. Their predictions or classifications are often though inscrutable in the sense that they act as "black boxes" where it is not exactly known how did they reach results. This has led to the rise of so-called artificial intelligence explainability (XAI) or the desire for interpretability of machine learning model decisions, in a form, that humans can understand. The ability of explaining decisions is increasingly seen as an important part of building trust in AI and this is increasingly being demanded by regulators as well. “Right to Explanation” has thus become one of the key features of the GDPR regulation. Similar requirements in the Equal Credit Opportunity Act (ECOA) and the Fair Credit Reporting Act (FCRA). The website categorization service is one of the few services of this kind which has integrated explainability to its results. Each categorization is thus provided with explanation for it. Example:  # Form of json Example output from IAB1 Website Categorization API on example domain: ``` { "classification": [ { "category": "Style & Fashion", "value": 0.6335134346543948 }, { "category": "Religion & Spirituality", "value": 0.31965677636420087 }, { "category": "Events and Attractions", "value": 0.028203161466589827 }, { "category": "Pop Culture", "value": 0.008486557302356994 }, { "category": "Books and Literature", "value": 0.0028975322143729425 }, { "category": "Shopping", "value": 0.0014989265842864407 }, { "category": "Fine Art", "value": 0.0014698938766846063 }, { "category": "Family and Relationships", "value": 0.0008695569530150543 }, { "category": "Hobbies & Interests", "value": 0.0007021051093678122 }, { "category": "Travel", "value": 0.00045551400716377827 }, { "category": "Movies", "value": 0.0003105774008160576 }, { "category": "Television", "value": 0.0002812439624312471 }, { "category": "Healthy Living", "value": 0.00027001968240167887 }, { "category": "Careers", "value": 0.0002666186301324818 }, { "category": "Food & Drink", "value": 0.0002460227720972317 }, { "category": "Home & Garden", "value": 0.00021331353597162862 }, { "category": "Medical Health", "value": 0.00018344636503169902 }, { "category": "Music and Audio", "value": 0.00007348860474246987 }, { "category": "Video Gaming", "value": 0.00006822010822593386 }, { "category": "Real Estate", "value": 0.00006517844821148466 }, { "category": "Pets", "value": 0.00006069812911973799 }, { "category": "Education", "value": 0.00004860296854985923 }, { "category": "News and Politics", "value": 0.000035123587801619264 }, { "category": "Sports", "value": 0.00003402965849228489 }, { "category": "Science", "value": 0.000026461875107857055 }, { "category": "Automotive", "value": 0.000024825949895016523 }, { "category": "Personal Finance", "value": 0.00001581204114251354 }, { "category": "Technology & Computing", "value": 0.000015037047929356491 }, { "category": "Business and Finance", "value": 0.000007820699466562138 } ], "language": "en" } ``` # Curl Supported API calls (in curl) that can be adapted to javascript: ``` curl --location --request POST 'https://www.websitecategorizationapi.com/api/iab/gpt_category1.php' \ --header 'Content-Type: application/x-www-form-urlencoded' \ --data-urlencode 'query=polaroid land camera' \ --data-urlencode 'api_key=b4dcde2ce5fb2d0b887b5e' curl --location --request POST 'https://www.websitecategorizationapi.com/api/iab/gpt_category2.php' \ --header 'Content-Type: application/x-www-form-urlencoded' \ --data-urlencode 'query=polaroid land camera' \ --data-urlencode 'api_key=b4dcde2ce5fb2d0b887b5e' curl --location --request POST 'https://www.websitecategorizationapi.com/api/gpt_new1/gpt_category3.php' \ --header 'Content-Type: application/x-www-form-urlencoded' \ --data-urlencode 'query=polaroid land camera' \ --data-urlencode 'api_key=b4dcde2ce5fb2d0b887b5e' curl --location --request POST 'https://www.websitecategorizationapi.com/api/iab/gpt_category1.php' \ --header 'Content-Type: application/x-www-form-urlencoded' \ --data-urlencode 'query=credit card' \ --data-urlencode 'api_key=b4dcde2ce5fb2d0b887b5e' curl --location --request POST 'https://www.websitecategorizationapi.com/api/iab/gpt_category2.php' \ --header 'Content-Type: application/x-www-form-urlencoded' \ --data-urlencode 'query=credit card' \ --data-urlencode 'api_key=b4dcde2ce5fb2d0b887b5e' ``` # UI Dashboard Website categorization service can be used both as API or in form of dashboard UI, as seen here:  # Support for languages Service supports website categorization of texts written in german, french, italian, spanish, portuguese and many other languages. # Useful resources - IAB taxonomy: [https://iabtechlab.com/press-releases/tech-lab-releases-content-taxonomy-3-0/](https://iabtechlab.com/press-releases/tech-lab-releases-content-taxonomy-3-0/) - Facebook Taxonomy: [https://www.facebook.com/business/help/526764014610932?id=725943027795860](https://www.facebook.com/business/help/526764014610932?id=725943027795860) - [Introduction to Website Categorization](https://www.alpha-quantum.com/blog/website-categorization/website-categorization-api/) - Survey of text classification models: [https://github.com/kk7nc/Text_Classification](https://github.com/kk7nc/Text_Classification) - [Text and product classification models](https://medium.com/product-categorization/product-categorization-introduction-d62bb92e8515) A fast-growing filtering requirement in 2026 is controlling employee and student access to AI applications. As highlighted by the [NIST AI Risk Management Framework](https://www.nist.gov/artificial-intelligence), organizations need structured governance over which AI tools employees and students interact with, and the [OECD AI Policy Observatory](https://oecd.ai/en/) tracks how governments worldwide are drafting regulations that mandate such controls. Our [AI domain blocklist](https://www.aitoolsblocklist.com) provides tens of thousands of classified AI-tool domains — chatbots, code assistants, image and video generators, voice cloners — refreshed daily and organized into functional categories, so acceptable-use policies can distinguish an approved AI tutor from a deepfake generator. The blocklist separates AI services into granular functional categories (conversational AI, code generation, image synthesis, voice cloning, AI companions) so administrators can write per-category rules rather than blanket bans. It ships in the same CSV/API formats as this package and drops into DNS resolvers, proxies, and NGFW rules. # Package available on: - [https://www.npmjs.com/package/websitecategorization](https://www.npmjs.com/package/websitecategorization) - [https://npmmirror.com/package/websitecategorization](https://npmmirror.com/package/websitecategorization) - [https://yarnpkg.com/package/websitecategorization](https://yarnpkg.com/package/websitecategorization) - [https://www.npmtrends.com/websitecategorization](https://www.npmtrends.com/websitecategorization) - [https://libraries.io/npm/@websitecategorization%2Fwebsitecategorization](https://libraries.io/npm/@websitecategorization%2Fwebsitecategorization) - [https://openbase.com/js/websitecategorization/documentation](https://openbase.com/js/websitecategorization/documentation) - [https://openhub.net/p/websitecategorizationapi](https://openhub.net/p/websitecategorizationapi) - [https://socket.dev/npm/package/websitecategorization/overview](https://socket.dev/npm/package/websitecategorization/overview) - [https://www.jsdelivr.com/package/npm/websitecategorization](https://www.jsdelivr.com/package/npm/websitecategorization) - [https://www.npmjs.com/package/cipawebfiltering](https://www.npmjs.com/package/cipawebfiltering) — CIPA web filtering database client for schools and libraries - [https://www.aitoolsblocklist.com](https://www.aitoolsblocklist.com) — AI tools blocklist for web filtering and acceptable-use enforcement