Features of the API
Article Text Extraction
Easily extract the main text of an article and key information such as author, publish date with a simple API call.
Classify your English text using our Wikipedia based model trained on over 1 million articles and blog entries.
Named Entity Recognition
Our 100+ million entity database is updated regularly to include the latest worldly names and concepts.
Language detection can be tricky. We can detect the language of short sentences and long text alike in over 100 languages.
Text Extraction and Mining for your Applications
Ujeebu helps your applications process human text
Q :There are several Open source tools that do text extraction, why go with the Ujeebu Extractor?
A : Yes, but not on all sites. Only the ones where we deem it necessary. The user however can always override our automatic JS detection and tell us whether to run JS or not.
Q :How much does your service cost?
A : We offer some of the most competitive pricing plans on the market. Get started now with our free plan.
Q :What is the average parsing time of a URL?
A : Parsing time of a URL depends on several factors, namely the load on the server hosting the article, the length of the article in question, and whether JS execution is needed. We do however provide several customization parameters in the API to let you fine tune the parsing process to your liking in order to reduce the parsing time. We also cache results on our end for quicker requests.
Ujeebu was born out of a lack of affordable enterprise grade tools for clean text extraction and analysis.
Who We Are
- A team of passionate Software Engineers with diverse backgrounds including Machine Learning, Computer Vision, Software engineering and API development.
- We are a self-funded private company with no external funding. If you are interested in investing let's talk
Try out Ujeebu
Enter a URL in the box below