Extractiv enables automatic conversion of unstructured web content into structured semantic data. We combine a powerful web crawler with sophisticated text extraction tools to provide a service that can:
- Crawl millions of web pages and domains every hour
- Extract thousands of entities (people, places, and anything else) from any text (blogs, tweets, and more) on those pages
Using Extractiv is easy. Just take the following steps:
- Login to our Web Portal at http://portal.extractiv.com.
- Click on Create New Job.
- Customize your Extractiv job using the job form.
- Submit your job and wait for it to complete.
That’s all there is to it. When your job completes, you’ll get highly-structured semantic data that you can use in your own applications or business processes.
Extractiv can play a critical step in you or your company’s ability to discover, aggregate and utilize web content. Let’s take a few examples to show what’s possible:
Ad Network
Online ad networks need to know what kind of content exists on millions of different websites. They need to know if that content is suitable and relevant for their clients. With Extractiv, they can create a job that crawls to all of those websites and identifies any of the following content:
Celebrities
Consumer products
Etc
Etc.
Using the results from Extractiv, ad networks can quickly identify websites that should be included in their distribution channels and increase the value of those channels.
Financial Firms
If you’re in the business of investing, you’re probably constantly on the hunt for new information about companies, stocks and related data. Extractiv can help with this by automatically running a job every day, week or month for the latest financial events. With our upcoming API, you’ll be able to automatically dump any uncovered financial data into your own system.