is in Beta. No guarantees, no promises.

We use Open Calais in some projects where we parse the text of a web page to get some semantic information about it. They have a new service called Semantic Proxy, where you can pass just a url of a web page and it will look for the text for you. Great! However it is in Beta…

I passed the White October home page to it just for fun…see if you can spot what is wrong in this picture…or do they know something that we don’t!

Reblog this post [with Zemanta]


  1. Posted 9 October 2008 at 1:13 pm | Permalink

    Tom Tague from Calais here.

    Well, if the Girls Brigade is anything like the Girl Scouts here in the States – during cookie selling time of the year they can certainly look like a polished military organization.

    As you probably know SemanticProxy was really designed to deal with a content rich page like a news article or Wikipedia entry. Though there will always be some error rate associated with automated metadata generation – we’re releasing enhancements each month to both improve existing capabilities and implement new features.

    In the meantime – when they ask you to buy cookies – Buy. The. Cookies.

  2. Posted 9 October 2008 at 1:32 pm | Permalink

    Hi Tom,

    It was the first url that came to me when I was doing a quick show and tell in the office, but later on I tried a few others and was very impressed.

    The grabbing quotes was excellent. I used this page and it got at least 3 quotes.

    Parsing relevant text from a page is always difficult, so we would always use Calais direct but for say legacy or for sites you don’t have control of it is useful. Saves us doing the text parsing!

Post a Comment

Your email address is never published nor shared. Required fields are marked *

Ready to talk?

Whether you want to create a new digital product or make an existing one even better, we'd love to talk it through.

Get in touch