what tools or languages or How can i build the site like google news

I have to build the website where i need to crawl to filter or u can say re开发者_运维技巧ad the 50 webistes. then after reading those webistes i need to filter the news e,g news related to Mercedez benz and then i need to display that on that webiste with refrence to original source.

Basically what google news is doing

Currently i know PHP and can build complex websites in that. But i have no idea about how to read other websites. and i don't know how to proceed , i mean which things i need to learn before attempting to make site. or i can dive the site straight way.

Please help , how should i proceed

I believe Google News (like a lot of Google stuff;-) is in a mixture of C++, Java, and Python, plus Javascript on the front-most part too -- but there's no reason you should use all or even any of these excellent languages (well, you will want Javascript if you need highly interactive user experience with your site, of course;-); just about any language makes it easy to do web crawling. For example, for a web crawler in PHP, see this tutorial!