Big Data Programmer/Scientist Needed Badly!!

I am looking for someone to help me take my news aggregation site to the next level. I have a large list of keywords and websites that I would like to use to gather all the news on a given subject matter each day (a test revealed this to be approx. 4,500 articles). I would like someone, first and foremost, to design a framework for collecting these articles. I would then like to run text analytics to determine what people and places* are mentioned in those 4,500 articles. I then need to be able to determine "source" articles. In other words, of those 4,500 stories, there are only several hundred original stories, the rest are simply "re-writes" by other publications. I would then like to create a system for taking the events referenced in those "source articles" and create a "timeline" of that event. This way, people can click on today's headline and read the story, but they can also read past headlines and get a quick understanding of what has happened. Finally, I need a simple way to view the "source stories", have the ability to select certain stories for the home page of my website, and edit the headline of that story as well. *A secondary piece to this project is finding some way to "scrape" the data for people and places. When someone clicks on a person or place mentioned in an article, I'd like them to get a small bio/map/picture of that person or place. There are encyclopedias of places and of world leaders across the web, I am hoping we can find that data somewhere there.