Intention recognition from website data -- 2

We need some talents to help us to extract some investors' intention from their website. We have gathered their website content into TXT file and already removed the web code. Each page is one file, the structure example, 1 1.1 1.1.1 1.1.1.1 home 1.1.1.2 about us 1.1.1.3 our team 2 2.1 2.1.1xxxx The numbers is just for keeping the content structure from the original webpage. So they can be ignored. Data resource: All the website is the official website of some investors. Such as investment bank, investor company, capital management company, Law firm focused on finance industry. Goal: We want to extract the investment intention for each company. Such as, [login to view URL] preference (the industry they focused on or interested in, usually they will mention in their self-desciption, or the industry of the case they did is the preference) [login to view URL] preference (The location they are interested to invest. The same as the industry preference) [login to view URL] preference (range, example: 1million - 100million ) [login to view URL] preference (seed round, round A, B, C....) 5. (optional)case they did (the company they have invested) Candidate requirement We need some expert who has good experience of same or similar project. We will ask for proof. It can be a demo program, or video of program, or any other way. The price is still negotiable. We will negotiate base on how accurate you can reach.