advanced data scraping, processing and mining

I'm looking to have a solution built to scrape information from a few sites (all on the same platform and so have the exact same layout/structure). The problem is a big part of the text is unstructed/free text (it's short biographies/profiles of clients) I then want to store all of this in google sheets and send the content scraped from one particular field via API from google sheets to thompson reuters free "open calais" tool and send the results back to google sheets. This will label all the geographic place names in the unstructured text. then, using regex, I want to process this labeled text to find the most likely current location for the people who details have been scraped. In many cases there will be more than one location listed, for example "john smithe was born in new york city, but now lives in seattle", we need to use regex to find the location that is preceded by words like "lives in" or "resides in", etc to find the current location. I then want [login to view URL] to take the processed data which now has the following in separate columns: "first name", "family name", "city" and [login to view URL] will need to login to a phone directory site that I have an account with, search using the first name, family name and city and find all the possible phone numbers for each person and return those back to the google sheet in a new column. the end result: I have a google sheet with populated columns for first name, family name, city, phone number for customers whose data could not be scraped, processed and searched using the system above which I can do manually.