Python中集合A - 集B的计算

I have 2 files: File A contains 11746774 tweets and File B contains 704060 tweets. I want to calculate the tweets that are not present in File A - File B i.e. 1174674 - 704060 = 470614. PFB program. MatchWise-Tweets.zip contains the list of 49 files where tweets are stored in 49 separate files. Intention is to fetch the file-names and pass each of the file-names to get the list of tweets present in each of the 49 files. I have 2 files: File A contains 11746774 tweets