# this code is split in two parts:
# going through the description html files and gathering the interesting words in a json file;
# and going through the files again to replace words that also appear in the json with an a href version

import sys, os
import nltk
from nltk import word_tokenize
from nltk.util import trigrams

# text analysis
def analysis(file):
    # print("yes")
    file_trigrams = trigrams(content)
    print(file_trigrams)



# reading each individual html file
path = "static/files/"
for path, subdirs, files in os.walk(path):
    for name in files:
        if name.endswith('html'):
            file = os.path.join(path, name)
            with open(file) as f:
                content = f.read()
            analysis(content)