Amazon_ReviewText.py

import gzip
import sys
import logging
print("BEGIN NOTEBOOK")
print("OPENING GZIP FILE")
#sys.stdout.write()
with gzip.open ('/mnt/data/rajiv/AmazonProductReviewDataset/all.txt.gz' , 'rt') as f:
     file_content = f.read()
            
print("FILE READ")
## LIST OF SEPERATED SENTENCES
b = str(file_content).split('review/text')
texts = " "
for i in range(len(b)):
    if i == 0:
        continue
    texts = texts + '\n' +  b[i].split('\\n')[0]
    
with open('/home/rajivratn/laiba/AmazonReviews/Amazon_Reviews_Seperated.txt', 'w') as f:
        f.write(texts)
        
print("FILE WRITTEN")