In [2]:
import os
import shutil

In [6]:
file_path = "/home/daniel/nltk_data/corpora/"
#print(len(os.listdir(file_path)))
corpora_actual = [x for x in os.listdir(file_path) if x[-4:] != '.zip']
print(len(corpora_actual))

corpora_zips = [x[:-4] for x in os.listdir(file_path) if x[-4:] == '.zip']
#print((corpora_zips))
difference = list(set(corpora_zips) - set(corpora_actual))
print(difference)
#shutil.rmtree(file_path + corpora[0])
#print(os.listdir(file_path))

#shutil.copyfile('/home/daniel/nltk_data (copy)/corpora/' + corpora[0], file_path + corpora[0])
#print(os.listdir(file_path))


83
[]

In [74]:
print(corpora_actual[0])
shutil.rmtree(file_path + corpora_actual[0])


subjectivity

In [36]:
#shutil.copyfile(copy_file_path + difference[0], file_path + difference[0])

In [4]:
import zipfile
for file in difference:
    zip_ref = zipfile.ZipFile(file_path + file + ".zip", 'r')
    zip_ref.extractall(file_path)
zip_ref.close()

In [ ]: