def test_get_optimal_subset_by_percent_words(self): # takes about 1.2 seconds
with open('sample_text.txt', encoding="utf8") as text_file:
# Load text
sample_text = str(text_file.read())
# Remove unwanted text in the essay. ie '(fr)'
sample_text = sample_text.replace('(fr) ', '')
# Load document class
summarizer = Summarizer(text=sample_text)
# Find summary with 25% words
val, summary = summarizer.get_optimal_subset_by_percent_words(.25, ret_as="str")
# Write out summary
with open('output.txt', 'w+') as w_file:
w_file.write(summary)
subj, text = body_from_website(copied_text.lower())
if text == '':
if len(copied_text) > 100:
text = copied_text
subj = ''
else:
print(f'Invalid Input: {copied_text}')
input('Press enter to continue...')
sys.exit()
else:
print(f'Loading text from: {copied_text}')
document = Summarizer(text)
_, summary = document.get_optimal_subset_by_percent_words(.15,
ret_as='str')
# Generate response
response_body = 'Title: ' + subj + '\n\n'
if len(summary) != 0:
response_body += summary
else:
response_body += 'Text Too Short'
response_body += '\n\n--------------\n\n'
print(response_body)
loc = 'output.txt'
with open(loc, "w") as output_file:
output_file.write(str(response_body))
