def main():
filename = "gutenbergscifi.csv"
json_filename = "gendered_words.json"
if os.path.isfile(filename):
print "file exists"
else:
write_csv = extract_text_urls(filename)
print "file created"
book_list = open_csv(filename)
print book_list
for i, value in enumerate(book_list):
#print i, value
a = int(book_list[i][2]) # a = book number
print i, a
author = book_list[i][0]
title = book_list[i][1]
try:
text = strip_headers(load_etext(a)).strip()
except ValueError:
pass
#print text
clean_text = remove_punc_html(text)
ratio = gender_ratio(clean_text)
print author, title, ratio
uber_key = author
sub_key = title
sub_value = ratio
uber_value = {author: {title:ratio}}
json_source = read_write_json_object(json_filename="gendered_words.json", uber_key=uber_key, uber_value=uber_value, sub_key=sub_key, sub_value=sub_value, READ=False, WRITE=True)
def test_gender_ration(self):
ratio = gender_ratio(self.text)
self.assertEqual(ratio, 2)
self.assertEqual(ratio, 2.0)
self.assertEqual(type(ratio), type(1.0))
def test_printing_gender_ratio(clean_text):
clean_text = remove_punc_html(text)
return gender_ratio(clean_text)
