extract text from simpsons_script_lines.csv

extract_text.py

data_dir = './data/simpsons_script_lines.csv'
input_file = os.path.join(data_dir)

clean_text = ''

with open(input_file, "r", encoding="utf8") as f:
    for line in f:
        text = re.search('[0-9]*,[0-9]*,[0-9]*,(.+?),[0-9]*,', line)
        if text:
            text = text.group(1).replace('"', '')
            text_parts = text.split(':')
            text_parts[0] = text_parts[0].replace(' ', '_')
            text = ':'.join(text_parts)
            clean_text += text + '\n'

print('\n'.join(clean_text.split('\n')[:10]))