'''
2021-06-04
Transformed Specific HTML Pages to Raw Text
    [Redacted] & ----- (meaning the same) throughout

If I knew grep, sed, or similar,
    I'd probably would have used instead.

# # #

Created on Mar 11, 2018
@author: Brett Paufler
Copyright Brett Paufler

ONE SHOT: CAN KILL

This is quite possibly a throw-away
    Rip Text from [Redacted] HTML
    Save as txt file
    
Takes a HTML
    isolates [Redacted] text
    returns txt
'''

import re
from os import listdir

begin = '''<pre class="-----" id="-----"><span id="------1">'''
end = '''</span></pre>'''

pattern = re.compile(
    '%s(.*?)%s' % (begin, end),
    re.IGNORECASE | re.DOTALL)
    
for file_in in listdir('.\\input'):
    print file_in
    file_out = file_in[:-4] + 'txt'
    save_name = '.\\output\\' + file_out
    print file_out
    print save_name

    with open('.\\input\\' + file_in) as f:
        text = f.read()
    
    print text
    text = section_list = re.findall(
        pattern, text)[0]
    print text
    with open(save_name, 'w') as f:
        f.write(text)