Simple CSS class extraction script from HTML file

get_classes_from_html.py

"""
Usage: get_classes_from_html.py path/to/file.html
"""

def convert_html_to_string(html_file_path):
    html_file = open(html_file_path, 'r')
    return html_file.read()


def get_css_classes(html_string, attribute='class'):
    # TODO: Add dynamic attribute finding, agnostic quote types
    # TODO: split up multiple classes
    class_list = html_string.split('class="')
    class_list.pop(0)  # first item will not be in list due to split
    for index, class_block in enumerate(class_list):
        trim_index = class_block.find('"')
        class_list[index] = ''.join(['.', class_block[0:trim_index], ' {\n}\n'])
    return class_list


import sys 

if __name__ == "__main__":
    html_file_path = sys.argv[1]
    html_string = convert_html_to_string(html_file_path)
    css_classes = get_css_classes(html_string)
    for css_class in css_classes:
        print css_class