Gainsight/Scripts/all_default_class_names.py

import re
from html.parser import HTMLParser
from pathlib import Path
# import pandas as pd
from bs4 import BeautifulSoup

# MASDICT = {'file': "", 'attributes' : { 'id': [], 'class': [] } }
MASLIST = []
PARS = HTMLParser
p = Path('/Users/normrasmussen/Documents/Work/Custom_Templates/current_templates_2-15-2024/')
x = list(p.glob('**/*.html.liquid'))
for posfile in x:
    file = str(posfile)
    htmlfile = open(file, 'r', encoding='utf-8')
    file2 = open(file, 'r', encoding='utf-8')
    # finfile = file.split('/')[-1]
    code = file2.readlines()
    inclst = [include for include in code if '{% include' in include]
    print(inclst)
    for lines in code:
        if '{% include' in lines:
            pass

    soup = BeautifulSoup(htmlfile, 'html.parser')
    clst = [node['class'] for node in soup.find_all() if node.has_attr('class')]
    # print(clst)
    ilst = [node['id'] for node in soup.find_all() if node.has_attr('id')]
    # print(ilst)

    # ids = []
    # classes = []
    #     if "class=" in lines:
    #         tmpline = lines
    #         if "id=" not in tmpline:
    #             try:
    #                 htmlclass = re.search('class="(.*)"', tmpline)
    #                 classes.append(htmlclass.group(1))
    #             except AttributeError as t:
    #                 print("Class: ", t)
    #                 pass
    #             finally:
    #                 pass
    #     elif "id=" in lines:
    #         try:
    #             id = re.search('id="(.*)"', lines)
    #             ids.append(id.group(1))
    #         except AttributeError as t:
    #             print("ID: ", t)
    #             pass
    #         finally:
    #             pass
    #     else:
    #         pass
    # seconddict = { 'file': finfile, 'attributes': { 'id' : ids, 'class': classes } }
    # MASLIST.append(seconddict)
    #
# df = pd.json_normalize(MASLIST)
# print(df)
# kp = (df.set_index('file').apply(lambda x: x.str.split(",").explode()).reset_index())
# ksp = df.set_index('file').apply(lambda x: df['attributes.class']([x.split(',') ]))
# print(ksp)
# kp2 = (df.set_index('file').apply(lambda x: x.str.split(" ").explode('attributes.class')).reset_index())
# print(kp2)