52 lines
1.7 KiB
Python
52 lines
1.7 KiB
Python
|
import re
|
||
|
|
from html.parser import HTMLParser
|
||
|
|
from pathlib import Path
|
||
|
|
import pandas as pd
|
||
|
|
|
||
|
|
# 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')
|
||
|
|
finfile = file.split('/')[-1]
|
||
|
|
code = htmlfile.readlines()
|
||
|
|
ids = []
|
||
|
|
classes = []
|
||
|
|
for lines in code:
|
||
|
|
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)
|
||
|
|
|