Skuid templates were changed on a demo. Williams-Sonoma improvements. Script was updated slightly.

This commit is contained in:
Norm Rasmussen
2024-10-15 17:02:33 -04:00
parent acb4e38d79
commit b3b6b4afea
4 changed files with 63 additions and 38 deletions

View File

@ -1,7 +1,8 @@
import re
from html.parser import HTMLParser
from pathlib import Path
import pandas as pd
# import pandas as pd
from bs4 import BeautifulSoup
# MASDICT = {'file': "", 'attributes' : { 'id': [], 'class': [] } }
MASLIST = []
@ -11,38 +12,50 @@ 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 = []
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 "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:
if '{% include' in lines:
pass
seconddict = { 'file': finfile, 'attributes': { 'id' : ids, 'class': classes } }
MASLIST.append(seconddict)
df = pd.json_normalize(MASLIST)
print(df)
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)