Gainsight/Scripts/all_default_class_names.py

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

# from collections import Iterable

# MASDICT = {'file': "", 'attributes' : { 'id': [], 'class': [] } }
pp = pprint.PrettyPrinter(indent=4)
MASDICT = {}
MASLIST = {}
PARS = HTMLParser


def main():
    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)
        strpfile = file.split("/")[7]
        htmlfile = open(file, "r", encoding="utf-8")
        file2 = open(file, "r", encoding="utf-8")
        code = file2.readlines()
        liq = [liquid for liquid in code if re.search('{{(.*)}}', liquid)]
        quidlist = []
        for quid in liq:
            liqcludes = quid.strip()
            liqclude = re.search('{{(.*)}}', liqcludes)
            quidlist.append(liqclude.group(0))
        inclst = [include for include in code if "{% include" in include]
        inclist = []
        for item in inclst:
            includes = item.strip().split(" ")[2].replace('"','')
            inclist.append(includes)

        soup = BeautifulSoup(htmlfile, "html.parser")
        clst = [node["class"] for node in soup.find_all() if node.has_attr("class")]
        flatclass = flatten(clst)
        flatclass = [it for it in flatclass if "np" in it]
        ilst = [node["id"] for node in soup.find_all() if node.has_attr("id")]
        flatid = flatten(ilst)

        MASLIST.update({strpfile: {"includes": inclist,"liquid": quidlist, "class": flatclass, "id": flatid}})
        MASDICT = {"data": MASLIST}
    # pp.pprint(MASDICT)
    to_pandas(MASDICT)


def flatten(xs):
    # Initialize list for this layer
    flat_list = []
    for x in xs:
        # If it's a list, recurse down and return the interior list
        if isinstance(x, list):
            flat_list += flatten(x)
        # Otherwise, add to this layer's list
        else:
            flat_list.append(x)
    return flat_list

def to_pandas(obj):
    # df = pd.json_normalize(obj)
    # df = pd.DataFrame(obj['data'])
    results = obj['data']
    df = pd.DataFrame.from_dict(results, orient='index')
    df = df.reset_index().rename(columns={"index": "filename"})
    print(df)
    df.to_csv('/Users/normrasmussen/Downloads/example_liquid.csv')

if __name__ == "__main__":
    main()