h5ai-scraper.py

from bs4 import BeautifulSoup
from urllib import request
import json 
HOST = ""

folder_arr = []

json_build = {}

def loop_child(path,object):
    resp = request.urlopen(HOST+path)
    soup = BeautifulSoup(resp, features="html.parser")
    el = soup.select("#fallback > table > tr > td.fb-n > a")
    object["files"] = []
    for i in el:
        if i["href"].endswith("/"):
            object[i.text] = {}
            # print(json_build) # just to know if the script is running and what is collected
            loop_child(i.attrs["href"],object[i.text])
        else:
            if "Parent Directory" not in i.text:
                object["files"].append(i.text)
    if object["files"] == []:
        del object["files"]

        
loop_child("/",json_build)
print("--------------------\n\n\n")
#final product
print(json.dumps(json_build,indent=2))