html_to_json2

from lxml import html
from bs4 import BeautifulSoup
import json
import os


"""pip install bs4"""


def html2json2(path):
    #NB: Works for any html file that has 1414701776531394236.htm and 315022854031645383.htm format
    #NB: Works for any html file that has 5397124106352075058.htm and 1259815981046145990.htm format
    #NB path is the path to folder
    #NB The python script should be run in the folder where the html files are located

    qnums = []
    results = []
    container = []
    qnum = ''
    tank = []
    str_container = []

    for path_, dirs, files in os.walk(path):
        for file in files:
            if file.endswith("htm") or file.endswith("html"):
                with open(os.path.join(path_, file)) as f:
                    content = f.read()


            soup = BeautifulSoup(content, "html5lib")
            paras = soup.findAll("p", {"align":"JUSTIFY"})
            indexes = []

            a = [f"{x}." for x in range(1, 340)]
            b = [f"{x}" for x in range(1, 340)]

            for i,item in enumerate(paras):
                try:
                    if item.find("b").text.strip() in a or item.find("b").text.strip() in b:
                        indexes.append(i)

                except Exception as e:
                    pass


            for i,item in enumerate(indexes):
                try:
                    container.append(paras[indexes[i]:indexes[i+1]])
                except IndexError:
                    pass



            for item in container:
                for sub in item:
                    try:
                        if sub.find("b"):
                            content = sub.find("b").text.strip()
                    except:
                        pass
                qnums.append(content)

            str_container = [str(item).replace("[", "").replace('<p align="JUSTIFY">', "")
                                 .replace("</p>", "").replace(",", "")
                                 .replace("]", "").replace("IND", "NEL").strip() for item in container]


            for x in range(len(str_container)):
                obj = {"Question Number":"", "Correct Option":"", "Solution":""}
                obj["Question Number"] = qnums[x]
                obj["Correct Option"] = ""

                try:
                    obj["Solution"] = str_container[x]
                except IndexError:
                    pass

                results.append(obj)

            final = {"results":results}


            result_name = file.split(".")[0]

            #Saves result as json in the current working directory
            with open(f"{result_name}.json", "w") as f:
                json.dump(final, f)
            print("Done!")