Kumar

import os
from bs4 import BeautifulSoup
import json


def read_html(path):
	tank = []
	c=0
	indexes = []
	htmls = []
	files = os.listdir(path)
	for file in files:
		if file.endswith("html") or file.endswith("htm"):
			htmls.append(file)

	with open(htmls[0]) as f:
		container = f.read()


	soup = BeautifulSoup(container, "html.parser")
	paras = soup.findAll("p", {"align":"JUSTIFY"})

	content = str(paras)
	target = content.split("\n")

	for i, item in enumerate(target):
		if "Sol" in item:
			indexes.append(int(i))

	for i, item in enumerate(indexes):
		current = i
		next = i+1
		try:
			tank.append(target[indexes[current]:indexes[next]])
		except IndexError:
			pass

		tank = [str(item).replace('p align="JUSTIFY"', "br").replace(",", " ").replace('<p align="CENTER"', "").replace("[", "").replace("]", "").replace("</p>", "") for item in tank]

	print(tank)