Revert html parsing

import argparse

import re

import json

from os import path

from pathlib import Path

import glob

    here = Path(__file__).parent.resolve()

    with open(input,'r') as infile:

        report = infile.read()

    cmds_enc=[]

    cmds_dec=[]

    cmds_rend=[]

    cmds_isar_post_rend=[]

        # Depending on pytest-html version, the data may be in a json-blob. If so, the code below should handle this format.

    if path.isdir(input):

        input = Path(input).rglob('*.html')

    else:

        input = [input]

    for html_report in input:

        with open(html_report,'r') as infile:

            for line in infile.readlines():

                    cmds_enc.extend(re.findall(r"DUT encoder command:\\n\\t(.*?)\\n", line))

                    cmds_dec.extend(re.findall(r"DUT decoder command:\\n\\t(.*?)\\n", line))

                    cmds_rend.extend(re.findall(r"Running command\\n(.*?)\\n", line))

                    cmds_isar_post_rend.extend(re.findall(r"Running ISAR post renderer command\\n(.*?)\\n", line))

    # If pytest-html < v4 is used, the parsing will fail and render empty lists. This is a work-around in case that happens.

    if all(not x for x in [cmds_enc, cmds_dec, cmds_rend, cmds_isar_post_rend]):

            lines = re.split(r'\\n', report)

        for html_report in input:

            with open(html_report,'r') as infile:

                enc_cmd = False

                dec_cmd = False

                rend_cmd = False

                isar_post_rend_cmd = False

            for line in lines:

                line = line.split("<br/>")[0].replace('\\t','') # Remove trailing html tags

                for line in infile.readlines():

                    line = line.split("<br/>")[0] # Remove trailing html tags

                    if enc_cmd:

                        cmds_enc.append(line)

                        enc_cmd = False

                        cmds_isar_post_rend.append(line)

                        isar_post_rend_cmd = False                        

                    else:

                    if "REF encoder command" in line:

                        if "DUT encoder command" in line:

                            enc_cmd = True

                    elif "REF decoder command" in line:

                        elif "DUT decoder command" in line:

                            dec_cmd = True

                        elif "Running command" in line:

                            rend_cmd = True                             

                        elif "Running ISAR post renderer command" in line:

                            isar_post_rend_cmd = True                            

    # If the above reading failed, try this variant instead.

    if all(not x for x in [cmds_enc, cmds_dec, cmds_rend, cmds_isar_post_rend]):

        with open(input,'r') as infile:

            for line in infile.readlines():

                    cmds_enc.extend(re.findall(r"DUT encoder command:\\n\\t(.*?)\\n", line))

                    cmds_dec.extend(re.findall(r"DUT decoder command:\\n\\t(.*?)\\n", line))

                    cmds_rend.extend(re.findall(r"Running command\\n(.*?)\\n", line))

                    cmds_isar_post_rend.extend(re.findall(r"Running ISAR post renderer command\\n(.*?)\\n", line))

    # Remove trailing HTML tags, if any

    cmds_rend = [x.split('<')[0] for x in cmds_rend]

    cmds_isar_post_rend = [x.split('<')[0] for x in cmds_isar_post_rend]

    # Sort lists to keep deterministic order between runs

    cmds_enc.sort()

    cmds_dec.sort()