mht2html/main.py

import base64
import os
import platform
import re


class Convertor:
    def __init__(self):
        self.mht_file_path = None
        self.output_folder = None
        self.clear_console = None
        self.mht_file_size = None
        self.mht_file = None
        self.boundary = None
        if self.prepare():
            self.convert()
        self.mht_file.close()

    def prepare(self):
        if platform.system() == 'Windows':
            self.clear_console = lambda: os.system('cls')
        else:
            self.clear_console = lambda: os.system('clear')

        self.clear_console()
        print('======mht2html======\n' +
              'A mht file convertor\n' +
              'by kdxcxs(cx@kdxcxs.com)\n')

        while True:
            self.mht_file_path = input('[#] Please entry the path to the mht file to be converted\n===>')
            try:
                self.mht_file = open(self.mht_file_path, 'r', encoding='utf8')
                self.mht_file_size = os.stat(self.mht_file_path).st_size
                break
            except FileNotFoundError:
                print('[!] No such file')
                continue
        self.output_folder = input('[#] Please entry the path to the output folder\n===>')
        if not os.path.isdir(self.output_folder):
            os.makedirs(self.output_folder)
        if self.output_folder[-1] != os.sep:
            self.output_folder += os.sep
        return True

    def convert(self):
        print('[#] Start converting')

        # header
        if not self.analyse_header(self.read_mht_file()):
            return

        # content
        while self.mht_file.readable():
            if self.analyse_content(self.read_mht_file()):
                continue
            break

    def print_progress(self):
        print('[#] %.3f%% converted' % (self.mht_file.tell() / self.mht_file_size * 100), end='\r')

    def read_mht_file(self):
        header_mode = False
        if self.mht_file.tell() == 0:
            header_mode = True
        file_content = ''

        if not header_mode:
            while self.mht_file.readable():
                if self.mht_file.readline() == f'--{self.boundary}\n':
                    self.print_progress()
                    break
                self.print_progress()
                continue

        while self.mht_file.readable():
            line = self.mht_file.readline()
            self.print_progress()
            if line == '\n':
                if header_mode:
                    break
                header_mode = True  # if it's the first time to read the file we just need one '\n' to finish to get
            file_content += line  # the file's header,or we need to wait the second '\n' to get both header and content

        return file_content

    def analyse_header(self, header):
        if 'boundary' not in header:
            print('[!] Not a mht file')
            return False
        # find boundary
        boundary_re = re.search('boundary=".*"', header)
        self.boundary = header[boundary_re.span()[0] + 10: boundary_re.span()[1] - 1]
        return True

    def analyse_content(self, content):
        # only support text and base64 image file
        # TODO:support other file formats
        header, content = content.split('\n\n')
        header = header.replace(' ', '')
        header = header.split('\n')
        for i in range(len(header)):
            header.extend(header.pop(0).split(':'))
        get_header = lambda key_name: header[header.index(key_name) + 1]
        if get_header('Content-Type') == 'text/html':
            with open(f'{self.output_folder}index.html', 'w', encoding='utf8') as htmlf:
                htmlf.write(content)
            return True
        elif get_header('Content-Type').split('/')[0] == 'image':
            with open(f'{self.output_folder}{get_header("Content-Location")}', 'wb') as imgf:
                imgf.write(base64.decodebytes(content.encode()))
            return True


if __name__ == '__main__':
    convertor = Convertor()