repurposed chrome extension download and extraction script

ChromeExtensionDownload.py

#!/usr/bin/python3
# -*- coding: utf-8 -*-

"""
Python Script to download the Chrome Extensions (CRX) file directly from the google chrome web store.
Referred from http://chrome-extension-downloader.com/how-does-it-work.php
"""


import argparse
import requests
import urllib.parse
import sys
import os
import fnmatch
import zipfile

__author__ = 'arul'


class ChromeAppDownloader():
    CRX_URL = "https://clients2.google.com/service/update2/crx?" \
              "response=redirect&prodversion=38.0&x=id%3D~~~~%26installsource%3Dondemand%26uc"
    USER_AGENT = "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.111 Safari/537.36"
    global headers
    headers = {
        "User-Agent": USER_AGENT,
        "Referer": "https://chrome.google.com",
    }

    def __init__(self):
        pass

    def download(self, _download_url_, _file_name_):
        """
        Download the given URL into given filename.
        :param _download_url_:
        :param _file_name_:
        :return:
        """
        try:
            # Download as Stream
            r = requests.get(url=_download_url_, headers=headers, stream=True)
            redirects = r.history
            if len(redirects) > 0:
                redirect_header = redirects[-1].headers
                if "location" in redirect_header:
                    loc = redirect_header["location"]
                    uparse = urllib.parse.urlparse(loc)
                    splits = uparse.path.split("/")
                    _fname_ = splits[-1]

            if _fname_:
                _file_name_ = _fname_.replace("extension", _file_name_)
            else:
                _file_name_ += ".crx"

            chunk_size = 16 * 1024
            dowloaded_bytes = 0
            with open(_file_name_, 'wb') as fd:
                for chunk in r.iter_content(chunk_size):
                    fd.write(chunk)

            return _file_name_
        except Exception as e:
            raise ValueError("Error in downloading %s " % _download_url_, e)

    def parse(self, chrome_store_url):
        """
        Validate the given input is chrome store URL or not.
        Returning app ID and app Name from the URL
        :param chrome_store_url:
        :return:
        """
        try:
            # Try to validate the URL
            uparse = urllib.parse.urlparse(chrome_store_url)
            if uparse.netloc != "chrome.google.com":
                raise ValueError("Not a valid URL %s" % chrome_store_url)
            splits = uparse.path.split("/")
            if not (len(splits) == 4 and uparse.path.startswith("/webstore/detail/")):
                raise ValueError("Not a valid URL %s" % chrome_store_url)
        except Exception as e:
            pass

        return splits[-1], splits[-2]


if __name__ == '__main__':
    # Getting webstore URL from User
    parser = argparse.ArgumentParser(description='Download CRX file from Google Chrome Webstore.')
    parser.add_argument('-u', '--url', help='URL of the chrome store', required=True)
    args = parser.parse_args()

    downloader = ChromeAppDownloader()
    try:
        file_name = None
        # Validating and building app ID, file name for the given URL
        chrome_app_id, file_name = downloader.parse(chrome_store_url=args.url)
        if chrome_app_id:
            download_url = downloader.CRX_URL.replace("~~~~", chrome_app_id)
            # Downloading the CRX file
            extension_file = downloader.download(download_url, file_name)
            
            # Grab downloaded .crx, strip first 307 bytes and write to zip removing crx file
            f = open(extension_file, 'rb')
            f.seek(307) # skip first x bytes
            zipcontent = f.read()
            zip_name = extension_file.replace("crx", "zip")
            open(zip_name, "wb").write(zipcontent)
            os.remove(extension_file)

            # extract content
            zip_path = zip_name.replace(".zip", "")
            with zipfile.ZipFile(zip_name, 'r') as zip_ref:
                zip_ref.extractall(zip_path)

    except Exception as e:
        print(e)