digital-forensics-lab/AI4Forensics/CKIM2024/BrowserHistory/browser_proprocess.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Extracted 241 titles and stored them in titles.txt\n"
     ]
    }
   ],
   "source": [
    "import json\n",
    "\n",
    "# Define the input and output file names\n",
    "input_file = 'Chrome\\History.json'\n",
    "output_file = 'titles.txt'\n",
    "\n",
    "# Read the JSON data from the input file\n",
    "with open(input_file, 'r') as file:\n",
    "    data = json.load(file)\n",
    "\n",
    "# Extract titles from the JSON data\n",
    "titles = [entry['title'] for entry in data.get('Browser History', [])]\n",
    "\n",
    "# Write the extracted titles to the output file\n",
    "with open(output_file, 'w') as file:\n",
    "    for title in titles:\n",
    "        if len(title.strip()) != 0:\n",
    "            file.write(f\"{title}\\n\")\n",
    "\n",
    "print(f\"Extracted {len(titles)} titles and stored them in {output_file}\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2024-03-13 11:57:15\n"
     ]
    }
   ],
   "source": [
    "from datetime import datetime\n",
    "\n",
    "\n",
    "def convert_time_usec_to_readable(time_usec):\n",
    "    # Convert microseconds to seconds\n",
    "    time_seconds = time_usec / 1000000\n",
    "\n",
    "    # Convert Unix timestamp to a datetime object\n",
    "    dt_object = datetime.fromtimestamp(time_seconds)\n",
    "\n",
    "    # Format the datetime object to a readable string\n",
    "    readable_time = dt_object.strftime(\"%Y-%m-%d %H:%M:%S\")\n",
    "\n",
    "    return readable_time\n",
    "\n",
    "\n",
    "# Example time_usec value\n",
    "time_usec = 1710345435804090\n",
    "print(convert_time_usec_to_readable(time_usec))  # Output: '2024-05-22 14:37:15'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Extracted 241 titles and stored them along with timestamp in titles_with_timestamp.txt\n"
     ]
    }
   ],
   "source": [
    "import json\n",
    "from datetime import datetime\n",
    "\n",
    "# Define the input and output file names\n",
    "input_file = \"Chrome\\History.json\"\n",
    "output_file = \"titles_with_timestamp.txt\"\n",
    "\n",
    "# Read the JSON data from the input file\n",
    "with open(input_file, \"r\") as file:\n",
    "    data = json.load(file)\n",
    "\n",
    "# Extract titles from the JSON data\n",
    "entries = [\n",
    "    (entry[\"title\"], entry[\"time_usec\"]) for entry in data.get(\"Browser History\", [])\n",
    "]\n",
    "\n",
    "\n",
    "# Write the extracted titles with timestamp to the output file\n",
    "with open(output_file, \"w\") as file:\n",
    "    for title, time_usec in entries:\n",
    "        if len(title.strip()) != 0:\n",
    "            readable_timestamp = convert_time_usec_to_readable(time_usec)\n",
    "            file.write(f\"{readable_timestamp}: {title}\\n\")\n",
    "\n",
    "print(\n",
    "    f\"Extracted {len(titles)} titles and stored them along with timestamp in {output_file}\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "torch2",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}