log2ml/Elasticsearch.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "eda4ddbf-c146-45b5-8a40-b9ac90f1465f",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Elasticsearch \n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f8747542-a2d1-4814-8dc2-acf172db2d0c",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import requests\n",
    "import pandas as pd\n",
    "\n",
    "# Elasticsearch base URL\n",
    "base_url = \"http://192.168.20.106:9200\"\n",
    "# Index name\n",
    "index = \"winlogbeat-*\"\n",
    "\n",
    "# Initial search request to start scrolling\n",
    "initial_response = requests.post(\n",
    "    f\"{base_url}/{index}/_search?scroll=1m\",\n",
    "    json={\n",
    "        \"size\": 10000,  # Adjust the size as per your requirement\n",
    "        \"query\": {\"match_all\": {}}\n",
    "    }\n",
    ").json()\n",
    "\n",
    "# Extract scroll ID from the initial response\n",
    "scroll_id = initial_response[\"_scroll_id\"]\n",
    "\n",
    "# Process initial batch of documents\n",
    "hits = initial_response[\"hits\"][\"hits\"]\n",
    "data = [hit[\"_source\"] for hit in hits]\n",
    "\n",
    "# Track total documents retrieved\n",
    "total_documents_retrieved = len(data)\n",
    "print(f\"Retrieved {total_documents_retrieved} documents.\")\n",
    "\n",
    "# Loop to fetch subsequent batches of documents until no more documents are left\n",
    "while hits:\n",
    "    # Fetch next batch of documents using scroll API\n",
    "    response = requests.post(\n",
    "        f\"{base_url}/_search/scroll\",\n",
    "        json={\"scroll\": \"1m\", \"scroll_id\": scroll_id}\n",
    "    ).json()\n",
    "    \n",
    "    # Extract scroll ID from the response\n",
    "    scroll_id = response[\"_scroll_id\"]\n",
    "    \n",
    "    # Process batch of documents\n",
    "    hits = response[\"hits\"][\"hits\"]\n",
    "    \n",
    "    # If no hits, break out of the loop\n",
    "    if not hits:\n",
    "        break\n",
    "    \n",
    "    # Extend data with new batch of documents\n",
    "    data.extend([hit[\"_source\"] for hit in hits])\n",
    "    \n",
    "    # Update total documents retrieved\n",
    "    total_documents_retrieved += len(hits)\n",
    "    print(f\"Retrieved {total_documents_retrieved} documents.\")\n",
    "\n",
    "# Convert data to pandas DataFrame\n",
    "df = pd.DataFrame(data)\n",
    "\n",
    "# Display DataFrame\n",
    "print(df)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "deb60f70-f62d-4802-8928-5ea18bbc7b3e",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "df.to_json(\"lab_logs_normal_activity_may_6_2024.json\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9faae732-f464-4d11-924e-aeba4f293def",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}