Merge pull request #4 from Triwoods2333/main

download_npm

download_npm.ipynb

@@ -0,0 +1,137 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "e:\\anaconda\\envs\\jut_env\\lib\\site-packages\\scipy\\__init__.py:146: UserWarning: A NumPy version >=1.16.5 and <1.23.0 is required for this version of SciPy (detected version 1.23.5\n",
+      "  warnings.warn(f\"A NumPy version >={np_minversion} and <{np_maxversion}\"\n"
+     ]
+    }
+   ],
+   "source": [
+    "import pandas as pd\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "import warnings\n",
+    "warnings.filterwarnings('ignore')\n",
+    "pd.set_option('display.max_columns', None)\n",
+    "pd.set_option('display.max_rows', None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>Package Repository</th>\n",
+       "      <th>Package Name</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>NPM</td>\n",
+       "      <td>URIjs-1.16.1</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "  Package Repository  Package Name\n",
+       "0                NPM  URIjs-1.16.1"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "# 数据读取\n",
+    "df = pd.read_excel('Labelled_Dataset.xlsx',sheet_name=0)\n",
+    "# 取前5行查看数据\n",
+    "df = df.iloc[:1,1:3]\n",
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "URIjs 1.16.1\n"
+     ]
+    }
+   ],
+   "source": [
+    "import subprocess\n",
+    "import os\n",
+    "\n",
+    "# 更新 PATH 环境变量\n",
+    "os.environ['PATH'] += os.pathsep + 'D:/nodejs'\n",
+    "\n",
+    "# 遍历每一行\n",
+    "for index, row in df.iterrows():\n",
+    "    package_name = row['Package Name']\n",
+    "    # 分割包名和版本号\n",
+    "    name, version = package_name.split('-')\n",
+    "    print(name, version)\n",
+    "    # 使用npm命令行工具下载包\n",
+    "    subprocess.run(['D:/nodejs/npm.cmd', 'pack', f'{name}@{version}'], cwd=r'F:\\git_workspace\\malicious_samples-features-identification\\npm_download')\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "jut_env",
+   "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": "3.9.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}