{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1894,1101.507\n",
      "https://media.britishmuseum.org/media/Repository/Documents/2014_10/6_14/c5015a41_782e_4eb7_badf_a3bc00f54f2c/preview_00426109_001.jpg\n",
      "Image downloaded successfully!\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/james/.virtualenvs/ArtifactClassification/lib/python3.10/site-packages/urllib3/connectionpool.py:1103: InsecureRequestWarning: Unverified HTTPS request is being made to host 'media.britishmuseum.org'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1903,1215.10\n",
      "https://media.britishmuseum.org/media/Repository/Documents/2014_10/15_13/532668b9_0af1_4402_8e13_a3c500e1907c/preview_00944260_001.jpg\n",
      "Image downloaded successfully!\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/james/.virtualenvs/ArtifactClassification/lib/python3.10/site-packages/urllib3/connectionpool.py:1103: InsecureRequestWarning: Unverified HTTPS request is being made to host 'media.britishmuseum.org'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#tls-warnings\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[9], line 27\u001b[0m\n\u001b[1;32m     25\u001b[0m         \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mFailed to download image. Status code:\u001b[39m\u001b[38;5;124m\"\u001b[39m, response\u001b[38;5;241m.\u001b[39mstatus_code)\n\u001b[1;32m     26\u001b[0m     \u001b[38;5;66;03m# wait 20 seconds\u001b[39;00m\n\u001b[0;32m---> 27\u001b[0m     \u001b[43mtime\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43msleep\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m20\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m     28\u001b[0m \u001b[38;5;66;03m# response = requests.get(url, headers=headers)\u001b[39;00m\n\u001b[1;32m     29\u001b[0m \n\u001b[1;32m     30\u001b[0m \u001b[38;5;66;03m# if response.status_code == 200:\u001b[39;00m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m     34\u001b[0m \u001b[38;5;66;03m# else:\u001b[39;00m\n\u001b[1;32m     35\u001b[0m \u001b[38;5;66;03m#     print(\"Failed to download image. Status code:\", response.status_code)\u001b[39;00m\n",
      "\u001b[0;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "import requests\n",
    "import pandas as pd\n",
    "import time\n",
    "\n",
    "url = \"http://media.britishmuseum.org/media/Repository/Documents/2020_2/25_11/8772f2ea_b08f_46cf_8af2_ab6c00c10b84/preview_DSC_0760.jpg\"\n",
    "headers = {\n",
    "    \"User-Agent\": \"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3\"\n",
    "}\n",
    "\n",
    "\n",
    "df = pd.read_csv(\"../data/raw/BM_csv_files/3000BC-AD500/europe_999BC-600.csv\")\n",
    "df[\"Museum number\"] = df[\"Museum number\"].str.replace(r\"^No: \", \"\", regex=True)\n",
    "\n",
    "for index, row in df.iterrows():\n",
    "    print(row[\"Museum number\"])\n",
    "    url = row[\"Image\"]\n",
    "    print(url)\n",
    "    response = requests.get(url, verify=False)\n",
    "    if response.status_code == 200:\n",
    "        with open(f\"../data/raw/BM_images/{row['Museum number']}.jpg\", \"wb\") as f:\n",
    "            f.write(response.content)\n",
    "        print(\"Image downloaded successfully!\")\n",
    "    else:\n",
    "        print(\"Failed to download image. Status code:\", response.status_code)\n",
    "    # wait 20 seconds\n",
    "    time.sleep(20)\n",
    "# response = requests.get(url, headers=headers)\n",
    "\n",
    "# if response.status_code == 200:\n",
    "#     with open(\"image.jpg\", \"wb\") as f:\n",
    "#         f.write(response.content)\n",
    "#     print(\"Image downloaded successfully!\")\n",
    "# else:\n",
    "#     print(\"Failed to download image. Status code:\", response.status_code)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "460"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(df[\"Museum number\"] == \"null\").sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "ArtifactClassification",
   "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": "3.10.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}