Add Jupyter notebook for MARCXML to MARC21 processing via OAI-PMH

a39f67ea · csteindl · feac28db · a39f67ea · a39f67ea · a39f67ea
Commit a39f67ea authored 2 years ago by csteindl
--- a/MARCXML to MARC21.ipynb
+++ b/MARCXML to MARC21.ipynb
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from sickle import Sickle\n",
+    "from lxml import etree\n",
+    "from typing import List\n",
+    "import pymarc\n",
+    "import os\n",
+    "\n",
+    "ns = {\n",
+    "    'marc': 'http://www.loc.gov/MARC21/slim',\n",
+    "    'oai': 'http://www.openarchives.org/OAI/2.0/'\n",
+    "}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def save_records_as_marc(records: List[etree.Element], filename: str, tmp_filename:str = 'tmp.xml'):\n",
+    "    \"\"\"Save a list of lxml representations of MARCXML records in MARC21 format to a file.\n",
+    "\n",
+    "        Parameters\n",
+    "        ----------\n",
+    "        records : List[etree.Element]\n",
+    "            The list of lxml records to process\n",
+    "        filename : str\n",
+    "            The location where to store the generated MARC21 file. Often ends with *.mrc suffix.\n",
+    "        tmp_filename : str, optional\n",
+    "            The function writes a temp file for processing. tmp_filename is the location for this file.\n",
+    "            It will be removed at the end of the function.\n",
+    "    \"\"\"\n",
+    "    # temporarily create xml file to feed the pymarc parser\n",
+    "    root = etree.Element('records')\n",
+    "    {root.append(e) for e in records}\n",
+    "    et = etree.ElementTree(root)\n",
+    "    et.write(tmp_filename)\n",
+    "\n",
+    "    # convert elements to marc21\n",
+    "    writer = pymarc.MARCWriter(open(filename, 'wb')) \n",
+    "    pymarc.map_xml(writer.write, tmp_filename) \n",
+    "    writer.close()\n",
+    "\n",
+    "    # remove temporary file\n",
+    "    os.remove(tmp_filename)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sickle = Sickle('https://eu02.alma.exlibrisgroup.com/view/oai/43ACC_ONB/request', encoding='utf-8')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "KeyboardInterrupt",
+     "evalue": "",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
+      "\u001b[1;32m~\\AppData\\Local\\Temp/ipykernel_11580/1222585073.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     11\u001b[0m \u001b[0mbatch\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;33m[\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     12\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 13\u001b[1;33m \u001b[1;32mfor\u001b[0m \u001b[0mrecord\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrecords\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     14\u001b[0m     \u001b[0mcounter\u001b[0m \u001b[1;33m+=\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     15\u001b[0m     \u001b[0mrecord_xml\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0metree\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfromstring\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrecord\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mraw\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfind\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'.//marc:record'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnamespaces\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mns\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\sickle\\iterator.py\u001b[0m in \u001b[0;36m__next__\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m     50\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     51\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__next__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 52\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnext\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     53\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     54\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m__repr__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\sickle\\iterator.py\u001b[0m in \u001b[0;36mnext\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    149\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[0mmapped\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    150\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresumption_token\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mresumption_token\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtoken\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 151\u001b[1;33m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_next_response\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    152\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    153\u001b[0m                 \u001b[1;32mraise\u001b[0m \u001b[0mStopIteration\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\sickle\\iterator.py\u001b[0m in \u001b[0;36m_next_response\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    136\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    137\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_next_response\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 138\u001b[1;33m         \u001b[0msuper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mOAIItemIterator\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_next_response\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    139\u001b[0m         self._items = self.oai_response.xml.iterfind(\n\u001b[0;32m    140\u001b[0m             './/' + self.sickle.oai_namespace + self.element)\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\sickle\\iterator.py\u001b[0m in \u001b[0;36m_next_response\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m     82\u001b[0m                 \u001b[1;34m'verb'\u001b[0m\u001b[1;33m:\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mverb\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     83\u001b[0m             }\n\u001b[1;32m---> 84\u001b[1;33m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0moai_response\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msickle\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mharvest\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m**\u001b[0m\u001b[0mparams\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     85\u001b[0m         error = self.oai_response.xml.find(\n\u001b[0;32m     86\u001b[0m             './/' + self.sickle.oai_namespace + 'error')\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\sickle\\app.py\u001b[0m in \u001b[0;36mharvest\u001b[1;34m(self, **kwargs)\u001b[0m\n\u001b[0;32m    119\u001b[0m         \u001b[1;33m:\u001b[0m\u001b[0mrtype\u001b[0m\u001b[1;33m:\u001b[0m \u001b[1;33m:\u001b[0m\u001b[1;32mclass\u001b[0m\u001b[1;33m:\u001b[0m\u001b[0;31m`\u001b[0m\u001b[0msickle\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mOAIResponse\u001b[0m\u001b[0;31m`\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    120\u001b[0m         \"\"\"\n\u001b[1;32m--> 121\u001b[1;33m         \u001b[0mhttp_response\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_request\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    122\u001b[0m         \u001b[1;32mfor\u001b[0m \u001b[0m_\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmax_retries\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    123\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_is_error_code\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mhttp_response\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mstatus_code\u001b[0m\u001b[1;33m)\u001b[0m\u001b[0;31m \u001b[0m\u001b[0;31m\\\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\sickle\\app.py\u001b[0m in \u001b[0;36m_request\u001b[1;34m(self, kwargs)\u001b[0m\n\u001b[0;32m    135\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_request\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    136\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mhttp_method\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;34m'GET'\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 137\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mrequests\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mendpoint\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequest_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    138\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mrequests\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpost\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mendpoint\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequest_args\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    139\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\requests\\api.py\u001b[0m in \u001b[0;36mget\u001b[1;34m(url, params, **kwargs)\u001b[0m\n\u001b[0;32m     73\u001b[0m     \"\"\"\n\u001b[0;32m     74\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 75\u001b[1;33m     \u001b[1;32mreturn\u001b[0m \u001b[0mrequest\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'get'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mparams\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     76\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     77\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\requests\\api.py\u001b[0m in \u001b[0;36mrequest\u001b[1;34m(method, url, **kwargs)\u001b[0m\n\u001b[0;32m     59\u001b[0m     \u001b[1;31m# cases, and look like a memory leak in others.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     60\u001b[0m     \u001b[1;32mwith\u001b[0m \u001b[0msessions\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSession\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0msession\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 61\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0msession\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequest\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     62\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     63\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\requests\\sessions.py\u001b[0m in \u001b[0;36mrequest\u001b[1;34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[0m\n\u001b[0;32m    540\u001b[0m         }\n\u001b[0;32m    541\u001b[0m         \u001b[0msend_kwargs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msettings\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 542\u001b[1;33m         \u001b[0mresp\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mprep\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0msend_kwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    543\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    544\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mresp\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\requests\\sessions.py\u001b[0m in \u001b[0;36msend\u001b[1;34m(self, request, **kwargs)\u001b[0m\n\u001b[0;32m    653\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    654\u001b[0m         \u001b[1;31m# Send the request\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 655\u001b[1;33m         \u001b[0mr\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0madapter\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    656\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    657\u001b[0m         \u001b[1;31m# Total elapsed time of the request (approximately)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\requests\\adapters.py\u001b[0m in \u001b[0;36msend\u001b[1;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[0;32m    437\u001b[0m         \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    438\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[0mchunked\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 439\u001b[1;33m                 resp = conn.urlopen(\n\u001b[0m\u001b[0;32m    440\u001b[0m                     \u001b[0mmethod\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mrequest\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    441\u001b[0m                     \u001b[0murl\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\urllib3\\connectionpool.py\u001b[0m in \u001b[0;36murlopen\u001b[1;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)\u001b[0m\n\u001b[0;32m    697\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    698\u001b[0m             \u001b[1;31m# Make the request on the httplib connection object.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 699\u001b[1;33m             httplib_response = self._make_request(\n\u001b[0m\u001b[0;32m    700\u001b[0m                 \u001b[0mconn\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    701\u001b[0m                 \u001b[0mmethod\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\urllib3\\connectionpool.py\u001b[0m in \u001b[0;36m_make_request\u001b[1;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[0;32m    443\u001b[0m                     \u001b[1;31m# Python 3 (including for exceptions like SystemExit).\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    444\u001b[0m                     \u001b[1;31m# Otherwise it looks like a bug in the code.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 445\u001b[1;33m                     \u001b[0msix\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mraise_from\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0me\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    446\u001b[0m         \u001b[1;32mexcept\u001b[0m \u001b[1;33m(\u001b[0m\u001b[0mSocketTimeout\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mBaseSSLError\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mSocketError\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    447\u001b[0m             \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_raise_timeout\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0merr\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0me\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mtimeout_value\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mread_timeout\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\urllib3\\packages\\six.py\u001b[0m in \u001b[0;36mraise_from\u001b[1;34m(value, from_value)\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\site-packages\\urllib3\\connectionpool.py\u001b[0m in \u001b[0;36m_make_request\u001b[1;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[0;32m    438\u001b[0m                 \u001b[1;31m# Python 3\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    439\u001b[0m                 \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 440\u001b[1;33m                     \u001b[0mhttplib_response\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mconn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgetresponse\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    441\u001b[0m                 \u001b[1;32mexcept\u001b[0m \u001b[0mBaseException\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    442\u001b[0m                     \u001b[1;31m# Remove the TypeError from the exception chain in\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\http\\client.py\u001b[0m in \u001b[0;36mgetresponse\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m   1347\u001b[0m         \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1348\u001b[0m             \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1349\u001b[1;33m                 \u001b[0mresponse\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbegin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1350\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mConnectionError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1351\u001b[0m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\http\\client.py\u001b[0m in \u001b[0;36mbegin\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    314\u001b[0m         \u001b[1;31m# read until we get a non-100 response\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    315\u001b[0m         \u001b[1;32mwhile\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 316\u001b[1;33m             \u001b[0mversion\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstatus\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mreason\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_read_status\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    317\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[1;33m!=\u001b[0m \u001b[0mCONTINUE\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    318\u001b[0m                 \u001b[1;32mbreak\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\http\\client.py\u001b[0m in \u001b[0;36m_read_status\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    275\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    276\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_read_status\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 277\u001b[1;33m         \u001b[0mline\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mstr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreadline\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_MAXLINE\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"iso-8859-1\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    278\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mline\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m>\u001b[0m \u001b[0m_MAXLINE\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    279\u001b[0m             \u001b[1;32mraise\u001b[0m \u001b[0mLineTooLong\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"status line\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\socket.py\u001b[0m in \u001b[0;36mreadinto\u001b[1;34m(self, b)\u001b[0m\n\u001b[0;32m    702\u001b[0m         \u001b[1;32mwhile\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    703\u001b[0m             \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 704\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_sock\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mb\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    705\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    706\u001b[0m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_timeout_occurred\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\ssl.py\u001b[0m in \u001b[0;36mrecv_into\u001b[1;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[0;32m   1239\u001b[0m                   \u001b[1;34m\"non-zero flags not allowed in calls to recv_into() on %s\"\u001b[0m \u001b[1;33m%\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1240\u001b[0m                   self.__class__)\n\u001b[1;32m-> 1241\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mnbytes\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mbuffer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1242\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1243\u001b[0m             \u001b[1;32mreturn\u001b[0m \u001b[0msuper\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbuffer\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnbytes\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mflags\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;32mc:\\Users\\onbcst\\AppData\\Local\\Programs\\Python\\Python39\\lib\\ssl.py\u001b[0m in \u001b[0;36mread\u001b[1;34m(self, len, buffer)\u001b[0m\n\u001b[0;32m   1097\u001b[0m         \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1098\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mbuffer\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mnot\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1099\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_sslobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mbuffer\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1100\u001b[0m             \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1101\u001b[0m                 \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_sslobj\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mread\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlen\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
+      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
+     ]
+    }
+   ],
+   "source": [
+    "# get all records from set FULLMARC in marcxml format\n",
+    "records = sickle.ListRecords(metadataPrefix='marc21', set='FULLMARC', ignore_deleted=True)\n",
+    "counter = 0\n",
+    "\n",
+    "# exit loop after processing certain amount of records\n",
+    "# set to 0 if all records should be processed\n",
+    "max_records = 0\n",
+    "\n",
+    "# store results in batches\n",
+    "batch_size = 100\n",
+    "batch = []\n",
+    "\n",
+    "for record in records:\n",
+    "    counter += 1\n",
+    "    record_xml = etree.fromstring(record.raw).find('.//marc:record', namespaces=ns)\n",
+    "    batch.append(record_xml)\n",
+    "\n",
+    "    if counter % batch_size == 0:\n",
+    "        save_records_as_marc(batch, f\"batch_{int(counter/batch_size)}.mrc\")\n",
+    "        batch = []\n",
+    "\n",
+    "    if max_records > 0 and counter >= max_records:\n",
+    "        break\n",
+    "\n",
+    "# save last batch\n",
+    "save_records_as_marc(batch, f\"batch_{int(counter/batch_size) + 1}.mrc\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "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": "3.9.6"
+  },
+  "orig_nbformat": 4,
+  "vscode": {
+   "interpreter": {
+    "hash": "0fe26630646663b41c23429e0772f18e982197f76592089c7393ecaaee9e49a0"
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}
+%% Cell type:code id: tags:
+
+``` python
+from sickle import Sickle
+from lxml import etree
+from typing import List
+import pymarc
+import os
+
+ns = {
+    'marc': 'http://www.loc.gov/MARC21/slim',
+    'oai': 'http://www.openarchives.org/OAI/2.0/'
+}
+```
+
+%% Cell type:code id: tags:
+
+``` python
+def save_records_as_marc(records: List[etree.Element], filename: str, tmp_filename:str = 'tmp.xml'):
+    """Save a list of lxml representations of MARCXML records in MARC21 format to a file.
+
+        Parameters
+        ----------
+        records : List[etree.Element]
+            The list of lxml records to process
+        filename : str
+            The location where to store the generated MARC21 file. Often ends with *.mrc suffix.
+        tmp_filename : str, optional
+            The function writes a temp file for processing. tmp_filename is the location for this file.
+            It will be removed at the end of the function.
+    """
+    # temporarily create xml file to feed the pymarc parser
+    root = etree.Element('records')
+    {root.append(e) for e in records}
+    et = etree.ElementTree(root)
+    et.write(tmp_filename)
+
+    # convert elements to marc21
+    writer = pymarc.MARCWriter(open(filename, 'wb'))
+    pymarc.map_xml(writer.write, tmp_filename)
+    writer.close()
+
+    # remove temporary file
+    os.remove(tmp_filename)
+```
+
+%% Cell type:code id: tags:
+
+``` python
+sickle = Sickle('https://eu02.alma.exlibrisgroup.com/view/oai/43ACC_ONB/request', encoding='utf-8')
+```
+
+%% Cell type:code id: tags:
+
+``` python
+# get all records from set FULLMARC in marcxml format
+records = sickle.ListRecords(metadataPrefix='marc21', set='FULLMARC', ignore_deleted=True)
+counter = 0
+
+# exit loop after processing certain amount of records
+# set to 0 if all records should be processed
+max_records = 0
+
+# store results in batches
+batch_size = 100
+batch = []
+
+for record in records:
+    counter += 1
+    record_xml = etree.fromstring(record.raw).find('.//marc:record', namespaces=ns)
+    batch.append(record_xml)
+
+    if counter % batch_size == 0:
+        save_records_as_marc(batch, f"batch_{int(counter/batch_size)}.mrc")
+        batch = []
+
+    if max_records > 0 and counter >= max_records:
+        break
+
+# save last batch
+save_records_as_marc(batch, f"batch_{int(counter/batch_size) + 1}.mrc")
+```
+
+%% Output
+
+    ---------------------------------------------------------------------------
+    KeyboardInterrupt                         Traceback (most recent call last)
+    ~\AppData\Local\Temp/ipykernel_11580/1222585073.py in <module>
+         11 batch = []
+         12
+    ---> 13 for record in records:
+         14     counter += 1
+         15     record_xml = etree.fromstring(record.raw).find('.//marc:record', namespaces=ns)
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\sickle\iterator.py in __next__(self)
+         50
+         51     def __next__(self):
+    ---> 52         return self.next()
+         53
+         54     def __repr__(self):
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\sickle\iterator.py in next(self)
+        149                 return mapped
+        150             if self.resumption_token and self.resumption_token.token:
+    --> 151                 self._next_response()
+        152             else:
+        153                 raise StopIteration
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\sickle\iterator.py in _next_response(self)
+        136
+        137     def _next_response(self):
+    --> 138         super(OAIItemIterator, self)._next_response()
+        139         self._items = self.oai_response.xml.iterfind(
+        140             './/' + self.sickle.oai_namespace + self.element)
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\sickle\iterator.py in _next_response(self)
+         82                 'verb': self.verb
+         83             }
+    ---> 84         self.oai_response = self.sickle.harvest(**params)
+         85         error = self.oai_response.xml.find(
+         86             './/' + self.sickle.oai_namespace + 'error')
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\sickle\app.py in harvest(self, **kwargs)
+        119         :rtype: :class:`sickle.OAIResponse`
+        120         """
+    --> 121         http_response = self._request(kwargs)
+        122         for _ in range(self.max_retries):
+        123             if self._is_error_code(http_response.status_code) \
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\sickle\app.py in _request(self, kwargs)
+        135     def _request(self, kwargs):
+        136         if self.http_method == 'GET':
+    --> 137             return requests.get(self.endpoint, params=kwargs, **self.request_args)
+        138         return requests.post(self.endpoint, data=kwargs, **self.request_args)
+        139
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\requests\api.py in get(url, params, **kwargs)
+         73     """
+         74
+    ---> 75     return request('get', url, params=params, **kwargs)
+         76
+         77
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\requests\api.py in request(method, url, **kwargs)
+         59     # cases, and look like a memory leak in others.
+         60     with sessions.Session() as session:
+    ---> 61         return session.request(method=method, url=url, **kwargs)
+         62
+         63
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\requests\sessions.py in request(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)
+        540         }
+        541         send_kwargs.update(settings)
+    --> 542         resp = self.send(prep, **send_kwargs)
+        543
+        544         return resp
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\requests\sessions.py in send(self, request, **kwargs)
+        653
+        654         # Send the request
+    --> 655         r = adapter.send(request, **kwargs)
+        656
+        657         # Total elapsed time of the request (approximately)
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\requests\adapters.py in send(self, request, stream, timeout, verify, cert, proxies)
+        437         try:
+        438             if not chunked:
+    --> 439                 resp = conn.urlopen(
+        440                     method=request.method,
+        441                     url=url,
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\urllib3\connectionpool.py in urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
+        697
+        698             # Make the request on the httplib connection object.
+    --> 699             httplib_response = self._make_request(
+        700                 conn,
+        701                 method,
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\urllib3\connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
+        443                     # Python 3 (including for exceptions like SystemExit).
+        444                     # Otherwise it looks like a bug in the code.
+    --> 445                     six.raise_from(e, None)
+        446         except (SocketTimeout, BaseSSLError, SocketError) as e:
+        447             self._raise_timeout(err=e, url=url, timeout_value=read_timeout)
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\urllib3\packages\six.py in raise_from(value, from_value)
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\site-packages\urllib3\connectionpool.py in _make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
+        438                 # Python 3
+        439                 try:
+    --> 440                     httplib_response = conn.getresponse()
+        441                 except BaseException as e:
+        442                     # Remove the TypeError from the exception chain in
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\http\client.py in getresponse(self)
+       1347         try:
+       1348             try:
+    -> 1349                 response.begin()
+       1350             except ConnectionError:
+       1351                 self.close()
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\http\client.py in begin(self)
+        314         # read until we get a non-100 response
+        315         while True:
+    --> 316             version, status, reason = self._read_status()
+        317             if status != CONTINUE:
+        318                 break
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\http\client.py in _read_status(self)
+        275
+        276     def _read_status(self):
+    --> 277         line = str(self.fp.readline(_MAXLINE + 1), "iso-8859-1")
+        278         if len(line) > _MAXLINE:
+        279             raise LineTooLong("status line")
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\socket.py in readinto(self, b)
+        702         while True:
+        703             try:
+    --> 704                 return self._sock.recv_into(b)
+        705             except timeout:
+        706                 self._timeout_occurred = True
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\ssl.py in recv_into(self, buffer, nbytes, flags)
+       1239                   "non-zero flags not allowed in calls to recv_into() on %s" %
+       1240                   self.__class__)
+    -> 1241             return self.read(nbytes, buffer)
+       1242         else:
+       1243             return super().recv_into(buffer, nbytes, flags)
+    c:\Users\onbcst\AppData\Local\Programs\Python\Python39\lib\ssl.py in read(self, len, buffer)
+       1097         try:
+       1098             if buffer is not None:
+    -> 1099                 return self._sslobj.read(len, buffer)
+       1100             else:
+       1101                 return self._sslobj.read(len)
+    KeyboardInterrupt:
+
+%% Cell type:code id: tags:
+
+``` python
+```
--- a/README.md
+++ b/README.md
@@ -33,4 +33,8 @@ the number of entries in one specific set.

 Small script to harvest ABO metadata in Marc format via OAI-PMH.

+## [MARCXML to MARC21 transformation](MARCXML to MARC21.ipynb)
+
+Small script to harvest MARCXML records via OAI-PMH and to store it as raw MARC21. This step can help if you want to process the data e.g. via [MarcEdit](https://marcedit.reeset.net/).
+
 [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/git/https%3A%2F%2Flabs.onb.ac.at%2Fgitlab%2Flabs-team%2FLOD/master)
\ No newline at end of file
--- a/requirements.txt
+++ b/requirements.txt
@@ -6,3 +6,4 @@ xlsxwriter
 SPARQLWrapper
 sickle
 mysql-connector-python
+pymarc
\ No newline at end of file