diff --git a/Travelogues.ipynb b/Travelogues.ipynb index 8f82e7ee2e26e982d36622915d269c9c8a1ea57a..e169d50b353944bcb1c4f3627529d5343707fbdf 100644 --- a/Travelogues.ipynb +++ b/Travelogues.ipynb @@ -2,14 +2,14 @@ "cells": [ { "cell_type": "code", - "execution_count": 1, "metadata": {}, - "outputs": [], "source": [ "from lxml import etree\n", "import requests\n", "import pandas as pd" - ] + ], + "outputs": [], + "execution_count": null }, { "cell_type": "markdown", @@ -32,9 +32,7 @@ }, { "cell_type": "code", - "execution_count": 2, "metadata": {}, - "outputs": [], "source": [ "def getMMS_ID(barcode):\n", " cont=requests.get('https://obv-at-oenb.alma.exlibrisgroup.com/view/sru/43ACC_ONB?version=1.2&query=alma.barcode=%2BZ' + barcode + '&startRecord=0&maximumRecords=1&operation=searchRetrieve&recordSchema=dc').content\n", @@ -59,6 +57,20 @@ " place = \"; \".join(placeResult) if placeResult else ''\n", " return[year, place]\n", "\n", + "def getSignature(barcode):\n", + " cont=requests.get('https://obv-at-oenb.alma.exlibrisgroup.com/view/sru/43ACC_ONB?version=1.2&query=alma.barcode=%2BZ' + barcode + '&startRecord=0&maximumRecords=1&operation=searchRetrieve&recordSchema=marcxml').content\n", + " e = etree.XML(cont)\n", + " namespaces = {\n", + " 'srw': 'http://www.loc.gov/zing/srw/',\n", + " 'marc21': 'http://www.loc.gov/MARC21/slim'\n", + " }\n", + " xpath = '/srw:searchRetrieveResponse/srw:records/srw:record/srw:recordData/marc21:record/marc21:datafield[@tag=\\'264\\']/marc21:subfield[@code=\\'{}\\']/text()'\n", + " yearResult = e.xpath(xpath.format('c'), namespaces=namespaces)\n", + " year = \"; \".join(yearResult) if yearResult else ''\n", + " placeResult = e.xpath(xpath.format('a'), namespaces=namespaces)\n", + " place = \"; \".join(placeResult) if placeResult else ''\n", + " return[year, place]\n", + "\n", "def getDCDataMMS(mms_id):\n", " cont=requests.get('https://obv-at-oenb.alma.exlibrisgroup.com/view/sru/43ACC_ONB?version=1.2&query=alma.mms_id=' + mms_id + '&startRecord=0&maximumRecords=1&operation=searchRetrieve&recordSchema=dc').content\n", " e = etree.XML(cont)\n", @@ -136,167 +148,77 @@ " if not result:\n", " result = e.xpath('/rdf:RDF/bf:Instance/bf:identifiedBy/bf:Local/rdf:value/text()', namespaces=namespaces)\n", " return 'http://data.onb.ac.at/rec/' + result[0]" - ] + ], + "outputs": [], + "execution_count": null }, { "cell_type": "code", - "execution_count": 3, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "['Sammlung der besten Reisebeschreibungen', '', '1784']\n" - ] - }, - { - "data": { - "text/plain": [ - "['Sammlung der besten Reisebeschreibungen', '', '1784']" - ] - }, - "execution_count": 3, - "metadata": {}, - "output_type": "execute_result" - } - ], "source": [ "getDCDataMMS(str(990048102650603338))" - ] + ], + "outputs": [], + "execution_count": null }, { "cell_type": "code", - "execution_count": 4, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "['Vorstellung der vornehmsten Völkerschaften der Welt nach ihrer Abstammung, Ausbreitung und Sprachen', 'Breitenbauch, Georg-August vonaut', '1786']\n", - "['Vorstellung der vornehmsten Völkerschaften der Welt nach ihrer Abstammung, Ausbreitung und Sprachen', 'Breitenbauch, Georg-August vonaut', '1786']\n" - ] - } - ], "source": [ "dc = getDCData(str(178966306))\n", "print(dc)" - ] + ], + "outputs": [], + "execution_count": null }, { "cell_type": "code", - "execution_count": 5, "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
\n", - "\n", - "\n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - " \n", - "
Identifier
0Z164418102
2Z97787406
3Z198357107
\n", - "
" - ], - "text/plain": [ - " Identifier\n", - "0 Z164418102\n", - "2 Z97787406\n", - "3 Z198357107" - ] - }, - "execution_count": 5, - "metadata": {}, - "output_type": "execute_result" - } - ], "source": [ "df = pd.read_excel('exampleBarcodes.xlsx')\n", "df_sample = df.sample(3).copy()\n", "df_sample" - ] + ], + "outputs": [], + "execution_count": null }, { "cell_type": "code", - "execution_count": 6, "metadata": {}, - "outputs": [ - { - "name": "stdout", - "output_type": "stream", - "text": [ - "['Sammlung der besten Reisebeschreibungen', '', '1784']\n", - "['Sammlung der besten Reisebeschreibungen', '', '1784']\n", - "['Geschichte der Reisen die seit Cook an der Nordwest- und Nordost-Küste von Amerika und in dem nördlichsten Amerika selbst von Meares, Dixon, Portlock, Coxe, Long u. a. m. unternommen worden sind Mit vielen Karten und Kupfern', 'Forster, Georg1754-1794(DE-588)118534416edtO:H; Dixon, George1755-1800(DE-588)130525294ctbO:H; Long, JohnctbO:H; Meares, John1756-1809(DE-588)121248275ctbO:H; Portlock, Nathaniel1748-1817(DE-588)133848531ctbO:H; Portlock, NathanielautO:800O:H; Forster, [Johann] GeorgautAdamO:806O:H; Vossische BuchhandlungBerlin(DE-588)64386-5pblO:H', '1792']\n", - "['Sammlung der besten Reisebeschreibungen', 'Traßler, Joseph Georg1759-1816(DE-588)129262358prt', '1784']\n", - "['', '', '']\n", - "['Sammlung der besten Reisebeschreibungen', '', '1784']\n", - "['Beschreibung der äussern und innern Merkwürdigkeiten der Königlichen Schlösser in Berlin, Charlottenburg, Schönhausen in und bey Potsdam', 'Rumpf, Friedrichaut', '1794']\n", - "[\"Neues Elementarwerk für die niedern Klassen lateinischer Schulen und Gymnasien nach einem zusammenhängenden und auf die Lesung klassischer Autoren in den obern Klassen, wie auch auf die übrigen Vorerkenntnisse künftiger Studirenden gründlich vorbereitenden Plane; <> Elementargeographie; M. J. E. Fabri's Elementargeographie; Fabri's Elementargeographie; M. J. E. Fabri's Elementargeographie; zweiten Zweiter\", 'Fabri, Johann Ernst1755-1825(DE-588)11536028Xaut; Gebauer, Johann Jakobpbl', '1790']\n", - "['', '', '']\n" - ] - } - ], "source": [ "df[['Titel', 'Autor', 'Erscheinungsjahr']] = df.apply(lambda row: getDCData(str(row['Identifier'])[1:]), axis=1, result_type='expand')" - ] + ], + "outputs": [], + "execution_count": null }, { "cell_type": "code", - "execution_count": 7, "metadata": {}, - "outputs": [], "source": [ - "writer = pd.ExcelWriter(r'exampleBarcodes_extended.xlsx', engine='xlsxwriter',options={'strings_to_urls': False})\n", + "writer = pd.ExcelWriter(\n", + " r'exampleBarcodes_extended.xlsx',\n", + " engine='xlsxwriter',\n", + " engine_kwargs={'options': {'strings_to_urls': False}}\n", + ")\n", "df.to_excel(writer)\n", "writer.close()" - ] + ], + "outputs": [], + "execution_count": null }, { "cell_type": "code", - "execution_count": null, "metadata": {}, + "source": [], "outputs": [], - "source": [] + "execution_count": null } ], "metadata": { "kernelspec": { - "display_name": "labs", + "display_name": "Python 3 (ipykernel)", "language": "python", - "name": "labs" + "name": "python3" }, "language_info": { "codemirror_mode": { diff --git a/requirements.txt b/requirements.txt index b513a2609edc4be45684864fef71225bde4e7df6..6556f54e128b983e4eb6ad3924472758e2f66914 100644 --- a/requirements.txt +++ b/requirements.txt @@ -6,4 +6,5 @@ xlsxwriter SPARQLWrapper sickle mysql-connector-python -pymarc \ No newline at end of file +pymarc +openpyxl \ No newline at end of file