Commit 216cbb19 authored by Georg Petz's avatar Georg Petz

enrich Excel table with Viewerlinks and Barcodes

parent b1462368
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"from lxml import etree\n",
"import requests\n",
"import pandas as pd"
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [],
"source": [
"def getLinksAndBarcodes(local_mms_id):\n",
" cont=requests.get('https://open-na.hosted.exlibrisgroup.com/alma/43ACC_ONB/bf/entity/instance/' + local_mms_id).content\n",
" e = etree.XML(cont)\n",
" namespaces = {\n",
" 'rdf': 'http://www.w3.org/1999/02/22-rdf-syntax-ns#',\n",
" 'bf': 'http://id.loc.gov/ontologies/bibframe/',\n",
" 'rdfs': 'http://www.w3.org/2000/01/rdf-schema#',\n",
" 'bflc': 'http://id.loc.gov/ontologies/bflc/'\n",
" }\n",
" result = e.xpath('/rdf:RDF/bf:Instance/bf:hasItem/bf:Item/bf:electronicLocator/rdfs:Resource/bflc:locator/@rdf:resource', namespaces=namespaces)\n",
" barcodes = []\n",
" for link in result:\n",
" splits = link.split('%2B')\n",
" if len(splits) >= 2:\n",
" barcodes.append('+' + link.split('%2B')[1])\n",
" print (local_mms_id + ': ' + \", \".join(barcodes))\n",
" linksJoined = \", \".join(result)\n",
" barcodesJoined = \", \".join(barcodes)\n",
" return [linksJoined, barcodesJoined]"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"NaN 990032334150603338\nNaN 990035648370603338\nNaN 990031644540603338\nName: MMS-ID, dtype: int64"
]
},
"execution_count": 11,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_excel('ABOExamplesFromALMA.xlsx')\n",
"df_sample = df.sample(3).copy()\n",
"df_sample['MMS-ID']"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"990032334150603338: +Z227525900, +Z172047601\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"990035648370603338: +Z219890307, +Z255756803\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"990031644540603338: +Z136879807, +Z172905502\n"
]
}
],
"source": [
"df_sample[['Viewerlinks','Barcodes']] = df_sample.apply(lambda row: getLinksAndBarcodes(str(row['MMS-ID'])), axis=1, result_type='expand')"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"writer = pd.ExcelWriter(r'ABOExamplesFromALMAextended.xlsx', engine='xlsxwriter',options={'strings_to_urls': False})\n",
"df_sample.to_excel(writer)\n",
"writer.close()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 2",
"language": "python",
"name": "python2"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 0
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment