SB user ID lookup

SB user ID lookup.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Getting the SB person Id, Display name and Organization using pandas:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "email = \"[email protected]\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://www.sciencebase.gov/directory/people/list?format=html&email={}\".format(email.replace('@', '%40'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style>\n",
       "    .dataframe thead tr:only-child th {\n",
       "        text-align: right;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: left;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Id</th>\n",
       "      <th>Display Name</th>\n",
       "      <th>URL</th>\n",
       "      <th>Email</th>\n",
       "      <th>Organization</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>NaN</td>\n",
       "      <td>10199</td>\n",
       "      <td>Colin Talbert</td>\n",
       "      <td>NaN</td>\n",
       "      <td>[email protected]</td>\n",
       "      <td>Fort Collins Science Center</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0     Id   Display Name  URL              Email  \\\n",
       "0         NaN  10199  Colin Talbert  NaN  [email protected]   \n",
       "\n",
       "                  Organization  \n",
       "0  Fort Collins Science Center  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_html(url)[0]\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "10199"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.Id[0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### But if you want the full contact info back you can get json back that contains additional info"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "import requests\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'_classSimpleName': 'UsgsPerson',\n",
       " 'active': True,\n",
       " 'description': None,\n",
       " 'displayName': 'Colin Talbert',\n",
       " 'displayText': 'Colin Talbert',\n",
       " 'distinguishedName': 'CN=Colin Talbert,OU=Fort Collins,OU=Users,OU=FortCollinsCO-B,OU=CR,DC=gs,DC=doi,DC=net',\n",
       " 'email': '[email protected]',\n",
       " 'extensions': {'personExtension': {'cellPhone': None,\n",
       "   'firstName': 'Colin',\n",
       "   'generationalQualifier': None,\n",
       "   'jobTitle': 'Ecologist',\n",
       "   'lastName': 'Talbert',\n",
       "   'middleName': None,\n",
       "   'orcId': None,\n",
       "   'organization': {'_classSimpleName': 'UsgsOrganization',\n",
       "    'displayText': 'Fort Collins Science Center',\n",
       "    'id': 17368},\n",
       "   'organizationDisplayText': 'Fort Collins Science Center',\n",
       "   'organizationId': 17368,\n",
       "   'personalTitle': None,\n",
       "   'professionalQualifier': None,\n",
       "   'supervisor': {'_classSimpleName': 'UsgsPerson',\n",
       "    'displayText': 'Tim Kern',\n",
       "    'id': 5432},\n",
       "   'supervisorDisplayText': 'Tim Kern',\n",
       "   'supervisorId': 5432,\n",
       "   'username': '[email protected]'},\n",
       "  'usgsPersonExtension': {'buildingCode': 'KBA',\n",
       "   'employeeId': 59787,\n",
       "   'employeeType': 'EMPLOYEE',\n",
       "   'endOccupationalSeries': None,\n",
       "   'endOrgCode': None,\n",
       "   'endYear': None,\n",
       "   'orgCode': 'GGCMRB0000',\n",
       "   'startOccupationalSeries': None,\n",
       "   'startOrgCode': None,\n",
       "   'startYear': None}},\n",
       " 'firstName': 'Colin',\n",
       " 'id': 10199,\n",
       " 'jobTitle': 'Ecologist',\n",
       " 'lastName': 'Talbert',\n",
       " 'link': {'href': 'https://www.sciencebase.gov/directory/person/10199',\n",
       "  'rel': 'self'},\n",
       " 'links': [{'rel': 'self',\n",
       "   'url': 'https://www.sciencebase.gov/directory/person/10199'}],\n",
       " 'name': 'Colin Talbert/BRD/USGS/DOI',\n",
       " 'note': None,\n",
       " 'orcId': '0000-0002-9505-1876',\n",
       " 'organization': {'displayText': 'Fort Collins Science Center', 'id': 17368},\n",
       " 'permissions': {'read': {'acl': ['ROLE:ScienceBase_DataAdmin',\n",
       "    'ROLE:ScienceBase_Directory_DataAdmin']},\n",
       "  'write': {'acl': ['ROLE:ScienceBase_DataAdmin',\n",
       "    'ROLE:ScienceBase_Directory_DataAdmin']}},\n",
       " 'primaryLocation': {'areaCode': '970',\n",
       "  'building': 'NRRC Bldg C',\n",
       "  'buildingCode': 'KBA',\n",
       "  'description': None,\n",
       "  'faxPhone': '9702269230',\n",
       "  'id': 10872,\n",
       "  'mailAddress': {'city': 'Fort Collins',\n",
       "   'country': 'USA',\n",
       "   'line1': '2150 Centre Avenue, Building C',\n",
       "   'line2': None,\n",
       "   'mailStopCode': None,\n",
       "   'state': 'CO',\n",
       "   'zip': '80526-8118'},\n",
       "  'name': 'Colin Talbert/BRD/CONT/USGS/DOI - Primary Location',\n",
       "  'phone': '9702269425',\n",
       "  'shortName': None,\n",
       "  'streetAddress': {'city': 'Fort Collins',\n",
       "   'country': None,\n",
       "   'line1': '2150 Centre Avenue Bldg C',\n",
       "   'line2': None,\n",
       "   'mailStopCode': None,\n",
       "   'state': 'CO',\n",
       "   'zip': '80526'}},\n",
       " 'richDescriptionHtml': None,\n",
       " 'type': 'person',\n",
       " 'url': None,\n",
       " 'username': '[email protected]'}"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "person_0 = json.loads(requests.get(url+'&format=json').text)['people'][0]\n",
    "person_0"
   ]
  }
 ],
 "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}