Jupyter Notebook for extracting all PMIDs in CIViC

civic_pmids.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import requests"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "url = \"https://civic.genome.wustl.edu/api/sources\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "pmids = set()\n",
    "next_page = url\n",
    "while next_page:\n",
    "    resp = requests.get(next_page)\n",
    "    resp.raise_for_status()\n",
    "    json = resp.json()\n",
    "    for record in json['records']:\n",
    "        pmid = record.get('pubmed_id', None)\n",
    "        if pmid is None:\n",
    "            continue\n",
    "        pmids.add(pmid)\n",
    "    next_page = json['_meta']['links']['next']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "1752"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(pmids)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "with open('pmids.txt', 'w') as out:\n",
    "    for pmid in pmids:\n",
    "        print(pmid, file=out)"
   ]
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [py36]",
   "language": "python",
   "name": "Python [py36]"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}

Yup, doesn't work anymore. Go look at API docs and update url