A simple parser for Google Scholar profiles.

Google+Scholar-Simple-Parser.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "from urllib.request import FancyURLopener\n",
    "import re\n",
    "from bs4 import BeautifulSoup as bs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "class GoogleOpener(FancyURLopener):\n",
    "    # useragent\n",
    "    version = \"Mozilla\"\n",
    "\n",
    "class Scholar():\n",
    "    def __init__(self, url):\n",
    "        self.url = url\n",
    "        self.fullname = None\n",
    "        self.title = []\n",
    "        self.orgid = None\n",
    "        self.institution = None\n",
    "        self.institution_urls = []\n",
    "        self.keywords = []\n",
    "        try:\n",
    "            self.getProfile(url)\n",
    "        except:\n",
    "            raise\n",
    "    \n",
    "    def getProfile(self, url):\n",
    "        opener = GoogleOpener()\n",
    "        if not url.startswith('https://scholar.google.com/citations?user='):\n",
    "            pos = url.find('user=')\n",
    "            if pos:\n",
    "                url = 'https://scholar.google.com/citations?user=' + url[pos:] + '&hl=en'\n",
    "            else:\n",
    "                raise Exception('Invalid Google Scholar URL')\n",
    "        handle = opener.open(url)\n",
    "        html = bs(handle.readline(), 'html.parser')\n",
    "        handle.close()\n",
    "        prof_attrs = []\n",
    "        self.fullname = html.find_all(id='gsc_prf_in')[0].string\n",
    "        for item in html.find_all(class_='gsc_prf_il'):\n",
    "            prof_attrs.append(item)\n",
    "        self.title = ''.join(i.string for i in prof_attrs[0])\n",
    "        self.orgid = getOrg([i for i in prof_attrs[0].children][1].attrs['href'])\n",
    "        self.keywords = [i.string.lower() for i in prof_attrs[1].children if i != ', ']\n",
    "        self.institution = ''.join([i.string for i in html.find_all(id='gsc_prf_ivh')[0].children])\n",
    "        self.institution_urls = [i.attrs['href'] for i in html.find_all(id='gsc_prf_ivh')[0].children if i.name == 'a']\n",
    "        return 0\n",
    "\n",
    "def getOrg(url):\n",
    "    pos = url.find('org=') + 4\n",
    "    orgid = url[pos:]\n",
    "    try:\n",
    "        orgid = int(orgid)\n",
    "    except ValueError:\n",
    "        raise Exception(stry(orgid) + ' is a bad id.')\n",
    "    return orgid"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.5/site-packages/ipykernel/__main__.py:20: DeprecationWarning: GoogleOpener style of invoking requests is deprecated. Use newer urlopen functions/methods\n"
     ]
    }
   ],
   "source": [
    "AlanWang = Scholar('https://scholar.google.com/citations?user=onKvwjAAAAAJ&hl=en')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied (use --upgrade to upgrade): beautifulsoup4 in /opt/conda/lib/python3.5/site-packages\n",
      "\u001b[33mYou are using pip version 8.1.2, however version 9.0.1 is available.\n",
      "You should consider upgrading via the 'pip install --upgrade pip' command.\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "!pip install beautifulsoup4"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Verified email at vt.edu - Homepage'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "AlanWang.institution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Associate Professor in Business Information Technology, Pamplin College of Business, Virginia Tech'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "AlanWang.title"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "17003267462049548924"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "AlanWang.orgid"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['data mining',\n",
       " 'text mining',\n",
       " 'information retrieval',\n",
       " 'business intelligence',\n",
       " 'social computing']"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "AlanWang.keywords"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Alan Wang 王刚'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "AlanWang.fullname"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'https://scholar.google.com/citations?user=onKvwjAAAAAJ&hl=en'"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "AlanWang.url"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/opt/conda/lib/python3.5/site-packages/ipykernel/__main__.py:20: DeprecationWarning: GoogleOpener style of invoking requests is deprecated. Use newer urlopen functions/methods\n"
     ]
    }
   ],
   "source": [
    "random = Scholar('https://scholar.google.com/citations?user=A-H-yvQAAAAJ&hl=en')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'Phd student of Business Information Technology, Virginia Tech'"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "random.title"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "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": "3.5.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}