E-Mails from HepNames.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Get e-mail address from HepNames"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import urllib\n",
    "import urllib.request\n",
    "import re\n",
    "\n",
    "def to_query_string(s):\n",
    "    l = s.split(' ')\n",
    "    l = [urllib.parse.quote(p.lower()) for p in l]\n",
    "    return '+'.join(l)\n",
    "\n",
    "query_url = 'https://inspirehep.net/search?cc=HepNames&p=author+{}&sf=exactfirstauthor&so=a&rm=&rg=25&sc=0&of=hb'\n",
    "\n",
    "def read_url(name):\n",
    "    url = query_url.format(to_query_string(name))\n",
    "    with urllib.request.urlopen(url) as f:\n",
    "        s = f.read()\n",
    "    return s.decode('utf-8')\n",
    "\n",
    "def get_mail_from_string(s):\n",
    "    matches = re.findall(r\"mailto:([\\w\\.\\-\\@]+)\", s)\n",
    "    for match in matches:\n",
    "        if not 'inspire' in match and '@' in match:\n",
    "            return match\n",
    "    return ''\n",
    "\n",
    "def get_mail(name, include_name=True):\n",
    "    s = read_url(name)\n",
    "    mail = get_mail_from_string(s)\n",
    "    if not include_name:\n",
    "        return mail\n",
    "    else:\n",
    "        if not mail:\n",
    "            return mail\n",
    "        return '{} <{}>'.format(name, mail)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Demo"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "names = \"\"\"Andrzej Buras\n",
    "Matthias Neubert\n",
    "Riccardo Barbieri\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Andrzej Buras <[email protected]>\n",
      "Matthias Neubert <[email protected]>\n",
      "Riccardo Barbieri <[email protected]>\n"
     ]
    }
   ],
   "source": [
    "for name in names.splitlines():\n",
    "    print(get_mail(name))"
   ]
  },
  {
   "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": "3.5.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}