{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\nThis is an intro to regular expressions\\n\\nI use https://regex101.com/#python to check my work!\\n'"
      ]
     },
     "execution_count": 1,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"\"\"\n",
    "This is an intro to regular expressions\n",
    "\n",
    "I use https://regex101.com/#python to check my work!\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "# flow:\n",
    "# create a re pattern object\n",
    "# search (or match) it against text\n",
    "# organize the captures patterns in groups"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2'"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# \\d matches a SINGLE number\n",
    "text = \"Hello! My name is Sinan. It is 2014 and it's amazing.\"\n",
    "\n",
    "# create a re pattern object\n",
    "pattern1 = re.compile(\"\\d\")\n",
    "\n",
    "# search (or match) it against text\n",
    "re.search(pattern1, text) # == a search object\n",
    "\n",
    "# organize the captures patterns in groups\n",
    "# use group to get each instance in the regular expression\n",
    "# \\d is just ONE number, so it only finds the \"2\" in \"2014\"\n",
    "re.search(pattern1, text).group(0)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'2014'"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# adding a + means \"at least one\" but potentially more\n",
    "pattern2 = re.compile(\"\\d+\")\n",
    "re.search(pattern2, text).group(0) # == '2014'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'c'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# use square brackets [] to match one of the items present\n",
    "alphabet = 'abcdefg'\n",
    "pattern3 = re.compile('[cfg]')\n",
    "re.search(pattern3, alphabet).group(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'906-365-6776'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mystery_pattern = re.compile(\"\\d+-\\d+-\\d+\")\n",
    "# take a few minutes, and discuss, what application could this mystery_pattern have\n",
    "re.search(mystery_pattern, \"my phone number is 906-365-6776 dude\").group(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'dmzhvbekuhvbc     dfljghwco87rc6geinsr6t4gi7rgwefiuvbekuhvbdfljghwco87rc6geinsr6t4gi7rgwefiu ywgsfybcstzvgbrtybte'"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# . matches ANYTHING\n",
    "all_of_the_text = \"dmzhvbekuhvbc     dfljghwco87rc6geinsr6t4gi7rgwefiuvbekuhvbdfljghwco87rc6geinsr6t4gi7rgwefiu ywgsfybcstzvgbrtybte\"\n",
    "anything_pattern = re.compile(\".+\")\n",
    "re.search(anything_pattern, all_of_the_text).group(0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'sinan+test@legionanalytics.com'"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# \\w matches any word character, alphanumeric\n",
    "# if you want to match an actual period, do \\.\n",
    "email_pattern = re.compile(\"[\\w\\.\\+]+@\\w+\\.com\")\n",
    "re.search(email_pattern, \"my email address is sinan+test@legionanalytics.com\").group(0)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [sfdat26-env]",
   "language": "python",
   "name": "Python [sfdat26-env]"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}