CRGE Intersectional Research Database scrape

crge_convert.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Extracting Intersectional Research Database Content"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import csv\n",
    "import requests\n",
    "from bs4 import BeautifulSoup, NavigableString"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "All the entries from the database can be accessed as a single HTML page, which can be parsed using the [BeautifulSoup](https://www.crummy.com/software/BeautifulSoup/bs4/doc/) library for easy access to the data. Use of class names is consistent and makes it easy to target different bits of the page."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "r = requests.get('http://ird.crge.umd.edu/list_entries.php')\n",
    "parsed_html = BeautifulSoup(r.text, 'html.parser')\n",
    "entries = parsed_html.find_all('div', 'ird_entry')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "652"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(entries)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def get_type(entry):\n",
    "    it = entry.find('td', 'entry_num').stripped_strings\n",
    "    type_string = list(filter(lambda x: x != 'Datatype:', it))[0]\n",
    "    return type_string.lower()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def get_citation(entry):\n",
    "    return entry.find('td', 'entry_citation').p.get_text()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "(I noticed when eyeballing some of the annotations that there were some funky encoding issues — the data is not encoded as UTF-8 but rather using a funky Windows-specific encoding. Used an online [encoding detection widget](https://nlp.fi.muni.cz/projects/chared/) to guess the correct encoding so the requests library could handle it)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 146,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def get_annotation(entry):\n",
    "    link = 'http://ird.crge.umd.edu/{0}'.format(entry.find('td', 'entry_controls').a.get('href'))\n",
    "    anno_request = requests.get(link)\n",
    "    anno_request.encoding = 'cp1252'\n",
    "    anno_div = BeautifulSoup(anno_request.text, 'html.parser').find('div', 'annotations')\n",
    "    data = list(filter(lambda x: x != 'Annotations', anno_div.strings))\n",
    "    anno_string = ''.join(data).strip()\n",
    "    return anno_string"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 148,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def get_id(entry):\n",
    "    return entry.find('td', 'entry_controls').a.get('href').split('=')[1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 166,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def get_keywords(entry):\n",
    "    kw_str = entry.find('td', 'entry_keywords').p.get_text()\n",
    "    return ';'.join(kw_str.split(','))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Turn each blob of HTML representing an entry into a dictionary …"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 167,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "db = []\n",
    "for e in entries:\n",
    "    entry_parsed = {\n",
    "        'id': get_id(e),\n",
    "        'type': get_type(e),\n",
    "        'citation': get_citation(e),\n",
    "        'annotation': get_annotation(e),\n",
    "        'keywords': get_keywords(e)\n",
    "    }\n",
    "    db.append(entry_parsed)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Write the result to a CSV file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 168,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "output_fieldnames = ['id', 'type', 'citation', 'annotation', 'keywords']\n",
    "with open('/Users/umd-laptop/Downloads/crge_converted.csv', 'w') as outfile:\n",
    "    writer = csv.DictWriter(outfile, fieldnames=output_fieldnames)\n",
    "    \n",
    "    writer.writeheader()\n",
    "    \n",
    "    for item in db:\n",
    "        writer.writerow(item)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "display_name": "Python [conda env:html-tasks]",
   "language": "python",
   "name": "conda-env-html-tasks-py"
  },
  "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": 1
}