Small script to parse the data from SIIAU class schedules list into an associative array

SIIAU scrapper

Script para sacar los datos de la oferta academica del SIIAU en PHP

composer.json

{
    "require": {
        "fabpot/goutte": "~3.1"
    }
}

siiau.php

<?php

require __DIR__ . '/vendor/autoload.php';

use Symfony\Component\DomCrawler\Crawler;
use Goutte\Client;

class Siiau {

  // Keys for the data and the URL won't change
  const URL = 'http://consulta.siiau.udg.mx/wco/sspseca.forma_consulta';
  const SCHEDULE_KEYS = ['time', 'days', 'building', 'classroom'];
  const TIME_KEYS = ['start', 'finish'];
  const KEYS = ['nrc', 'key', 'topic', 'section', 'credits', 
                'limit', 'available', 'schedule', 'professor'];

  // Neither the indexes of the td elements
  const ENTRY_OFFSET = 3;
  const SCHEDULE_OFFSET = 4;

  private $client;
  public $entries;

  public function __construct() {
    $this->client = new Client();
    $this->entries = [];
  }

  /** 
   * Parse the input data from the SIIAU
   * html response
   *
   * @return Array
   */
  public function parse()
  {

    $submitText = 'Consultar';
    $selector = 'body > style + table > tr';

    $form = $this
      ->client
      ->request('POST', self::URL)
      ->selectButton($submitText)->form();

    $crawler = $this->client->submit($form);

    $entries = $crawler
      ->filter($selector)
      ->slice(self::ENTRY_OFFSET);

    $this->entries = $entries->each(function(Crawler $entry, $i)
    {
      $values = $entry
        ->children()
        ->slice(1)
        ->each($this->parseEntry());

      return array_combine(self::KEYS, $values);
    });
  }

  /** 
   * Returns the function used to properly
   * set the values of each entry in an
   * associative array
   *
   * @return Function
   */

  private function parseEntry()
    {
    return function(Crawler $value, $i)
    {
      if (self::KEYS[$i] == 'schedule') {
        $value = $this->parseSchedule($value);

      } elseif (self::KEYS[$i] == 'professor') {
        $value = $this->parseProfessor($value);
      }

      // Schedules returns an array but the rest
      // of the keys returns a Crawler
      // so we check for it
      $subject = is_array($value) ? $value : $value->text();

      $value = preg_replace('/(\s)+/', ' ', $subject);
      return $value;
    };
  }

  /** 
   * Put the schedule properties in an associative array
   * 
   * @param schedules
   * @return Array
   */
  private function parseSchedule($schedules)
  {

    $selector = 'table > tr';

    $schedules = $schedules
      ->filter($selector)
      ->each(function(Crawler $row, $i) {
        $row = $row
          ->children()
          ->slice(1, self::SCHEDULE_OFFSET)
          ->each(function(Crawler $cell, $i) {

            $value = $cell->text();

            if (self::SCHEDULE_KEYS[$i] == 'days') {
              $value = str_split(preg_replace('/([\.\s])+/', '', $value));
              
            } elseif (self::SCHEDULE_KEYS[$i] == 'time') {

              $value = explode('-', $value);
              $value = array_combine(self::TIME_KEYS, $value);
            }
            return $value;
          });

        return array_combine(self::SCHEDULE_KEYS, $row);
      });

    return $schedules;
  }

  /** 
   * Gets only the professor name from the entry
   *
   * @param professor
   * @return Crawler
   */
  private function parseProfessor($professor)
  {
    $selector = 'td:last-child';

    return $professor->filter($selector);
  }
}

// Lets create a new instance and dump the values
$siiau = new Siiau();
$siiau->parse();

var_dump($siiau->entries);