/**
* Public function setCollegeList
* No parameters
*
* @operates by searching wikipedia for all the state college categories and scraping all the college names.
* Should get 3147 colleges as of 07/25/11
*
* Postcondition: the database is loaded with all the scrapeable colleges off of wikipedia.
*/
private function setCollegeList()
{
$stateList = array("Alabama", "Alaska", "Arizona", "Arkansas", "California", "Colorado", "Connecticut", "Delaware", "Washington, D.C.", "Florida", "Georgia", "Hawaii", "Idaho", "Illinois", "Indiana", "Iowa", "Kansas", "Kentucky", "Louisiana", "Maine", "Maryland", "Massachusetts", "Michigan", "Minnesota", "Mississippi", "Missouri", "Montana", "Nebraska", "Nevada", "New Hampshire", "New Jersey", "New Mexico", "New York", "North Carolina", "North Dakota", "Ohio", "Oklahoma", "Oregon", "Pennsylvania", "Rhode Island", "South Carolina", "South Dakota", "Tennessee", "Texas", "Utah", "Vermont", "Virginia", "Washington", "West Virginia", "Wisconsin", "Wyoming");
$filteringKeywords = array("University", "College");
$totalLinks = array();
for ($i = 0; $i < count($stateList); $i++) {
$temp = array();
$links = $this->_wikipedia->getLinks("List_of_colleges_and_universities_in_" . $stateList[$i]);
for ($j = 0; $j < count($links); $j++) {
$temp[$j] = $links[$j]["title"];
}
$totalLinks = array_merge($totalLinks, $temp);
}
$filteredArray = urlParser::compareSearchArray($totalLinks, $filteringKeywords, true);
for ($i = 0; $i < count($filteredArray); $i++) {
// print_r($filteredArray[$i]);
// print_r("<p>");
$array_fieldValues = array("CollegeName" => $filteredArray[$i]);
$this->_dbConnection->insertIntoTable("CollegeSummary", $array_fieldValues);
}
}
/**
* Retrieves the websiteURL via externalLinks
*/
public function getUrl()
{
$array = $this->getExternalLinks($this->_college);
$completeArray = array(".edu");
// print_r($array);
$newArray = array();
for ($i = 0; $i < count($array); $i++) {
$newArray[] = $array[$i]["*"];
}
$filtered = urlParser::compareSearchArray($newArray, $completeArray, false);
return $filtered[0];
}
