Last active
August 29, 2015 14:19
-
-
Save toddbranch/8b78531e1e4d6d347d9b to your computer and use it in GitHub Desktop.
NFL draft scraper and SQL schema / import
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Schema for a draft table to hold all of the picks | |
| CREATE TABLE IF NOT EXISTS draft | |
| ( | |
| year smallint(4) unsigned, | |
| pick smallint(3) unsigned, | |
| name varchar(255), | |
| team varchar(255), | |
| position varchar(5), | |
| school varchar(255) | |
| ); |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Commands to import the picks | |
| # Ensure you've created the draft table first | |
| # You'll have to change the file location | |
| TRUNCATE draft; | |
| LOAD DATA INFILE '/home/toddbranch/php/nfl_draft/results.csv' | |
| INTO TABLE draft | |
| FIELDS TERMINATED BY ',' | |
| LINES TERMINATED BY '\n'; |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| # Usage: php scraper.php > results.csv | |
| # | |
| # Scrapes from www.nfl.com/draft/history/fulldraft?season=2014 | |
| <?php | |
| class Pick | |
| { | |
| private $year; | |
| private $pick; | |
| private $name; | |
| private $team; | |
| private $position; | |
| private $school; | |
| public function __construct($row, $year) | |
| { | |
| $tds = $row->getElementsByTagName('td'); | |
| $this->pick = $tds[0]->textContent; | |
| $this->name = $tds[2]->getElementsByTagName('a')[0]->textContent; | |
| $this->team = $tds[1]->getElementsByTagName('a')[0]->textContent; | |
| $this->position = $tds[3]->textContent; | |
| $this->school = $tds[4]->textContent; | |
| $this->year = $year; | |
| } | |
| private function toArray() | |
| { | |
| return [ | |
| 'year' => $this->year, | |
| 'pick' => $this->pick, | |
| 'name' => $this->name, | |
| 'team' => $this->team, | |
| 'position' => $this->position, | |
| 'school' => $this->school | |
| ]; | |
| } | |
| public function printCSV() | |
| { | |
| echo implode(",", $this->toArray()) . "\n"; | |
| } | |
| public function printReadable() | |
| { | |
| echo implode("\t", $this->toArray()) . "\n"; | |
| } | |
| public function isPosition($position) | |
| { | |
| return $position == $this->position; | |
| } | |
| } | |
| libxml_use_internal_errors(true); | |
| $dom = new DOMDocument; | |
| for ($i = 1967; $i < 2015; $i++) { | |
| $page = file_get_contents('http://www.nfl.com/draft/history/fulldraft?season=' . $i); | |
| $dom->loadHTML($page); | |
| $rounds = $dom->getElementsByTagName('table'); | |
| foreach ($rounds as $round) { | |
| $table = $round; | |
| $rows = $table->getElementsByTagName('tr'); | |
| $rowArray = []; | |
| foreach ($rows as $row) { | |
| $rowArray[] = $row; | |
| } | |
| $rowArray = array_slice($rowArray, 2); | |
| foreach ($rowArray as $row) { | |
| $pick = new Pick($row, $i); | |
| $pick->printCSV(); | |
| } | |
| } | |
| } |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment