Created
June 8, 2014 17:27
-
-
Save alexstone/26efb6290923e9052e03 to your computer and use it in GitHub Desktop.
Parse through Chomicron page for comic book sales figures
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
<?php | |
system("clear"); | |
$data = file_get_contents("http://www.comichron.com/monthlycomicssales/2014/2014-04.html"); | |
$dom = new domDocument; | |
@$dom->loadHTML($data); | |
$dom->preserveWhiteSpace = false; | |
$tables = $dom->getElementsByTagName("table"); | |
// Find the largest table to isolate the table we want to work with | |
$top_row_count = 0; | |
foreach($tables as $table) { | |
$rows = $table->getElementsByTagName("tr"); | |
if($rows->length > $top_row_count) { | |
$top_row_count = $rows->length; | |
$data_rows = $rows; | |
} | |
} | |
foreach($data_rows as $data_row) { | |
$cols = $data_row->getElementsByTagName("td"); | |
$rank = $cols->item(0)->nodeValue; | |
$title = preg_replace("/\n/", "", $cols->item(1)->nodeValue); | |
$issue_no = $cols->item(2)->nodeValue; | |
$cover_price = preg_replace("/[^0-9\.]/", "", $cols->item(3)->nodeValue); | |
$publisher = $cols->item(4)->nodeValue; | |
$est_sales = preg_replace("/\,/", "", $cols->item(5)->nodeValue); | |
// Stop once we get to the trade paperbacks | |
if(strtolower($title) == "trade paperback title") | |
break; | |
// Make sure we only work with validated rows | |
if(!empty($est_sales)) { | |
echo "$title #$issue_no, ranked #$rank, selling $est_sales copies at $cover_price\t($" . $est_sales * $cover_price . ")\n"; | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment