omundy/scraper_bbc_regex.php

## scraper_bbc_regex.php
<?php

/*	Basic scraping demo with "foreach" and "regex" parsing
 *	Owen Mundy Copyright 2011 GNU/GPL */

// url to start
$url = "http://www.bbc.co.uk/news/";

// get contents of url in an array
$lines = file($url);

// look for the string
foreach ($lines as $line_num => $line)
{
	// find opening string
	if(strpos($line, '<h2 class="top-story-header ">'))
	{
		$get_content = true;
	}

	// if opening string is found
	// then print content until closing string appears
	if($get_content == true)
	{
		$data .= $line . "\n";
	}

	// closing string
	if(strpos($line, "</h2>"))
	{
		$get_content = false;
	}
}

// use regular expressions to extract only what we need...

// png, jpg, or gif inside a src="..." or src='...'
$pattern = "/src=[\"']?([^\"']?.*(png|jpg|gif))[\"']?/i";
preg_match_all($pattern, $data, $images);

// text from link
$pattern = "/(<a.*>)(\w.*)(<.*>)/ismU";
preg_match_all($pattern, $data, $text);

// link
$pattern = "/(href=[\"'])(.*?)([\"'])/i";
preg_match_all($pattern, $data, $link);

/*
// test if you like
print "<pre>";
print_r($images);
print_r($text);
print_r($link);
print "</pre>";
*/

?>

<html>
<head>
<style>
body { margin:0; }
.textblock { position:absolute; top:600px; left:0px; }
span { font:5.0em/1.0em Arial, Helvetica, sans-serif; line-height:normal;
background:url(trans.png); color:#fff; font-weight:bold; padding:5px }
a { text-decoration:none; color:#900 }
</style>
</head>
<body>
<img src="<?php print $images[1][0] ?>" height="100%"> </div>
<div class="textblock"><span><a href="<?php print "http://www.bbc.co.uk".$link[2][0] ?>"><?php print $text[2][0] ?></a></span><br>
</div>
</body>
</html>
	<?php

	/* Basic scraping demo with "foreach" and "regex" parsing
	* Owen Mundy Copyright 2011 GNU/GPL */

	// url to start
	$url = "http://www.bbc.co.uk/news/";

	// get contents of url in an array
	$lines = file($url);

	// look for the string
	foreach ($lines as $line_num => $line)
	{
	// find opening string
	if(strpos($line, '<h2 class="top-story-header ">'))
	{
	$get_content = true;
	}

	// if opening string is found
	// then print content until closing string appears
	if($get_content == true)
	{
	$data .= $line . "\n";
	}

	// closing string
	if(strpos($line, "</h2>"))
	{
	$get_content = false;
	}
	}

	// use regular expressions to extract only what we need...

	// png, jpg, or gif inside a src="..." or src='...'
	$pattern = "/src=[\"']?([^\"']?.*(png\|jpg\|gif))[\"']?/i";
	preg_match_all($pattern, $data, $images);

	// text from link
	$pattern = "/(<a.>)(\w.)(<.*>)/ismU";
	preg_match_all($pattern, $data, $text);

	// link
	$pattern = "/(href=[\"'])(.*?)([\"'])/i";
	preg_match_all($pattern, $data, $link);

	/*
	// test if you like
	print "<pre>";
	print_r($images);
	print_r($text);
	print_r($link);
	print "</pre>";
	*/

	?>

	<html>
	<head>
	<style>
	body { margin:0; }
	.textblock { position:absolute; top:600px; left:0px; }
	span { font:5.0em/1.0em Arial, Helvetica, sans-serif; line-height:normal;
	background:url(trans.png); color:#fff; font-weight:bold; padding:5px }
	a { text-decoration:none; color:#900 }
	</style>
	</head>
	<body>
	<img src="<?php print $images[1][0] ?>" height="100%"> </div>
	<div class="textblock"><span><a href="<?php print "http://www.bbc.co.uk".$link[2][0] ?>"><?php print $text[2][0] ?></a></span><br>
	</div>
	</body>
	</html>