<?php // Plug-in 22: Get Links From URL
// This is an executable example with additional code supplied
// To obtain just the plug-ins please click on the Download link
$result = PIPHP_GetLinksFromURL("http://pluginphp.com");
echo "<ul>";
for ($j = 0 ; $j < count($result) ; ++$j)
echo "<li>$result[$j]</li>";
function PIPHP_GetLinksFromURL($page)
{
// Plug-in 22: get Links From URL
//
// This plug-in accepts the URL or a web page and returns
// an array of all the links found in it. The argument
// required is:
//
// $page: The web site's main URL
$contents = @file_get_contents($page);
if (!$contents) return NULL;
$urls = array();
$dom = new domdocument();
@$dom ->loadhtml($contents);
$xpath = new domxpath($dom);
$hrefs = $xpath->evaluate("/html/body//a");
for ($j = 0 ; $j < $hrefs->length ; $j++)
$urls[$j] = PIPHP_RelToAbsURL($page,
$hrefs->item($j)->getAttribute('href'));
return $urls;
}
// The below function is repeated here to ensure that it's
// available to the main function which relies on it
function PIPHP_RelToAbsURL($page, $url)
{
// Plug-in 21: Relative To Absolute URL
// This plug-in accepts the absolute URL of a web page
// and a link featured within that page. The link is then
// turned into an absolute URL which can be independently
// accessed. Only applies to http:// URLs. Arguments are:
// $page: The web page containing the URL
// $url: The URL to convert to absolute
if (substr($page, 0, 7) != "http://") return $url;
$parse = parse_url($page);
$root = $parse['scheme'] . "://" . $parse['host'];
$p = strrpos(substr($page, 7), '/');
if ($p) $base = substr($page, 0, $p + 8);
else $base = "$page/";
if (substr($url, 0, 1) == '/') $url = $root . $url;
elseif (substr($url, 0, 7) != "http://") $url = $base . $url;
return $url;
}
?>
插件说明:
本插件接受一个web页面的URL地址,对他进行解析,只寻找"<a href "超链接标签,以数组的形式返回所有找到的超链接地址。他需要一个参数:
$page: 一个web页面的URL地址,包括前导符“http://”和域名。
本文介绍了一个PHP插件,用于从指定网址提取所有超链接,并以数组形式返回。
1万+

被折叠的 条评论
为什么被折叠?



