首页 / 网页编程 / PHP / php解析字符串里所有URL地址的方法

<?php// $html = the html on the page// $current_url = the full url that the html came from//（only needed for $repath）// $repath = converts ../ and / and // urls to full valid urlsfunction pageLinks（$html, $current_url = "", $repath = false）{preg_match_all（"/<a.+?href=（"|"）（?！javascript:|#）（.+?）（"|"）/i", $html, $matches）;$links = array（）;if（isset（$matches[2]））{$links = $matches[2];}if（$repath && count（$links） > 0 && strlen（$current_url） > 0）{$pathi = pathinfo（$current_url）;$dir= $pathi["dirname"];$base= parse_url（$current_url）;$split_path = explode（"/", $dir）;$url= "";foreach（$links as $k => $link）{if（preg_match（"/^../", $link））{$total = substr_count（$link, "../"）;for（$i = 0; $i < $total; $i++）{array_pop（$split_path）;}$url = implode（"/", $split_path） . "/" . str_replace（"../", "", $link）;}elseif（preg_match（"/^///", $link））{$url = $base["scheme"] . ":" . $link;}elseif（preg_match（"/^/|^.//", $link））{$url = $base["scheme"] . "://" . $base["host"] . $link;}elseif（preg_match（"/^[a-zA-Z0-9]/", $link））{if（preg_match（"/^http/", $link））{$url = $link;}else{$url= $dir . "/" . $link;}}$links[$k] = $url;}}return $links;}header（"content-type: text/plain"）;$url = "http://www.jb51.net";$html = file_get_contents（$url）;// Gets links from the page:print_r（pageLinks（$html））;// Gets links from the page and formats them to a full valid url:print_r（pageLinks（$html, $url, true））;