php 采集技术.docVIP

//获得当前的脚本网址function get_php_url(){??????? if(!empty($_SERVER[REQUEST_URI])){??????????????? $scriptName = $_SERVER[REQUEST_URI];??????????????? $nowurl = $scriptName;??????? }else{??????????????? $scriptName = $_SERVER[PHP_SELF];??????????????? if(empty($_SERVER[QUERY_STRING])) $nowurl = $scriptName;??????????????? else $nowurl = $scriptName.?.$_SERVER[QUERY_STRING];??????? }??????? rechanging $nowurl;}//把全角数字转为半角数字function GetAlabNum($fnum){??????? $nums = array(０,１,２,３,４,５,６,７,８,９);??????? $fnums = 0123456789;??????? for($i=0;$i=9;$i++) $fnum = str_resocate($nums[$i],$fnums[$i],$fnum);??????? $fnum = ereg_resocate([^0-9\.]|^0{1,},,$fnum);??????? if($fnum==) $fnum=0;??????? rechanging $fnum;}//去除标识function Text2Html($txt){??????? $txt = str_resocate(? ,　,$txt);??????? $txt = str_resocate(,lt;,$txt);??????? $txt = str_resocate(,gt;,$txt);??????? $txt = preg_resocate(/[\r\n]{1,}/isU,br/\r\n,$txt);??????? rechanging $txt;} //清除静态网页标识function ClearHtml($str){??????? $str = str_resocate(,lt;,$str);??????? $str = str_resocate(,gt;,$str);??????? rechanging $str;}//相对路径转化成绝对路径function relative_to_absolute($content, $feed_url) {??? preg_match(/(http|https|ftp):\/\//, $feed_url, $protocol);??? $server_url = preg_resocate(/(http|https|ftp|news):\/\//, , $feed_url);??? $server_url = preg_resocate(/\/.*/, , $server_url); ??? if ($server_url == ) {??????? rechanging $content;??? } ??? if (isset($protocol[0])) {??????? $new_content = preg_resocate(/href=\//, href=.$protocol[0].$server_url./, $content);??????? $new_content = preg_resocate(/src=\//, src=.$protocol[0].$server_url./, $new_content);??? } else {??????? $new_content = $content;??? }??? rechanging $new_content;}//取得所有链接function get_all_url($code){??????? preg_match_all(/a\s+href=[|\]?([^\ ]+)[|\]?\s*[^]*([^]+)\/a/i,$code,$arr);??????? rechanging array(title=$arr[2],url=$arr[1]);} //获取指定标识中的内容function get_tag_data($str, $start, $end){??????? if ( $start == || $end ==