這幾天關注了一下PHP的采集程序,才發現用PHP采集內容是這么方便,把經常用到的采集函數在這里總結一下,方便以后使用.
在php采集頁面中最常用的就是過濾一些特殊字符或把內容中的圖片也采集保存下來,下面我來給大家介紹我在寫php采集程序時一些常用的函數.
- 獲取所有鏈接內容和地址
- function getAllURL($code){
- preg_match_all('/<as+href=["|']?([^>"' ]+)["|']?s*[^>]*>([^>]+)</a>/i',$code,$arr);
- return array('name'=>$arr[2],'url'=>$arr[1]);
- }
- 獲取所有的圖片地址
- function getImgSrc($code){
- $reg = "/]*src="(http://(.+)/(.+).(jpg|gif|bmp|bnp|png))"/isU";
- preg_match_all($reg, $code, $img_array, PREG_PATTERN_ORDER);
- return $img_array[1];
- }
- 當前的腳本網址
- function getSelfURL(){
- if(!emptyempty($_SERVER["REQUEST_URI"])){
- $scriptName = $_SERVER["REQUEST_URI"];
- $nowurl = $scriptName;
- }else{
- $scriptName = $_SERVER["PHP_SELF"];
- if(emptyempty($_SERVER["QUERY_STRING"])) $nowurl = $scriptName;
- else $nowurl = $scriptName."?".$_SERVER["QUERY_STRING"];
- }
- return $nowurl;
- }
- 把全角數字轉為半角數字
- function getAlabNum($fnum){
- $nums = array("0","1","2","3","4","5","6","7","8","9");
- $fnums = "0123456789";
- for($i=0;$i<=9;$i++) $fnum = str_replace($nums[$i],$fnums[$i],$fnum);
- $fnum = ereg_replace("[^0-9.]|^0{1,}","",$fnum);
- if($fnum=="") $fnum=0;
- return $fnum;
- }
- 去除HTML標記
- function text2Html($txt){
- $txt = str_replace(" "," ",$txt);
- $txt = str_replace("<","<",$txt);
- $txt = str_replace(">",">",$txt);
- $txt = preg_replace("/[rn]{1,}/isU","<br/>rn",$txt);
- return $txt;
- }
- 清除HTML標記
- function clearHtml($str){
- $str = str_replace('<','<',$str);
- $str = str_replace('>','>',$str);
- return $str;
- }
- 相對路徑轉化成絕對路徑
- function relative2Absolute($content, $feed_url) {
- preg_match('/(http|https|ftp):///', $feed_url, $protocol);
- $server_url = preg_replace("/(http|https|ftp|news):///", "", $feed_url);
- $server_url = preg_replace("//.*/", "", $server_url);
- if ($server_url == '') {
- return $content;
- }
- if (isset($protocol[0])) {
- $new_content = preg_replace('/href="//', 'href="'.$protocol[0].$server_url.'/', $content);
- $new_content = preg_replace('/src="//', 'src="'.$protocol[0].$server_url.'/', $new_content);
- } else {
- $new_content = $content;
- }
- return $new_content;
- }
- 獲取指定標記中的內容
- function getTagData($str, $start, $end){
- if ( $start == '' || $end == '' ){
- return;
- }
- $str = explode($start, $str);
- $str = explode($end, $str[1]);
- return $str[0];
- }
- HTML表格的每行轉為CSV格式數組
- function getTrArray($table) {
- $table = preg_replace("'<td[^>]*?>'si",'"',$table);
- $table = str_replace("</td>",'",',$table);
- $table = str_replace("</tr>","{tr}",$table);
- //去掉 HTML 標記
- $table = preg_replace("'<[/!]*?[^<>]*?>'si","",$table);
- //去掉空白字符
- $table = preg_replace("'([rn])[s]+'","",$table);
- $table = str_replace(" ","",$table);
- $table = str_replace(" ","",$table);
- $table = explode(",{tr}",$table);
- array_pop($table);
- return $table;
- }
- 將HTML表格的每行每列轉為數組,采集表格數據
- function getTdArray($table) {
- $table = preg_replace("'<table[^>]*?>'si","",$table);
- $table = preg_replace("'<tr[^>]*?>'si","",$table);
- $table = preg_replace("'<td[^>]*?>'si","",$table);
- $table = str_replace("</tr>","{tr}",$table);
- $table = str_replace("</td>","{td}",$table);
- //去掉 HTML 標記
- $table = preg_replace("'<[/!]*?[^<>]*?>'si","",$table);
- //去掉空白字符
- $table = preg_replace("'([rn])[s]+'","",$table);
- $table = str_replace(" ","",$table);
- $table = str_replace(" ","",$table);
- $table = explode('{tr}', $table);
- array_pop($table);
- foreach ($table as $key=>$tr) {
- $td = explode('{td}', $tr);
- array_pop($td);
- $td_array[] = $td;
- }
- return $td_array;
- }
- 返回字符串中的所有單詞 $distinct=true 去除重復
- function splitEnStr($str,$distinct=true) {
- preg_match_all('/([a-zA-Z]+)/',$str,$match);
- if ($distinct == true) {
- $match[1] = array_unique($match[1]);
- }
- sort($match[1]);
- return $match[1];
- }
新聞熱點
疑難解答