這幾天關(guān)注了一下PHP的采集程序，才發(fā)現(xiàn)用PHP采集內(nèi)容是這么方便，把經(jīng)常用到的采集函數(shù)在這里總結(jié)一下，方便以后使用!

獲取所有鏈接內(nèi)容和地址

function getAllURL($code){
preg_match_all('/<a\s+href=["|\']?([^>"\' ]+)["|\']?\s*[^>]*>([^>]+)<\/a>/i',$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(dāng)前的腳本網(wǎng)址

function getSelfURL(){
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"];
}
return $nowurl;
}

把全角數(shù)字轉(zhuǎn)為半角數(shù)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(biāo)記

function text2Html($txt){
$txt = str_replace(" ","　",$txt);
$txt = str_replace("<","<",$txt);
$txt = str_replace(">",">",$txt);
$txt = preg_replace("/[\r\n]{1,}/isU","<br/>\r\n",$txt);
return $txt;
}

清除HTML標(biāo)記

function clearHtml($str){
$str = str_replace('<','<',$str);
$str = str_replace('>','>',$str);
return $str;
}

相對(duì)路徑轉(zhuǎn)化成絕對(duì)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(biāo)記中的內(nèi)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(zhuǎn)為CSV格式數(shù)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(biāo)記
$table = preg_replace("'<[\/\!]*?[^<>]*?>'si","",$table);
//去掉空白字符
$table = preg_replace("'([\r\n])[\s]+'","",$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(zhuǎn)為數(shù)組，采集表格數(shù)據(jù)

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(biāo)記
$table = preg_replace("'<[\/\!]*?[^<>]*?>'si","",$table);
//去掉空白字符
$table = preg_replace("'([\r\n])[\s]+'","",$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(fù)

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];
}

相關(guān)推薦：

PHP采集程序中常用的函數(shù)

php 使用CURL函數(shù)采集

以上就是php中常用的采集函數(shù)的總結(jié)（附代碼）的詳細(xì)內(nèi)容，更多請(qǐng)關(guān)注php中文網(wǎng)其它相關(guān)文章！