大发体育娱乐在线-大发体育娱乐官方网站-大发体育娱乐登录网址
做最好的网站

PHP搜罗程序常用的收罗函数收藏,php去除重复字

来源:http://www.dfwstonefabricators.com 作者:关于计算机 人气:145 发布时间:2019-09-28
摘要:方法一 这几天关注了一下PHP的采集程序,才发现用PHP采集内容是这么方便,把经常用到的采集函数在这里总结一下,方便以后使用! //假定以“;”为每组词的分割符   代码如下 03 $te

方法一

这几天关注了一下PHP的采集程序,才发现用PHP采集内容是这么方便,把经常用到的采集函数在这里总结一下,方便以后使用!

//假定以“;”为每组词的分割符 

 代码如下

03 $text = 'a->b;b->a;c->a;a->c'; 

获取所有链接内容和地址
function getAllURL($code){
preg_match_all('/<as+href=["|']?([^>"' ]+)["|']?s*[^>]*>([^>]+)</a>/i',$code,$arr);
return array('name'=>$arr[2],'url'=>$arr[1]);
}

04 $arr = explode(";", $text); 

获取所有的图片地址
function getImgSrc($code){
$reg = "/]*src="(";
preg_match_all($reg, $code, $img_array, PREG_PATTERN_ORDER);
return $img_array[1];
}

05 $arrSorted = array(); 

当前的脚本网址
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;
}

06 foreach($arr as $str) { 

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++) $fnum = str_replace($nums[$i],$fnums[$i],$fnum);
$fnum = ereg_replace("[^0-9.]|^0{1,}","",$fnum);
if($fnum=="") $fnum=0;
return $fnum;
}

07     list($front, $back) = explode("->", $str); 

去除HTML标记
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;
}

08     //将唯一的字符串保存在$arrSorted的键值里 

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

09     if (!isset($arrSorted[$front.$back]) and !isset($arrSorted[$back.$front])) { 

相对路径转化成绝对路径
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;
}

10         $arrSorted[$front.$back] = $front.'->'.$back;    

获取指定标记中的内容
function getTagData($str, $start, $end){
if ( $start == '' || $end == '' ){
return;
}
$str = explode($start, $str);
$str = explode($end, $str[1]);
return $str[0];
}

11     } 

HTML表格的每行转为CSV格式数组
function getTrArray($table) {
$table = preg_replace("'<td[^>]*?>'si",'"',$table);
$table = str_replace("</td>",'",',$table);
$table = str_replace("</tr>","{tr}",$table);
//去掉 HTML 标记
$table = preg_replace("'<[/!]*?[^<>]*?>'si","",$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;
}

12 } 

将HTML表格的每行每列转为数组,采集表格数据
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 标记
$table = preg_replace("'<[/!]*?[^<>]*?>'si","",$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;
}

13 //打印 

返回字符串中的所有单词 $distinct=true 去除重复
function splitEnStr($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];
}

14 foreach($arrSorted as $str) { 

15     echo $str . '<br/>'; 

16 }

方法二

$reg1 = 'a->b';
$content; //这里是你所有的内容
preg_match_all($reg1, $content, $match); //这里得到的是所有的'a->b'的内容存为数组
preg_replace($reg1, '', $match);

 

本文由大发体育娱乐在线发布于关于计算机,转载请注明出处:PHP搜罗程序常用的收罗函数收藏,php去除重复字

关键词:

最火资讯