php采集常见方法和函数

$url="http://www.xxx.com/";
$user_agent = "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)";
$cookiefile="/tmp/getgb.txt";
$ch = curl_init();
curl_setopt ($ch, CURLOPT_URL, $url);
curl_setopt ($ch, CURLOPT_USERAGENT, $user_agent);
curl_setopt ($ch, CURLOPT_COOKIEJAR, $cookiefile);
curl_setopt ($ch, CURLOPT_HEADER, 1);
curl_setopt ($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt ($ch, CURLOPT_FOLLOWLOCATION, 1);
//curl_setopt($ch, CURLOPT_POST, 1);
curl_setopt ($ch, CURLOPT_TIMEOUT, 60);
$result = curl_exec ($ch);

$result=str_replace(array(),array(),$result);

preg_match_all("/\d/",$result,$matches);

<?php
//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"];
        }
        return $nowurl;
}
//把全角数字转为半角数字
function GetAlabNum($fnum){
        $nums = array("０","１","２","３","４","５","６","７","８","９");
        $fnums = "0123456789";
        for($i=0;$i<=9;$i++) $fnum = str_replace($nums[$i],$fnums[$i],$fnum);
        $fnum = ereg_replace("[^0-9\.]|^0{1,}","",$fnum);
        if($fnum=="") $fnum=0;
        return $fnum;
}
//去除HTML标记
function Text2Html($txt){
        $txt = str_replace(" ","　",$txt);
        $txt = str_replace("<","&lt;",$txt);
        $txt = str_replace(">","&gt;",$txt);
        $txt = preg_replace("/[\r\n]{1,}/isU","<br/>\r\n",$txt);
        return $txt;
}

//清除HTML标记
function ClearHtml($str){
        $str = str_replace('<','&lt;',$str);
        $str = str_replace('>','&gt;',$str);
        return $str;
}
//相对路径转化成绝对路径
function relative_to_absolute($content, $feed_url) {
    preg_match('/(http|https|ftp):\/\//', $feed_url, $protocol);
    $server_url = preg_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 $new_content;
}
//取得所有链接
function get_all_url($code){
        preg_match_all('/<a\s+href=["|\']?([^>"\' ]+)["|\']?\s*[^>]*>([^>]+)<\/a>/i',$code,$arr);
        return array('name'=>$arr[2],'url'=>$arr[1]);
}

//获取指定标记中的内容
function get_tag_data($str, $start, $end){
        if ( $start == '' || $end == '' ){
               return;
        }
        $str = explode($start, $str);
        $str = explode($end, $str[1]);
        return $str[0];
}
function str_cut($str,$start,$end){
$str=strstr($str,$start);
$str=substr_replace($str,'',strpos($str,$end)).$end;
return $str;
}
//HTML表格的每行转为CSV格式数组

function get_tr_array($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
        $table = preg_replace("'([\r\n])[\s]+'","",$table);
        $table = str_replace(" ","",$table);
        $table = str_replace(" ","",$table);

        $table = explode(",{tr}",$table);
        array_pop($table);
        return $table;
}

//将HTML表格的每行每列转为数组，采集表格数据
function get_td_array($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
        $table = preg_replace("'([\r\n])[\s]+'","",$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单词 $distinct=true 去除重复
function split_en_str($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];
}
?>

上一篇: php整除方法
下一篇: php字符串处理函数
文章来自: 本站原创
引用通告: 查看所有引用 | 我要引用此文章
Tags: php
相关日志: