Question

我有PHP报废脚本，它从另一个网站获取HTML表格内容。该脚本不会获取HTML特殊字符（标记），这会导致内容看起来没有格式化。

如何修改以下代码以获取HTML特殊字符，包括所有标记？

完整代码：

<?php
error_reporting(E_ERROR);
set_time_limit(0);

function createRSSFile($tag,$value,$data)
{
    # this will return the each element with tag.
    $tag=strtolower(str_replace(" ","_",$tag));
    $tag=strtolower(str_replace(":","",$tag));
    $tag=strtolower(str_replace("&","and",$tag));
    //  $returnITEM = "<".$tag.">".htmlspecialchars(str_replace(" 00:00:00","",$value))."</".$tag.">";
    $returnITEM = "<".$tag.">".htmlspecialchars(str_replace("â¢","<br/><br/> ",$value))."</".$tag.">";
    return $returnITEM;
} 

// function extraFields($data){
//print_r($data);

//  $returnITEM = "<".strtolower(str_replace(" ","_",$data[18][0])).">".htmlspecialchars($data[18][1])."</".strtolower(str_replace(" ","_",$data[18][0])).">";
//  $returnITEM = "<".strtolower(str_replace("&","or",$data[19][0])).">".htmlspecialchars($data[19][1])."</".strtolower(str_replace("&","or",$data[19][0])).">";
//  $returnITEM .= "<".strtolower(str_replace(" ","_",$data[20][0])).">".htmlspecialchars($data[20][1])."</".strtolower(str_replace(" ","_",$data[20][0])).">";
//  $returnITEM .= "<".strtolower(str_replace(" ","_",$data[22][0])).">".htmlspecialchars($data[23][0])."</".strtolower(str_replace(" ","_",$data[22][0])).">";
//  $returnITEM .= "<".strtolower(str_replace(" ","_",$data[24][0])).">".htmlspecialchars($data[25][0])."</".strtolower(str_replace(" ","_",$data[24][0])).">";
//  $returnITEM .= "<".strtolower(str_replace(" ","_",$data[26][0])).">".htmlspecialchars($data[26][1])."</".strtolower(str_replace(" ","_",$data[26][0])).">";
//  preg_match('/[a-z0-9]+([_\\.-][a-z0-9]+)*@([a-z0-9]+([\.-][a-z0-9]+)*)+\\.[a-z]{2,}/i',$data[25][0],$email);
//  $email=$email[0];
//  $returnITEM .= "<email>".$email."</email>";
//  return $returnITEM;

// }

function fileRead(){
    $filename = "count.txt";
    $handle = fopen($filename, "r");
    $contents = fread($handle, filesize($filename));
    fclose($handle);
    return $contents;
}

function fileWrite ($val) {
    $filename = 'count.txt';
    $somecontent = $val;

    if (is_writable($filename)) {
        if (!$handle = fopen($filename, 'w')) {
            echo "Cannot open file ($filename)";
            exit;
        }
        if (fwrite($handle, $somecontent) === FALSE) {
            echo "Cannot write to file ($filename)";
            exit;
        }
        fclose($handle);
    } else {
        echo "The file $filename is not writable";
    } 
}

function fetchData($jobid) {
    $html=file_get_contents('http://acbar.org/JobDetail.aspx?id='.$jobid);
    $html=str_replace("<td></td>", "",$html);
    $html=str_replace("<td style=\"font-size:8pt;font-weight:bold;\"></td>","<td style=\"font-size:8pt;font-weight:bold;\">Null</td>",$html);
    $html=str_replace("<td style=\"font-size:8pt;font-weight:bold;\" colspan=\"2\" ></td>","<td style=\"font-size:8pt;font-weight:bold;\" colspan=\"2\" >Null</td>",$html);

    $html=str_replace("&nbsp;", " ",$html);
    $html=str_replace("", "<br>",$html);
    $html=str_replace("<br>", "_br_",$html);
    // $html=str_replace("\â\u","'",$html);


    $dom = new DOMDocument;
    $dom->loadHTML( $html );

   //echo $dom->saveHTML();
   //exit;
    $rows = array();
    foreach( $dom->getElementsByTagName( 'tr' ) as $tr ) {
        $cells = array();
        foreach( $tr->getElementsByTagName( 'td' ) as $td ) {
            if(trim($td->nodeValue)!='')
                $cells[] = str_replace("br","<br>",trim($td->nodeValue));
            }
            if(sizeof($cells)>0)
                $rows[] = $cells;
        }
        for($i=0;$i<0;$i++) 
            array_shift ($rows);
        // echo "<pre>"; print_r($rows); echo "</pre>";
        // exit;

        if($rows[0][1]=="")
            return false;  
        else
            return $rows;  
    }

// Lets build the page
$latestBuild = date("r");

// Lets define the the type of doc we're creating.
$createXML ="<?xml version=\"1.0\" encoding=\"UTF-8\" ?>";
$createXML .= "<rss version=\"0.92\">";
$createXML .= "<channel>
    <title>Job List</title>
    <link>http://acbar.org</link>
    <description>Job List</description>
    <lastBuildDate>$latestBuild</lastBuildDate>
    <language>en</language>";
 $startFrom=fileRead();
 $startFrom=$startFrom+1;
 $endWith=$startFrom+3;


for($jid=$startFrom;$jid<$endWith;$jid++) {
    $data=fetchData($jid);

    if(!$data) 
        break;

    $srcurl='http://acbar.org/JobDetail.aspx?id='.$jid;

    $createXML .= '<item><sourceurl>'.htmlspecialchars($srcurl).'</sourceurl>';
    for($i=0;$i<23;$i++) 
    {
        $tag=$data[$i][0];
        $value=$data[$i][1];
        $createXML .= createRSSFile($tag,$value,$data);
    }
    // $extra=extraFields($data);
    // $createXML .= $extra;
    $createXML .= "</item>";
    // fileWrite($jid);
}
// preg_match('/[a-z0-9]+([_\\.-][a-z0-9]+)*@([a-z0-9]+([\.-][a-z0-9]+)*)+\\.[a-z]{2,}/i',$data[26][1],$email);
// $email=$email[0];

header("content-type: text/xml");
echo $createXML .= "</channel></rss>";

?>

Answer 1

这适合我...

function fetchData($jobid) {
    $html=file_get_contents('http://acbar.org/JobDetail.aspx?id='.$jobid);
    $html=str_replace("<td></td>", "",$html);
    $html=str_replace("&nbsp;", " ",$html);
    $html=str_replace("<br/>", "_br_",$html);

    $dom = new DOMDocument;
    $html = mb_convert_encoding($html, "HTML-ENTITIES", "UTF-8"); 
    $dom->loadHTML($html);
    $rows = array();
    foreach( $dom->getElementsByTagName( 'tr' ) as $tr ) {
        $cells = array();
        foreach( $tr->getElementsByTagName( 'td' ) as $td ) {
            if(trim($td->nodeValue)!='')
                $cells[] = htmlspecialchars(trim($td->nodeValue));
        }
        if(sizeof($cells)>0)
            $rows[] = $cells;
    }

    // this will return the each element with tag.
    foreach($rows as $ntag){
        $tag = strtolower(str_replace(" ","_",$ntag[0]));
        $tag = strtolower(str_replace(":","",$tag));
        $tag = strtolower(str_replace("&","and",$tag));
        $returnITEM .= "<".$tag.">".str_replace('_br_', '<br />', htmlspecialchars(str_replace(" 00:00:00","",$ntag[1])))."</".$tag.">";
    }

    return $returnITEM;
} 

echo fetchData(3350);

编辑...添加了$html = mb_convert_encoding($html, "HTML-ENTITIES", "UTF-8");

获取html表数据的特殊字符

1 个答案: