簡體   English   中英

HTML簡單解析器如何在For Each循環中跳過td內的tr

[英]HTML simple parser How to skip a tr inside a td in For each loop

我有這樣的html內容...

$html = <<<EOF
<table  id="specialTbl">
   <tbody>
      <tr>
         <td> row-1-td-1</td>
         <td> row-1-td-2</td>
         <td> row-1-td-3</td>
         <td>
            <table class="runsOn">  // Problem starts here
               <tbody>
                  <tr>
                    <td>row-1-td-4-Child-1</td> 
                    <td>row-1-td-4-Child-2</td>               
                  </tr>               
               </tbody>
            </table>
         </td>
         <td> row-1-td-5</td>
         <td> row-1-td-6</td>
      </tr>
      <tr>
         <td> row-2-td-1</td>
         <td> row-2-td-2</td>
         <td> row-2-td-3</td>
         <td>
            <table class="runsOn">
               <tbody>
                  <tr>
                    <td>row-2-td-4-Child-1</td>
                    <td>row-2-td-4-Child-2</td>               
                  </tr>               
               </tbody>
            </table>
         </td>
         <td> row-2-td-5</td>
         <td> row-2-td-6</td>
      </tr>
      <tr>
         <td> row-3-td-1</td>
         <td> row-3-td-2</td>
         <td> row-3-td-3</td>
         <td>
            <table class="runsOn">
               <tbody>
                  <tr>
                    <td>row-3-td-4-Child-1</td>
                    <td>row-3-td-4-Child-2</td>               
                  </tr>               
               </tbody>
            </table>
         </td>
         <td> row-3-td-5</td>
         <td> row-3-td-6</td>
      </tr>
      <tr>
         <td> row-4-td-1</td>
         <td> row-4-td-2</td>
         <td> row-4-td-3</td>
         <td>
            <table class="runsOn">
               <tbody>
                  <tr>
                    <td>row-4-td-4-Child-1</td>
                    <td>row-4-td-4-Child-2</td>               
                  </tr>               
               </tbody>
            </table>
         </td>
         <td> row-4-td-5</td>
         <td> row-4-td-6</td>
      </tr>
      <tr>
         <td> row-5-td-1</td>
         <td> row-5-td-2</td>
         <td> row-5-td-3</td>
         <td>
            <table class="runsOn">
               <tbody>
                  <tr>
                    <td>row-5-td-4-Child-1</td>
                    <td>row-5-td-4-Child-2</td>               
                  </tr>               
               </tbody>
            </table>
         </td>
         <td> row-5-td-5</td>
         <td> row-5-td-6</td>
      </tr>
      <tr>
         <td> row-6-td-1</td>
         <td> row-6-td-2</td>
         <td> row-6-td-3</td>
         <td>
            <table class="runsOn">
               <tbody>
                  <tr>
                    <td>row-6-td-4-Child-1</td>
                    <td>row-6-td-4-Child-2</td>               
                  </tr>               
               </tbody>
            </table>
         </td>
         <td> row-6-td-5</td>
         <td> row-6-td-6</td>
      </tr>
      <tr>
         <td> row-7-td-1</td>
         <td> row-7-td-2</td>
         <td> row-7-td-3</td>
         <td>
            <table class="runsOn">
               <tbody>
                  <tr>
                    <td>row-7-td-4-Child-1</td>
                    <td>row-7-td-4-Child-2</td>               
                  </tr>               
               </tbody>
            </table>
         </td>
         <td> row-7-td-5</td>
         <td> row-7-td-6</td>
      </tr>  
   </tbody>
</table>
EOF;



$html= str_get_html($html);
$table =$html->find('table#specialTbl',0) ; 
$response["response_code"] = 200;
$response["rows"]   = array();
foreach($table->find('tr') as $key=>$value) {
 $post["td1"]= trim(strip_tags($value->find('td',0)->plaintext));
 $post["td2"]= trim(strip_tags($value->find('td',1)->plaintext));
 $post["td3"]= trim(strip_tags($value->find('td',2)->plaintext));
 $post["td4"]= trim(strip_tags($value->find('td',3)->plaintext)); 
 $post["td5"]= trim(strip_tags($value->find('td',4)->plaintext));
 $post["td6"]= trim(strip_tags($value->find('td',5)->plaintext)); 
  array_push($response["rows"], $post);  
}
$json = json_encode($response);
echo $json_content;

Json Response是

{
"response_code":200,
"rows":[
{
"td1":"row-1-td-1",
"td2":"row-1-td-2",
"td3":"row-1-td-3",
"td4":"row-1-td-4-Child-1 row-1-td-4-Child-2",
"td5":"row-1-td-4-Child-1",
"td6":"row-1-td-4-Child-2"
},
{
"td1":"row-1-td-4-Child-1",
"td2":"row-1-td-4-Child-2",
"td3":"",
"td4":"",
"td5":"",
"td6":""
},
{
"td1":"row-2-td-1",
"td2":"row-2-td-2",
"td3":"row-2-td-3",
"td4":"row-2-td-4-Child-1 row-2-td-4-Child-2",
"td5":"row-2-td-4-Child-1",
"td6":"row-2-td-4-Child-2"
},
{
"td1":"row-2-td-4-Child-1",
"td2":"row-2-td-4-Child-2",
"td3":"",
"td4":"",
"td5":"",
"td6":""
},
{
"td1":"row-3-td-1",
"td2":"row-3-td-2",
"td3":"row-3-td-3",
"td4":"row-3-td-4-Child-1 row-3-td-4-Child-2",
"td5":"row-3-td-4-Child-1",
"td6":"row-3-td-4-Child-2"
},
{
"td1":"row-3-td-4-Child-1",
"td2":"row-3-td-4-Child-2",
"td3":"",
"td4":"",
"td5":"",
"td6":""
},
{
"td1":"row-4-td-1",
"td2":"row-4-td-2",
"td3":"row-4-td-3",
"td4":"row-4-td-4-Child-1 row-4-td-4-Child-2",
"td5":"row-4-td-4-Child-1",
"td6":"row-4-td-4-Child-2"
},
{
"td1":"row-4-td-4-Child-1",
"td2":"row-4-td-4-Child-2",
"td3":"",
"td4":"",
"td5":"",
"td6":""
},
{
"td1":"row-5-td-1",
"td2":"row-5-td-2",
"td3":"row-5-td-3",
"td4":"row-5-td-4-Child-1 row-5-td-4-Child-2",
"td5":"row-5-td-4-Child-1",
"td6":"row-5-td-4-Child-2"
},
{
"td1":"row-5-td-4-Child-1",
"td2":"row-5-td-4-Child-2",
"td3":"",
"td4":"",
"td5":"",
"td6":""
},
{
"td1":"row-6-td-1",
"td2":"row-6-td-2",
"td3":"row-6-td-3",
"td4":"row-6-td-4-Child-1 row-6-td-4-Child-2",
"td5":"row-6-td-4-Child-1",
"td6":"row-6-td-4-Child-2"
},
{
"td1":"row-6-td-4-Child-1",
"td2":"row-6-td-4-Child-2",
"td3":"",
"td4":"",
"td5":"",
"td6":""
},
{
"td1":"row-7-td-1",
"td2":"row-7-td-2",
"td3":"row-7-td-3",
"td4":"row-7-td-4-Child-1 row-7-td-4-Child-2",
"td5":"row-7-td-4-Child-1",
"td6":"row-7-td-4-Child-2"
},
{
"td1":"row-7-td-4-Child-1",
"td2":"row-7-td-4-Child-2",
"td3":"",
"td4":"",
"td5":"",
"td6":""
}
]
}

問題出在foreach 我怎么能跳過tr一個內部td 我在表中有7行,其ID為“ specialTbl”。 但是, for each循環,它在稱為runsOn的表中循環時會在json中返回14行。

我如何避免在td(4th)內部遍歷表

如下所述,將DomDocument與Xpath一起使用會更容易。 DomDocument已經存在於PHP5中。 它將為您提供所需的輸出。

$doc = new DOMDocument();
$doc->loadHTML($html);
$xpath = new DOMXpath($doc);
$response["response_code"] = 200;
$response["rows"]   = array();
$trs = $xpath->query("//table[@id='specialTbl']/tbody/tr"); // all child tr's in all child tbody's in any table that has id 'specialTbl'
foreach ($trs as $tr) {
    $post = array();
    $tds = $xpath->query("td", $tr); // all child td's in $tr
    foreach ($tds as $key => $td) {
        $post["td" . ++$key] = $td->textContent;
    }
    array_push($response["rows"], $post);
}
$json_content = json_encode($response);
echo $json_content;

但是您也可以繼續使用http://simplehtmldom.sourceforge.net/manual.htm並使用類似CSS的選擇器(未經測試的代碼,我沒有simplehtmldom):

$html= str_get_html($html);
$response["response_code"] = 200;
$response["rows"]   = array();
$trs = $html->find("table#specialTbl>tbody>tr");
foreach ($trs as $tr) {
    $post = array();
    $tds = $tr->children();
    foreach ($tds as $key => $td) {
        $post["td" . ++$key] = $td->innertext;
    }
    array_push($response["rows"], $post);
}
$json_content = json_encode($response);
echo $json_content;

您可以使用PHP的DOM解析器 ,並在搜索tr項之前,先從HTML結構中修剪出所有嵌套表:

// Parse the HTML into a DOM object & find the table by ID
$doc = new DOMDocument();
$doc->loadHTML($html);
$table = $doc->getElementById('specialTbl');

// Remove all nested TRs from the DOM table object
$nested = $table->getElementsByTagName('table');
foreach ($nested as $element)
{
    // Remove the TRs from thi nested table
    foreach ($element->getElementsByTagName('tr') as $tr)
        $tr->parentNode->removeChild($tr);
} 

// Now when we search through TRs, we only get the top level ones
$rows = $table->getElementsByTagName('tr');
$response = array();
foreach ($rows as $row)
{
    // Collect the values of this row's TDs
    $tds = array();
    foreach ($row->getElementsByTagName('td') as $td)
    {
        $tds[] = trim($td->nodeValue);
    }

    // Add this row to the response
    $response['rows'][] = $tds;
}

// Add extra response details
$response['response_code'] = 200; // You shouldn't need to explicitly send this
$json = json_encode($response);

// Output JSON
header('Content-type: application/json'); // Use the correct MIME type
echo $json;

暫無
暫無

聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.

 
粵ICP備18138465號  © 2020-2024 STACKOOM.COM