blocks|key|1199615|text|要取消警告，您可以使用libxml_use_internal_errors(true)|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|1199616|//+create+new+DOMDocument
$document+=+new+\DOMDocument('1.0',+'UTF-8');

//+set+error+level
$internalErrors+=+libxml_use_internal_errors(true);

//+load+HTML
$document->loadHTML($html);

//+Restore+error+level
libxml_use_internal_errors($internalErrors);|code-block|syntax|javascript|1199617|entityMap|0|LINK|mutability|MUTABLE|url|http://www.php.net/manual/en/function.libxml-use-internal-errors.php^0|B|W|B|W|0|0|0^^$0|@$1|2|3|4|5|6|7|S|8|@$9|T|A|U|B|C]]|D|@$9|V|A|W|1|X]]|E|$]]|$1|F|3|G|5|H|7|Y|8|@]|D|@]|E|$I|J]]|$1|K|3|-4|5|6|7|Z|8|@]|D|@]|E|$]]]|L|$M|$5|N|O|P|E|$Q|R]]]]

To evaporate the warning, you can use <a href="http://www.php.net/manual/en/function.libxml-use-internal-errors.php"><code>libxml_use_internal_errors(true)</code></a>

<pre><code>// create new DOMDocument
$document = new \DOMDocument('1.0', 'UTF-8');

// set error level
$internalErrors = libxml_use_internal_errors(true);

// load HTML
$document-&gt;loadHTML($html);

// Restore error level
libxml_use_internal_errors($internalErrors);
</code></pre>

blocks|key|1414697|text|我敢打赌，如果你查看http://www.somesite.com/的源代码，你会发现一些特殊的字符还没有被转换成超文本标记语言。可能是这样的：|type|unstyled|depth|inlineStyleRanges|offset|length|style|CODE|entityRanges|data|1414698|<a+href="/script.php?foo=bar&hello=world">link</a>|code-block|syntax|javascript|1414699|应该是|1414700|<a+href="/script.php?foo=bar&amp;hello=world">link</a>|1414701|entityMap^0|A|O|0|0|0|0^^$0|@$1|2|3|4|5|6|7|Q|8|@$9|R|A|S|B|C]]|D|@]|E|$]]|$1|F|3|G|5|H|7|T|8|@]|D|@]|E|$I|J]]|$1|K|3|L|5|6|7|U|8|@]|D|@]|E|$]]|$1|M|3|N|5|H|7|V|8|@]|D|@]|E|$I|J]]|$1|O|3|-4|5|6|7|W|8|@]|D|@]|E|$]]]|P|$]]

I would bet that if you looked at the source of <code>http://www.somesite.com/</code> you would find special characters that haven't been converted to HTML. Maybe something like this:

<pre><code>&lt;a href="/script.php?foo=bar&amp;hello=world"&gt;link&lt;/a&gt;
</code></pre>

Should be

<pre><code>&lt;a href="/script.php?foo=bar&amp;amp;hello=world"&gt;link&lt;/a&gt;
</code></pre>

blocks|key|1199511|text|$dom->@loadHTML($html);|type|code-block|depth|inlineStyleRanges|entityRanges|data|syntax|javascript|1199512|这是不正确的，请使用以下命令：|unstyled|1199513|@$dom->loadHTML($html);|1199514|entityMap^0|0|0|0^^$0|@$1|2|3|4|5|6|7|K|8|@]|9|@]|A|$B|C]]|$1|D|3|E|5|F|7|L|8|@]|9|@]|A|$]]|$1|G|3|H|5|6|7|M|8|@]|9|@]|A|$B|C]]|$1|I|3|-4|5|F|7|N|8|@]|9|@]|A|$]]]|J|$]]

<pre><code>$dom-&gt;@loadHTML($html);
</code></pre>

This is incorrect, use this instead:

<pre><code>@$dom-&gt;loadHTML($html);
</code></pre>

blocks|key|1414591|text|致命错误的原因是DOMDocument没有__toString()方法，因此无法回显。|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|1414592|你可能在找|1414593|echo+$dom->saveHTML();|code-block|syntax|javascript|1414594|entityMap|0|LINK|mutability|MUTABLE|url|http://us2.php.net/DOMDocument^0|8|B|0|0|0|0^^$0|@$1|2|3|4|5|6|7|S|8|@]|9|@$A|T|B|U|1|V]]|C|$]]|$1|D|3|E|5|6|7|W|8|@]|9|@]|C|$]]|$1|F|3|G|5|H|7|X|8|@]|9|@]|C|$I|J]]|$1|K|3|-4|5|6|7|Y|8|@]|9|@]|C|$]]]|L|$M|$5|N|O|P|C|$Q|R]]]]

The reason for your fatal error is <a href="http://us2.php.net/DOMDocument" rel="noreferrer">DOMDocument</a> does not have a __toString() method and thus can not be echo'ed. 

You're probably looking for

<pre><code>echo $dom-&gt;saveHTML();
</code></pre>

blocks|key|1414825|text|替换简单的|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1414826|$dom->loadHTML($html);|code-block|syntax|javascript|1414827|更健壮的.|1414828|libxml_use_internal_errors(true);

if+(!$DOM->loadHTML($page))
++++{
++++++++$errors="";
++++++++foreach+(libxml_get_errors()+as+$error)++{
++++++++++++$errors.=$error->message." ";
++++++++}
++++++++libxml_clear_errors();
++++++++print+"libxml+errors: $errors";
++++++++return;
++++}|1414829|entityMap^0|0|0|0|0^^$0|@$1|2|3|4|5|6|7|M|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|N|8|@]|9|@]|A|$E|F]]|$1|G|3|H|5|6|7|O|8|@]|9|@]|A|$]]|$1|I|3|J|5|D|7|P|8|@]|9|@]|A|$E|F]]|$1|K|3|-4|5|6|7|Q|8|@]|9|@]|A|$]]]|L|$]]

replace the simple

<pre><code>$dom-&gt;loadHTML($html);
</code></pre>

with the more robust ...

<pre><code>libxml_use_internal_errors(true);

if (!$DOM-&gt;loadHTML($page))
 {
 $errors="";
 foreach (libxml_get_errors() as $error) {
 $errors.=$error-&gt;message."&lt;br/&gt;";
 }
 libxml_clear_errors();
 print "libxml errors:&lt;br&gt;$errors";
 return;
 }
</code></pre>

blocks|key|1199791|text|$html+=+file_get_contents("http://www.somesite.com/");

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

echo+$dom;|type|code-block|depth|inlineStyleRanges|entityRanges|data|syntax|javascript|1199792|尝尝这个|unstyled|1199793|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$B|C]]|$1|D|3|E|5|F|7|J|8|@]|9|@]|A|$]]|$1|G|3|-4|5|F|7|K|8|@]|9|@]|A|$]]]|H|$]]

<pre><code>$html = file_get_contents("http://www.somesite.com/");

$dom = new DOMDocument();
$dom-&gt;loadHTML(htmlspecialchars($html));

echo $dom;
</code></pre>

try this

blocks|key|1199781|text|我知道这是一个老生常谈的问题，但是如果你想修复HTML中格式错误的'&‘符号。您可以使用类似以下内容的代码：|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1199782|$page+=+file_get_contents('http://www.example.com');
$page+=+preg_replace('/\s%2B/',+'+',+trim($page));
fixAmps($page,+0);
$dom->loadHTML($page);


function+fixAmps(&$html,+$offset)+{
++++$positionAmp+=+strpos($html,+'&',+$offset);
++++$positionSemiColumn+=+strpos($html,+';',+$positionAmp%2B1);

++++$string+=+substr($html,+$positionAmp,+$positionSemiColumn-$positionAmp%2B1);

++++if+($positionAmp+!==+false)+{+//+If+an+'&'+can+be+found.
++++++++if+($positionSemiColumn+===+false)+{+//+If+no+';'+can+be+found.
++++++++++++$html+=+substr_replace($html,+'&amp;',+$positionAmp,+1);+//+Replace+straight+away.
++++++++}+else+if+(preg_match('/&(#[0-9]%2B%7C[A-Z%7Ca-z%7C0-9]%2B);/',+$string)+===+0)+{+//+If+a+standard+escape+cannot+be+found.
++++++++++++$html+=+substr_replace($html,+'&amp;',+$positionAmp,+1);+//+This+mean+we+need+to+escape+the+'&'+sign.
++++++++++++fixAmps($html,+$positionAmp%2B5);+//+Recursive+call+from+the+new+position.
++++++++}+else+{
++++++++++++fixAmps($html,+$positionAmp%2B1);+//+Recursive+call+from+the+new+position.
++++++++}
++++}
}|code-block|syntax|javascript|1199783|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

I know this is an old question, but if you ever want ot fix the malformed '&amp;' signs in your HTML. You can use code similar to this:

<pre><code>$page = file_get_contents('http://www.example.com');
$page = preg_replace('/\s+/', ' ', trim($page));
fixAmps($page, 0);
$dom-&gt;loadHTML($page);


function fixAmps(&amp;$html, $offset) {
 $positionAmp = strpos($html, '&amp;', $offset);
 $positionSemiColumn = strpos($html, ';', $positionAmp+1);

 $string = substr($html, $positionAmp, $positionSemiColumn-$positionAmp+1);

 if ($positionAmp !== false) { // If an '&amp;' can be found.
 if ($positionSemiColumn === false) { // If no ';' can be found.
 $html = substr_replace($html, '&amp;amp;', $positionAmp, 1); // Replace straight away.
 } else if (preg_match('/&amp;(#[0-9]+|[A-Z|a-z|0-9]+);/', $string) === 0) { // If a standard escape cannot be found.
 $html = substr_replace($html, '&amp;amp;', $positionAmp, 1); // This mean we need to escape the '&amp;' sign.
 fixAmps($html, $positionAmp+5); // Recursive call from the new position.
 } else {
 fixAmps($html, $positionAmp+1); // Recursive call from the new position.
 }
 }
}
</code></pre>

blocks|key|1414802|text|另一种可能的解决方案是|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1414803|$sContent+=+htmlspecialchars($sHTML);
$oDom+=+new+DOMDocument();
$oDom->loadHTML($sContent);
echo+html_entity_decode($oDom->saveHTML());|code-block|syntax|javascript|1414804|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

Another possibile solution is

<pre><code>$sContent = htmlspecialchars($sHTML);
$oDom = new DOMDocument();
$oDom-&gt;loadHTML($sContent);
echo html_entity_decode($oDom-&gt;saveHTML());
</code></pre>

blocks|key|1199827|text|另一个可行的解决方案是，也许你的文件是ASCII类型的文件，只要改变你的文件类型即可。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1199828|entityMap^0|0^^$0|@$1|2|3|4|5|6|7|D|8|@]|9|@]|A|$]]|$1|B|3|-4|5|6|7|E|8|@]|9|@]|A|$]]]|C|$]]

Another possibile solution is,maybe your file is ASCII type file,just change the type of your files.

blocks|key|1199863|text|即使这样，我的代码仍然可以正常工作，所以我只是删除了第1行的所有警告消息。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1199864|<?php+error_reporting(E_ERROR);+?>|code-block|syntax|javascript|1199865|entityMap^0|0|0^^$0|@$1|2|3|4|5|6|7|I|8|@]|9|@]|A|$]]|$1|B|3|C|5|D|7|J|8|@]|9|@]|A|$E|F]]|$1|G|3|-4|5|6|7|K|8|@]|9|@]|A|$]]]|H|$]]

Even after this my code is working fine , so i just removed all warning messages with this statement at line 1 .
<pre><code>&lt;?php error_reporting(E_ERROR); ?&gt;
</code></pre>

<pre><code>$html = file_get_contents("http://www.somesite.com/");

$dom = new DOMDocument();
$dom-&gt;loadHTML($html);

echo $dom;
</code></pre>

throws

<pre><code>Warning: DOMDocument::loadHTML(): htmlParseEntityRef: expecting ';' in Entity,
Catchable fatal error: Object of class DOMDocument could not be converted to string in test.php on line 10
</code></pre>

Warning: DOMDocument::loadHTML(): htmlParseEntityRef: expecting ';' in Entity,

$html = file_get_contents("http://www.somesite.com/");$dom = new DOMDocument();$dom->loadHTML($html);echo $dom;抛出Warning: DOMDocument::loadHTML(): htmlParseEntityRef: expecting ';' in Entity,Catchable

问警告: DOMDocument::loadHTML()：htmlParseEntityRef:实体中应为';‘，
EN

回答 10

Stack Overflow用户

Stack Overflow用户

Stack Overflow用户

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问警告: DOMDocument::loadHTML()：htmlParseEntityRef:实体中应为';‘，EN

回答 10

Stack Overflow用户

Stack Overflow用户

Stack Overflow用户

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问警告: DOMDocument::loadHTML()：htmlParseEntityRef:实体中应为';‘，
EN