Php 在使用DomDocument解析html时，是否有方法保持实体完整？
我有这个功能来确保每个img标签都有绝对URL：Php 在使用DomDocument解析html时，是否有方法保持实体完整？,php,domdocument,entities,Php,Domdocument,Entities,我有这个功能来确保每个img标签都有绝对URL： function absoluteSrc($html, $encoding = 'utf-8') { $dom = new DOMDocument(); // Workaround to use proper encoding $prehtml = "<html><head><meta http-equiv=\"Content-Type\" content=\"text/html; char
function absoluteSrc($html, $encoding = 'utf-8')
{
$dom = new DOMDocument();
// Workaround to use proper encoding
$prehtml = "<html><head><meta http-equiv=\"Content-Type\" content=\"text/html; charset={$encoding}\"></head><body>";
$posthtml = "</body></html>";
if($dom->loadHTML( $prehtml . trim($html) . $posthtml)){
foreach($dom->getElementsByTagName('img') as $img){
if($img instanceof DOMElement){
$src = $img->getAttribute('src');
if( strpos($src, 'http://') !== 0 ){
$img->setAttribute('src', 'http://my.server/' . $src);
}
}
}
$html = $dom->saveHTML();
// Remove remains of workaround / DomDocument additions
$cut_start = strpos($html, '<body>') + 6;
$cut_length = -1 * (1+strlen($posthtml));
$html = substr($html, $cut_start, $cut_length);
}
return $html;
}
function absoluteSrc（$html，$encoding='utf-8'）
{
$dom=新的DOMDocument（）；
//使用正确编码的变通方法
$prehtml=“”；
$posthtml=“”；
if（$dom->loadHTML（$prehtml.trim（$html）。$posthtml））{
foreach（$dom->getElementsByTagName（'img'）作为$img）{
如果（$img-instanceof-domeElement）{
$src=$img->getAttribute（'src'）；
if（strpos（$src，'http://'）！==0）{
$img->setAttribute（'src'，'http://my.server/“.$src）；
}
}
}
$html=$dom->saveHTML（）；
//删除剩余的解决方法/DOM文档添加
$cut_start=strpos（$html，'）+6；
$cut_length=-1*（1+strlen（$posthtml））；
$html=substr（$html，$cut\u start，$cut\u length）；
}
返回$html；
}
$html = <<< EOHTML
<p><img src="images/lorem.jpg" alt="lorem" align="left">
Lorem ipsum dolor sit amet consectetuer Nullam felis laoreet
Cum magna. Suscipit sed vel tincidunt urna.<br>
Vel consequat pretium Curabitur faucibus justo adipiscing elit.
<img src="others/ipsum.png" alt="ipsum" align="right"></p>
<center>© Dr Jekyll & Mr Hyde</center>
EOHTML;
echo absoluteSrc($html);
$html=我也想知道这个问题的答案
我最终转变了&。。；在解析之前将实体转换为**ENTITY-…-ENTITY**
，并在解析完成后将其转换回。以下代码似乎有效
$dom= new DOMDocument('1.0', 'UTF-8');
$dom->loadHTML($this->htmlentities2stringcode(rawurldecode($content)) );
$dom->preserveWhiteSpace = true;
$innerHTML = str_replace("<html></html><html><body>", "",
str_replace("</body></html>", "",
str_replace("+","%2B",str_replace("<p></p>", "", $this->getInnerHTML( $dom )))));
return $this->stringcode2htmlentities($innerHTML));
}
// ----------------------------------------------------------
function htmlentities2stringcode($string) {
// This method will convert htmlentities such as © into the pseudo string version ^copy^; etc
$from = array_keys($this->getHTMLEntityStringCodeArray());
$to = array_values($this->getHTMLEntityStringCodeArray());
return str_replace($from, $to, $string);
}
// ----------------------------------------------------------
function stringcode2htmlentities ($string) {
// This method will convert pseudo string such as ^copy^ to the original html entity © etc
$from = array_values($this->getHTMLEntityStringCodeArray());
$to = array_keys($this->getHTMLEntityStringCodeArray());
return str_replace($from, $to, $string);
}
// -------------------------------------------------------------
function getHTMLEntityStringCodeArray() {
return array('Α'=>'^Alpha^',
'Β'=>'^Beta^',
'Χ'=>'^Chi^',
'‡'=>'^Dagger^',
'Δ'=>'^Delta^',
'Ε'=>'^Epsilon^',
'Η'=>'^Eta^',
'Γ'=>'^Gamma^',
'Ι'=>'^lota^',
'Κ'=>'^Kappa^',
'Λ'=>'^Lambda^',
'Μ'=>'^Mu^',
'Ν'=>'^Nu^',
'Œ'=>'^OElig^',
'Ω'=>'^Omega^',
'Ο'=>'^Omicron^',
'Φ'=>'^Phi^',
'Π'=>'^Pi^',
'″'=>'^Prime^',
'Ψ'=>'^Psi^',
'Ρ'=>'^Rho^',
'Š'=>'^Scaron^',
'Š'=>'^Scaron^',
'Σ'=>'^Sigma^',
'Τ'=>'^Tau^',
'Θ'=>'^Theta^',
'Υ'=>'^Upsilon^',
'Ξ'=>'^Xi^',
'Ÿ'=>'^Yuml^',
'Ζ'=>'^Zeta^',
'ℵ'=>'^alefsym^',
'α'=>'^alpha^',
'∧'=>'^and^',
'∠'=>'^ang^',
'≈'=>'^asymp^',
'„'=>'^bdquo^',
'β'=>'^beta^',
'•'=>'^bull^',
'∩'=>'^cap^',
'χ'=>'^chi^',
'ˆ'=>'^circ^',
'♣'=>'^clubs^',
'≅'=>'^cong^',
'↵'=>'^crarr^',
'∪'=>'^cup^',
'⇓'=>'^dArr^',
'†'=>'^dagger^',
'↓'=>'^darr^',
'δ'=>'^delta^',
'♦'=>'^diams^',
'∅'=>'^empty^',
' '=>'^emsp^',
' '=>'^ensp^',
'ε'=>'^epsilon^',
'≡'=>'^equiv^',
'η'=>'^eta^',
'€'=>'^euro^',
'∃'=>'^exist^',
'ƒ'=>'^fnof^',
'∀'=>'^forall^',
'⁄'=>'^frasl^',
'γ'=>'^gamma^',
'≥'=>'^ge^',
'⇔'=>'^hArr^',
'↔'=>'^harr^',
'♥'=>'^hearts^',
'…'=>'^hellip^',
'ℑ'=>'^image^',
'∞'=>'^infin^',
'∫'=>'^int^',
'ι'=>'^iota^',
'∈'=>'^isin^',
'κ'=>'^kappa^',
'⇐'=>'^lArr^',
'λ'=>'^lambda^',
'⟨'=>'^lang^',
'←'=>'^larr^',
'⌈'=>'^lceil^',
'“'=>'^ldquo^',
'≤'=>'^le^',
'⌊'=>'^lfloor^',
'∗'=>'^lowast^',
'◊'=>'^loz^',
'‎'=>'^lrm^',
'‹'=>'^lsaquo^',
'‘'=>'^lsquo^',
'—'=>'^mdash^',
'−'=>'^minus^',
'μ'=>'^mu^',
'∇'=>'^nabla^',
'–'=>'^ndash^',
'≠'=>'^ne^',
'∋'=>'^ni^',
'∉'=>'^notin^',
'⊄'=>'^nsub^',
'ν'=>'^nu^',
'œ'=>'^oelig^',
'‾'=>'^oline^',
'ω'=>'^omega^',
'ο'=>'^omicron^',
'⊕'=>'^oplus^',
'∨'=>'^or^',
'⊗'=>'^otimes^',
'∂'=>'^part^',
'‰'=>'^permil^',
'⊥'=>'^perp^',
'φ'=>'^phi^',
'π'=>'^pi^',
'ϖ'=>'^piv^',
'′'=>'^prime^',
'∏'=>'^prod^',
'∝'=>'^prop^',
'ψ'=>'^psi^',
'⇒'=>'^rArr^',
'√'=>'^radic^',
'⟩'=>'^rang^',
'→'=>'^rarr^',
'⌉'=>'^rceil^',
'”'=>'^rdquo^',
'ℜ'=>'^real^',
'⌋'=>'^rfloor^',
'ρ'=>'^rho^',
'‏'=>'^rlm^',
'›'=>'^rsaquo^',
'’'=>'^rsquo^',
'‚'=>'^sbquo^',
'š'=>'^scaron^',
'⋅'=>'^sdot^',
'σ'=>'^sigma^',
'ς'=>'^sigmaf^',
'∼'=>'^sim^',
'♠'=>'^spades^',
'⊂'=>'^sub^',
'⊆'=>'^sube^',
'∑'=>'^sum^',
'⊃'=>'^sup^',
'⊇'=>'^supe^',
'τ'=>'^tau^',
'∴'=>'^there4^',
'θ'=>'^thetasym^',
'ϑ'=>'^thetasym^',
' '=>'^thinsp^',
'˜'=>'^tilde^',
'™'=>'^trade^',
'⇑'=>'^uArr^',
'↑'=>'^uarr^',
'ϒ'=>'^upsih^',
'υ'=>'^upsilon^',
'℘'=>'^weierp^',
'ξ'=>'^xi^',
'ÿ'=>'^yuml^',
'ζ'=>'^zeta^',
'‍'=>'^zwj^',
'‌'=>'^zwnj^');
}
$dom=新的DOMDocument（'1.0'，'UTF-8'）；
$dom->loadHTML（$this->htmlentities2stringcode（rawurldecode（$content））；
$dom->preserveWhiteSpace=true；
$innerHTML=str_replace（“，”，
str_替换（“，”，
str_replace（“+”，“%2B”，str_replace（“”，“，$this->getInnerHTML（$dom‘）！”）；
返回$this->stringcode2htmlentities（$innerHTML））；
}
// ----------------------------------------------------------
函数htmlentities2stringcode（$string）{
//此方法将把诸如©；之类的HTML属性转换为伪字符串版本^copy^；等
$from=array_keys（$this->getHTMLEntityStringCodeArray（））；
$to=array_值（$this->getHTMLEntityStringCodeArray（））；
返回str_replace（$from，$to，$string）；
}
// ----------------------------------------------------------
函数stringcode2htmlentities（$string）{
//此方法将伪字符串（如^copy^）转换为原始html实体©；等
$from=array_值（$this->getHTMLEntityStringCodeArray（））；
$to=array_key（$this->getHTMLEntityStringCodeArray（））；
返回str_replace（$from，$to，$string）；
}
// -------------------------------------------------------------
函数getHTMLEntityStringCodeArray（）{
返回数组（“&Alpha；”=>“^Alpha^”，
“&Beta；”=>“^Beta^”，
“&Chi；”=>“^Chi^”，
“&Dagger；”=>“^Dagger^”，
“&Delta；”=>“^Delta^”，
“&Epsilon；”=>“^Epsilon^”，
“&Eta；”=>“^Eta^”，
“&Gamma；”=>“^Gamma^”，
“&Iota；”=>“^lota^”，
“&Kappa；”=>“^Kappa^”，
“&Lambda；”=>“^Lambda^”，
“&Mu；”=>“^Mu^”，
“&Nu；”=>“^Nu^”，
“&OElig；”=>“^OElig^”，
“&Omega；”=>“^Omega^”，
“&Omicron；”=>“^Omicron^”，
“&Phi；”=>“^Phi^”，
“&Pi；”=>“^Pi^”，
“&Prime；”=>“^Prime^”，
“&Psi；”=>“^Psi^”，
“&Rho；”=>“^Rho^”，
“&Scaron；”=>“^Scaron^”，
“&Scaron；”=>“^Scaron^”，
“&Sigma；”=>“^Sigma^”，
“&Tau；”=>“^Tau^”，
“&Theta；”=>“^Theta^”，
“&Upsilon；”=>“^Upsilon^”，
“&Xi；”=>“^Xi^”，
“&Yuml；”=>“^Yuml^”，
“&Zeta；”=>“^Zeta^”，
“&alefsym；”=>“^alefsym^”，
“&alpha；”=>“^alpha^”，
“&和；”=>“^和^”，
“&ang；”=>“^ang^”，
“&asymp；”=>“^asymp^”，
“&bdquo；”=>“^bdquo^”，
“&beta；”=>“^beta^”，
“&bull；”=>“^bull^”，
“&cap；”=>“^cap^”，
“&chi；”=>“^chi^”，
“&circ；”=>“^circ^”，
“&clubs；”=>“^clubs^”，
“&cong；”=>“^cong^”，
“&crarr；”=>“^crarr^”，
“&cup；”=>“^cup^”，
“&dArr；”=>“^dArr^”，
“&dagger；”=>“^dagger^”，
“&darr；”=>“^darr^”，
“&delta；”=>“^delta^”，
“&diams；”=>“^diams^”，
“&empty；”=>“^empty^”，
“&emsp；”=>“^emsp^”，
“&ensp；”=>“^ensp^”，
“&epsilon；”=>“^epsilon^”，
“&equiv；”=>“^equiv^”，
“&eta；”=>“^eta^”，
“&euro；”=>“^euro^”，
“&exist；”=>“^exist^”，
“&fnof；”=>“^fnof^”，
“&forall；”=>“^forall^”，
$dom= new DOMDocument('1.0', 'UTF-8');
$dom->loadHTML($this->htmlentities2stringcode(rawurldecode($content)) );
$dom->preserveWhiteSpace = true;
$innerHTML = str_replace("<html></html><html><body>", "",
str_replace("</body></html>", "",
str_replace("+","%2B",str_replace("<p></p>", "", $this->getInnerHTML( $dom )))));
return $this->stringcode2htmlentities($innerHTML));
}
// ----------------------------------------------------------
function htmlentities2stringcode($string) {
// This method will convert htmlentities such as © into the pseudo string version ^copy^; etc
$from = array_keys($this->getHTMLEntityStringCodeArray());
$to = array_values($this->getHTMLEntityStringCodeArray());
return str_replace($from, $to, $string);
}
// ----------------------------------------------------------
function stringcode2htmlentities ($string) {
// This method will convert pseudo string such as ^copy^ to the original html entity © etc
$from = array_values($this->getHTMLEntityStringCodeArray());
$to = array_keys($this->getHTMLEntityStringCodeArray());
return str_replace($from, $to, $string);
}
// -------------------------------------------------------------
function getHTMLEntityStringCodeArray() {
return array('Α'=>'^Alpha^',
'Β'=>'^Beta^',
'Χ'=>'^Chi^',
'‡'=>'^Dagger^',
'Δ'=>'^Delta^',
'Ε'=>'^Epsilon^',
'Η'=>'^Eta^',
'Γ'=>'^Gamma^',
'Ι'=>'^lota^',
'Κ'=>'^Kappa^',
'Λ'=>'^Lambda^',
'Μ'=>'^Mu^',
'Ν'=>'^Nu^',
'Œ'=>'^OElig^',
'Ω'=>'^Omega^',
'Ο'=>'^Omicron^',
'Φ'=>'^Phi^',
'Π'=>'^Pi^',
'″'=>'^Prime^',
'Ψ'=>'^Psi^',
'Ρ'=>'^Rho^',
'Š'=>'^Scaron^',
'Š'=>'^Scaron^',
'Σ'=>'^Sigma^',
'Τ'=>'^Tau^',
'Θ'=>'^Theta^',
'Υ'=>'^Upsilon^',
'Ξ'=>'^Xi^',
'Ÿ'=>'^Yuml^',
'Ζ'=>'^Zeta^',
'ℵ'=>'^alefsym^',
'α'=>'^alpha^',
'∧'=>'^and^',
'∠'=>'^ang^',
'≈'=>'^asymp^',
'„'=>'^bdquo^',
'β'=>'^beta^',
'•'=>'^bull^',
'∩'=>'^cap^',
'χ'=>'^chi^',
'ˆ'=>'^circ^',
'♣'=>'^clubs^',
'≅'=>'^cong^',
'↵'=>'^crarr^',
'∪'=>'^cup^',
'⇓'=>'^dArr^',
'†'=>'^dagger^',
'↓'=>'^darr^',
'δ'=>'^delta^',
'♦'=>'^diams^',
'∅'=>'^empty^',
' '=>'^emsp^',
' '=>'^ensp^',
'ε'=>'^epsilon^',
'≡'=>'^equiv^',
'η'=>'^eta^',
'€'=>'^euro^',
'∃'=>'^exist^',
'ƒ'=>'^fnof^',
'∀'=>'^forall^',
'⁄'=>'^frasl^',
'γ'=>'^gamma^',
'≥'=>'^ge^',
'⇔'=>'^hArr^',
'↔'=>'^harr^',
'♥'=>'^hearts^',
'…'=>'^hellip^',
'ℑ'=>'^image^',
'∞'=>'^infin^',
'∫'=>'^int^',
'ι'=>'^iota^',
'∈'=>'^isin^',
'κ'=>'^kappa^',
'⇐'=>'^lArr^',
'λ'=>'^lambda^',
'⟨'=>'^lang^',
'←'=>'^larr^',
'⌈'=>'^lceil^',
'“'=>'^ldquo^',
'≤'=>'^le^',
'⌊'=>'^lfloor^',
'∗'=>'^lowast^',
'◊'=>'^loz^',
'‎'=>'^lrm^',
'‹'=>'^lsaquo^',
'‘'=>'^lsquo^',
'—'=>'^mdash^',
'−'=>'^minus^',
'μ'=>'^mu^',
'∇'=>'^nabla^',
'–'=>'^ndash^',
'≠'=>'^ne^',
'∋'=>'^ni^',
'∉'=>'^notin^',
'⊄'=>'^nsub^',
'ν'=>'^nu^',
'œ'=>'^oelig^',
'‾'=>'^oline^',
'ω'=>'^omega^',
'ο'=>'^omicron^',
'⊕'=>'^oplus^',
'∨'=>'^or^',
'⊗'=>'^otimes^',
'∂'=>'^part^',
'‰'=>'^permil^',
'⊥'=>'^perp^',
'φ'=>'^phi^',
'π'=>'^pi^',
'ϖ'=>'^piv^',
'′'=>'^prime^',
'∏'=>'^prod^',
'∝'=>'^prop^',
'ψ'=>'^psi^',
'⇒'=>'^rArr^',
'√'=>'^radic^',
'⟩'=>'^rang^',
'→'=>'^rarr^',
'⌉'=>'^rceil^',
'”'=>'^rdquo^',
'ℜ'=>'^real^',
'⌋'=>'^rfloor^',
'ρ'=>'^rho^',
'‏'=>'^rlm^',
'›'=>'^rsaquo^',
'’'=>'^rsquo^',
'‚'=>'^sbquo^',
'š'=>'^scaron^',
'⋅'=>'^sdot^',
'σ'=>'^sigma^',
'ς'=>'^sigmaf^',
'∼'=>'^sim^',
'♠'=>'^spades^',
'⊂'=>'^sub^',
'⊆'=>'^sube^',
'∑'=>'^sum^',
'⊃'=>'^sup^',
'⊇'=>'^supe^',
'τ'=>'^tau^',
'∴'=>'^there4^',
'θ'=>'^thetasym^',
'ϑ'=>'^thetasym^',
' '=>'^thinsp^',
'˜'=>'^tilde^',
'™'=>'^trade^',
'⇑'=>'^uArr^',
'↑'=>'^uarr^',
'ϒ'=>'^upsih^',
'υ'=>'^upsilon^',
'℘'=>'^weierp^',
'ξ'=>'^xi^',
'ÿ'=>'^yuml^',
'ζ'=>'^zeta^',
'‍'=>'^zwj^',
'‌'=>'^zwnj^');
}