| <?php Class Readability {
The tag bit name that holds the result of the decision
Const Attr_content_score = "Contentscore"; The DOM parsing class currently supports only UTF-8 encoding
Const DOM_DEFAULT_CHARSET = "Utf-8"; What is displayed when a decision fails
Const MESSAGE_CAN_NOT_GET = "Readability is unable to parse this page for content." DOM parsing class (PHP5 already built in)
protected $DOM = null; Source code that needs to be parsed
protected $source = ""; List of parent elements of chapter
Private $parentNodes = Array (); Labels that need to be deleted
note:added Extra tags from http://www.111cn.net Private $junkTags = Array ("Style", "form", "iframe", "Script", "button", "Input", "textarea",
& nbsp; "NoScript", "select", "option", " Object ", applet," Basefont ",
" Bgsound "," Blink "," Canvas "," command "," menu "," Nav "," DataList ",
"Embed", "frame", "frameset", "keygen", "label", "marquee", "link"); Properties that need to be removed
Private $junkAttrs = Array ("Style", "Class", "onclick", "onmouseover", "align", "border", "margin");
/**
* Constructor
* @param $input The encoding of the _char string. Default Utf-8, you can omit
*/
function __construct ($source, $input _char = "Utf-8") {
$this->source = $source;
DOM parsing classes can only handle characters in UTF-8 format
$source = mb_convert_encoding ($source, ' html-entities ', $input _char); preprocessing HTML tags, eliminating redundant tags, etc.
$source = $this->preparsource ($source); //Generate DOM Resolution classes
$this- >dom = new DOMDocument (' 1.0 ', $input _char);
try {
//libxml_use_internal_errors (TRUE);
//There will be some error messages, but not tight: ^)
if (!@ $this->dom->loadhtml (' <?xml encoding= '). Readability::D om_default_charset. ' " > '. $source)) {
throw new Exception ("Parse HTML error!");
} foreach ($this->dom->childnodes as $ Item) {
if ($item- >nodetype = = Xml_pi_node) {
$this->dom->removechild ($item); Remove Hack
}
} //Insert proper
$this->dom->encoding = readability::D om_default_charset;
} catch (Exception $e) {
//...
}
}
/**
* Preprocessing HTML tags so that they can be handled accurately by DOM parsing classes
*
* @return String
*/
Private function Preparsource ($string) {
//Eliminate extra HTML encoding tags to avoid parsing errors
Preg_match ("/charset=" ([\w|\-]+); /", $string, $match);
if (isset ($match [1])) {
$string = preg_replace ("/charset=" ([\w|\-]+); /"," ", $string, 1);
} Replace all doubled-up <BR> tags with <P> tags, and remove fonts.
$string = Preg_replace ("/<br\/?>[\r\n\s]*<br\/?>/i", "</p><p>", $string);
$string = Preg_replace ("/<\/?font[^>]*>/i", "", $string); @see HTTPS://GITHUB.COM/FEELINGLUCKY/PHP-READABILITY/ISSUES/7
-From Http://stackoverflow.com/questions/7130867/remove-script-tag-from-html-content
$string = Preg_replace ("#<script" (. *?) > (. *?) </script> #is "," ", $string); Return trim ($string);
}
/**
* Delete all $TagName tags in the DOM element
*
* @return DOMDocument
*/
Private Function Removejunktag ($RootNode, $TagName) {
$Tags = $RootNode->getelementsbytagname ($TagName);
Note:always index 0, because removing a tag removes it from the results as.
while ($Tag = $Tags->item (0)) {
$parentNode = $Tag->parentnode;
$parentNode->removechild ($TAG);
}
return $RootNode;
}
/**
* Delete all unwanted attributes in the element
*/
Private Function Removejunkattr ($RootNode, $Attr) {
$Tags = $RootNode->getelementsbytagname ("*"); $i = 0;
while ($Tag = $Tags->item ($i + +)) {
$Tag->removeattribute ($Attr);
} return $RootNode;
} /**
* Get the box model of the main content of the page according to the score
* Decision algorithm from: http://code.google.com/p/arc90labs-readability/
* This is forwarded by Zhengxiao Blog
* @return Domnode
*/
Private Function Gettopbox () {
Get all the chapters in a page
$allParagraphs = $this->dom->getelementsbytagname ("P"); Study the paragraphs and find the chunk that has the best score.
A score is determined by things like:number of <p> ' s, commas, special classes, etc.
$i = 0;
while ($paragraph = $allParagraphs->item ($i + +)) {
$parentNode = $paragraph->parentnode;
$contentScore = Intval ($parentNode->getattribute (Readability::attr_content_score));
$className = $parentNode->getattribute ("class");
$id = $parentNode->getattribute ("id"); //Look for a special classname
if (Preg_match ("/(comment|meta|footer|footnote)/I", $className)) {
$ Contentscore-= 50;
} else if (Preg_match (
[(^|\\s) (post|hentry|entry[-]? ( content|text|body)? | Article[-]? (content|text|body)?) (\\s|$)) /i ",
$className)) {
$contentScore + = 25;
} //Look for a special ID
if (Preg_match ("/(comment|meta|footer|footnote)/i", $id)) {
$contentScore-= 50;
} else if (Preg_match (
"/^ (post|hentry|entry[-]?" ( content|text|body)? | Article[-]? (content|text|body)?) $/i ",
$id)) {
$contentScore + 25;
} Add a point for the paragraph found
Add points for no commas within this paragraph
if (strlen ($paragraph->nodevalue) > 10) {
$contentScore + + strlen ($paragraph->nodevalue);
} Save the decision score for the parent element
$parentNode->setattribute (Readability::attr_content_score, $contentScore); //Save the parent element of the chapter so that the next quick fetch
Array_push ($this->parentnodes, $parentNode);
} $topBox = null;
//assignment from Index for performance.
// http://www.peachpit.com/articles/ Article.aspx?p=31567&seqnum=5
for ($i = 0, $len = sizeof ($this-> Parentnodes); $i < $len; $i + +) {
$parentNode = $this->parentnodes[$i];
$contentScore = intval ($ Parentnode->getattribute (Readability::attr_content_score));
$orgContentScore = intval ($topBox? $topBox- >getattribute (Readability::attr_content_score): 0; if ($contentScore && $contentScore > $orgContentScore) {
$topBox = $parentNode;
}
}
//At this point, $topBox Should be the main element of the page content that has been judged
return $topBox;
}
/**
* Get HTML page title
*
& nbsp; * @return String
*/
public Function GetTitle () br> $split _point = '-';
$titleNodes = $this->dom->getelementsbytagname ("title"); if ($titleNodes->length
&& $titleNode = $titleNodes->item (0)) {
@see Http://stackoverflow.com/questions/717328/how-to-explode-string-right-to-left
$title = Trim ($titleNode->nodevalue);
$result = Array_map (' Strrev ', explode ($split _point, Strrev ($title));
return sizeof ($result) > 1? Array_pop ($result): $title;
} return null;
}
/**
* Get leading Image URL
*
* @return String
*/
Public Function Getleadimageurl ($node) {
$images = $node->getelementsbytagname ("img");
if ($images->length && $leadImage = $images->item (0)) {
return $leadImage->getattribute ("src");
} return null;
}
/**
* Get the main content of the page (readability content later)
*
* @return Array
*/
Public Function getcontent () {
if (! $this->dom) return false;
Get page title
$ContentTitle = $this->gettitle (); /Get page main contents
$ Contentbox = $this->gettopbox ();
//check if we found a Suitable top-box.
if ($ContentBox = = null)
throw new RuntimeException (Readability::message_can_not_get);
//copy content to new DOMDocument
$Target = new DOMDocument;
$Target->appendchild ($Target->importnode ($ContentBox, True)); Delete unwanted labels
foreach ($this->junktags as $tag) {
$Target = $this->removejunktag ($Target, $tag);
} Delete unwanted properties
foreach ($this->junkattrs as $attr) {
$Target = $this->removejunkattr ($Target, $attr);
} $content = mb_convert_encoding ($Target->savehtml (), readability::D om_default_charset, "html-entities"); Multiple data, returned as an array
Return Array (
' Lead_image_url ' => $this->getleadimageurl ($Target),
' Word_count ' => mb_strlen (Strip_tags ($content), readability::D om_default_charset),
' title ' => $ContentTitle? $ContentTitle: null,
' Content ' => $content
);
} function __destruct () {}
} |
