0
凌晨1時試圖提取元描述的內容,從網頁在搜索結果中&顯示。 但它像顯示它:提取元描述的內容使用DOM文檔()和XPath在PHP
內容=「Lorem存有胡蘿蔔,改善生態環境茉莉花便利保留需求茉莉花質量當拉手光芒超級碗山瞬間。。 「
而只需要1:
Lorem存有胡蘿蔔,改善生態環境。保留茉莉方便的需要。茉莉花質量。當拉手光芒超級碗山瞬間。
任何猜測,有什麼錯在我的代碼?
CODE:
$doc = new DOMDocument();
@$doc->loadHTMLFile($page_path);
$xpath = new DOMXPath($doc);
$body = $xpath->query('//meta[@name="description"]/@content');
$page_title = @$doc->getElementsByTagName('title')->item(0)->textContent;
$page_title = $page_title ? $page_title : $page_path;
$page_body = html2text($doc->saveXml($body->item(0)));// this is meta-description, which i want
Functions :
function html2text($html)
{
$text = $html;
static $search = array(
'@<script.+?</script>@usi', // Strip out javascript content
'@<style.+?</style>@usi', // Strip style content
'@<!--.+?-->@us', // Strip multi-line comments including CDATA
'@</?[a-z].*?\>@usi', // Strip out HTML tags
);
$text = preg_replace($search, ' ', $text);
/*
* normalize common entities
*/
$text = normalizeEntities($text);
/*
* decode other entities
*/
$text = html_entity_decode($text, ENT_QUOTES, 'utf-8');
/*
* normalize possibly repeated newlines, tabs, spaces to spaces
*/
$text = preg_replace('/\s+/u', ' ', $text);
$text = trim($text);
return $text;
}
/**
* Replace encoded and double encoded entities to equivalent unicode character
* @param string $text
* @return string - the same as $text but without encoded entries
* @access public
*/
function normalizeEntities($text)
{
static $find = array();
static $repl = array();
if (!count($find)) {
/*
* build $find and $replace from map one time
*/
$map = array(
array('\'', 'apos', 39, 'x27'), // Apostrophe
array('\'', '‘', 'lsquo', 8216, 'x2018'), // Open single quote
array('\'', '’', 'rsquo', 8217, 'x2019'), // Close single quote
array('"', '「', 'ldquo', 8220, 'x201C'), // Open double quotes
array('"', '」', 'rdquo', 8221, 'x201D'), // Close double quotes
array('\'', '‚', 'sbquo', 8218, 'x201A'), // Single low-9 quote
array('"', '„', 'bdquo', 8222, 'x201E'), // Double low-9 quote
array('\'', '′', 'prime', 8242, 'x2032'), // Prime/minutes/feet
array('"', '″', 'Prime', 8243, 'x2033'), // Double prime/seconds/inches
array(' ', 'nbsp', 160, 'xA0'), // Non-breaking space
array('-', '‐', 8208, 'x2010'), // Hyphen
array('-', '–', 'ndash', 8211, 150, 'x2013'), // En dash
array('--', '—', 'mdash', 8212, 151, 'x2014'), // Em dash
array(' ', ' ', 'ensp', 8194, 'x2002'), // En space
array(' ', ' ', 'emsp', 8195, 'x2003'), // Em space
array(' ', ' ', 'thinsp', 8201, 'x2009'), // Thin space
array('*', '•', 'bull', 8226, 'x2022'), // Bullet
array('*', '‣', 8227, 'x2023'), // Triangular bullet
array('...', '…', 'hellip', 8230, 'x2026'), // Horizontal ellipsis
array('°', 'deg', 176, 'xB0'), // Degree
array('€', 'euro', 8364, 'x20AC'), // Euro
array('¥', 'yen', 165, 'xA5'), // Yen
array('£', 'pound', 163, 'xA3'), // British Pound
array('©', 'copy', 169, 'xA9'), // Copyright Sign
array('®', 'reg', 174, 'xAE'), // Registered Sign
array('™', 'trade', 8482, 'x2122') // TM Sign
);
foreach ($map as $e) {
for ($i = 1; $i < count($e); ++$i) {
$code = $e[$i];
if (is_int($code)) {
// numeric entity
$regex = "/&(amp;)?#0*$code;/";
} elseif (preg_match('/^.$/u', $code)/* one unicode char*/) {
// single character
$regex = "/$code/u";
} elseif (preg_match('/^x([0-9A-F]{2}){1,2}$/i', $code)) {
// hex entity
$regex = "/&(amp;)?#x0*" . substr($code, 1) . ";/i";
} else {
// named entity
$regex = "/&(amp;)?$code;/";
}
$find[] = $regex;
$repl[] = $e[0];
}
}
}
return preg_replace($find, $repl, $text);
}
1中使用 - 評估。它仍然給我含量=「一些說明」,然而,我只是需要 - 一些介紹,說再見內容=「」符號 –
1圖片複製原來保存的使用字符串函數的'body'元素作爲XML和;試圖反序列化它。這是不需要的,剛讀值作爲字符串。 – ThW