做采集經常遇到的問題是內容排版問題，用了一些時間寫了個用正則替換html標簽和樣式的函數，共享下。
復制代碼 代碼如下:
/**
* 格式化內容
* @param string $content 內容最好統一用utf-8編碼
* @return string
* !本函數需要開啟tidy擴展
*/
function removeFormat($content) {
$replaces = array (
"/<font.*?>/i" => '',
"/<\/font>/i" => '',
"/<strong>/i" => '',
"/<\/strong>/i" => '',
"/<span.*?>/i" => '',
"/<\/span>/i" => '',
"/<div.*?>/i" => "<p>",
"/<\/div>/i" => "</p>",
"/<!--<.*?>*-->/i"=>'',
/* "/<table.*?>/i" => '',//遇到有表格的內容就不要啟用
"/<\/table>/i" => '',
"/<tbody.*?>/i" => '',
"/<\/tbody>/i" => '',
"/<tr.*?>/i" => '<p>',
"/<\/tr>/i" => '</p>',
"/<td.*?>/i" => '', */
"/style=.+?['|\"]/i" => '',
"/class=.+?['|\"]/i" => '',
"/id=.+?['|\"]/i"=>'',
"/lang=.+?['|\"]/i"=>'',
//"/width=.+?['|\"]/i"=>'',//不好控制注釋掉
//"/height=.+?['|\"]/i"=>'',
"/border=.+?['|\"]/i"=>'',
"/face=.+?['|\"]/i"=>'',
"/<br.*?>[ ]*/i" => "</p><p>",
"/<iframe.*?>.*<\/iframe>/i" => '',
"/ /i" => ' ',//空格替換掉
"/<p.*?>[ |\x{3000}|\r\n]*/ui" => '<p> ',//替換半角、全角空格，換行符，用 排除寫入數據庫時產生的編碼問題
);
$config = array(
//'indent' => TRUE, //是否縮進
'output-html' => TRUE,//是否是輸出xhtml
'show-body-only'=>TRUE,//是否只獲得到body
'wrap' => 0
);
$content = tidy_repair_string($content, $config, 'utf8');//先利用php自帶的tidy類庫修復html標簽，不然替換的時候容易出現各種詭異的情況
$content = trim($content);
foreach ( $replaces as $k => $v ) {
$content = preg_replace ( $k, $v, $content );
}
if(strpos($content,'<p>')>6)//部分內容開頭可能缺失<p>標簽
$content = '<p> '.$content;
$content = tidy_repair_string($content, $config, 'utf8');//再修復一次，可以去除html空標簽
$content = trim($content);
return $content;
}
