论坛 › php › php获取网页标题和内容函数（不包含html标签）

aini 发表于 2017-4-14 06:59:13

php获取网页标题和内容函数（不包含html标签）

　　function getPageContent($url) {    //$url='http://www.phplover.cn';    $pageinfo = array();    $pageinfo = '';    $pageinfo = '';    $pageinfo = '';    $pageinfo = '';    $pageinfo = '';    $pageinfo = '';    $pageinfo['httpcode'] = 200;    $pageinfo['all'] = '';    $ch = curl_init();    curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)");    curl_setopt($ch, CURLOPT_RETURNTRANSFER,1);    curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);    curl_setopt($ch, CURLOPT_SSL_VERIFYPEER,0);    curl_setopt($ch, CURLOPT_TIMEOUT, 8);    curl_setopt($ch, CURLOPT_FILETIME, 1);    curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);    //curl_setopt($ch, CURLOPT_HEADER, 1);          curl_setopt($ch, CURLOPT_URL,$url);    $curl_start = microtime(true);    $store = curl_exec ($ch);    $curl_time = microtime(true) - $curl_start;    if( curl_error($ch) ) {    $pageinfo['httpcode'] = 505;//gate way error    echo 'Curl error: ' . curl_error($ch) ."/n";    return $pageinfo;    }    //print_r(curl_getinfo($ch));    $pageinfo['httpcode'] = curl_getinfo($ch,CURLINFO_HTTP_CODE);    //echo curl_getinfo($ch,CURLINFO_CONTENT_TYPE)."/n";    $pageinfo = curl_getinfo($ch,CURLINFO_CONTENT_TYPE);    if(intval($pageinfo['httpcode']) <> 200 or !preg_match('@text/html@',curl_getinfo($ch,CURLINFO_CONTENT_TYPE) )   ) {    //print_r(curl_getinfo($ch) );    //exit;    return $pageinfo;    }    preg_match('/charset=([^/s/n/r]+)/i',curl_getinfo($ch,CURLINFO_CONTENT_TYPE),$matches); //从header 里取charset    if( trim($matches) ) {    $pageinfo = trim($matches);    }    //echo $pageinfo;    //exit;    curl_close ($ch);    //echo $store;    //remove javascript    $store = preg_replace("/<mce:script.*><!--(.*)<//script>/smUi",'',$store);    //remove link   $store = preg_replace("/<link/s+[^>]+>/smUi",'',$store);    //remove <!---->    $store = preg_replace("/<!--.*-->/smUi",'',$store);    //remove <style</<style>    $store = preg_replace("/<style.*>(.*)<//style>/smUi",'',$store);    //remove 中文空格    $store = preg_replace("/　/",'',$store);    //remove 标点符号    //$store = preg_replace("/[/~`!@#$%^&*()_/-+={}|/[/]//;':"/</>/?/,/.//]/",'',$store);    //preg_match("/<head.*>(.*)<//head>/smUi",$store, $matches);    //$head = $matches;    //echo $head. "/n";    //charset    if($pageinfo == '' ) {   preg_match('@<meta.+charset=(+)[^>]*>@i',$store,$matches);   $pageinfo = trim($matches);   }   //desctiption   preg_match('@<meta/s+name=/"*description/"*/s+content/s*=/s*([^/>]+)/*>@i',$store,$matches);   //print_r($matches);   $desc = trim($matches);   $pageinfo = str_replace("/"", '',$desc);   preg_match('@<meta/s+name=/"*keywords/"*/s+content/s*=/s*([^/>]+)/*>@i',$store,$matches);   //print_r($matches);   $keywords = trim($matches);   $pageinfo = str_replace("/"", '',$keywords);   preg_match("/<title>(.*)<//title>/smUi",$store, $matches);   $pageinfo = trim($matches);   preg_match("/<body.*>(.*)<//body>/smUi",$store, $matches);   $pageinfo = addslashes( replaceHtmlAndJs($matches) ) ;   $pageinfo['all'] = addslashes( replaceHtmlAndJs($store) ) ;   //echo "charset = " . $pageinfo . "/n";   //print_r($pageinfo);   //exit;   return $pageinfo;   }   /**   * 去掉所有的HTML标记和JavaScript标记   */   function replaceHtmlAndJs($document)    {    $document = trim($document);    if (strlen($document) <= 0)    {    return $document;    }    $search = array (          "'<script[^>]*?>.*?// --></mce:script>'si",// 去掉 javascript    "'<[///!]*?[^<>]*?>'si",          // 去掉 HTML 标记    "''",                // 去掉空白字符    "'&(/w+);'i"            // 替换 HTML 实体    );                  // 作为 PHP 代码运行    $replace = array ( "", "", "", "");    return @preg_replace ($search, $replace, $document);    }   
function getPageContent($url) {

//$url='http://www.phplover.cn';

$pageinfo = array();
$pageinfo = '';
$pageinfo = '';
$pageinfo = '';
$pageinfo = '';
$pageinfo = '';
$pageinfo = '';
$pageinfo['httpcode'] = 200;
$pageinfo['all'] = '';




$ch = curl_init();
curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 5.01; Windows NT 5.0)");
curl_setopt($ch, CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER,0);
curl_setopt($ch, CURLOPT_TIMEOUT, 8);
curl_setopt($ch, CURLOPT_FILETIME, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
//curl_setopt($ch, CURLOPT_HEADER, 1);
curl_setopt($ch, CURLOPT_URL,$url);

$curl_start = microtime(true);
$store = curl_exec ($ch);

$curl_time = microtime(true) - $curl_start;
if( curl_error($ch) ) {
$pageinfo['httpcode'] = 505; //gate way error
echo 'Curl error: ' . curl_error($ch) ."/n";
return $pageinfo;
}

//print_r(curl_getinfo($ch));
$pageinfo['httpcode'] = curl_getinfo($ch,CURLINFO_HTTP_CODE);
//echo curl_getinfo($ch,CURLINFO_CONTENT_TYPE)."/n";
$pageinfo = curl_getinfo($ch,CURLINFO_CONTENT_TYPE);
if(intval($pageinfo['httpcode']) <> 200 or !preg_match('@text/html@',curl_getinfo($ch,CURLINFO_CONTENT_TYPE) ) ) {
//print_r(curl_getinfo($ch) );
//exit;
return $pageinfo;
}
preg_match('/charset=([^/s/n/r]+)/i',curl_getinfo($ch,CURLINFO_CONTENT_TYPE),$matches); //从header 里取charset
if( trim($matches) ) {
$pageinfo = trim($matches);
}
//echo $pageinfo;
//exit;
curl_close ($ch);
//echo $store;


//remove javascript
$store = preg_replace("/<script.*>(.*)<//script>/smUi",'',$store);
//remove link
$store = preg_replace("/<link/s+[^>]+>/smUi",'',$store);
//remove <!-- -->
$store = preg_replace("/<!--.*-->/smUi",'',$store);
//remove <style </<style>
$store = preg_replace("/<style.*>(.*)<//style>/smUi",'',$store);
//remove 中文空格
$store = preg_replace("/　/",'',$store);
//remove 标点符号
//$store = preg_replace("/[/~`!@#$%^&*()_/-+={}|/[/]//;':"/</>/?/,/.//]/",'',$store);


//preg_match("/<head.*>(.*)<//head>/smUi",$store, $matches);
//$head = $matches;
//echo $head. "/n";

//charset
if($pageinfo == '' ) {
preg_match('@<meta.+charset=(+)[^>]*>@i',$store,$matches);
$pageinfo = trim($matches);
}
//desctiption
preg_match('@<meta/s+name=/"*description/"*/s+content/s*=/s*([^/>]+)/*>@i',$store,$matches);
//print_r($matches);
$desc = trim($matches);
$pageinfo = str_replace("/"", '',$desc);


preg_match('@<meta/s+name=/"*keywords/"*/s+content/s*=/s*([^/>]+)/*>@i',$store,$matches);
//print_r($matches);
$keywords = trim($matches);
$pageinfo = str_replace("/"", '',$keywords);


preg_match("/<title>(.*)<//title>/smUi",$store, $matches);
$pageinfo = trim($matches);

preg_match("/<body.*>(.*)<//body>/smUi",$store, $matches);
$pageinfo = addslashes( replaceHtmlAndJs($matches) ) ;
$pageinfo['all'] = addslashes( replaceHtmlAndJs($store) ) ;

//echo "charset = " . $pageinfo . "/n";

//print_r($pageinfo);
//exit;


return $pageinfo;

}

/**
* 去掉所有的HTML标记和JavaScript标记
*/
function replaceHtmlAndJs($document)
{
$document = trim($document);
if (strlen($document) <= 0)
{
return $document;
}
$search = array (
"'<script[^>]*?>.*?</script>'si", // 去掉 javascript
"'<[///!]*?[^<>]*?>'si", // 去掉 HTML 标记
"''", // 去掉空白字符
"'&(/w+);'i" // 替换 HTML 实体
); // 作为 PHP 代码运行

$replace = array ( "", "", "", "" );

return @preg_replace ($search, $replace, $document);

}
本文来源于php爱好者 http://www.phplover.cn/ , 原文地址：http://www.phplover.cn/post/phphuoquwangyebiaotiheneirongdehanshu.html

查看完整版本: php获取网页标题和内容函数（不包含html标签）