php获取网页标题和内容函数(不包含html标签)
function getpagecontent($url) {
//$url='http://www.ttphp.com;
$pageinfo = array();
$pageinfo[content_type] = '';
$pageinfo[charset] = '';
$pageinfo[title] = '';
$pageinfo[description] = '';
$pageinfo[keywords] = '';
$pageinfo[body] = '';
$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";
$pageinfo[content_type] = curl_getinfo($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[1]) ) {
$pageinfo[charset] = trim($matches[1]);
}
//echo $pageinfo[charset];
//exit;
curl_close ($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[1];
//echo $head. "/n";
//charset
if($pageinfo[charset] == '' ) {
preg_match('@<meta.+charset=([/w/-]+)[^>]*>@i',$store,$matches);
$pageinfo[charset] = trim($matches[1]);
}
//desctiption
preg_match('@<meta/s+name=/"*description/"*/s+content/s*=/s*([^/>]+)/*>@i',$store,$matches);
//print_r($matches);
$desc = trim($matches[1]);
$pageinfo[description] = str_replace("/"", '',$desc);
preg_match('@<meta/s+name=/"*keywords/"*/s+content/s*=/s*([^/>]+)/*>@i',$store,$matches);
//print_r($matches);
$keywords = trim($matches[1]);
$pageinfo[keywords] = str_replace("/"", '',$keywords);
preg_match("/<title>(.*)<//title>/smui",$store, $matches);
$pageinfo[title] = trim($matches[1]);
preg_match("/<body.*>(.*)<//body>/smui",$store, $matches);
$pageinfo[body] = addslashes( replacehtmlandjs($matches[1]) ) ;
$pageinfo['all'] = addslashes( replacehtmlandjs($store) ) ;
//echo "charset = " . $pageinfo[charset] . "/n";
//print_r($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
"'[/r/n/s+]'", // 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);
}
使用例子
$a = getpagecontent(www.ttphp.com);
print_r($a);
如对本文有疑问，
点击进行留言回复！！
我要评论
网友评论