您的位置：首页 > 编程语言 > PHP开发

php利用curl获取网页title内容

2017-05-09 09:57 681 查看

/**$html = curl_get_file_contents($url);
$title = get_title_contents($html);
var_dump($title);*/
function curl_get_file_contents($url,$referer='') {
static $curl_loops = 0;//避免死了循环必备
static $curl_max_loops = 3;
$useragent = "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36";

$ch = curl_init();
curl_setopt($ch,CURLOPT_URL,$url);
curl_setopt($ch,CURLOPT_HEADER,true);
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false); //不验证证书
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false); //不验证证书
curl_setopt($ch,CURLOPT_USERAGENT,$useragent);
curl_setopt($ch,CURLOPT_RETURNTRANSFER,true);
curl_setopt($ch,CURLOPT_REFERER,$referer);
$data = curl_exec($ch);
$ret = $data;
list($header,$data) = explode("\r\n\r\n",$data,2);
$http_code = curl_getinfo($ch,CURLINFO_HTTP_CODE);
$last_url = curl_getinfo($ch,CURLINFO_EFFECTIVE_URL);
curl_close($ch);
if ($http_code == 301 || $http_code == 302) {
$matches = array();
preg_match('/Location:(.*?)\n/',$header,$matches);
$url = @parse_url(trim(array_pop($matches)));
if (!$url) {
return $data;
}
$new_url = $url['scheme'] . '://' . $url['host'] . $url['path'] . (isset($url['query']) ? '?' . $url['query'] : '');
if ($curl_loops++ >= $curl_max_loops) {
return false;
}else {
$new_url = stripslashes($new_url);
return curl_get_file_contents($new_url);
}
} else {
list($header,$data) = explode("\r\n\r\n",$ret,2);
return $data;
}
}
function get_title_contents($html){
// 解析 HTML 的 <head> 区段
//	<meta http-equiv="Content-type" content="text/html; charset=utf-8" />
//	<meta content="text/html; charset=gb2312" http-equiv="Content-Type">
preg_match("/<head.*>(.*)<\/head>/smUi",$html, $htmlHeaders);
//var_dump($output);die();
if(!count($htmlHeaders)){
$title = "无法解析数据中的 <head> 区段";
}

// 取得 <head> 中 meta 设置的编码格式<meta charset="gb2312">
if(preg_match('/<meta.*charset=(("){0,1}[a-zA-Z0-9-]*("){0,1})/',$htmlHeaders[1], $results)){
$charset =  $results[1];
}else{
$charset = "None";
}
$charset = str_replace('"','',$charset);

// 取得 <title> 中的文字
if(preg_match("/<title>(.*)<\/title>/Ui",$htmlHeaders[1], $htmlTitles)){
if(!count($htmlTitles)){
$title = "无法解析 <title> 的内容";
exit;
}

// 将  <title> 的文字编码格式转成 UTF-8
if($charset == "None"){
$title=$htmlTitles[1];
}else{
$title=iconv($charset, "UTF-8", $htmlTitles[1]);
}
}
return html_entity_decode($title);
}

　　支持https，302跳转

内容来自用户分享和网络整理，不保证内容的准确性，如有侵权内容，可联系管理员处理

标签：

相关文章推荐

新的分享

章节导航