資源簡介
<?php
function curl_get_file_contents($url,$referer='') {
set_time_limit(0);
static $curl_loops = 0;//避免死了循環必備
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($ch, CURLOPT_SSL_VERIFYPEER, false); //不驗證證書
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false); //不驗證證書
curl_setopt($ch,CURLOPT_USERAGENT,$useragent);
curl_setopt($ch,CURLOPT_RETURNTRANSFER,true);
curl_setopt($ch,CURLOPT_REFERER,$referer);
curl_setopt($ch, CURLOPT_TIMEOUT,60);
$data = curl_exec($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> 區段
// <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)){
$title = "無法解析數據中的 <head> 區段";
}
// 取得 <head> 中 meta 設置的編碼格式<meta charset="gb2312">
if(preg_match('/<meta.*charset=(("){0,1}[a-zA-Z0-9-]*("){0,1})/',$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)){
$title = "無法解析 <title> 的內容";
exit;
}
// 將<title> 的文字編碼格式轉成 UTF-8
if($charset == "None"){
$title=$htmlTitles[1];
}else{
$title=iconv($charset, "UTF-8", $htmlTitles[1]);
}
}
return html_entity_decode($title);
}
/*網址寫入*/
$urla = array('這里填入數組網址'
);
foreach ($urla as $key => $url) {
$html = curl_get_file_contents($url);
$title = get_title_contents($html);
echo $title;
echo '</br>';
}
function curl_get_file_contents($url,$referer='') {
set_time_limit(0);
static $curl_loops = 0;//避免死了循環必備
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($ch, CURLOPT_SSL_VERIFYPEER, false); //不驗證證書
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false); //不驗證證書
curl_setopt($ch,CURLOPT_USERAGENT,$useragent);
curl_setopt($ch,CURLOPT_RETURNTRANSFER,true);
curl_setopt($ch,CURLOPT_REFERER,$referer);
curl_setopt($ch, CURLOPT_TIMEOUT,60);
$data = curl_exec($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> 區段
// <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)){
$title = "無法解析數據中的 <head> 區段";
}
// 取得 <head> 中 meta 設置的編碼格式<meta charset="gb2312">
if(preg_match('/<meta.*charset=(("){0,1}[a-zA-Z0-9-]*("){0,1})/',$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)){
$title = "無法解析 <title> 的內容";
exit;
}
// 將<title> 的文字編碼格式轉成 UTF-8
if($charset == "None"){
$title=$htmlTitles[1];
}else{
$title=iconv($charset, "UTF-8", $htmlTitles[1]);
}
}
return html_entity_decode($title);
}
/*網址寫入*/
$urla = array('這里填入數組網址'
);
foreach ($urla as $key => $url) {
$html = curl_get_file_contents($url);
$title = get_title_contents($html);
echo $title;
echo '</br>';
}
代碼片段和文件信息
- 上一篇:upload-lab靶場PHP源碼
- 下一篇:php獲取企業微信用戶信息
評論
共有 條評論
相關資源
- php獲取企業微信用戶信息
- upload-lab靶場PHP源碼
- ucms_1.4.8 php源碼
- 微信小程序支付付款Deom(php|小程序代
- PHP圖片驗證碼案列
- 學生信息登記表(php代碼)
- php上傳、編輯用戶頭像
- PHP許愿墻(源碼+數據庫)
- php查詢天氣預報
- 公司核名系統(php源碼)
-
php excel 操作源碼 xm
l - php 日歷控件(DATE PICKER - JQUERY PLUGIN)
- php 日歷(bootstrap-datetimepicker)
-
php將 xm
l解析成array - 實現excel數據的導入導出 thinkphp
- php判斷pc端和手機端
- php上傳文件
- php訂單管理系統,附贈設計報告
- 微直播(php直播源碼)
- ThinkPHP 課程管理系統源碼含sql文件
- php 企業建站系統源碼zzzcms
- php評測系統源碼含數據庫腳本
- 公司網站,企業網站 CodeIgniter,PHP
- 百度貼吧簽到助手PHP源碼
- 生成驗證碼
- php實現進度條
- php cms系統(dede-cms)
- thinkphp教學
- thinkPHP微信基礎類
- 然之協同管理系統ranzhi.4.0