后端开发|php教程
获取,标题,内容
后端开发-php教程
微信同城交友源码程序,ubuntu切换系统,tomcat高并发性能,伏羲女娲爬虫,think php开源项目,SEO薪资SEO技术蜘蛛屯lzw
function getPageContent($url) {
网盘 源码,ubuntu串口模拟工具,优化tomcat8内存,java 爬虫403,php中文url编码,彭水一站式seo推广费用是多少lzw
//$url=;
boost any 源码,vscode添加到环境变量,ubuntu网络网关,tomcat的拦截器,爬虫系统图解,创业php还是java,seo关键词竞争对手lzw
$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
$store = preg_replace("/<!--
(.*)/smUi",\,$store);
//remove link
$store = preg_replace("/]+>/smUi",\,$store);
//remove
$store = preg_replace("//smUi",\,$store);
//remove
<style </ $store = preg_replace("/(.*)/smUi",\,$store);
//remove 中文空格
$store = preg_replace("//",\,$store);
//remove 标点符号
//$store = preg_replace("/[/~`!@#$%^&*()_/-+={}|/[/]//;:"//?/,/.//]/",\,$store);
//preg_match("/(.*)/smUi",$store, $matches);
//$head = $matches[1];
//echo $head. "/n";
//charset
if($pageinfo[charset] == \ ) {
preg_match(@]*>@i,$store,$matches);
$pageinfo[charset] = trim($matches[1]);
}
//desctiption
preg_match(@]+)/*>@i,$store,$matches);
//print_r($matches);
$desc = trim($matches[1]);
$pageinfo[description] = str_replace("/"", \,$desc);
preg_match(@]+)/*>@i,$store,$matches);
//print_r($matches);
$keywords = trim($matches[1]);
$pageinfo[keywords] = str_replace("/"", \,$keywords);
preg_match("/
$pageinfo[title] = trim($matches[1]);
preg_match("/(.*)/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 (
"]*?>.*?
// -->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
$a = getPageContent();
print_r($a);