PHP get page title and content function

Source: Internet
Author: User
Tags exit curl html tags php code trim
Sometimes we need to get the title and content of the page, is a collection function, here to share a simple, convenient to need friends   code as follows: 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) ");        &NBSp   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 ($pageinfo [' Httpcode ']) <> or!preg_match (' @text/html@ ', Curl_getinfo ($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), $matches); From header charset            if (Trim ($matches [1]) {         & nbsp     $pageinfo [CharSet] = Trim ($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 = P Reg_replace ("/<!--. *-->/smui", ", $store)";           //remove <style  </<style>          &NB Sp $store = Preg_replace ("/<style.*> (. *) <//style>/smui", ", $store);           //remove Chinese space            $store = preg_replace ("// ", ', $store);           //remove punctuation mark           //$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           p Reg_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> (. *) <//ti Tle>/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;              &NBsp         return $pageinfo;    }    /**    * Remove all HTML tags and javascript tags    */  function Replacehtmlandjs ($document)    {             $document = Trim ($document);             if (strlen ($document) <= 0)             {   & nbsp         return $document;                           $search = Array (  & nbsp                                  &NBS P               "' <script[^>]*?>.*? --></mce:script> ' Si ',  //remove JavaScript                  &NB Sp           "' <[///!] *? [^<>]*?> ' Si ', &nBsp        //Remove HTML tags                      &NBSP ;       "[/r/n/s+]" "               //remove whitespace character      & nbsp                       "' & (/w+); ' I "             //replacement HTML entity                &N Bsp            );                    //as PHP code run          &NBS P     $replace = Array ("", "", "", ""  );               return @preg_replace ($search, $replace, $document);     }         Use example   code as follows: $a = getpagecontent (www.ttphp.com);    Print_r ($a);   
Related Article

E-Commerce Solutions

Leverage the same tools powering the Alibaba Ecosystem

Learn more >

Apsara Conference 2019

The Rise of Data Intelligence, September 25th - 27th, Hangzhou, China

Learn more >

Alibaba Cloud Free Trial

Learn and experience the power of Alibaba Cloud with a free trial worth $300-1200 USD

Learn more >

Contact Us

The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion; products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the content of the page makes you feel confusing, please write us an email, we will handle the problem within 5 days after receiving your email.

If you find any instances of plagiarism from the community, please send an email to: info-contact@alibabacloud.com and provide relevant evidence. A staff member will contact you within 5 working days.