PHP multi-thread batch collection and downloading image implementation code

PHP multi-thread batch collection and downloading image implementation code

The use of curl multithreading, in addition, curl can set the request time, in the event of a very slow url resource, you can decisively give up, so there is no blocking, and there are multi-threaded requests, the efficiency should be relatively high /** * Curl multithreading * @ Param array $ array parallel URL * @ Param int $ timeout * @ Return mix */ Public function Curl_http ($ array, $ timeout = '15 '){ $ Res = array (); $ Mh = curl_multi_init (); // create multiple curl handles Foreach ($ array as $ k => $ url ){ $ Conn [$ k] = curl_init ($ url); // Initialization Curl_setopt ($ conn [$ k], CURLOPT_TIMEOUT, $ timeout); // Set the timeout time Curl_setopt ($ conn [$ k], CURLOPT_USERAGENT, 'mozilla/5.0 (compatible; MSIE 5.01; Windows NT 5.0 )'); Curl_setopt ($ conn [$ k], CURLOPT_MAXREDIRS, 7); // HTTp targeting level, top 7 Curl_setopt ($ conn [$ k], CURLOPT_HEADER, false); // no header here, block efficiency Curl_setopt ($ conn [$ k], CURLOPT_FOLLOWLOCATION, 1); // 302 redirect Curl_setopt ($ conn [$ k], CURLOPT_RETURNTRANSFER, 1); // The result must be a string and output to the screen. Curl_setopt ($ conn [$ k], CURLOPT_HTTPGET, true ); Curl_multi_add_handle ($ mh, $ conn [$ k]); } // Prevent endless loop consumption of cpu. this section is based on the online statement. Do { $ Mrc = curl_multi_exec ($ mh, $ active); // when no data exists, active = true } While ($ mrc = CURLM_CALL_MULTI_PERFORM); // when receiving data While ($ active and $ mrc = CURLM_ OK) {// when there is no data or the request is paused, active = true If (curl_multi_select ($ mh )! =-1 ){ Do { $ Mrc = curl_multi_exec ($ mh, $ active ); } While ($ mrc = CURLM_CALL_MULTI_PERFORM ); } } Foreach ($ array as $ k => $ url ){ If (! Curl_errno ($ conn [$ k]) { $ Data [$ k] = curl_multi_getcontent ($ conn [$ k]); // convert data to array $ Header [$ k] = curl_getinfo ($ conn [$ k]); // return http header information Curl_close ($ conn [$ k]); // Close the slogan. Curl_multi_remove_handle ($ mh, $ conn [$ k]); // release resources } Else { Unset ($ k, $ url ); } } Curl_multi_close ($ mh ); Return $ data; } // Receive parameters $ Callback = $ _ GET ['callback']; $ Hrefs = $ _ GET ['hrefs']; $ Urlarray = explode (',', trim ($ hrefs ,',')); $ Date = date ('ymmd', time ()); // Instantiate $ Img = new HttpImg (); $ Stime = $ img-> getMicrotime (); // start time $ Data = $ img-> Curl_http ($ urlarray, '20'); // list data Mkdir ('./img/'. $ date, 0777 ); Foreach (array) $ data as $ k => $ v ){ Preg_match_all ("/(href | src) = ([" | ']?) ([^ "'>] +. (Jpg | png | PNG | JPG | gif) \ 2/I", $ v, $ matches [$ k]); If (count ($ matches [$ k] [3])> 0 ){ $ Dataimg = $ img-> Curl_http ($ matches [$ k] [3], '20'); // binary of all image data $ J = 0; Foreach (array) $ dataimg as $ kk => $ vv ){ If ($ vv! = ''){ $ Rand = rand ); $ Basename = time (). "_". $ rand. ".". jpg; // save as a jpg file $ Fname = './img/'. $ date. "/". "$ basename "; File_put_contents ($ fname, $ vv ); $ J ++; Echo "create the". $ j. "Picture". "$ fname "." "; } Else { Unset ($ kk, $ vv ); } } } Else { Unset ($ matches ); } } $ Etime = $ img-> getMicrotime (); // end time Echo "time used". ($ etime-$ stime). "seconds "; Exit;

Multithreading, image download, PHP