Function code for downloading remote images in content through regular expressions in PHP_PHP Tutorial

if (preg_match_all("/http://[^ "']+[. jpg|.gif|.jpeg|.png]+/ui",stripcslashes($content),$aliurl)){
$i=0; //Multiple files++
while(list($ key ,$v) = each($aliurl[0])){
//echo $v."
";
$filetype = pathinfo($v, PATHINFO_EXTENSION); // Get the suffix name
$ff = @file_get_contents($v); //Get the binary file content
if(!stripos($v,"jb51.net")){//Determine whether it is your own website The picture below
if (!empty($ff)){ //Perform the following operations after obtaining the file
$dir = "upload/".date("Ymd")."/";// Specify a new storage path
if (!file_exists($dir)){//Determine whether the directory exists
@mkdir($dir,511,true); //Create a multi-level directory, 511 is converted into decimal 777 has executable permissions
}
$nfn = $dir.date("Ymdhis").$i.".".$filetype; //New name of build file
$nf = @fopen ($nfn,"w"); //Create file
fwrite($nf,$ff); //Write file
fclose($nf); //Close file
$i++; / /Multiple files++
echo "";
$content = str_replace($v,$nfn, $content);//Replace content Parameters
}else{//If the image cannot be obtained, replace it with the default image
$content = str_replace($v,"/upload/201204/20120417213810742.gif", $content);//Replace content Parameters
}
}
}
}

/*
author: ssh_kobe
date: 20110602
shortage: If in the web page If the image path is not an absolute path, it cannot be crawled
*/
set_time_limit(0);//The crawling is not limited by time

$URL='http://pp.baidu. com/';//Any URL

get_pic($URL);

function get_pic($pic_url) {
//Get the image binary stream
$data=CurlGet( $pic_url);
/*Use regular expressions to get image links*/
$pattern_src = '/<[img|IMG].*?src=['|"](.*?(?: [.gif|.jpg]))['|"].*?[/]?>/';
$num = preg_match_all($pattern_src, $data, $match_src);
$arr_src= $match_src[1];//Get the image array
get_name($arr_src);

echo "
finished!!!";
return 0;
}

/*Get the picture type and save it to the same directory as the file*/
function get_name($pic_arr)
{
//Picture type
$pattern_type = '/ (/.(jpg|bmp|jpeg|gif|png))/';

foreach($pic_arr as $pic_item){//Loop out the address of each picture
$num = preg_match_all( $pattern_type, $pic_item, $match_type);
$pic_name = get_unique().$match_type[1][0];//Change the microsecond timestamp naming
//Save the picture in the form of a stream
$write_fd = @fopen($pic_name,"wb");
@fwrite($write_fd, CurlGet($pic_item));
@fclose($write_fd);
echo "[OK] ..!";
}
return 0;
}

//Get the unique ID through microsecond time
function get_unique(){
list($msec, $sec) = explode(" ",microtime());
return $sec.intval($msec*1000000);
}

//Capture web page content
function CurlGet ($url){
$url=str_replace('&','&',$url);
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_HEADER, false);

//curl_setopt($curl, CURLOPT_REFERER,$url);
curl_setopt($curl, CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 6.0 ; SeaPort/1.2; Windows NT 5.1; SV1; InfoPath.2)");
curl_setopt($curl, CURLOPT_COOKIEJAR, 'cookie.txt');
curl_setopt($curl, CURLOPT_COOKIEFILE, 'cookie.txt' );
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 0);
$values ​​= curl_exec($curl);
curl_close($curl);
return $values;
}
?>