Copy code The code is as follows:
/*
author: ssh_kobe
date: 20110602
shortage: If the image path in the web page is not an absolute path, it cannot be crawled
*/
set_time_limit (0); //Fetching 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 the image link*/
$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($arr_src);
echo "
finished!!!";
return 0;
}
/*Get the image type and add it Save to the same directory as the file*/
function get_name($pic_arr)
{
//Picture type
$pattern_type = '/(/.(jpg|bmp|jpeg|gif|png))/';
foreach( $pic_arr as $pic_item){//Loop to get 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 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($curl, CURLOPT_FOLLOWLOCATION, 0);
curl_close($curl);
return $values;
}
?>