This procedure is actually part of the "Thief procedure". This part of the program just download the remote picture of the paragraph, the program is written relatively simple, most of the comments are made.
Copy Code code as follows:
if (Preg_match_all ("/http://[^")]+[.jpg|. Gif|. Jpeg|. Png]+/ui ", Stripcslashes ($content), $aliurl)) {
$i = 0; Multiple files + +
while (the list ($key, $v) = each ($aliurl [0])) {
echo $v. " <br/> ";
$filetype = PathInfo ($v, pathinfo_extension); Get suffix Name
$FF = @file_get_contents ($v); Get the contents of the 2 file
if (!stripos ($v, "jb51.net")) {//Judge whether it is a picture under your own website
if (!empty ($FF)) {//Get to file do the following
$dir = "upload/". Date ("Ymd"). " /";//Specify a new storage path
if (!file_exists ($dir)) {//To determine whether the directory exists
@mkdir ($dir, 511,true); Create multilevel directories, 511 to decimal is 777 with executable permission
}
$NFN = $dir. Date ("Ymdhis"). $i. "." $filetype; Build a new name for the file
$NF = @fopen ($nfn, "w"); Create a file
Fwrite ($NF, $FF); Write to File
Fclose ($NF); Close File
$i + +; Multi-file + +
echo " ";
$content = Str_replace ($v, $NFN, $content);//Replace parameters in content
}else{//can't get a picture and replace it with a default picture
$content = Str_replace ($v, "/upload/201204/20120417213810742.gif", $content);//Replace parameters in content
}
}
}
}
PHP Downloads pictures to local implementation code through regular expressions
Copy Code code as follows:
<?php
/*
Author:ssh_kobe
date:20110602
Shortage: If the picture path in the Web page is not an absolute path, you cannot crawl
*/
Set_time_limit (0);//crawl is not limited by time
$URL = ' http://pp.baidu.com/';//any URL
Get_pic ($URL);
function Get_pic ($pic _url) {
Get Picture binary stream
$data =curlget ($pic _url);
/* Use regular expression to get picture link * *
$pattern _src = '/<[img| Img].*?src=[\ ' |\ '] (. *?: [\.gif|\.jpg])) [\ ' |\ '].*? [\/]?>/';
$num = Preg_match_all ($pattern _src, $data, $match _src);
$arr _src= $match _src[1];//get an array of pictures
Get_name ($arr _src);
echo "<br>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 a microsecond timestamp name when _type[1][0];//changed
Save a picture as a stream
$write _fd = @fopen ($pic _name, "WB");
@fwrite ($write _fd, Curlget ($pic _item));
@fclose ($write _fd);
echo "[ok]..!";
}
return 0;
}
Get unique IDs through microsecond time
function Get_unique () {
List ($msec, $sec) = Explode ("", Microtime ());
Return $sec. Intval ($msec *1000000);
}
Crawl 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);
$values = curl_exec ($curl);
Curl_close ($curl);
return $values;
}
?>