沒事的時候想抓取點網頁看看,也不太懂,只是玩玩,寫了點代碼,聊以娛樂。
稍微有點意義的函數是:get_content_by_socket(), get_url(), get_content_url(), get_content_object 幾個函數,也許能夠給你點什麼想法。
<?php
//擷取所有內容url儲存到檔案
function get_index($save_file, $prefix="index_"){
$count = 68;
$i = 1;
if (file_exists($save_file)) @unlink($save_file);
$fp = fopen($save_file, "a+") or die("Open ". $save_file ." failed");
while($i<$count){
$url = $prefix . $i .".htm";
echo "Get ". $url ."...";
$url_str = get_content_url(get_url($url));
echo " OK/n";
fwrite($fp, $url_str);
++$i;
}
fclose($fp);
}
//擷取目標多媒體對象
function get_object($url_file, $save_file, $split="|--:**:--|"){
if (!file_exists($url_file)) die($url_file ." not exist");
$file_arr = file($url_file);
if (!is_array($file_arr) || empty($file_arr)) die($url_file ." not content");
$url_arr = array_unique($file_arr);
if (file_exists($save_file)) @unlink($save_file);
$fp = fopen($save_file, "a+") or die("Open save file ". $save_file ." failed");
foreach($url_arr as $url){
if (empty($url)) continue;
echo "Get ". $url ."...";
$html_str = get_url($url);
echo $html_str;
echo $url;
exit;
$obj_str = get_content_object($html_str);
echo " OK/n";
fwrite($fp, $obj_str);
}
fclose($fp);
}
//遍曆目錄擷取檔案內容
function get_dir($save_file, $dir){
$dp = opendir($dir);
if (file_exists($save_file)) @unlink($save_file);
$fp = fopen($save_file, "a+") or die("Open save file ". $save_file ." failed");
while(($file = readdir($dp)) != false){
if ($file!="." && $file!=".."){
echo "Read file ". $file ."...";
$file_content = file_get_contents($dir . $file);
$obj_str = get_content_object($file_content);
echo " OK/n";
fwrite($fp, $obj_str);
}
}
fclose($fp);
}
//擷取指定url內容
function get_url($url){
$reg = '/^http:////[^//].+$/';
if (!preg_match($reg, $url)) die($url ." invalid");
$fp = fopen($url, "r") or die("Open url: ". $url ." failed.");
while($fc = fread($fp, 8192)){
$content .= $fc;
}
fclose($fp);
if (empty($content)){
die("Get url: ". $url ." content failed.");
}
return $content;
}
//使用socket擷取指定網頁
function get_content_by_socket($url, $host){
$fp = fsockopen($host, 80) or die("Open ". $url ." failed");
$header = "GET /".$url ." HTTP/1.1/r/n";
$header .= "Accept: */*/r/n";
$header .= "Accept-Language: zh-cn/r/n";
$header .= "Accept-Encoding: gzip, deflate/r/n";
$header .= "User-Agent: Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; Maxthon; InfoPath.1; .NET CLR 2.0.50727)/r/n";
$header .= "Host: ". $host ."/r/n";
$header .= "Connection: Keep-Alive/r/n";
//$header .= "Cookie: cnzz02=2; rtime=1; ltime=1148456424859; cnzz_eid=56601755-/r/n/r/n";
$header .= "Connection: Close/r/n/r/n";
fwrite($fp, $header);
while (!feof($fp)) {
$contents .= fgets($fp, 8192);
}
fclose($fp);
return $contents;
}
//擷取指定內容裡的url
function get_content_url($host_url, $file_contents){
//$reg = '/^(#|javascript.*?|ftp:////.+|http:////.+|.*?href.*?|play.*?|index.*?|.*?asp)+$/i';
//$reg = '/^(down.*?/.html|/d+_/d+/.htm.*?)$/i';
$rex = "/([hH][rR][eE][Ff])/s*=/s*['/"]*([^>'/"/s]+)[/"'>]*/s*/i";
$reg = '/^(down.*?/.html)$/i';
preg_match_all ($rex, $file_contents, $r);
$result = ""; //array();
foreach($r as $c){
if (is_array($c)){
foreach($c as $d){
if (preg_match($reg, $d)){ $result .= $host_url . $d."/n"; }
}
}
}
return $result;
}
//擷取指定內容中的多媒體檔案
function get_content_object($str, $split="|--:**:--|"){
$regx = "/href/s*=/s*['/"]*([^>'/"/s]+)[/"'>]*/s*(<b>.*?<//b>)/i";
preg_match_all($regx, $str, $result);
if (count($result) == 3){
$result[2] = str_replace("<b>多媒體: ", "", $result[2]);
$result[2] = str_replace("</b>", "", $result[2]);
$result = $result[1][0] . $split .$result[2][0] . "/n";
}
return $result;
}
?>