php网页分析内容抓取爬虫资料分析

WBOY

Release： 2016-06-13 13:08:00

Original

1056 people have browsed it

php网页分析内容抓取爬虫文件分析

//获取所有内容url保存到文件
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        $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);
}

//获取目标多媒体对象
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);
}

//遍历目录获取文件内容
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);
}

//获取指定url内容
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获取指定网页
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;
}

//获取指定内容里的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;
}

//获取指定内容中的多媒体文件
function get_content_object($str, $split="|--:**:--|"){
    $regx = "/href\s*=\s*['\"]*([^>'\"\s]+)[\"'>]*\s*(.*?)/i";
    preg_match_all($regx, $str, $result);

    if (count($result) == 3){
        $result[2] = str_replace("多媒体： ", "", $result[2]);
        $result[2] = str_replace("", "", $result[2]);
        $result = $result[1][0] . $split .$result[2][0] . "\n";
    }
    return $result;
}

?>

//PHP 访问网页
$page = '';
$handler = fopen('http://www.baidu.com','r');
while(!feof($handler)){
   $page.=fread($handler,1048576);
}
fclose($handler);
echo $page;
?>

2:判断这个页面是否是报错页面

/**
      *   $host   服务器地址
      *   $get   请求页面
      *
      */
function   getHttpStatus($host,$get="")   {
$fp   =   fsockopen($host,   80);
if   (!$fp)   {
          $res=   -1;
}   else   {

          fwrite($fp,   "GET   /".$get."   HTTP/1.0\r\n\r\n");
          stream_set_timeout($fp,   2);
          $res   =   fread($fp,   128);
          $info   =   stream_get_meta_data($fp);
          fclose($fp);
          if   ($info['timed_out'])   {
                  $res=0;
          }   else   {
                  $res=   substr($res,9,3);
          }
}
return   $res;
}

$good=array("200","302");
if(in_array(getHttpStatus("5y.nuc.edu.cn","/"),$good))   {
echo   "正常";
}   else   {
echo   getHttpStatus("5y.nuc.edu.cn","/");
}

if(in_array(getHttpStatus("5y.nuc.edu.cn","/error.php"),$good))   {
echo   "正常";
}   else   {
echo   getHttpStatus("5y.nuc.edu.cn","/error.php");
}
?>

返回
第一个返回"正常"
第二个不存在返回"404"

function   getHttpStatus($host,$get="")   {
//访问网页获得服务器状态码
$fp   =   fsockopen($host,   80);
if   (!$fp)   {
          $res=   -1;
}   else   {

          fwrite($fp,   "GET   /".$get."   HTTP/1.0\r\n\r\n");
          stream_set_timeout($fp,   2);
          $res   =   fread($fp,   128);
          $info   =   stream_get_meta_data($fp);
          fclose($fp);
          if   ($info['timed_out'])   {
                  $res=0;
          }   else   {
                  $res=   substr($res,9,3);
          }
}
return   $res;
}

echo   getHttpStatus("5y.nuc.edu.cn","/");
echo   getHttpStatus("community.csdn.net","Expert/topic/4758/4758574.xml?temp=.1661646");

返回
1   无法连接服务器
0   超时
200   OK   (成功返回)
302   Found   (找到)
404   没有找到
...


//遍历所有网页   ($type指定类型)
function   getAllPage($path="./",$type=array("html","htm"))   {
global   $p;
if   ($handle   =   opendir($path))   {
          while   (false   !==   ($file   =   readdir($handle)))   {
              if(is_dir($file)   &&   $file!="."   &&   $file!="..")   {
              getAllPage($path.$file."/",$type);
              }   else   {
                  $ex=array_pop(explode(".",$file));

                  if(in_array(strtolower($ex),$type))   {
                    array_push($p,   $path.$file);
                  }
                  }
          }
                  closedir($handle);
}
}

$p=array();
getAllPage("./");
echo   "

";  <br>print_r($p);  <br>echo   "

Copy after login

";

?>

//抓取页面内容中所有URL。
$str='2006年05月30日   15:13:00   |   评论   (0)';

preg_match_all("/href=\"([^\"]*\.*php[^\"]*)\"/si",$str,$m);
//换用下面这个获取所有类型URL
//preg_match_all("/href=\"([^\"]*)\"/si",$str,$m);

print_r($m[1]);
?>

包含在链接里带get参数的地址
$str=file_get_contents("http://www.php.net");
preg_match_all("/href=\"([^\"]*\.*php\?[^\"]*)\"/si",$str,$m);
print_r($m[1]);
?>