提取google,baidu等搜索网页内容

PHP中文网

发布时间：2016-05-25 17:11:05

1666人浏览过

来源于php中文网

原创

在本地上没什么问题,测试结果在附图里.

1. [代码][PHP]代码



Search test










Google
Baidu
php
mysql
Java
html





');
//echo $start.'start
';
$end=strpos($contents,'';
$inf=substr($contents,$start,$len);
//过滤掉google伪链接,替换搜索链接,尾部链接
$inf=str_replace('/url?q=','',$inf);
$inf=str_replace('search?q=','index.php?engine=google&keywords=',$inf);
//过滤google js带来的无用后缀
//$pattern='&sa=([a-z0-9_\-]){1}&ei=([a-z0-9_\-]){18,22}&ved=([a-z0-9_\-]){9,13}&usg=([a-z0-9_\-]){34}';
$pattern2='&sa=([a-z0-9_\-]){1}&ei=([a-z0-9_\-]){22}&ved=([a-z0-9_\-]){9,13}&usg=([a-z0-9_\-]){34}';
//test regular expression below
$inf=eregi_replace($pattern2,' ',$inf);
//$write='test writing ability';
//file_put_contents('/home/mageia/search_test',$inf);
//替换类似内容链接无法打开链接
$inf=str_replace('/search?','http://www.google.com/search?',$inf);
//替换google对链接的转换
$inf=urldecode($inf);
echo $inf;
$guid='
1
        2
        3
        4
        5
        6
        7
        8
        9
        10
        11
        12
        ';
//$currentpage当前所在页
$currentpage=$pn/10+1;
$currentpos=strpos($guid,$currentpage.'<');
//$guid为最低下的导航页内容
$guid=substr_replace($guid,'O',$currentpos,($currentpage<10)?1:2);
echo $guid;
}
elseif($engine=='baidu'){

header("Content-type:text/html;charset=utf-8");//加个头
require('baidu.sty');
$url='http://www.baidu.com/s?wd='.$keywords.'&pn='.$pn;
//please check the url
//echo $url;
//$contents=file_get_contents($url);

//try with curl
$contents=get_data($url);
//echo $contents;
$start=strpos($contents,'');
//echo $start.'
';
//real start position
$start=strpos($contents,'',$start);
//real end position
$end=strpos($contents,'
',$start);
$len=$end-$start;
//echo $end.'
';
$inf=substr($contents,$start,$len);
//替换一些失效链接
$inf=str_replace('/s?wd=','index.php?engine=baidu&keywords=',$inf);
echo $inf;

$guid='
1
        2
        3
        4
        5
        6
        7
        8
        9
        10
        ';
//$currentpage当前所在页
$currentpage=$pn/10+1;
$currentpos=strpos($guid,$currentpage.'<');
//$guid为最低下的导航页内容
$guid=substr_replace($guid,'O',$currentpos,($currentpage<10)?1:2);
echo $guid;
}
elseif($engine=='php'){

/*it will only search php functions within http://www.php.cn/ . If the function name you *give does not exist, it returns nothing but a empty page.
*/
require('php_print.css');
require('php_site.css');
require('php_mirror.css');
$url='http://php.net/search.php?&pattern='.$keywords.'&show=quickref';

//try with file_get_contents,failed remote in us server
$phpcontents=file_get_contents($url);

//try with curl,failed local
//$phpcontents=get_data($url);
//echo $phpcontents;
$start=strpos($phpcontents,'';
//actual start position
$start+=8;
//echo $start.'
';
$start=strpos($phpcontents,'
');
$phpinf=substr($phpcontents,$start,$end-$start);
echo $phpinf;
}
elseif(($engine=='mysql')||($engine=='java')){

header("Content-type:text/html;charset=utf-8");//加个头
require('search-core.sty');
require('search.sty');
require('results.sty');
require('grids-ses.sty');
require('tabview-ses.sty');
require('treeview-ses.sty');

//enable page links to work
$pgstart=$pn+1;
$pgend=$start+9;

//url中不能有回车符
if($engine=='mysql'){
$url='http://search.oracle.com/search/search?&q='.$keywords.'&group=MySQL&search_startnum='.$pgstart.'&search_endnum='.$pgend.'&num=10';}
else{
$url='http://search.oracle.com/search/search?search_p_main_operator=all&group=Documentation&q='.$keywords.'+url:/javase'.'&search_startnum='.$pgstart.'&search_endnum='.$pgend.'&num=10';
}
//echo $url;
//$mysqlcontents=file_get_contents($url);

//try with curl
$mysqlcontents=get_data($url);

$start=strpos($mysqlcontents,'
');
$end=strpos($mysqlcontents,'
');
$mysqlinf=substr($mysqlcontents,$start,$end-$start);
echo $mysqlinf;
if($engine=='mysql'){
$guid='
1
        2
        3
        4
        5
        ';
}else{
$guid='1
        2
        3
        4
        5
        ';
}
 
$currentpage=$pn/10+1;
$currentpos=strpos($guid,$currentpage.'<');
//$guid为最低下的导航页内容
$guid=substr_replace($guid,'O',$currentpos,($currentpage<10)?1:2);
echo $guid;
}
else{
echo 'Sorry,This search engine will be supported soon.';
}


/* gets the data from a URL */
function get_data($url) 
{   
  $ch = curl_init();
  $timeout = 5; 
  curl_setopt($ch,CURLOPT_URL,$url);
  curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
  curl_setopt($ch,CURLOPT_CONNECTTIMEOUT,$timeout);
  $data = curl_exec($ch);
  curl_close($ch);
  return $data;
} 
?>

2. [图片]屏幕截图.png

动软商城系统

动软商城系统是一款优秀的网上商城系统，经营者只需要轻松的后台操作，就可以马上拥有功能强的网上销售系统，同时动软商城系统提供多样的营销手段帮助您成功打开网上销售市场。动软的模版界面机制，可以轻松的搭建出风格各异的界面，最大限度的满足经营者的要求，还拥有专业SEO优化系统，大大提高网页被搜索引擎抓取收录的几率。动软商城系统先进的流程控制技术全面促进进、销、存等系统的协同，支持企业数据整合和网络资源信息

下载

提取google,baidu等搜索网页内容