思享工具箱

对网站的代码采集实例

摘要：
整数（$_GET['id']）：1；$listArr=文件（'list.txt'）；如果（！

1.采集的网站：http://www.abnova.com/support/publication.asp

2. 相关的代码：列表（规则采集）页面使用：phpQuery.php，可以参考：PHP curl_setopt函数用法介绍中篇

3.产品详情页面：信息（不规则采集），参考代码如下：

<?php
header('Content-Type:text/html;charset=UTF-8');
include 'phpQuery/phpQuery.php';
set_time_limit(0);
$id = isset($_GET['id']) ? intval($_GET['id']) : 1;
$listArr = file('list.txt');
if (!array_key_exists($id,$listArr)){
    echo 'finished';
    exit;
}
$url = preg_replace('/[
]+/','',$listArr[$id]);
phpQuery::newDocumentFile($url);
$artList = pq("#sub_product_info");
echo '<pre>';
foreach($artList as $li){
    $data = array();
    $datacode = array();
    $datacode = explode('=',$url);
    $data['code'] = $datacode[1];
    $one = '';
    $one_a = '';
    $one_a = pq($li)->find("#10000 b")->html();
    $one_a = trim(strip_tags($one_a));
    if($one_a == 'Product Description:'){
        //echo 1;
     $one = pq($li)->find('#10000 li')->eq(1)->html();
     $one =  trim(strip_tags($one));
     echo "Product Description:   ".$one;   
    }else{
        echo "Product Description:   ".$one;
        //echo "wrong!<br/>";
}
    $data['Description'] = $one;
     echo '<br/>';
    #########################
    $two = '';
    $two_a = '';
    $two_a = pq($li)->find("#90000 b")->html();
    $two_a = trim(strip_tags($two_a));
    if($two_a == 'Immunogen:'){
     $two = pq($li)->find('#90000 li')->eq(1)->html();
     $two =  trim(strip_tags($two));
     echo "Immunogen:   ".$two;   
    }else{
        echo "Immunogen:   ".$two;
        //echo "wrong<br/>";
}
    $data['Immunogen'] = $two;
     echo '<br/>';
    #########################
    $three = '';
    $three_a = '';
    $three_a = pq($li)->find("#110000 b")->html();
    $three_a = trim(strip_tags($three_a));
    if($three_a == 'Host:'){
     $three = pq($li)->find('#110000 li')->eq(1)->html();
     $three =  trim(strip_tags($three));
     echo "Host:   ".$three;   
    }else{
        echo "Host:   ".$three;
        //echo "wrong<br/>";
}
    $data['Host'] = $three;
     echo '<br/>';
     #########################
     $four = '';
     $four_a = '';
    $four_a = pq($li)->find("#130000 b")->html();
    $four_a = trim(strip_tags($four_a));
    if($four_a == 'Reactivity:'){
     $four = pq($li)->find('#130000 li')->eq(1)->html();
     $four =  trim(strip_tags($four));
     echo "Reactivity:   ".$four;   
    }else{
        echo "Reactivity:   ".$four;
        //echo "wrong<br/>";
}
    $data['Reactivity'] = $four;
     echo '<br/>';
     #########################
    $five = '';
    $five_a ='';
    $five_a = pq($li)->find("#240000 b")->html();
    $five_a = trim(strip_tags($five_a));
    if($five_a == 'Isotype:'){
     $five = pq($li)->find('#240000 li')->eq(1)->html();
     $five =  trim(strip_tags($five));
     echo "Isotype:   ".$five;   
    }else{
        echo "Isotype:   ".$five;
        //echo "wrong<br/>";
}
    $data['Isotype'] = $five;
     echo '<br/>';
     #########################
    $six = '';
    $six_a = '';
    $six_a = pq($li)->find("#290000 b")->html();
    $six_a = trim(strip_tags($six_a));
    if($six_a == 'Quality Control Testing:'){
     $six_all = pq($li)->find('#290000 li')->eq(1)->html();
     $six_all =  trim(strip_tags($six_all,"<br>"));
     //$six_all = str_replace("<br><br><br/>",'###',)
     $six_arr = explode("<br><br><br>",$six_all);
     //var_dump($six_arr);
     $six = trim($six_arr[0]);   
     echo "Quality Control Testing:    ".$six;   
    }else{
        echo "Quality Control Testing:    ".$six;
        //echo "wrong<br/>";
}
    $data['Testing'] = $six;
     echo '<br/>';
     echo '<hr/>';
     #########################
     $wh_11 = '';
     $wh_11 = pq($li) -> find(".part")->eq(2)->find(".first_title b")->html();
     $wh_11 = trim(strip_tags($wh_11));
     echo "APP:   ".$wh_11;
     echo '<br/>';
     $wh_22 = '';
     $wh_22 = pq($li) -> find(".part")->eq(2)->find("ul")->eq(1)->find("li")->eq(0)->html();
     $wh_22 = trim(strip_tags($wh_22));
     echo "Western:   ".$wh_22;
     echo '<br/>';
     $wh_33 = '';
     $wh_33 = pq($li) -> find(".part")->eq(2)->find("ul")->eq(2)->find("li")->eq(0)->html();
     $wh_33 = trim(strip_tags($wh_33));
     echo "Western Blot:   ".$wh_33;
     echo '<br/>';
     $wh_44 = '';
     $wh_44 = pq($li) -> find(".part")->eq(2)->find("ul")->eq(3)->find("li")->eq(0)->html();
     $wh_44 = trim(strip_tags($wh_44));
     echo "Immunohistochemistry:    ".$wh_44;
     echo '<br/>';
     $wh_55 = '';
     $wh_55 = pq($li) -> find(".part")->eq(2)->find("ul")->eq(4)->find("li")->eq(0)->html();
     $wh_55 = trim(strip_tags($wh_55));
     echo "Immunofluorescence:    ".$wh_55;
     echo '<br/>';
     $wh_66 = '';
     $wh_66 = pq($li) -> find(".part")->eq(2)->find("ul")->eq(5)->find("li")->eq(0)->html();
     $wh_66 = trim(strip_tags($wh_66));
     echo "Sandwich ELISA:   ".$wh_66;
     echo '<br/>';
     $wh_77 = '';
     $wh_77 = pq($li) -> find(".part")->eq(2)->find("ul")->eq(6)->find("li")->eq(0)->html();
     $wh_77 = trim(strip_tags($wh_77));
     echo "ELISA:   ".$wh_77;
     echo '<br/>';
    $app = array();
    $appstr = '';
    if ($wh_22 != '') $app['w1'] = $wh_22;
    if ($wh_33 != '') $app['w2'] = $wh_33;
    if ($wh_44 != '') $app['w3'] = $wh_44;
    if ($wh_55 != '') $app['w4'] = $wh_55;
    if ($wh_66 != '') $app['w5'] = $wh_66;
    if ($wh_77 != '') $app['w6'] = $wh_77;
    echo $appstr = implode(',',$app);
    $data['app'] = $appstr;
     echo '<hr/>';
     #########################
     // $length = pq($li) -> find(".part")->eq(3)->find("ul")->find("li")->html();
     // $length = trim(strip_tags($length,'<b>'));
     // $length = str_replace("<b>","####",$length);
     // // $length = str_replace("</b>",",",$length);
     // echo $length;
     // $arr = explode(",",$length);
     // var_dump($arr);
     // foreach($length as $list){
     //  echo $list;
     //  // exit;
     // }
      echo '<hr/>';
     echo '<br/>';
     $heng_11 = '';
     $heng_11_a = '';
     $heng_11_a = pq($li) -> find(".part")->eq(3)->find("ul")->eq(1)->find("li")->eq(0)->find("b")->html();
     $heng_11_a = trim(strip_tags($heng_11_a));
     if($heng_11_a == 'Entrez GeneID:'){
      $heng_11 = pq($li) -> find(".part")->eq(3)->find("ul")->eq(1)->find("li")->eq(1)->find("a")->html();
      $heng_11 = trim(strip_tags($heng_11));
      echo "Entrez GeneID:   ".$heng_11;
     }else{
         echo "Entrez GeneID:   ".$heng_11;
     }
    $data['GeneID'] = $heng_11;
     echo '<br/>';
     $heng_22 = '';
     $heng_22_a = '';
     $heng_22_a = pq($li) -> find(".part")->eq(3)->find("ul")->eq(2)->find("li")->eq(0)->find("b")->html();
     $heng_22_a = trim(strip_tags($heng_22_a));
     if($heng_22_a == 'GeneBank Accession#:'){
     $heng_22 = pq($li) -> find(".part")->eq(3)->find("ul")->eq(2)->find("li")->eq(1)->find("a")->html();
     $heng_22 = trim(strip_tags($heng_22));
     echo "GeneBank Accession#:   ".$heng_22;
     }else{
         echo "GeneBank Accession#:   ".$heng_22;
     }
     $data['GeneBank Accession'] = $heng_22;
     echo '<br/>';
     $heng_33 = '';
     $heng_33_a = '';
     $heng_33_a = pq($li) -> find(".part")->eq(3)->find("ul")->eq(3)->find("li")->eq(0)->find("b")->html();
     $heng_33_a = trim(strip_tags($heng_33_a));
     if($heng_33_a == 'Protein Accession#:'){
     $heng_33 = pq($li) -> find(".part")->eq(3)->find("ul")->eq(3)->find("li")->eq(1)->find("a")->html();
     $heng_33 = trim(strip_tags($heng_33));
     echo "Protein Accession#:   ".$heng_33;
     }else{
         echo "Protein Accession#:   ".$heng_33;
     }
     $data['Protein Accession'] = $heng_33;
     echo '<br/>';
      $heng_44 = '';
      $heng_44_a = '';
      $heng_44_a = pq($li) -> find(".part")->eq(3)->find("ul")->eq(4)->find("li")->eq(0)->find("b")->html();
      $heng_44_a = trim(strip_tags($heng_44_a));
      if($heng_44_a == 'Gene Name:'){
        $heng_44 = pq($li) -> find(".part")->eq(3)->find("ul")->eq(4)->find("li")->eq(1)->html();
         $heng_44 = trim(strip_tags($heng_44));
         echo "Gene Name:   ".$heng_44;
      }else{
          echo "Gene Name:    ".$heng_44;
      }
    $data['Gene Name'] = $heng_44;
     echo '<br/>';
      $heng_55 = '';
      $heng_55_a = '';
      $heng_55_a = pq($li) -> find(".part")->eq(3)->find("ul")->eq(5)->find("li")->eq(0)->find("b")->html();
      $heng_55_a = trim(strip_tags($heng_55_a));
      if($heng_55_a == 'Gene Alias:'){
        $heng_55 = pq($li) -> find(".part")->eq(3)->find("ul")->eq(5)->find("li")->eq(1)->html();
        $heng_55 = trim(strip_tags($heng_55));
        echo "Gene Alias:   ".$heng_55;
      }else{
          echo "Gene Alias:  ".$heng_55;
      }
$data['Gene Alias'] = $heng_55;
     echo '<br/>';
      $heng_66 = '';
      $heng_66_a = '';
      $heng_66_a = pq($li) -> find(".part")->eq(3)->find("ul")->eq(7)->find("li")->eq(0)->find("b")->html();
      $heng_66_a = trim(strip_tags($heng_66_a));
      if($heng_66_a == 'Omim ID:'){
        $heng_66 = pq($li) -> find(".part")->eq(3)->find("ul")->eq(7)->find("li")->eq(1)->html();
        $heng_66 = trim(strip_tags($heng_66));
        echo "Omim ID:  ".$heng_66;
      }else{
          echo "Omim ID:  ".$heng_66;
      }
$data['Omim ID'] = $heng_66;
     echo '<br/>';
      $heng_77 = '';
      $heng_77_a = '';
      $heng_77_a = pq($li) -> find(".part")->eq(3)->find("ul")->eq(8)->find("li")->eq(0)->find("b")->html();
      $heng_77_a = trim(strip_tags($heng_77_a));
      if($heng_77_a == 'Gene Ontology:'){
        $heng_77 = pq($li) -> find(".part")->eq(3)->find("ul")->eq(8)->find("li")->eq(1)->find("a")->html();
        $heng_77 = trim(strip_tags($heng_77));
        echo "Gene Ontology:   ".$heng_77;
      }else{
          echo "Gene Ontology:   ".$heng_77;
      }
    $data['Gene Ontology'] = $heng_77;
     #获取文献
     $rarr = array();
     $Reference = '';
     if (preg_match('/Publication Reference/',$li->textContent)){
         preg_match_all('/Publication Reference(.*?)Applications/',preg_replace('/[
]+/','',$li->textContent),$rarr);
     }
    $Reference = $rarr[1][0];
    $data['Reference'] = $Reference;
    $rarr = array();
    print_r($data);
    #写入文件 
    $handle = fopen('list-new.csv','a');
    fputcsv($handle,$data);
    fclose($handle);
}
?>
<script>
functionJumpUrl(){
    location.href='http://t.zoukankan.com/?id=<?php echo ($id+1);?>';
}
setTimeout('JumpUrl()',0);
</script>

标签：#echo | 浏览：121 | 发布日期：

免责声明：文章转载自《对网站的代码采集实例》仅用于学习参考。如对内容有疑问，请及时联系本站处理。

上篇URL中#号(井号)的作用一、Vuforia_AR下篇

宿迁高防，2C2G15M，22元/月；香港BGP，2C5G5M，25元/月 雨云优惠码：MjYwNzM=

相关文章

Linux-018-Centos Shell 判断软件是否已经安装

编写自动化安装脚本或部署应用的初始化脚本时，通常需要判断软件是否已经安装，通过如下方法，可进行初步的软件安装判断，shell 示例脚本如下所示： #!/bin/bash IS_INSTALLED=$(rpm -qa |grepjava) if [ $? -eq 0] then echo 'installed' else echo 'no...

Python 命令行之旅：深入 click 之增强功能

作者：HelloGitHub-Prodesire HelloGitHub 的《讲解开源项目》系列，项目地址：https://github.com/HelloGitHub-Team/Article 一、前言 在前面三篇文章中，我们介绍了 click 中的参数、选项和命令，本文将介绍 click 锦上添花的功能，以帮助我们更加轻松地打造一个更加强大的命令行...

3389登陆记录的清除方法

一 .HKEY_CURRENT_USERSoftwareMicrosoftTerminal Server ClientDefault 把右边显示出来的，非原有的ip键值直接DEL就可以啦~~但是千万记住默认注册表打开的时候，当前键值是在哪儿（一般是主键，没有分树），照着默认一打开时候的树状模样恢复就ok 二 .另一个方法 xp和2003下 reg que...

【Centos7裁剪】

#!/bin/sh rootdir=`pwd` rm -rf ${rootdir}/centos* KERNEL_DIR=${rootdir}/kernel ROOTFS_DIR=${rootdir}/rootfs if [ -d ${KERNEL_DIR} ]; then echo "remove kernel dir" rm -rf...

WinXP、Win7脚本自动加域及用户资料迁移

WinXP、Win7脚本自动加域及用户资料迁移（一）最近公司要上AD域项目，所有的用户全部从工作组环境切换到域环境，本地账号迁移到域账号。因客户端比较多，仔细研究了一下微软的加域和用户迁移工具，结合在网上搜到的一些脚本，自己编写了一个Windows Xp，Windows 7自动加域及自动迁移用户配置文件的脚本。（工具已上传，其中USMT由于太大，请自行下...

（3.4）mysql基础深入——mysql.server启动脚本源码阅读与分析

（3.4）mysql基础深入——mysql.server启动脚本源码阅读与分析 my.server主要分为3大部分 【1】变量初始化部分　　【2】函数声明部分　　【3】具体执行部分 #!/bin/sh #【第1部分，变量初始化部分begin】 #【1.1】指定Mysql安装程序及数据目录的路径，默认是/usr/local/mysql，默认是空的 ba...

最新文章

随机推荐

思享工具箱导航