zoukankan      html  css  js  c++  java
  • perl 爬取某理财网站产品信息

    use  LWP::UserAgent;
    use utf8;
    use DBI;  
    $user="root";  
    $passwd="xxxxx";  
    $dbh="";  
    $dbh = DBI->connect("dbi:mysql:database=zjzc_vote;host=14.5.6.57;port=3306",$user,$passwd) or die "can't connect to  database ". DBI-errstr;  
    $dbh->do("SET NAMES utf8"); 
    use POSIX;
    use Data::Dumper;
    use HTML::TreeBuilder;
    open DATAFH,">data.html" || die "open data file failed:$!"; 
    my $ua = LWP::UserAgent->new;
    $ua->timeout(10);
    $ua->env_proxy;
    $ua->agent("Mozilla/8.0");
    my $response = $ua->get('https://licai.yingyinglicai.com/product/list.htm');
    
    
    if ($response->is_success) {
     print DATAFH  $response->decoded_content;  # or whatever
    # print   $response->decoded_content;  # or whatever
      use HTML::TreeBuilder::XPath;
      my $tree= HTML::TreeBuilder::XPath->new;
      $tree->parse_file( "data.html");
    
    my @arr1= $tree->find_by_tag_name("tr") ;
    shift @arr1;
    foreach my $row ( @arr1) {
       my @arr2= $row->content_list;
        
        my $str1= $arr2[0]->as_text;   
        my $str2= $arr2[1]->as_text;   
        my $str3= $arr2[2]->as_text;   
        print $str1,$str2,$str3."
    ";
    
         my $XDATE = strftime("%Y%m%d%H%M%S",localtime());
        my $sql = "SELECT count(*)   FROM p2p_product  where name='$str1' and cname='yylc'";
        my $sth = $dbh->prepare($sql);
        $sth->execute();
    
      my  $count = $sth->fetchrow_array();
      if ($count == 0 ){
       $dbh->do("insert into p2p_product  values ('$str1','$str2','$str3','$XDATE','yylc')") or $!;
                      }
        }}

  • 相关阅读:
    linux 下面 opcache 拓展
    php中函数前加&符号的作用分解
    apache 设置404页面
    nginx 环境搭建使用之入门
    curl获取http请求的状态码
    js打开新的窗体不被浏览器阻止
    YII 框架使用之——创建应用
    Yii 框架创建自己的 web 应用
    PHP中CURL方法curl_setopt()函数的一些参数
    Linux的学习--使用PuTTY
  • 原文地址:https://www.cnblogs.com/hzcya1995/p/13350996.html
Copyright © 2011-2022 走看看