zoukankan      html  css  js  c++  java
  • perl 循环类选择器 ,爬取内容

    jrhmpt01:/root/lwp/0526# cat 0526.txt 
    <div class="TXD_sy_title"><span class="TXD_sy_text_1">天下金专区</span> <span class="TXD_sy_text_2">投资期限自选  可进行债权转让  100元起投  每月还息,到期还本</span><span class="TXD_sy_text_3" style="float: right"><a href="/AnJuJinIntroduce.html" target="_blank">产品介绍 ></a>    <a href="/AnJuJinIndex.html" target="_blank" class="grey">更多项目 ></a></span></div>
            <div class="anjlist" id="txjDiv">
                <ul class="altitle TXD_top_title">
                    <li class="alcw1 TXD_top_title1">项目名称</li>
                    <li class="alcw2">投资金额</li>
                    <li class="alcw3">剩余投资期限</li>
                    <li class="alcw4">预期年化收益</li>
                    <li class="alcw4">进度</li>
                    <li class="alcw5">起投金额</li>
                    <li class="alcw6">操作</li>
                </ul>
    
    
                    <ul class="alcomment" style="overflow: visible;">
                            <li class="alcw1"><a target="_blank" href="/invest/fd6b88342c69470fb8ae9365589f78aa.html">天下金 201605253763</a></li>
    
                        <li class="alcw2">1,000,000.00元</li>
                            <li class="alcw3">27 天</li>
    
    
    
                            <li class="alcw4">5.5% </li>
                        
    
                        <li class="alcw4 alcw41">
                            <div class="ajjbfb txdbfb bfb100">100<span>%</span></div>
                        </li>
                        <li class="alcw5">100.00元</li>
                        <li class="alcw6">
                                <div class="txdbtns4 mt27 ml40"><a href="/invest/fd6b88342c69470fb8ae9365589f78aa.html" target="_blank" class="txdpng">查看</a></div>
                        </li>
                    </ul>
    
    jrhmpt01:/root/lwp/0526# cat a2.pl 
    use  LWP::UserAgent;
    use DBI;  
    use POSIX;
    use Data::Dumper;
    use HTML::TreeBuilder;
    my $ua = LWP::UserAgent->new;
    $ua->timeout(10);
    $ua->env_proxy;
    $ua->agent("Mozilla/8.0");
    
    
     use HTML::TreeBuilder::XPath;
       $tree= HTML::TreeBuilder::XPath->new;
      $tree->parse_file( "0526.txt");
    my    @pages=$tree->find_by_tag_name('li');
                          #先循环取出所有的li标签的 类选择器
                          foreach (@pages) {
                                                   @titlepage = $_->attr('class');
                                                   foreach (@titlepage) {
                                                     if ($_){ 
                                                    print "$_ is $_
    ";
                                                    unless ($_ ~~ @urlall) { push (@urlall ,$_);};
                                                         };
                                               };
    };
    
    print @urlall ;
    print "
    ";
    
    ##循环类选择器 查找li标签的@class="$var"的值,class代表类选择器: .开头 
    foreach my $var (@urlall){
    #my $url=qq(/html/body//li[@class='$var']);
    my $url="/html/body//li[@class=xxx]";
    $url =~ s/xxx/"$var"/g;
    print "$url is $url
    ";
    @total= $tree->findvalues("$url");
    print @total;
    print "
    ";
    #my @title= $tree->findvalues('/html/body//li[@class="alcw4 alcw41"]');
    
    };
    jrhmpt01:/root/lwp/0526# perl a2.pl 
    $_ is alcw1 TXD_top_title1
    $_ is alcw2
    $_ is alcw3
    $_ is alcw4
    $_ is alcw4
    $_ is alcw5
    $_ is alcw6
    $_ is alcw1
    $_ is alcw2
    $_ is alcw3
    $_ is alcw4
    $_ is alcw4 alcw41
    $_ is alcw5
    $_ is alcw6
    alcw1 TXD_top_title1alcw2alcw3alcw4alcw5alcw6alcw1alcw4 alcw41
    $url is /html/body//li[@class="alcw1 TXD_top_title1"]
    项目名称
    $url is /html/body//li[@class="alcw2"]
    投资金额1,000,000.00元
    $url is /html/body//li[@class="alcw3"]
    剩余投资期限27 天
    $url is /html/body//li[@class="alcw4"]
    预期年化收益进度5.5% 
    $url is /html/body//li[@class="alcw5"]
    起投金额100.00元
    $url is /html/body//li[@class="alcw6"]
    操作查看
    $url is /html/body//li[@class="alcw1"]
    天下金 201605253763
    $url is /html/body//li[@class="alcw4 alcw41"]
    100%

  • 相关阅读:
    将Web项目War包部署到Tomcat服务器基本步骤(完整版)
    性能实战分析-环境搭建(一)
    SQL Server Profiler追踪数据库死锁
    性能测试的各种监控工具大全
    python学习
    Linux常见面试题一
    Linux下用于查看系统当前登录用户信息的4种方法
    HDU 1394 Minimum Inversion Number(线段树求逆序对)
    SGU 180 Inversions(离散化 + 线段树求逆序对)
    Codeforces Round #FF (Div. 2) C. DZY Loves Sequences
  • 原文地址:https://www.cnblogs.com/zhaoyangjian724/p/6199980.html
Copyright © 2011-2022 走看看