［经验总结］Perl提取网页信息

 

  #!/usr/bin/perl -w
 
 

  

 
 

  # Gist: https://gist.github.com/2928006
 
 

  

 
 

  use 
  LWP::
  Simple
  ;
 
 

  my 
  $url
  =
  $ARGV
  [
  0
  ];
 
 

  my 
  $filename 
  =
  $ARGV
  [
  1
  ];
 
 

    
 
 

  my 
  $content 
  = 
  get
  (
  $url
  ) 
 
 

      
  or 
  die 
  "Couldn't get $url"
  ;
 
 

  

 
 

  #$content =~ s#^.*?(<div.*?</div>).*$##m;
 
 

  

 
 

  if 
  (
  $content 
  =~ 
  m
  #.*(<div id="enText" style="display:block">.*?</div>).*#sg) 
 
 

  {
 
 

      
  $text 
  = 
  $1
  ;
 
 

  

 
 

      
  # 打开模板文件  
 
 

      
  open
  (
  TEMPLATE
  , 
  "template.html"
  )
 
 

              
  or  
  die  
  " Couldn't open template.html for writing: $! " 
  ;
 
 

  

 
 

      
  # 读取模板文件  
 
 

      
  $/
  =
  "</html>"
  ; 
  # 读到</html>结束
 
 

      
  my 
  $reads 
  = 
  <TEMPLATE>
  ;
 
 

  

 
 

      
  # 替换听力文本  
 
 

      
  $reads 
  =~ 
  s/==TEXT_CONTENT==/$text/gix
  ;
 
 

      
  #print $reads;
 
 

  

 
 

      
  # 输出html文件  
 
 

      
  open 
  (
  OUT 
  , 
  " > $filename " 
  )
 
 

              
  or  
  die  
  " Couldn't open $filename for writing: $! "
  ;
 
 

      
  print 
  OUT 
  $reads
  ;
 
 

  

 
 

      
  # 下载听力    
 
 

      
  my 
  $baseUrl 
  = 
  $url
  ;
 
 

      
  $baseUrl 
  =~ 
  s/(.*)(//
  .*
  /.html)/
  $1
  /
  g
  ; 
 
 

      
  my 
  $reslink 
  = 
  $content
  ;
 
 

      
  $reslink 
  =~ 
  s/.*<a href="(.*?)" title="进入下载资料页面">下载听力<//
  a
  >.*
  /$1/sg
  ;
 
 

      
  $reslink 
  = 
  $baseUrl 
  . 
  "/" 
  . 
  $reslink
  ;
 
 

  

 
 

      
  print 
  "/nreslink:"
  ,
  $reslink
  ,
  "/n"
  ;
 
 

      
  my 
  $respage 
  = 
  get
  (
  $reslink
  ) 
 
 

          
  or 
  die 
  "Couldn't get $reslink"
  ;
 
 

  

 
 

      
  my 
  $mp3link 
  = 
  $respage
  ;
 
 

      
  print 
  $mp3link
  ;
 
 

  #$mp3link =~ s#.*<a href="(.*?)" target="_blank"><img src="/images/downloadurl1/.jpg"></a>.*#$1#sg;
 
 

  #if ($mp3link =~ m/.*<a href="(.*?)" target="_blank"><img src="//images//downloadurl1/.jpg"><//a>.*/sg) {
 
 

  

 
 

      
  # 没登录，下载链接获取不到，怎么办？
 
 

      
  if 
  (
  $mp3link 
  =~ 
  m/downloadurl1/sg
  ) 
  {
 
 

          
  print 
  "匹配/n"
  ;
 
 

      
  }
 
 

      
  else 
  {
 
 

          
  print 
  "不匹配/n"
  ;
 
 

      
  }
 
 

      
  #<a href="(.*?)" target="_blank"><img src="/images/downloadurl1.jpg"></a>   
 
 

  

 
 

      
  print 
  "/ndownload:"
  .
  $reslink
  .
  "/n"
  ;
 
 

  }
 
 

  else 
  {
 
 

      
  print 
  "不匹配/n"
  ;
 
 

  }