［經驗總結］Perl提取網頁資訊

#!/usr/bin/perl -w# Gist: https://gist.github.com/2928006use 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;
    # 開啟模板檔案      open(TEMPLATE, "template.html")            or  die  " Couldn't open template.html for writing: $! " ;
    # 讀模數板檔案      $/="</html>"; # 讀到</html>結束    my $reads = <TEMPLATE>;
    # 替換聽力文本      $reads =~ s/==TEXT_CONTENT==/$text/gix;    #print $reads;
    # 輸出html檔案      open (OUT , " > $filename " )            or  die  " Couldn't open $filename for writing: $! ";    print OUT $reads;
    # 下載聽力        my $baseUrl = $url;    $baseUrl =~ s/(.*)(//.*/.html)/$1/g;     my $reslink = $content;    $reslink =~ s/.*<a href="(.*?)" title="進入下載資料頁面">下載聽力<//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) {
    # 沒登入，下載連結擷取不到，怎麼辦？    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";}