973114 发表于 2018-8-31 10:38:10

【perl】使用LWP获取带cookie验证的HTTPS网页

#!/usr/bin/perl  package Livelink;
  use LWP::UserAgent;
  use MIME::Base64 qw(encode_base64);
  use HTTP::Cookies;
  my $Basic_Url = "https://wcdma-ll.app.alcatel-lucent.com/livelink/livelink.exe";
  sub new
  {
  my $invocant = shift;
  my $class = ref $invocant || $invocant;
  my $self = {
  login => shift,
  password => shift
  };
  bless $self, $class;
  $self->init();
  return $self;
  }
  sub init
  {
  my $self = shift;
  $self->{browser} = LWP::UserAgent->new(ssl_opts => {verify_hostname => 0});
  #设置http代理
  $self->{browser}->proxy('http', 'http://135.251.33.31:80');
  #将用户名密码进行base64编码
  die "Error: Login NONE.\n" if (! $self->{login});
  die "Error: Password NONE.\n" if (! $self->{password});
  $self->{encode_login} = encode_base64($self->{login} . ":" . $self->{password});
  #模拟浏览器的header,我访问的网页比较特殊,请求头中带有Authorization字段来进行鉴权。
  #也可以通过credentials方法来登录
  my @headers = ('User-Agent' => 'Mozilla/5.0',
  Authorization => "Basic $self->{encode_login}",
  );
  #这里是LWP::UserAgent对象调用default_header函数,它具有全局性
  #即后面对网页请求时,都会带有@headers的信息
  #在后面的HTTP::Reques对象也有个header函数,使用方法跟default_header一样
  #但是它的header信息只在当前的请求中生效。
  $self->{browser}->default_header(@headers);
  $self->{cookie_jar} = HTTP::Cookies->new;
  #设置cookie,正如前面所描述的,LWP::UserAgent对象调用的方法,在后面每次网页请求中都生效
  $self->{browser}->cookie_jar( $self->{cookie_jar} );
  #根据上面讲到的那段JAVASCRIPT,来构造post消息中的content字段。
  my $content = {
  #             NextURL=>'/livelink/livelink.exe?Redirect=1',
  func=>'ll.login',
  };
  #这里用$self->{browser}->post比较简单
  #如果用$req = HTTP::Request->new(POST => $Basic_Url)来POST的话
  #在构造$req->content之前,还需指明$req->content_type
  #my $resp = $self->{browser}->post( $Basic_Url, Content => $content );
  my $req = HTTP::Request->new(POST => $Basic_Url);
  $req->content_type('application/x-www-form-urlencoded');
  $req->content('func=ll.login');
  my $resp = $self->{browser}->request($req);
  if ($resp->is_success)
  {
  print "Login Success.\n";
  }
  else
  {
  print "Login Error.\n" . $resp->status_line . "\n";
  exit 1;
  }
  }
  sub get_web_content{
  my $self = shift;
  my ($url) = @_;
  print "\tNow, processing $url\n";
  my $get_cookie = 1;
  while ($get_cookie)
  {
  #调用HTTP::Request对象,对网页进行GET请求
  #效果和$self->{browser}->get($url)一样,这里是为了后面打印$request->headers_as_string
  my $request = HTTP::Request->new('GET', $url);
  #default_header设置好后,这里就不需要重复调用了
  #$request->header(Authorization => "Basic $self->{encode_login}");
  my $response = $self->{browser}->request($request);
  $self->{cookie_jar}->extract_cookies($response);
  print "=== Cookies:\n", $self->{cookie_jar}->as_string, "\n";
  if ($response->is_success)
  {
  #打印响应码,请求头,响应头和响应内容
  print "Login Success.\n** " . $response->status_line . " **\n";
  print "=== Request header: \n", $request->headers_as_string, "\n";
  print "=== Response header: \n", $response->headers_as_string, "\n";
  return $response->content;
  #访问成功后,即200 OK,就能获取到cookie值 $get_cookie = 0;
  }
  else
  {
  print "Login Error.\n** " . $response->status_line . " **\n";
  print $response->content . "\n";
  #如果发生网页重定向,将重组URL后继续访问
  if ($response->status_line =~ /302/)
  {
  my ($redirect_url) = ($response->content =~ m/new_abs来将$response->base链接起来
  $url = URI->new_abs($redirect_url, $response->base);
  next;
  }
  }
  exit 1;
  }
  }
  }
  sub get_file
  {
  my $self = shift;
  my $object_id = shift;
  unless($object_id)
  {

  die "$object_id is invalid>  }
  my $ll_url = "$Basic_Url/open/$object_id";
  return $self->get_web_content($ll_url);
  }
  package main;
  my $ll = new Livelink('username', 'password');
  my $content = $ll->get_file('50967038');
  open my $fh, '>', "myfile.html" or die "Can't open file, $!\n";
  print $fh $content;
  close $fh;

页: [1]
查看完整版本: 【perl】使用LWP获取带cookie验证的HTTPS网页