注意:
文章后的下载代码,还有小bug,遇到1-9号的时间可能会查不到数据。因为日期的天必须为 “00” 格式,请大家自行下载代码后修改。
2013.12.03修改:
发送正文已变为:
string parameter = @"condition=&queryMode=1&nyear2={0}&nyear2_new_value=true&nmonth2={1}&nmonth2_new_value=true&nday2={2}&nday2_new_value=false&startStation_ticketPrice1=
{3}&startStation_ticketPrice1_new_value=false&arriveStation_ticketPrice1={4}&arriveStation_ticketPrice1_new_value=false&trainCode=&trainCode_new_value=true&
rFlag=1&name_ckball=value_ckball&tFlagDC=DC&tFlagZ=Z&tFlagT=T&tFlagK=K&tFlagPK=PK&tFlagPKE=PKE&tFlagLK=LK&randCode={5}";
parameter = string.Format(parameter, fromDate.Year, fromDate.Month, fromDate.Day.ToString("00"), startStation, arriveStation, randCode);
最近打算做一个抓取12306车票信息的功能,自动登录实现起来有些问题,老是登录不成功。于是就做了不需要登录的一些查询的功能。先看看票价查询的读取。
也就是这个页面的查询这个页面是POST方式提交数据,有一个验证码图片的读取。
一般来说IE浏览器打开后(IE9),F12(开发人员工具)-网络,可以进行捕获提交的url,数据等。
可以查看每一步请求了哪些页面和传输了哪些数据,相当于火狐的firebug。这个可以用IE9研究一下,我试了下IE7、IE8都没有这个功能,IE9可以的。
如图,
具体过程就是点击开始捕获,然后完成当前页面的查询操作,再点击结束捕获,就会抓取所有访问的url和传输的参数。
大家可以自己尝试,直接上代码。
因此获取验证码图片方法可以这样写: private static string setCookie = string.Empty;
/// <summary>
/// 票价查询验证码
/// </summary>
/// <returns></returns>
public static string DoGetTrainTicketPriceRandCodeImage()
{
string resultImage = string.Empty;
try
{
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(@"http://dynamic.12306.cn/TrainQuery/passCodeActi0n.do?rand=rrand");
request.Accept = @"image/png, image/svg+xml, image/*;q=0.8, */*;q=0.5";
request.UserAgent = @"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)";
request.Referer = @"http://dynamic.12306.cn/TrainQuery/ticketPriceByStation.jsp";
request.Method = "GET";
using (HttpWebResponse response = (HttpWebResponse)request.GetResponse())
{
setCookie = response.GetResponseHeader("Set-cookie");
setCookie = Regex.Replace(setCookie, "path(?:[^,]+),?", "", RegexOptions.IgnoreCase);
using (Stream reader = response.GetResponseStream())
{
string path = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, new Random().Next(10000, 99999) + @"queryTicketPrice.JPEG");
using (FileStream file = new FileStream(path, FileMode.OpenOrCreate, FileAccess.Write))
{
reader.CopyTo(file);
}
resultImage = path;
}
}
}
catch { }
return resultImage;
}
之所以写的这么麻烦,我原本打算用WebClient直接将http://dynamic.12306.cn/TrainQuery/passCodeActi0n.do?rand=rrand这个路径的文件下载下来,但是,测试时发现直接下载下来的输入验证码后返回验证码过期。于是用这种方式下载文件然后保存。并将图片文件显示在界面上。
setCookie字段存放的是当前页面的请求时的cookie。这个也是为了后面调用查询票价url时用的,用同一个cookie才能保证查询结果正确。
那么下面看传参数读取票价信息的方法:
/// <summary>
/// 火车票票价信息字符串
/// </summary>
public static string DoQueryTrainTicketPriceInfo(DateTime fromDate, string startStation,string arriveStation,string randCode)
{
string result = string.Empty;
try
{
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(@"http://dynamic.12306.cn/TrainQuery/iframeTicketPriceByStation.jsp");
request.Accept = @"text/html, application/xhtml+xml, */*";
request.UserAgent = @"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)";
request.Referer = @"http://dynamic.12306.cn/TrainQuery/ticketPriceByStation.jsp";
request.ContentType = @"application/x-www-form-urlencoded";
request.Headers[HttpRequestHeader.Cookie] = setCookie;
request.Method = "POST";
byte[] buffer = new byte[0];
DoGetTrainTicketPriceRandCodeImage();
string parameter = @"condition=&queryMode=1&nmonth2={0}&nmonth2_new_value=true&nday2={1}&nday2_new_value=false&startStation_ticketPrice1={2}
&startStation_ticketPrice1_new_value=false&arriveStation_ticketPrice1={3}&arriveStation_ticketPrice1_new_value=false&trainCode=&trainCode_new_value=true&
rFlag=1&name_ckball=value_ckball&tFlagDC=DC&tFlagZ=Z&tFlagT=T&tFlagK=K&tFlagPK=PK&tFlagPKE=PKE&tFlagLK=LK&randCode={4}";
parameter = string.Format(parameter, fromDate.Month, fromDate.Day.ToString("00"), startStation, arriveStation, randCode);
buffer = Encoding.UTF8.GetBytes(parameter);
request.ContentLength = buffer.Length;
using (Stream writer = request.GetRequestStream())
{
writer.Write(buffer, 0, buffer.Length);
writer.Flush();
}
using (HttpWebResponse response = (HttpWebResponse)request.GetResponse())
{
using (StreamReader reader = new StreamReader(response.GetResponseStream(), Encoding.UTF8))
{
result = reader.ReadToEnd();
}
}
}
catch { }
return result;
}
这里比较关键的就是传输正文,也就是parameter字符串的内容,关键参数也就是代码中的那几个,时间,出发站,到达站和验证码。这里的request.Headers[HttpRequestHeader.Cookie]就要用到读取验证码文件那里的同一个cookie。
至于其他参数也是通过捕获查询过程获取的。
所有代码如下,这里是用Visual studio 2010,wpf实现的界面显示。
主要代码:
public class TrainTicketPriceQuery
{
private static string setCookie = string.Empty;
/// <summary>
/// 火车票票价信息字符串
/// </summary>
public static string DoQueryTrainTicketPriceInfo(DateTime fromDate, string startStation, string arriveStation, string randCode)
{
string result = string.Empty;
try
{
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(@"http://dynamic.12306.cn/TrainQuery/iframeTicketPriceByStation.jsp");
request.Accept = @"text/html, application/xhtml+xml, */*";
request.UserAgent = @"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)";
request.Referer = @"http://dynamic.12306.cn/TrainQuery/ticketPriceByStation.jsp";
request.ContentType = @"application/x-www-form-urlencoded";
request.Headers[HttpRequestHeader.Cookie] = setCookie;
request.Method = "POST";
byte[] buffer = new byte[0];
DoGetTrainTicketPriceRandCodeImage();
string parameter = @"condition=&queryMode=1&nmonth2={0}&nmonth2_new_value=true&nday2={1}&nday2_new_value=false&startStation_ticketPrice1={2}
&startStation_ticketPrice1_new_value=false&arriveStation_ticketPrice1={3}&arriveStation_ticketPrice1_new_value=false&trainCode=&trainCode_new_value=true&
rFlag=1&name_ckball=value_ckball&tFlagDC=DC&tFlagZ=Z&tFlagT=T&tFlagK=K&tFlagPK=PK&tFlagPKE=PKE&tFlagLK=LK&randCode={4}";
parameter = string.Format(parameter, fromDate.Month, fromDate.Day.ToString("00"), startStation, arriveStation, randCode);
buffer = Encoding.UTF8.GetBytes(parameter);
request.ContentLength = buffer.Length;
using (Stream writer = request.GetRequestStream())
{
writer.Write(buffer, 0, buffer.Length);
writer.Flush();
}
using (HttpWebResponse response = (HttpWebResponse)request.GetResponse())
{
using (StreamReader reader = new StreamReader(response.GetResponseStream(), Encoding.UTF8))
{
result = reader.ReadToEnd();
}
}
}
catch { }
return result;
}
/// <summary>
/// 票价查询验证码
/// </summary>
/// <returns></returns>
public static string DoGetTrainTicketPriceRandCodeImage()
{
string resultImage = string.Empty;
try
{
HttpWebRequest request = (HttpWebRequest)WebRequest.Create(@"http://dynamic.12306.cn/TrainQuery/passCodeActi0n.do?rand=rrand");
request.Accept = @"image/png, image/svg+xml, image/*;q=0.8, */*;q=0.5";
request.UserAgent = @"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; Trident/5.0)";
request.Referer = @"http://dynamic.12306.cn/TrainQuery/ticketPriceByStation.jsp";
request.Method = "GET";
using (HttpWebResponse response = (HttpWebResponse)request.GetResponse())
{
setCookie = response.GetResponseHeader("Set-cookie");
setCookie = Regex.Replace(setCookie, "path(?:[^,]+),?", "", RegexOptions.IgnoreCase);
using (Stream reader = response.GetResponseStream())
{
string path = Path.Combine(AppDomain.CurrentDomain.BaseDirectory, new Random().Next(10000, 99999) + @"queryTicketPrice.JPEG");
using (FileStream file = new FileStream(path, FileMode.OpenOrCreate, FileAccess.Write))
{
reader.CopyTo(file);
}
resultImage = path;
}
}
}
catch { }
return resultImage;
}
}
界面代码:
<Window x:Class="TestQueryTrainTicketPrice.MainWindow"
xmlns="http://schemas.microsoft.com/winfx/2006/xaml/presentation"
xmlns:x="http://schemas.microsoft.com/winfx/2006/xaml"
Title="MainWindow" Width="900" MinHeight="600">
<StackPanel>
<Grid>
<Grid.Resources>
<Style TargetType="TextBlock">
<Setter Property="FontFamily" Value="Microsoft YaHei"/>
<Setter Property="FontSize" Value="20"/>
<Setter Property="VerticalAlignment" Value="Center"/>
</Style>
<Style TargetType="TextBox">
<Setter Property="FontSize" Value="20"/>
<Setter Property="MinWidth" Value="300"/>
<Setter Property="Height" Value="50"/>
<Setter Property="VerticalAlignment" Value="Center"/>
</Style>
</Grid.Resources>
<Grid.RowDefinitions>
<RowDefinition Height="auto"/>
<RowDefinition Height="auto"/>
<RowDefinition Height="auto"/>
<RowDefinition Height="auto"/>
</Grid.RowDefinitions>
<Grid.ColumnDefinitions>
<ColumnDefinition Width="auto"/>
<ColumnDefinition Width="auto"/>
</Grid.ColumnDefinitions>
<TextBlock Grid.Row="0" Grid.Column="0" Text="日 期"/>
<TextBox Grid.Row="0" Grid.Column="1" x:Name="txtDate" />
<TextBlock Grid.Row="1" Grid.Column="0" Text="出发站"/>
<TextBox Grid.Row="1" Grid.Column="1" x:Name="txtStartStation" />
<TextBlock Grid.Row="2" Grid.Column="0" Text="到达站"/>
<TextBox Grid.Row="2" Grid.Column="1" x:Name="txtArriveStation" />
<TextBlock Grid.Row="3" Grid.Column="0" Text="验证码"/>
<StackPanel Grid.Row="3" Grid.Column="1" Orientation="Horizontal"
VerticalAlignment="Center">
<TextBox x:Name="txtRandCode" />
<Image x:Name="imageRandCode" Width="auto"/>
<Button Content="刷新验证码" Height="30" Width="100" Click="Button_Click_1" />
</StackPanel>
</Grid>
<Button Content="开始查询" Width="150" Height="50" Click="Button_Click" />
<RichTextBox x:Name="rtxResultInfo" VerticalScrollBarVisibility="Visible" Height="315"/>
</StackPanel>
</Window>
控制显示代码:
public partial class MainWindow : Window
{
public MainWindow()
{
InitializeComponent();
this.Loaded += new RoutedEventHandler(MainWindow_Loaded);
}
void MainWindow_Loaded(object sender, RoutedEventArgs e)
{
string date = DateTime.Now.AddDays(3).ToString(@"yyyy-MM-dd");
this.txtDate.Text = date;
this.txtStartStation.Text = @"广州";
this.txtArriveStation.Text = @"西安";
InitialRandCode();
}
private void InitialRandCode()
{
//初始化验证码
string randCodeImageUrl = TrainTicketPriceQuery.DoGetTrainTicketPriceRandCodeImage();
if (!string.IsNullOrEmpty(randCodeImageUrl))
{
ImageSource src = (ImageSource)(new ImageSourceConverter().ConvertFromString(randCodeImageUrl));
this.imageRandCode.Source = src;
}
}
/// <summary>
/// 开始查询
/// </summary>
/// <param name="sender"></param>
/// <param name="e"></param>
private void Button_Click(object sender, RoutedEventArgs e)
{
string startStation = this.txtStartStation.Text.Trim();
string arriveStation = this.txtArriveStation.Text.Trim();
string randCode = this.txtRandCode.Text.Trim();
string startDate = this.txtDate.Text;
if (string.IsNullOrEmpty(startStation) || string.IsNullOrEmpty(arriveStation) || string.IsNullOrEmpty(randCode) || string.IsNullOrEmpty(startDate))
{
MessageBox.Show("参数不完整,请重新填写!");
return;
}
DateTime fromDate = DateTime.Parse(startDate);
string queryResult = TrainTicketPriceQuery.DoQueryTrainTicketPriceInfo(DateTime.Now.AddDays(4), startStation, arriveStation, randCode);
System.Windows.Documents.FlowDocument doc = rtxResultInfo.Document;
doc.Blocks.Clear();
rtxResultInfo.AppendText(queryResult);
}
private void Button_Click_1(object sender, RoutedEventArgs e)
{
InitialRandCode();
}
}
效果,
其中比如:
parent.mygrid.addRow(0,"1,G832^skbcx.jsp?cxlx=cc&date=20131125&trainCode=G832_6c0000G83201,广州南^skbcx.jsp?cxlx=czjgcc&zm=&date=20131125&stationName_passTrain=%E5%B9%BF%E5%B7%9E%E5%8D%97^self,西安北^skbcx.jsp?cxlx=czjgcc&zm=&date=20131125&stationName_passTrain=%E8%A5%BF%E5%AE%89%E5%8C%97^self,--,--,1301.5,813.5,--,--,--,--,--,07:18,16:23,09:05,广州南^skbcx.jsp?cxlx=czjgcc&zm=&date=20131125&stationName_passTrain=%E5%B9%BF%E5%B7%9E%E5%8D%97^self,西安北^skbcx.jsp?cxlx=czjgcc&zm=&date=20131125&stationName_passTrain=%E8%A5%BF%E5%AE%89%E5%8C%97^self,高速,有",0);
这些才是票价信息,当然了还需要对字符串进行一些简单的处理。
用
Regex regex = new Regex(@"parent.mygrid.addRow");
string[] arrows = regex.Split(priceContent);
将整个字符串中的每一个车次的信息分离出来,然后再对每一条数据截取、替换等操作最终就能得到你想要的列车票价信息了。
代码下载(修改bug后)