Created
July 30, 2012 06:32
-
-
Save JerryBian/3205340 to your computer and use it in GitHub Desktop.
C# code,Regular Expression,obatin special url from html string
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
//gdfgfdg<a href="/excel/dsfsf-).xls">/excel/dsfsf-).xls</a>dsfdsfdsf.... | |
internal class Program | |
{ | |
public static string source = @"C:\Users\JBian\Documents\visual studio 2010\Projects\ConsoleApplication23\ConsoleApplication23\Files\source.txt"; | |
public static string result = @"C:\Users\JBian\Documents\visual studio 2010\Projects\ConsoleApplication23\ConsoleApplication23\Files\result.txt"; | |
private static void Main(string[] args) | |
{ | |
StreamReader sd = new StreamReader(source); | |
string pattern1 = "(<a href=\"\\/excel\\/[\\w|\\-|\\(|\\)]+\\.(xls|html)\">[\\w|\\-|\\(|\\)]+\\.(xls|html)</a>)"; | |
Regex reg1 = new Regex(pattern1, RegexOptions.IgnoreCase); | |
var qq = reg1.Matches(sd.ReadToEnd()); | |
string str = string.Empty; | |
for (int i = 0; i < qq.Count; i++) | |
{ | |
string cap = qq[i].Value; | |
string pattern2 = "[\\w|\\-|\\(|\\)]+\\.(xls|html)"; | |
Regex reg2 = new Regex(pattern2, RegexOptions.IgnoreCase); | |
if (reg2.Match(cap).Success) | |
{ | |
string result = reg2.Match(cap).Value; | |
Console.WriteLine(result); | |
str += result + Environment.NewLine; | |
} | |
} | |
OutputResult(str); | |
Console.ReadKey(); | |
} | |
private static void OutputResult(string str) | |
{ | |
using (StreamWriter sw = new StreamWriter(result)) | |
{ | |
sw.WriteLine(str + Environment.NewLine); | |
sw.Flush(); | |
} | |
} | |
} | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment