Run Code
|
API
|
Code Wall
|
Misc
|
Feedback
|
Login
|
Theme
|
Privacy
|
Patreon
WebScrape using Regex
//Rextester.Program.Main is the entry point for your code. Don't change it. //Compiler version 4.0.30319.17929 for Microsoft (R) .NET Framework 4.5 using System; using System.Collections.Generic; using System.Linq; using System.Text.RegularExpressions; using System.Net; namespace Rextester { public class Program { public static void Main(string[] args) { // 1. // URL: http://en.wikipedia.org/wiki/Main_Page WebClient w = new WebClient(); string s = w.DownloadString("http://en.wikipedia.org/wiki/Main_Page"); // 2. foreach (LinkItem i in LinkFinder.Find(s)) { Console.WriteLine(i); } } } public struct LinkItem { public string Href; public string Text; public override string ToString() { return Href + "\n\t" + Text; } } static class LinkFinder { public static List<LinkItem> Find(string file) { List<LinkItem> list = new List<LinkItem>(); // 1. // Find all matches in file. MatchCollection m1 = Regex.Matches(file, @"(<a.*?>.*?</a>)", RegexOptions.Singleline); // 2. // Loop over each match. foreach (Match m in m1) { string value = m.Groups[1].Value; LinkItem i = new LinkItem(); // 3. // Get href attribute. Match m2 = Regex.Match(value, @"href=\""(.*?)\""", RegexOptions.Singleline); if (m2.Success) { i.Href = m2.Groups[1].Value; } // 4. // Remove inner tags from text. string t = Regex.Replace(value, @"\s*<.*?>\s*", "", RegexOptions.Singleline); i.Text = t; list.Add(i); } return list; } } }
run
|
edit
|
history
|
help
0
hola1
How to use Lambda expression wiht generic delegate
cpp contact book
Uri builder
QLSV
convert String To Guid
UPDJLJ87258 Orderby grouping understanding
15
Reverse Array (!Array.Reverse())
Reverse linked list iterative method