WebScraper_dotNET 1.0.0
The WebScraper_dotNET Class Library is a high level wrapper around the WebRequest.
The library is currently compiled at .Net 4.0 so it should work with any application running .Net 4.0 and above.
WebScraper_dotNET is a library for scraping web data. It converts HTML code into a structured array of data.
Install-Package WebScraper_dotNET -Version 1.0.0
dotnet add package WebScraper_dotNET --version 1.0.0
<PackageReference Include="WebScraper_dotNET" Version="1.0.0" />
paket add WebScraper_dotNET --version 1.0.0
class Program
{
private static string siteUrl = "https://www.nuget.org/";
static void Main(string[] args)
{
WebScraper scrape = new WebScraper();
string html = scrape.Get(siteUrl);
//Console.WriteLine(html);
List<LinkItem> hyperlink_items = scrape.GetAllHyperlinks(html);
List<LinkItem> script_items = scrape.GetAllScripts(html);
List<LinkItem> link_items = scrape.GetAllLinks(html);
List<LinkItem> img_items = scrape.GetAllImages(html);
Console.WriteLine("Script: " + script_items.Count);
Console.WriteLine("Link: " + link_items.Count);
Console.WriteLine("Img: " + img_items.Count);
}
}
class Program
{
private static string siteUrl = "https://www.nuget.org/";
static void Main(string[] args)
{
WebScraper scrape = new WebScraper();
string html = scrape.Get(siteUrl);
//Console.WriteLine(html);
List<LinkItem> hyperlink_items = scrape.GetAllHyperlinks(html);
List<LinkItem> script_items = scrape.GetAllScripts(html);
List<LinkItem> link_items = scrape.GetAllLinks(html);
List<LinkItem> img_items = scrape.GetAllImages(html);
Console.WriteLine("Script: " + script_items.Count);
Console.WriteLine("Link: " + link_items.Count);
Console.WriteLine("Img: " + img_items.Count);
}
}
Release Notes
Extensions on the Fetch .NetFramework.
Dependencies
This package has no dependencies.
Used By
NuGet packages
This package is not used by any NuGet packages.
GitHub repositories
This package is not used by any popular GitHub repositories.
Version History
Version | Downloads | Last updated |
---|---|---|
1.0.0 | 217 | 10/11/2020 |