ByteScout PDF Extractor SDK – C# – Find Website Addresses in PDF with Regex

Home
/
Articles
/
ByteScout PDF Extractor SDK – C# – Find Website Addresses in PDF with Regex

printable version:
ByteScout-PDF-Extractor-SDK-C-sharp-Find-Website-Addresses-in-PDF-with-Regex.pdf

How to find website addresses in PDF with regex in C# with ByteScout PDF Extractor SDK

What is ByteScout PDF Extractor SDK? It is the SDK is designed to help developers with pdf tables and pdf data extraction from unstructured documents like pdf, tiff, scans, images, scanned and electronic forms. The library is powered by OCR, computer vision and AI to provide unique functionality like table detection, automatic table structure extraction, data restoration, data restructuring and reconstruction. Supports PDF, TIFF, PNG, JPG images as input and can output CSV, XML, JSON formatted data. Includes full set of utilities like pdf splitter, pdf merger, searchable pdf maker and other utilities.

On-demand (REST Web API) version:
Web API (on-demand version)

On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)

FindWebsiteAddressWithRegex.csproj

      <?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="15.0" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
  <Import Project="$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props" Condition="Exists('$(MSBuildExtensionsPath)\$(MSBuildToolsVersion)\Microsoft.Common.props')" />
  <PropertyGroup>
    <Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
    <Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
    <ProjectGuid>{99735776-2956-463D-9795-EBCE16928C30}</ProjectGuid>
    <OutputType>Exe</OutputType>
    <RootNamespace>FindWebsiteAddressWithRegex</RootNamespace>
    <AssemblyName>FindWebsiteAddressWithRegex</AssemblyName>
    <TargetFrameworkVersion>v2.0</TargetFrameworkVersion>
    <FileAlignment>512</FileAlignment>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Debug|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugSymbols>true</DebugSymbols>
    <DebugType>full</DebugType>
    <Optimize>false</Optimize>
    <OutputPath>bin\Debug\</OutputPath>
    <DefineConstants>DEBUG;TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <PropertyGroup Condition=" '$(Configuration)|$(Platform)' == 'Release|AnyCPU' ">
    <PlatformTarget>AnyCPU</PlatformTarget>
    <DebugType>pdbonly</DebugType>
    <Optimize>true</Optimize>
    <OutputPath>bin\Release\</OutputPath>
    <DefineConstants>TRACE</DefineConstants>
    <ErrorReport>prompt</ErrorReport>
    <WarningLevel>4</WarningLevel>
  </PropertyGroup>
  <ItemGroup>
    <Reference Include="Bytescout.PDFExtractor, Version=9.1.0.3170, Culture=neutral, PublicKeyToken=f7dd1bd9d40a50eb, processorArchitecture=MSIL">
      <SpecificVersion>False</SpecificVersion>
      <HintPath>c:\Program Files\Bytescout PDF Extractor SDK\net2.00\Bytescout.PDFExtractor.dll</HintPath>
    </Reference>
    <Reference Include="System" />
    <Reference Include="System.Data" />
    <Reference Include="System.Xml" />
  </ItemGroup>
  <ItemGroup>
    <Compile Include="Program.cs" />
  </ItemGroup>
  <ItemGroup>
    <None Include="SampleInvoice.pdf">
      <CopyToOutputDirectory>Always</CopyToOutputDirectory>
    </None>
  </ItemGroup>
  <Import Project="$(MSBuildToolsPath)\Microsoft.CSharp.targets" />
</Project>

ON-PREMISE OFFLINE SDK

60 Day Free Trial or Visit ByteScout PDF Extractor SDK Home Page

Explore ByteScout PDF Extractor SDK Documentation

Explore Samples

Sign Up for ByteScout PDF Extractor SDK Online Training

ON-DEMAND REST WEB API

Get Your API Key

Explore Web API Docs

Explore Web API Samples

Program.cs

      using Bytescout.PDFExtractor;
using System;

namespace FindWebsiteAddressWithRegexp
{

    // Note: if you are looking for a more higher level API to extract data from invoices, reports, statements
    // then please check Document Parser SDK and Web API at https://bytescout.com/products/developer/documentparsersdk/index.html
    // and https://pdf.co for secure and scalable web api

    class Program
    {
        static void Main(string[] args)
        {
            try
            {
                // Create Bytescout.PDFExtractor.TextExtractor instance
                using (TextExtractor extractor = new TextExtractor())
                {
                    extractor.RegistrationName = "demo";
                    extractor.RegistrationKey = "demo";

                    // Load sample PDF document
                    extractor.LoadDocumentFromFile("SampleInvoice.pdf");

                    extractor.RegexSearch = true; // Enable the regular expressions

                    int pageCount = extractor.GetPageCount();

                    // Search through pages
                    for (int i = 0; i < pageCount; i++)
                    {
                        // Search website address in document
                        string regexPattern = @"http(s)?://([\w-]+.)+[\w-]+(/[\w- ./?%&=])?";
                        // See the complete regular expressions reference at https://msdn.microsoft.com/en-us/library/az24scfc(v=vs.110).aspx

                        // Search each page for the pattern
                        if (extractor.Find(i, regexPattern, false))
                        {
                            do
                            {
                                // Iterate through each element in the found text
                                foreach (ISearchResultElement element in extractor.FoundText.Elements)
                                {
                                    Console.WriteLine("Found URL: " + element.Text);
                                }
                            }
                            while (extractor.FindNext());
                        }
                    }
                }
            }
            catch (Exception ex)
            {
                Console.WriteLine("Error: " + ex.Message);
            }

            Console.WriteLine();
            Console.WriteLine("Press enter key to continue...");
            Console.ReadLine();
        }
    }
}