Free Trial
Web API version
Licensing
Request A Quote
HAVE QUESTIONS OR NEED HELP? SUBMIT THE SUPPORT REQUEST FORM or write email to SUPPORT@BYTESCOUT.COM
Find US Address in PDF with Regex | C#
Program.cs:
C#
using Bytescout.PDFExtractor; using System; namespace FindUsAddressRegex { // 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("samplePDF_Address.pdf"); extractor.RegexSearch = true; // Enable the regular expressions int pageCount = extractor.GetPageCount(); // Search through pages for (int i = 0; i < pageCount; i++) { // Search Address string regexPattern = @"((\w+[ ,])+ ){2}([a-zA-Z]){2}[ , ] (\d+)"; // 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 Address: " + element.Text); } } while (extractor.FindNext()); } } } } catch (Exception ex) { Console.WriteLine("Error: " + ex.Message); } Console.WriteLine(); Console.WriteLine("Press enter key to continue..."); Console.ReadLine(); } } }