vmandic

public void ConfigureServices(IServiceCollection services)
{
	services.AddAngleSharp();
	
	// adding the AppPathsInfo singleton instance carrying the ContentRootPath
	// provided by the IHostingEnvironment injected instance
	services.AddSingleton(
		s => new AppPathsInfo(s.GetService<IHostingEnvironment>().ContentRootPath));
	
	services.AddSingleton<HzzoHtmlScraper>();

vmandic

using System;

namespace MedsProcessor.Common.Models
{
	public sealed class AppPathsInfo
	{
		public AppPathsInfo(string appRootPath)
		{
			if (appRootPath == null)
				throw new ArgumentNullException(nameof(appRootPath));

vmandic

public async Task<ActionResult> Index([FromServices] HzzoHtmlScraper scraper)
{
	var startTime = DateTime.Now;
	// TODO: implement scraper and parser logic
	var meds = await scraper.Run();

	var totalTime = startTime - DateTime.Now;

	return Ok(
		$"Done! Handler duration: {totalTime.Duration()}" +

vmandic

ISet<HzzoMedsDownloadDto> ParseHtmlDocuments(IDocument[] docs) =>
	docs.Aggregate(
		new HashSet<HzzoMedsDownloadDto>(),
		(docList, doc) => new HashSet<HzzoMedsDownloadDto>(docList.Concat(ParseHtmlDocument(doc)))
	);

static ISet<HzzoMedsDownloadDto> ParseMedsLiElements(IEnumerable<IElement> elems) =>
  elems.Aggregate(new HashSet<HzzoMedsDownloadDto>(), (medsList, li) =>
  {
    var href = li.QuerySelector("a").GetAttribute("href");

vmandic

using System;
using System.Linq;

namespace MedsProcessor.Common.Models
{
	public class HzzoMedsDownloadDto
	{
		private readonly string _rootLocation;

		public HzzoMedsDownloadDto(string href, string validFrom, string rootLocation)

vmandic

namespace MedsProcessor.Common
{
	public static class Constants
	{
		public const string CURRENT_LISTS_URL = "http://www.hzzo.hr/zdravstveni-sustav-rh/trazilica-za-lijekove-s-vazecih-lista/";
		public const string ARCHIVE_LISTS_URL = "http://www.hzzo.hr/zdravstveni-sustav-rh/trazilica-za-lijekove-s-vazecih-lista/arhiva-liste-lijekova/";
		public const string DOWNLOAD_DIR = "";
	}
}

vmandic

Task<IDocument[]> DownloadHtmlDocuments() =>
  Task.WhenAll(
    _browsingContext.OpenAsync(CURRENT_LISTS_URL),
    _browsingContext.OpenAsync(ARCHIVE_LISTS_URL)
  );

vmandic

public async Task<ISet<HzzoMedsDownloadDto>> Run()
{
  var htmlDocs = await DownloadHtmlDocuments();
  var parsedDocs = ParseHtmlDocuments(htmlDocs);

  return parsedDocs;
}

vmandic

using System;
using System.Collections.Generic;
using System.Linq;
using System.Threading.Tasks;
using MedsProcessor.Scraper;
using Microsoft.AspNetCore.Builder;
using Microsoft.AspNetCore.Hosting;
using Microsoft.AspNetCore.HttpsPolicy;
using Microsoft.AspNetCore.Mvc;
using Microsoft.Extensions.Configuration;

vmandic

using AngleSharp;
using Microsoft.Extensions.DependencyInjection;

namespace MedsProcessor.Scraper
{
	public static class ServiceCollectionExtensions
	{
		public static IServiceCollection AddAngleSharp(this IServiceCollection services) =>
			services.AddSingleton(BrowsingContext.New(
				AngleSharp.Configuration.Default.WithDefaultLoader()));