Добавьте файлы проекта.

Parsing/CatalogPageParser.cs

@@ -0,0 +1,86 @@
+using System;
+using System.Collections.Generic;
+using CRAWLER.Models;
+using HtmlAgilityPack;
+
+namespace CRAWLER.Parsing;
+
+internal sealed class CatalogPageParser
+{
+    public IReadOnlyList<CatalogListItem> Parse(string html, string baseUrl)
+    {
+        var document = new HtmlDocument();
+        document.LoadHtml(html ?? string.Empty);
+
+        var items = new List<CatalogListItem>();
+        var nodes = document.DocumentNode.SelectNodes("//div[contains(concat(' ', normalize-space(@class), ' '), ' sivreestre ')]");
+        if (nodes == null)
+        {
+            return items;
+        }
+
+        foreach (var node in nodes)
+        {
+            var item = new CatalogListItem
+            {
+                RegistryNumber = ReadBlockValue(node, "№ в госреестре"),
+                Name = ReadBlockValue(node, "Наименование"),
+                TypeDesignation = ReadBlockValue(node, "Тип"),
+                Manufacturer = ReadBlockValue(node, "Производитель"),
+                VerificationInterval = ReadBlockValue(node, "МПИ"),
+                CertificateOrSerialNumber = ReadBlockValue(node, "Cвидетельство завод. номер")
+                    ?? ReadBlockValue(node, "Свидетельство завод. номер"),
+                DetailUrl = ReadDetailUrl(node, baseUrl),
+                DescriptionTypePdfUrl = ReadPdfUrl(node, "/prof/opisanie/", baseUrl),
+                MethodologyPdfUrl = ReadPdfUrl(node, "/prof/metodiki/", baseUrl)
+            };
+
+            if (!string.IsNullOrWhiteSpace(item.RegistryNumber) || !string.IsNullOrWhiteSpace(item.Name))
+            {
+                items.Add(item);
+            }
+        }
+
+        return items;
+    }
+
+    private static string ReadBlockValue(HtmlNode root, string header)
+    {
+        var block = FindBlockByHeader(root, header);
+        return HtmlParsingHelpers.ExtractNodeTextExcludingChildParagraph(block);
+    }
+
+    private static HtmlNode FindBlockByHeader(HtmlNode root, string header)
+    {
+        var blocks = root.SelectNodes("./div");
+        if (blocks == null)
+        {
+            return null;
+        }
+
+        foreach (var block in blocks)
+        {
+            var paragraph = block.SelectSingleNode("./p");
+            var label = HtmlParsingHelpers.NormalizeLabel(paragraph?.InnerText);
+            if (string.Equals(label, header, StringComparison.OrdinalIgnoreCase))
+            {
+                return block;
+            }
+        }
+
+        return null;
+    }
+
+    private static string ReadDetailUrl(HtmlNode root, string baseUrl)
+    {
+        var link = root.SelectSingleNode(".//div[contains(@class,'resulttable6')]/a[1]")
+                   ?? root.SelectSingleNode(".//div[contains(@class,'resulttable4')]/a[1]");
+        return HtmlParsingHelpers.MakeAbsoluteUrl(baseUrl, link?.GetAttributeValue("href", null));
+    }
+
+    private static string ReadPdfUrl(HtmlNode root, string marker, string baseUrl)
+    {
+        var link = root.SelectSingleNode($".//a[contains(@href,'{marker}')]");
+        return HtmlParsingHelpers.MakeAbsoluteUrl(baseUrl, link?.GetAttributeValue("href", null));
+    }
+}

Parsing/DetailPageParser.cs

@@ -0,0 +1,65 @@
+using System;
+using System.Collections.Generic;
+using CRAWLER.Models;
+using HtmlAgilityPack;
+
+namespace CRAWLER.Parsing;
+
+internal sealed class DetailPageParser
+{
+    public ParsedInstrumentDetails Parse(string html, string baseUrl)
+    {
+        var document = new HtmlDocument();
+        document.LoadHtml(html ?? string.Empty);
+
+        var rows = document.DocumentNode.SelectNodes("//table[contains(@class,'resulttable1')]//tr");
+        var values = new Dictionary<string, string>(StringComparer.OrdinalIgnoreCase);
+        if (rows != null)
+        {
+            foreach (var row in rows)
+            {
+                var cells = row.SelectNodes("./td");
+                if (cells == null || cells.Count < 2)
+                {
+                    continue;
+                }
+
+                var label = HtmlParsingHelpers.NormalizeLabel(cells[0].InnerText);
+                var value = HtmlParsingHelpers.NormalizeWhitespace(cells[1].InnerText);
+                if (!string.IsNullOrWhiteSpace(label))
+                {
+                    values[label] = value;
+                }
+            }
+        }
+
+        return new ParsedInstrumentDetails
+        {
+            RegistryNumber = Get(values, "Номер в госреестре"),
+            Name = Get(values, "Наименование"),
+            TypeDesignation = Get(values, "Обозначение типа"),
+            Manufacturer = Get(values, "Производитель"),
+            VerificationInterval = Get(values, "Межповерочный интервал (МПИ)"),
+            CertificateOrSerialNumber = Get(values, "Срок свидетельства или заводской номер"),
+            AllowsBatchVerification = Get(values, "Допускается поверка партии"),
+            HasPeriodicVerification = Get(values, "Наличие периодической поверки"),
+            TypeInfo = Get(values, "Сведения о типе"),
+            Purpose = Get(values, "Назначение"),
+            Description = Get(values, "Описание"),
+            Software = Get(values, "Программное обеспечение"),
+            MetrologicalCharacteristics = Get(values, "Метрологические и технические характеристики"),
+            Completeness = Get(values, "Комплектность"),
+            Verification = Get(values, "Поверка"),
+            RegulatoryDocuments = Get(values, "Нормативные и технические документы"),
+            Applicant = Get(values, "Заявитель"),
+            TestCenter = Get(values, "Испытательный центр"),
+            DescriptionTypePdfUrl = HtmlParsingHelpers.MakeAbsoluteUrl(baseUrl, document.DocumentNode.SelectSingleNode("//a[contains(@href,'/prof/opisanie/')]")?.GetAttributeValue("href", null)),
+            MethodologyPdfUrl = HtmlParsingHelpers.MakeAbsoluteUrl(baseUrl, document.DocumentNode.SelectSingleNode("//a[contains(@href,'/prof/metodiki/')]")?.GetAttributeValue("href", null))
+        };
+    }
+
+    private static string Get(IDictionary<string, string> values, string key)
+    {
+        return values.TryGetValue(key, out var value) ? value : null;
+    }
+}

Parsing/HtmlParsingHelpers.cs

@@ -0,0 +1,64 @@
+using System;
+using System.Text.RegularExpressions;
+using HtmlAgilityPack;
+
+namespace CRAWLER.Parsing;
+
+internal static class HtmlParsingHelpers
+{
+    public static string NormalizeWhitespace(string value)
+    {
+        if (string.IsNullOrWhiteSpace(value))
+        {
+            return null;
+        }
+
+        var decoded = HtmlEntity.DeEntitize(value);
+        decoded = decoded.Replace('\u00A0', ' ');
+        decoded = Regex.Replace(decoded, @"\s+", " ");
+        return decoded.Trim();
+    }
+
+    public static string NormalizeLabel(string value)
+    {
+        return NormalizeWhitespace(value)
+            ?.Replace(" :", ":")
+            .Trim(':', ' ');
+    }
+
+    public static string MakeAbsoluteUrl(string baseUrl, string urlOrPath)
+    {
+        if (string.IsNullOrWhiteSpace(urlOrPath))
+        {
+            return null;
+        }
+
+        if (Uri.TryCreate(urlOrPath, UriKind.Absolute, out var absoluteUri))
+        {
+            return absoluteUri.ToString();
+        }
+
+        var baseUri = new Uri(baseUrl.TrimEnd('/') + "/");
+        return new Uri(baseUri, urlOrPath.TrimStart('/')).ToString();
+    }
+
+    public static string ExtractNodeTextExcludingChildParagraph(HtmlNode node)
+    {
+        if (node == null)
+        {
+            return null;
+        }
+
+        var clone = node.CloneNode(true);
+        var paragraphs = clone.SelectNodes("./p");
+        if (paragraphs != null)
+        {
+            foreach (var paragraph in paragraphs)
+            {
+                paragraph.Remove();
+            }
+        }
+
+        return NormalizeWhitespace(clone.InnerText);
+    }
+}