Добавьте файлы проекта.

2026-04-04 10:52:30 +03:00
parent 9b34a92f15
commit 5a55bc5f4c
30 changed files with 3446 additions and 0 deletions
--- a/Parsing/CatalogPageParser.cs
+++ b/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));
+    }
+}