Add medboom.ir as an ingestion source (doctor/dentist-heavy, VPN-free)

New MedboomListingSource: a WordPress medical-classifieds board crawled like medjobs
(wp-sitemap.xml -> posts-post-N.xml, newest first), filtered to clinical-role slugs and
Tehran-only for launch. medboom skews toward doctors/dentists/pharmacists and carries both
hiring and availability posts, so it directly broadens the role mix the nurse-heavy Divar
content lacks. Iranian-hosted -> no proxy/VPN needed (relevant now that Telegram is off).

Wired like the other sources: AppSetting toggles (MedboomEnabled/MaxAds/UseProxy) + EF
migration, SettingsService persistence, admin Settings UI, DI registration. Off by default.
Validated against live data: Tehran clinical ads at named clinics (pharmacy/dental/etc.).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

src/JobsMedical.Web/Services/Scraping/MedboomListingSource.cs

@@ -0,0 +1,155 @@
+using System.Text.RegularExpressions;
+using JobsMedical.Web.Models;
+
+namespace JobsMedical.Web.Services.Scraping;
+
+/// <summary>
+/// Scrapes clinical ads from medboom.ir («مرجع استخدام و نیازمندی علوم پزشکی») — a WordPress
+/// ad-listing site like medjobs.ir. It enumerates ad posts via the WP sitemap
+/// (wp-sitemap.xml → wp-sitemap-posts-post-N.xml), newest first, keeps clinical-role slugs, and
+/// extracts each ad's title + description (+ phone). medboom skews toward DOCTORS/DENTISTS and
+/// carries BOTH hiring («نیازمند…») and availability («آماده همکاری / جویای کار») posts, so it
+/// directly broadens the role mix the nurse-heavy classifieds sources miss. Tehran-only for launch.
+/// VPN-free (Iranian-hosted). Content-hash dedupe ingests each ad once; the validator/AI screen on top.
+/// </summary>
+public class MedboomListingSource : IListingSource
+{
+    private const string SitemapIndex = "https://medboom.ir/wp-sitemap.xml";
+    private readonly ScrapeHttpClients _clients;
+    private readonly ILogger<MedboomListingSource> _log;
+
+    public MedboomListingSource(ScrapeHttpClients clients, ILogger<MedboomListingSource> log)
+    {
+        _clients = clients;
+        _log = log;
+    }
+
+    public string Name => "مدبوم (medboom.ir)";
+
+    // Clinical-role markers matched against the decoded Persian ad slug.
+    private static readonly string[] RoleSlugs =
+    {
+        "پزشک", "دندان", "پرستار", "بهیار", "مامایی", "ماما", "تکنسین", "رادیولوژ", "سونوگراف",
+        "فیزیوتراپ", "کاردرمان", "گفتاردرمان", "شنوایی", "بینایی", "اپتومتر", "دیالیز", "اتاق-عمل",
+        "بیهوش", "هوشبری", "تزریقات", "فوریت", "اورژانس", "داروساز", "داروخانه", "نسخه", "سالمند",
+        "علوم-آزمایشگاهی", "آزمایشگاه", "مسئول-فنی", "مامو", "تغذیه", "روانشناس", "اپتیک",
+    };
+    // Veterinary + obvious non-staffing categories medboom also carries (equipment sale, real estate).
+    private static readonly string[] ExcludeSlugs =
+    {
+        "دامپزشک", "دام-پزشک", "دامپزشکی", "فروش", "اجاره", "املاک", "دستگاه", "تجهیزات", "ملک",
+    };
+
+    private const string Tehran = "تهران";
+    private static readonly string[] OtherCitySlugs =
+    {
+        "شیراز", "اصفهان", "مشهد", "تبریز", "کرج", "قم", "یزد", "رشت", "کرمان", "اراک", "اردبیل",
+        "همدان", "کرمانشاه", "زنجان", "قزوین", "ساری", "گرگان", "بندرعباس", "بوشهر", "سنندج",
+        "بیرجند", "سمنان", "شهرکرد", "ایلام", "یاسوج", "زاهدان", "ارومیه", "البرز", "اهواز", "کاشان",
+    };
+
+    public async Task<IReadOnlyList<ScrapedItem>> FetchAsync(AppSetting s, CancellationToken ct = default)
+    {
+        if (!s.MedboomEnabled) return Array.Empty<ScrapedItem>();
+        var max = Math.Clamp(s.MedboomMaxAds, 1, 500);
+        var client = _clients.For(s, s.MedboomUseProxy);
+
+        try
+        {
+            // 1. WP sitemap index → the ad-post sitemaps. Process newest first (highest-numbered).
+            var index = await client.GetStringAsync(SitemapIndex, ct);
+            var postMaps = Locs(index).Where(u => u.Contains("posts-post-"))
+                .OrderByDescending(u => u).ToList();
+            if (postMaps.Count == 0) { _log.LogWarning("medboom: no ad-post sitemaps found"); return Array.Empty<ScrapedItem>(); }
+
+            // 2. pool clinical candidate URLs (newest first within each map), pre-dropping other cities.
+            var pool = new List<string>();
+            var budget = max * 6;
+            foreach (var sm in postMaps)
+            {
+                if (pool.Count >= budget) break;
+                try
+                {
+                    var urls = Locs(await client.GetStringAsync(sm, ct)).Reverse();   // newest ads last → take from end
+                    foreach (var u in urls)
+                    {
+                        if (IsClinicalSlug(u) && !IsOtherCitySlug(u) && !pool.Contains(u)) pool.Add(u);
+                        if (pool.Count >= budget) break;
+                    }
+                }
+                catch (Exception ex) { _log.LogWarning(ex, "medboom: sitemap {Sm} failed", sm); }
+            }
+
+            // 3. fetch each ad → keep only Tehran ones, up to `max`.
+            var items = new List<ScrapedItem>();
+            foreach (var url in pool)
+            {
+                if (items.Count >= max) break;
+                ct.ThrowIfCancellationRequested();
+                try
+                {
+                    var html = await client.GetStringAsync(url, ct);
+                    var text = ExtractAd(html);
+                    if (text.Length < 25 || !text.Contains(Tehran)) continue;   // Tehran-only launch filter
+                    items.Add(new ScrapedItem("مدبوم", text, url));
+                }
+                catch (Exception ex) { _log.LogWarning(ex, "medboom: ad {Url} failed", url); }
+            }
+            _log.LogInformation("medboom: fetched {Count} Tehran clinical ads (from {Pool} pooled)", items.Count, pool.Count);
+            return items;
+        }
+        catch (Exception ex)
+        {
+            _log.LogWarning(ex, "medboom fetch failed");
+            return Array.Empty<ScrapedItem>();
+        }
+    }
+
+    private static bool IsClinicalSlug(string url)
+    {
+        var slug = Uri.UnescapeDataString(url);
+        if (ExcludeSlugs.Any(slug.Contains)) return false;
+        return RoleSlugs.Any(slug.Contains);
+    }
+
+    private static bool IsOtherCitySlug(string url)
+    {
+        var slug = Uri.UnescapeDataString(url);
+        return OtherCitySlugs.Any(slug.Contains);
+    }
+
+    private static IEnumerable<string> Locs(string xml)
+        => Regex.Matches(xml, "<loc>([^<]+)</loc>").Select(m => m.Groups[1].Value.Trim());
+
+    private static string ExtractAd(string html)
+    {
+        var title = Meta(html, "og:title");
+        if (title is not null) { var bar = title.IndexOf('|'); if (bar > 10) title = title[..bar].Trim(); }
+
+        var ogBody = Meta(html, "og:description");
+        var entry = BetweenClass(html, "entry-content");
+        var entryText = entry is null ? null : HtmlUtil.ToPlainText(entry);
+        var body = (entryText?.Length ?? 0) > (ogBody?.Length ?? 0) ? entryText : ogBody;
+
+        var text = HtmlUtil.ToPlainText(string.Join("\n", new[] { title, body }.Where(p => !string.IsNullOrWhiteSpace(p))));
+        if (text.Length > 1800) text = text[..1800];
+
+        var phones = HtmlUtil.HarvestPhones(body ?? "");
+        if (phones.Count > 0 && !phones.Any(text.Contains))
+            text += "\nشماره تماس: " + string.Join("، ", phones);
+        return text;
+    }
+
+    private static string? Meta(string html, string prop)
+    {
+        var m = Regex.Match(html, $"<meta[^>]+property=[\"']{Regex.Escape(prop)}[\"'][^>]+content=[\"']([^\"']*)[\"']");
+        return m.Success ? System.Net.WebUtility.HtmlDecode(m.Groups[1].Value) : null;
+    }
+
+    private static string? BetweenClass(string html, string cls)
+    {
+        var m = Regex.Match(html, $"<(?:div|article|section)[^>]+class=[\"'][^\"']*{Regex.Escape(cls)}[^\"']*[\"'][^>]*>(.*?)</(?:div|article|section)>",
+            RegexOptions.Singleline);
+        return m.Success ? m.Groups[1].Value : null;
+    }
+}

src/JobsMedical.Web/Services/Scraping/SettingsService.cs

@@ -58,6 +58,9 @@ public class SettingsService
         s.IranEstekhdamEnabled = incoming.IranEstekhdamEnabled;
         s.IranEstekhdamMaxAds = Math.Clamp(incoming.IranEstekhdamMaxAds, 1, 500);
         s.IranEstekhdamUseProxy = incoming.IranEstekhdamUseProxy;
+        s.MedboomEnabled = incoming.MedboomEnabled;
+        s.MedboomMaxAds = Math.Clamp(incoming.MedboomMaxAds, 1, 500);
+        s.MedboomUseProxy = incoming.MedboomUseProxy;
         s.SmsEnabled = incoming.SmsEnabled;
         s.SmsApiKey = incoming.SmsApiKey?.Trim();
         s.SmsTemplate = incoming.SmsTemplate?.Trim();