Add iranestekhdam.ir as an ingestion source (clinical job ads at named facilities)
CI/CD / CI · dotnet build (push) Successful in 1m43s
CI/CD / Deploy · hamkadr (push) Successful in 1m55s

New IranEstekhdamListingSource: reads the site monthly ad sitemaps
(sitemap-ads.xml -> sitemap-ads-YYYY-M.xml), keeps only ad URLs whose Persian slug names a
clinical role (veterinary/non-clinical excluded), then extracts each ad title + description
(+ phone). These are employer ads at NAMED facilities, so they directly improve the
unknown-facility problem the classifieds content has.

Wired in like Medjobs: AppSetting toggles (IranEstekhdamEnabled/MaxAds/UseProxy) + EF
migration, SettingsService persistence, admin Settings UI, and DI registration. Off by
default; the medical-gate validator + AI auditor + junk filters screen results downstream.

Note: e-estekhdam / jobinja / jobvision are JS-rendered SPAs whose ad lists are not in static
HTML, so they need API reverse-engineering (a separate effort), not this static-scrape path.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
This commit is contained in:
soroush.asadi
2026-06-21 07:39:39 +03:30
parent da55f82c6c
commit f118db55ef
9 changed files with 1869 additions and 0 deletions
@@ -147,6 +147,16 @@
</div>
</div>
<div class="source-box">
<label class="toggle-row">
<input type="checkbox" name="IranEstekhdamEnabled" value="true" checked="@Model.IranEstekhdamEnabled" />
<span class="t-body"><span>🏥 ایران‌استخدام (iranestekhdam.ir)</span><span class="t-hint">آگهی‌های استخدامِ مراکز درمانیِ نام‌دار از سایت‌مپِ ماهانه؛ فقط نقش‌های بالینی.</span></span>
</label>
<div class="filter-group"><label>حداکثر آگهی در هر اجرا</label><input type="number" name="IranEstekhdamMaxAds" min="1" max="500" value="@Model.IranEstekhdamMaxAds" dir="ltr" />
<label class="proxy-toggle"><input type="checkbox" name="IranEstekhdamUseProxy" value="true" checked="@Model.IranEstekhdamUseProxy" /> از پروکسی استفاده شود</label>
</div>
</div>
<div class="source-box">
<label class="toggle-row">
<input type="checkbox" name="WebsitesEnabled" value="true" checked="@Model.WebsitesEnabled" />
@@ -47,6 +47,9 @@ public class SettingsModel : PageModel
[BindProperty] public string? DivarQueries { get; set; }
[BindProperty] public bool MedjobsEnabled { get; set; }
[BindProperty] public int MedjobsMaxAds { get; set; } = 40;
[BindProperty] public bool IranEstekhdamEnabled { get; set; }
[BindProperty] public int IranEstekhdamMaxAds { get; set; } = 40;
[BindProperty] public bool IranEstekhdamUseProxy { get; set; }
[BindProperty] public bool SmsEnabled { get; set; }
[BindProperty] public string? SmsApiKey { get; set; }
[BindProperty] public string? SmsTemplate { get; set; }
@@ -95,6 +98,9 @@ public class SettingsModel : PageModel
DivarQueries = s.DivarQueries;
MedjobsEnabled = s.MedjobsEnabled;
MedjobsMaxAds = s.MedjobsMaxAds;
IranEstekhdamEnabled = s.IranEstekhdamEnabled;
IranEstekhdamMaxAds = s.IranEstekhdamMaxAds;
IranEstekhdamUseProxy = s.IranEstekhdamUseProxy;
SmsEnabled = s.SmsEnabled;
SmsApiKey = s.SmsApiKey;
SmsTemplate = s.SmsTemplate;
@@ -140,6 +146,9 @@ public class SettingsModel : PageModel
DivarQueries = DivarQueries,
MedjobsEnabled = MedjobsEnabled,
MedjobsMaxAds = MedjobsMaxAds,
IranEstekhdamEnabled = IranEstekhdamEnabled,
IranEstekhdamMaxAds = IranEstekhdamMaxAds,
IranEstekhdamUseProxy = IranEstekhdamUseProxy,
SmsEnabled = SmsEnabled,
SmsApiKey = SmsApiKey,
SmsTemplate = SmsTemplate,