feat(providers): add headless browser scraping via Playwright for SPA job sites
Build and Push Docker Images Staging / build (push) Successful in 5m20s

ejobs.ro migrated to a Nuxt SPA - plain HTTP GET returns only the JS
bundle. This change equips cv-search-job with a headless Chromium
(Playwright 1.60) so it can fully render SPA pages before extracting
job links.

- Add UseHeadlessBrowser flag to JobProviderEntity, JobProviderConfig,
  and CvSearchDbContext; map it in JobTokenService.ToConfig so the flag
  is included in the session provider-config snapshot
- Migration: add UseHeadlessBrowser column; fix ejobs.ro search URL
  (remove /user/ prefix that caused 404) and set UseHeadlessBrowser=true
- HtmlJobSearcher: detect flag and dispatch to FetchWithPlaywrightAsync;
  plain-HTTP path is unchanged; NetworkIdle timeout falls back to partial
  content rather than failing outright
- Dockerfile: download Playwright Chromium in the SDK build stage via
  npx; copy browser binaries to the final image; install Chromium system
  libs (Ubuntu noble t64 variants)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
2026-05-29 13:42:52 +03:00
parent 209325ace5
commit e38f40732f
11 changed files with 391 additions and 22 deletions
@@ -79,6 +79,7 @@ public sealed class CvSearchDbContext : DbContext
entity.Property(x => x.InitialKeywordsJson).HasMaxLength(2000).HasDefaultValue("[]").IsRequired();
entity.Property(x => x.MaxResults).HasDefaultValue(20);
entity.Property(x => x.DisplayOrder).HasDefaultValue(0);
entity.Property(x => x.UseHeadlessBrowser).HasDefaultValue(false);
});
}
}
@@ -30,4 +30,7 @@ public sealed class JobProviderEntity
/// <summary>Controls display ordering in future admin UIs.</summary>
public int DisplayOrder { get; set; }
/// <summary>When true, the scraper renders the page with headless Chromium instead of a plain HTTP GET.</summary>
public bool UseHeadlessBrowser { get; set; }
}
@@ -0,0 +1,234 @@
// <auto-generated />
using System;
using CvSearch.Data;
using Microsoft.EntityFrameworkCore;
using Microsoft.EntityFrameworkCore.Infrastructure;
using Microsoft.EntityFrameworkCore.Metadata;
using Microsoft.EntityFrameworkCore.Migrations;
using Microsoft.EntityFrameworkCore.Storage.ValueConversion;
#nullable disable
namespace CvSearch.Data.Migrations
{
[DbContext(typeof(CvSearchDbContext))]
[Migration("20260529170000_AddHeadlessBrowserToProviders")]
partial class AddHeadlessBrowserToProviders
{
/// <inheritdoc />
protected override void BuildTargetModel(ModelBuilder modelBuilder)
{
#pragma warning disable 612, 618
modelBuilder
.HasDefaultSchema("cvSearch")
.HasAnnotation("ProductVersion", "10.0.7")
.HasAnnotation("Relational:MaxIdentifierLength", 128);
SqlServerModelBuilderExtensions.UseIdentityColumns(modelBuilder);
modelBuilder.Entity("CvSearch.Data.Entities.JobProviderEntity", b =>
{
b.Property<int>("Id")
.ValueGeneratedOnAdd()
.HasColumnType("int");
SqlServerPropertyBuilderExtensions.UseIdentityColumn(b.Property<int>("Id"));
b.Property<int>("DisplayOrder")
.ValueGeneratedOnAdd()
.HasColumnType("int")
.HasDefaultValue(0);
b.Property<bool>("Enabled")
.HasColumnType("bit");
b.Property<string>("InitialKeywordsJson")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(2000)
.HasColumnType("nvarchar(2000)")
.HasDefaultValue("[]");
b.Property<string>("JobLinkContains")
.IsRequired()
.HasMaxLength(256)
.HasColumnType("nvarchar(256)");
b.Property<int>("MaxResults")
.ValueGeneratedOnAdd()
.HasColumnType("int")
.HasDefaultValue(20);
b.Property<string>("Name")
.IsRequired()
.HasMaxLength(128)
.HasColumnType("nvarchar(128)");
b.Property<string>("SearchUrlTemplate")
.IsRequired()
.HasMaxLength(1024)
.HasColumnType("nvarchar(1024)");
b.Property<bool>("UseHeadlessBrowser")
.ValueGeneratedOnAdd()
.HasColumnType("bit")
.HasDefaultValue(false);
b.HasKey("Id");
b.ToTable("JobProviders", "cvSearch");
});
modelBuilder.Entity("CvSearch.Data.Entities.JobSearchResultEntity", b =>
{
b.Property<string>("Id")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("JobText")
.IsRequired()
.HasColumnType("nvarchar(max)");
b.Property<string>("JobTitle")
.IsRequired()
.HasMaxLength(512)
.HasColumnType("nvarchar(512)");
b.Property<string>("JobUrl")
.IsRequired()
.HasMaxLength(2048)
.HasColumnType("nvarchar(2048)");
b.Property<string>("ProviderName")
.IsRequired()
.HasMaxLength(128)
.HasColumnType("nvarchar(128)");
b.Property<string>("ResultJson")
.IsRequired()
.HasColumnType("nvarchar(max)");
b.Property<int>("Score")
.HasColumnType("int");
b.Property<string>("SessionId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.HasKey("Id");
b.HasIndex("SessionId");
b.ToTable("JobSearchResults", "cvSearch");
});
modelBuilder.Entity("CvSearch.Data.Entities.JobSearchSessionEntity", b =>
{
b.Property<string>("Id")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("CvDocumentId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<string>("Email")
.IsRequired()
.HasMaxLength(256)
.HasColumnType("nvarchar(256)");
b.Property<string>("Keywords")
.IsRequired()
.HasMaxLength(1000)
.HasColumnType("nvarchar(1000)");
b.Property<string>("Language")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(8)
.HasColumnType("nvarchar(8)")
.HasDefaultValue("en");
b.Property<string>("ProviderConfigJson")
.HasColumnType("nvarchar(max)");
b.Property<string>("Status")
.IsRequired()
.HasMaxLength(32)
.HasColumnType("nvarchar(32)");
b.Property<string>("TokenId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.HasKey("Id");
b.HasIndex("Status");
b.ToTable("JobSearchSessions", "cvSearch");
});
modelBuilder.Entity("CvSearch.Data.Entities.JobSearchTokenEntity", b =>
{
b.Property<string>("Id")
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<DateTime>("CreatedAt")
.ValueGeneratedOnAdd()
.HasColumnType("datetime2")
.HasDefaultValueSql("SYSUTCDATETIME()");
b.Property<string>("CvDocumentId")
.IsRequired()
.HasMaxLength(64)
.HasColumnType("nvarchar(64)");
b.Property<string>("Email")
.IsRequired()
.HasMaxLength(256)
.HasColumnType("nvarchar(256)");
b.Property<DateTime>("ExpiresAt")
.HasColumnType("datetime2");
b.Property<string>("Keywords")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(1000)
.HasColumnType("nvarchar(1000)")
.HasDefaultValue("");
b.Property<string>("Language")
.IsRequired()
.ValueGeneratedOnAdd()
.HasMaxLength(8)
.HasColumnType("nvarchar(8)")
.HasDefaultValue("en");
b.Property<bool>("Used")
.ValueGeneratedOnAdd()
.HasColumnType("bit")
.HasDefaultValue(false);
b.HasKey("Id");
b.ToTable("JobSearchTokens", "cvSearch");
});
#pragma warning restore 612, 618
}
}
}
@@ -0,0 +1,50 @@
using Microsoft.EntityFrameworkCore.Migrations;
#nullable disable
namespace CvSearch.Data.Migrations
{
/// <inheritdoc />
public partial class AddHeadlessBrowserToProviders : Migration
{
/// <inheritdoc />
protected override void Up(MigrationBuilder migrationBuilder)
{
migrationBuilder.AddColumn<bool>(
name: "UseHeadlessBrowser",
schema: MigrationConstants.SchemaName,
table: "JobProviders",
type: "bit",
nullable: false,
defaultValue: false);
// ejobs.ro (Id=1) is a Nuxt SPA — the old /user/ URL 404s and plain HTTP GET
// returns only the JS bundle, not actual job listings.
// Fix: use the correct search URL and headless Chromium to render job results.
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "JobProviders",
keyColumn: "Id",
keyValue: 1,
columns: ["SearchUrlTemplate", "JobLinkContains", "UseHeadlessBrowser"],
values: new object[] { "https://www.ejobs.ro/locuri-de-munca?q={keywords}", "/locuri-de-munca/", true });
}
/// <inheritdoc />
protected override void Down(MigrationBuilder migrationBuilder)
{
migrationBuilder.UpdateData(
schema: MigrationConstants.SchemaName,
table: "JobProviders",
keyColumn: "Id",
keyValue: 1,
columns: ["SearchUrlTemplate", "JobLinkContains", "UseHeadlessBrowser"],
values: new object[] { "https://www.ejobs.ro/user/locuri-de-munca/?utm_source=myai&q={keywords}", "/user/locuri-de-munca/", false });
migrationBuilder.DropColumn(
name: "UseHeadlessBrowser",
schema: MigrationConstants.SchemaName,
table: "JobProviders");
}
}
}
@@ -66,6 +66,11 @@ namespace CvSearch.Data.Migrations
.HasMaxLength(1024)
.HasColumnType("nvarchar(1024)");
b.Property<bool>("UseHeadlessBrowser")
.ValueGeneratedOnAdd()
.HasColumnType("bit")
.HasDefaultValue(false);
b.HasKey("Id");
b.ToTable("JobProviders", "cvSearch");