feat: implement multiple new job crawlers and add corresponding test suites

2026-08-25 00:12:52 -07:00
parent 0de312edbd
commit 55d4f4a0d9
26 changed files with 4045 additions and 15 deletions
@@ -0,0 +1,110 @@
+package netflix
+
+import (
+	"bytes"
+	"context"
+	"io"
+	"net/http"
+	"strings"
+	"testing"
+
+	"github.com/hireme/hireme/internal/crawler/crawlertest"
+)
+
+type roundTripFunc func(req *http.Request) *http.Response
+
+func (f roundTripFunc) RoundTrip(req *http.Request) (*http.Response, error) {
+	return f(req), nil
+}
+
+func TestNetflixCrawler_DiscoverAndFetch(t *testing.T) {
+	mockClient := &http.Client{
+		Transport: roundTripFunc(func(r *http.Request) *http.Response {
+			if strings.Contains(r.URL.Path, "/api/search") {
+				body := `{
+					"records": {
+						"total": 1,
+						"postings": [
+							{
+								"id": 8192301,
+								"external_id": "8192301",
+								"text": "Senior Software Engineer - Cloud Platform",
+								"location": "Seattle, WA, United States"
+							}
+						]
+					}
+				}`
+				return &http.Response{
+					StatusCode: http.StatusOK,
+					Body:       io.NopCloser(bytes.NewBufferString(body)),
+					Header:     make(http.Header),
+				}
+			}
+
+			if strings.Contains(r.URL.Path, "/postings/8192301") {
+				body := `{
+					"id": 8192301,
+					"external_id": "8192301",
+					"text": "Senior Software Engineer - Cloud Platform",
+					"description": "<p>We are looking for senior engineers to evolve Netflix telemetry and control planes.</p>",
+					"location": "Seattle, WA, United States"
+				}`
+				return &http.Response{
+					StatusCode: http.StatusOK,
+					Body:       io.NopCloser(bytes.NewBufferString(body)),
+					Header:     make(http.Header),
+				}
+			}
+
+			return &http.Response{
+				StatusCode: http.StatusNotFound,
+				Body:       io.NopCloser(bytes.NewBufferString("not found")),
+				Header:     make(http.Header),
+			}
+		}),
+	}
+
+	c := NewNetflixCrawlerWithClient(mockClient)
+	if !c.CanHandle("netflix") {
+		t.Errorf("CanHandle should support netflix")
+	}
+
+	discovered, err := c.DiscoverJobs(context.Background(), "https://jobs.netflix.com/api/search?q=Software+Engineer")
+	if err != nil {
+		t.Fatalf("DiscoverJobs failed: %v", err)
+	}
+
+	if len(discovered) != 1 {
+		t.Fatalf("expected 1 discovered job, got %d", len(discovered))
+	}
+
+	if discovered[0].CanonicalID != "netflix:8192301" {
+		t.Errorf("unexpected canonical ID: %s", discovered[0].CanonicalID)
+	}
+
+	extracted, err := c.FetchJobDetail(context.Background(), "https://jobs.netflix.com/jobs/8192301")
+	if err != nil {
+		t.Fatalf("FetchJobDetail failed: %v", err)
+	}
+
+	if extracted.Title != "Senior Software Engineer - Cloud Platform" {
+		t.Errorf("unexpected title: %s", extracted.Title)
+	}
+	if extracted.Company != "Netflix" {
+		t.Errorf("unexpected company: %s", extracted.Company)
+	}
+	if extracted.Location != "Seattle, WA, United States" {
+		t.Errorf("unexpected location: %s", extracted.Location)
+	}
+}
+
+func TestNetflixCrawler_LiveIntegration(t *testing.T) {
+	crawlertest.RunLiveIntegration(t, crawlertest.LiveTestConfig{
+		PlatformName:            "Netflix",
+		Crawler:                 NewNetflixCrawler(),
+		TargetURL:               "https://jobs.netflix.com/api/search?q=Software+Engineer",
+		ExpectedCanonicalPrefix: "netflix:",
+		ExpectedCompany:         "Netflix",
+	})
+}
+