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 +1,104 @@
+package linkedin
+
+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 TestLinkedInCrawler_DiscoverAndFetch(t *testing.T) {
+	mockClient := &http.Client{
+		Transport: roundTripFunc(func(r *http.Request) *http.Response {
+			if strings.Contains(r.URL.Path, "seeMoreJobPostings") {
+				body := `<html>
+					<li data-row="1">
+						<div class="base-card" data-entity-urn="urn:li:jobPosting:3920192831">
+							<a class="base-card__full-link" href="https://www.linkedin.com/jobs/view/software-engineer-infra-at-linkedin-3920192831"></a>
+						</div>
+					</li>
+				</html>`
+				return &http.Response{
+					StatusCode: http.StatusOK,
+					Body:       io.NopCloser(bytes.NewBufferString(body)),
+					Header:     make(http.Header),
+				}
+			}
+
+			if strings.Contains(r.URL.Path, "3920192831") {
+				body := `<html>
+					<h2 class="top-card-layout__title">Staff Software Engineer - Distributed Graph</h2>
+					<a class="topcard__org-name-link">LinkedIn</a>
+					<span class="topcard__flavor--bullet">Bellevue, WA</span>
+					<div class="show-more-less-html__markup">
+						<p>LinkedIn graph systems scale to billions of edge connections.</p>
+					</div>
+				</html>`
+				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 := NewLinkedInCrawlerWithClient(mockClient)
+	if !c.CanHandle("linkedin") {
+		t.Errorf("CanHandle should support linkedin")
+	}
+
+	discovered, err := c.DiscoverJobs(context.Background(), "https://www.linkedin.com/jobs-guest/jobs/api/seeMoreJobPostings/search?keywords=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 != "linkedin:3920192831" {
+		t.Errorf("unexpected canonical ID: %s", discovered[0].CanonicalID)
+	}
+
+	extracted, err := c.FetchJobDetail(context.Background(), "https://www.linkedin.com/jobs/view/3920192831")
+	if err != nil {
+		t.Fatalf("FetchJobDetail failed: %v", err)
+	}
+
+	if extracted.Title != "Staff Software Engineer - Distributed Graph" {
+		t.Errorf("unexpected title: %s", extracted.Title)
+	}
+	if extracted.Company != "LinkedIn" {
+		t.Errorf("unexpected company: %s", extracted.Company)
+	}
+	if extracted.Location != "Bellevue, WA" {
+		t.Errorf("unexpected location: %s", extracted.Location)
+	}
+}
+
+func TestLinkedInCrawler_LiveIntegration(t *testing.T) {
+	crawlertest.RunLiveIntegration(t, crawlertest.LiveTestConfig{
+		PlatformName:            "LinkedIn",
+		Crawler:                 NewLinkedInCrawler(),
+		TargetURL:               "https://www.linkedin.com/jobs-guest/jobs/api/seeMoreJobPostings/search?keywords=Software+Engineer&location=Seattle%2C+Washington%2C+United+States",
+		ExpectedCanonicalPrefix: "linkedin:",
+		ExpectedCompany:         "",
+	})
+}