feat: linkedin

Dockerfile

@@ -1,4 +1,4 @@
-ARG egover=1.7.2
+ARG egover=1.8.0
 ARG baseimage=ghcr.io/edgelesssys/ego-deploy:v${egover}
 ARG VERSION
 

Makefile

@@ -79,6 +79,9 @@ test-jobs: docker-build-test
 test-twitter: docker-build-test
 	@docker run --user root $(ENV_FILE_ARG) -v $(PWD)/.masa:/home/masa -v $(PWD)/coverage:/app/coverage --rm --workdir /app -e DATA_DIR=/home/masa $(TEST_IMAGE) go test -v ./internal/jobs/twitter_test.go ./internal/jobs/jobs_suite_test.go
 
+test-linkedin: docker-build-test
+	@docker run --user root $(ENV_FILE_ARG) -v $(PWD)/.masa:/home/masa -v $(PWD)/coverage:/app/coverage --rm --workdir /app -e DATA_DIR=/home/masa $(TEST_IMAGE) go test -v ./internal/jobs/linkedin_test.go ./internal/jobs/jobs_suite_test.go
+
 test-tiktok: docker-build-test
 	@docker run --user root $(ENV_FILE_ARG) -v $(PWD)/.masa:/home/masa -v $(PWD)/coverage:/app/coverage --rm --workdir /app -e DATA_DIR=/home/masa $(TEST_IMAGE) go test -v ./internal/jobs/tiktok_test.go ./internal/jobs/jobs_suite_test.go
 

go.mod

@@ -1,47 +1,50 @@
 module github.com/masa-finance/tee-worker
 
-go 1.23.0
+go 1.24.0
 
-toolchain go1.24.3
+toolchain go1.24.6
 
 require (
-	github.com/edgelesssys/ego v1.7.2
+	github.com/edgelesssys/ego v1.8.0
 	github.com/google/uuid v1.6.0
 	github.com/imperatrona/twitter-scraper v0.0.18
 	github.com/joho/godotenv v1.5.1
 	github.com/labstack/echo-contrib v0.17.4
 	github.com/labstack/echo/v4 v4.13.4
-	github.com/masa-finance/tee-types v1.1.17
-	github.com/onsi/ginkgo/v2 v2.23.4
-	github.com/onsi/gomega v1.38.0
+	github.com/masa-finance/tee-types v1.2.0
+	github.com/onsi/ginkgo/v2 v2.26.0
+	github.com/onsi/gomega v1.38.2
 	github.com/sirupsen/logrus v1.9.3
 )
 
 replace github.com/imperatrona/twitter-scraper => github.com/masa-finance/twitter-scraper v1.0.2
 
 require (
 	github.com/AlexEidt/Vidio v1.5.1 // indirect
+	github.com/Masterminds/semver/v3 v3.4.0 // indirect
 	github.com/go-task/slim-sprig/v3 v3.0.0 // indirect
 	go.uber.org/automaxprocs v1.6.0 // indirect
+	go.yaml.in/yaml/v3 v3.0.4 // indirect
+	golang.org/x/mod v0.28.0 // indirect
+	golang.org/x/sync v0.17.0 // indirect
 )
 
 require (
-	github.com/go-jose/go-jose/v4 v4.1.2 // indirect
+	github.com/go-jose/go-jose/v4 v4.1.3 // indirect
 	github.com/go-logr/logr v1.4.3 // indirect
 	github.com/google/go-cmp v0.7.0 // indirect
-	github.com/google/pprof v0.0.0-20250630185457-6e76a2b096b5 // indirect
+	github.com/google/pprof v0.0.0-20251007162407-5df77e3f7d1d // indirect
 	github.com/labstack/gommon v0.4.2
 	github.com/mattn/go-colorable v0.1.14 // indirect
 	github.com/mattn/go-isatty v0.0.20 // indirect
 	github.com/valyala/bytebufferpool v1.0.0 // indirect
 	github.com/valyala/fasttemplate v1.2.2 // indirect
-	golang.org/x/crypto v0.41.0 // indirect
-	golang.org/x/exp v0.0.0-20250718183923-645b1fa84792
-	golang.org/x/net v0.43.0 // indirect
-	golang.org/x/sys v0.35.0 // indirect
-	golang.org/x/text v0.28.0 // indirect
-	golang.org/x/time v0.12.0 // indirect
-	golang.org/x/tools v0.35.0 // indirect
-	google.golang.org/protobuf v1.36.7 // indirect
-	gopkg.in/yaml.v3 v3.0.1 // indirect
+	golang.org/x/crypto v0.43.0 // indirect
+	golang.org/x/exp v0.0.0-20251002181428-27f1f14c8bb9
+	golang.org/x/net v0.46.0 // indirect
+	golang.org/x/sys v0.37.0 // indirect
+	golang.org/x/text v0.30.0 // indirect
+	golang.org/x/time v0.14.0 // indirect
+	golang.org/x/tools v0.37.0 // indirect
+	google.golang.org/protobuf v1.36.10 // indirect
 )

internal/apify/actors.go

@@ -11,6 +11,7 @@ type actorIds struct {
 	LLMDatasetProcessor   ActorId
 	TwitterFollowers      ActorId
 	WebScraper            ActorId
+	LinkedInSearchProfile ActorId
 }
 
 var ActorIds = actorIds{
@@ -20,6 +21,7 @@ var ActorIds = actorIds{
 	LLMDatasetProcessor:   "dusan.vystrcil~llm-dataset-processor",
 	TwitterFollowers:      "kaitoeasyapi~premium-x-follower-scraper-following-data",
 	WebScraper:            "apify~website-content-crawler",
+	LinkedInSearchProfile: "harvestapi~linkedin-profile-search",
 }
 
 type defaultActorInput map[string]any
@@ -63,4 +65,10 @@ var Actors = []ActorConfig{
 		Capabilities: teetypes.WebCaps,
 		JobType:      teetypes.WebJob,
 	},
+	{
+		ActorId:      ActorIds.LinkedInSearchProfile,
+		DefaultInput: defaultActorInput{},
+		Capabilities: teetypes.LinkedInCaps,
+		JobType:      teetypes.LinkedInJob,
+	},
 }

internal/jobs/linkedin.go

@@ -0,0 +1,108 @@
+package jobs
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+
+	"github.com/sirupsen/logrus"
+
+	"github.com/masa-finance/tee-worker/api/types"
+	"github.com/masa-finance/tee-worker/internal/config"
+	"github.com/masa-finance/tee-worker/internal/jobs/linkedinapify"
+	"github.com/masa-finance/tee-worker/internal/jobs/stats"
+	"github.com/masa-finance/tee-worker/pkg/client"
+
+	teeargs "github.com/masa-finance/tee-types/args"
+	profileArgs "github.com/masa-finance/tee-types/args/linkedin/profile"
+	teetypes "github.com/masa-finance/tee-types/types"
+	profileTypes "github.com/masa-finance/tee-types/types/linkedin/profile"
+)
+
+// LinkedInApifyClient defines the interface for the LinkedIn Apify client to allow mocking in tests
+type LinkedInApifyClient interface {
+	SearchProfiles(workerID string, args *profileArgs.Arguments, cursor client.Cursor) ([]*profileTypes.Profile, string, client.Cursor, error)
+	ValidateApiKey() error
+}
+
+// NewLinkedInApifyClient is a function variable that can be replaced in tests.
+// It defaults to the actual implementation.
+var NewLinkedInApifyClient = func(apiKey string, statsCollector *stats.StatsCollector) (LinkedInApifyClient, error) {
+	return linkedinapify.NewClient(apiKey, statsCollector)
+}
+
+type LinkedInScraper struct {
+	configuration  config.JobConfiguration
+	statsCollector *stats.StatsCollector
+	capabilities   []teetypes.Capability
+}
+
+func NewLinkedInScraper(jc config.JobConfiguration, statsCollector *stats.StatsCollector) *LinkedInScraper {
+	logrus.Info("LinkedIn scraper via Apify initialized")
+	return &LinkedInScraper{
+		configuration:  jc,
+		statsCollector: statsCollector,
+		capabilities:   teetypes.LinkedInCaps,
+	}
+}
+
+func (ls *LinkedInScraper) ExecuteJob(j types.Job) (types.JobResult, error) {
+	logrus.WithField("job_uuid", j.UUID).Info("Starting ExecuteJob for LinkedIn profile search")
+
+	// Require Apify key for LinkedIn scraping
+	apifyApiKey := ls.configuration.GetString("apify_api_key", "")
+	if apifyApiKey == "" {
+		msg := errors.New("Apify API key is required for LinkedIn job")
+		return types.JobResult{Error: msg.Error()}, msg
+	}
+
+	jobArgs, err := teeargs.UnmarshalJobArguments(teetypes.JobType(j.Type), map[string]any(j.Arguments))
+	if err != nil {
+		msg := fmt.Errorf("failed to unmarshal job arguments: %w", err)
+		return types.JobResult{Error: msg.Error()}, msg
+	}
+
+	linkedinArgs, ok := jobArgs.(*profileArgs.Arguments)
+	if !ok {
+		return types.JobResult{Error: "invalid argument type for LinkedIn job"}, errors.New("invalid argument type")
+	}
+	logrus.Debugf("LinkedIn job args: %+v", *linkedinArgs)
+
+	linkedinClient, err := NewLinkedInApifyClient(apifyApiKey, ls.statsCollector)
+	if err != nil {
+		return types.JobResult{Error: "error while creating LinkedIn Apify client"}, fmt.Errorf("error creating LinkedIn Apify client: %w", err)
+	}
+
+	profiles, datasetId, cursor, err := linkedinClient.SearchProfiles(j.WorkerID, linkedinArgs, client.EmptyCursor)
+	if err != nil {
+		return types.JobResult{Error: fmt.Sprintf("error while searching LinkedIn profiles: %s", err.Error())}, fmt.Errorf("error searching LinkedIn profiles: %w", err)
+	}
+
+	if datasetId == "" {
+		return types.JobResult{Error: "missing dataset id from LinkedIn profile search"}, errors.New("missing dataset id from LinkedIn profile search")
+	}
+
+	data, err := json.Marshal(profiles)
+	if err != nil {
+		return types.JobResult{Error: fmt.Sprintf("error marshalling LinkedIn response")}, fmt.Errorf("error marshalling LinkedIn response: %w", err)
+	}
+
+	return types.JobResult{
+		Data:       data,
+		Job:        j,
+		NextCursor: cursor.String(),
+	}, nil
+}
+
+// GetStructuredCapabilities returns the structured capabilities supported by the LinkedIn scraper
+// based on the available credentials and API keys
+func (ls *LinkedInScraper) GetStructuredCapabilities() teetypes.WorkerCapabilities {
+	capabilities := make(teetypes.WorkerCapabilities)
+
+	apifyApiKey := ls.configuration.GetString("apify_api_key", "")
+	if apifyApiKey != "" {
+		capabilities[teetypes.LinkedInJob] = teetypes.LinkedInCaps
+	}
+
+	return capabilities
+}