added in memory caching for 5 minutes

scraper.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"fmt"
 	"strings"
+	"time"
 
 	"github.com/aws/aws-lambda-go/lambda"
 	"github.com/gocolly/colly"
@@ -29,6 +30,12 @@ type skills struct {
 	Typescript bool `json:"typescript"`
 }
 
+var (
+	jobs      []job
+	lastFetch time.Time
+	cacheTTL  = time.Minute * 5
+)
+
 func skillChecker(description string) skills {
 	return skills{
 		React:      strings.Contains(description, "React"),
@@ -40,13 +47,9 @@ func skillChecker(description string) skills {
 	}
 }
 
-// Slice to store job details
-var jobs []job
-
-func handler(ctx context.Context) ([]job, error) {
+func fetchData() error {
 
 	baseUrl := "https://thehub.io"
-	searchString := "https://thehub.io/jobs?roles=frontenddeveloper&roles=fullstackdeveloper&roles=backenddeveloper&roles=devops&paid=true&countryCode=DK&sorting=newJobs"
 	// Instantiate default collector
 	c := colly.NewCollector(
 		// visit only the hub
@@ -109,8 +112,29 @@ func handler(ctx context.Context) ([]job, error) {
 			e.Request.Visit(fullNextPage)
 		}
 	})
+	// Visit the initial URL to start scraping
+	err := c.Visit("https://thehub.io/jobs?roles=frontenddeveloper&roles=fullstackdeveloper&roles=backenddeveloper&search=developer&paid=true&countryCode=DK&sorting=newJobs")
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+func handler(ctx context.Context) ([]job, error) {
+	// Check if cache is valid
+	if time.Since(lastFetch) < cacheTTL && len(jobs) > 0 {
+		return jobs, nil
+	}
+
+	// Fetch new data
+	err := fetchData()
+	if err != nil {
+		return nil, err
+	}
+
+	// Update cache timestamp
+	lastFetch = time.Now()
 
-	c.Visit(searchString)
 	return jobs, nil
 }