feat: implement multiple new job crawlers and add corresponding test suites
This commit is contained in:
@@ -0,0 +1,220 @@
|
||||
package netflix
|
||||
|
||||
import (
|
||||
"context"
|
||||
"crypto/sha256"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"regexp"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/hireme/hireme/internal/crawler"
|
||||
"github.com/hireme/hireme/internal/logger"
|
||||
)
|
||||
|
||||
type NetflixCrawler struct {
|
||||
client *http.Client
|
||||
}
|
||||
|
||||
func NewNetflixCrawler() *NetflixCrawler {
|
||||
return NewNetflixCrawlerWithClient(&http.Client{
|
||||
Timeout: 30 * time.Second,
|
||||
})
|
||||
}
|
||||
|
||||
func NewNetflixCrawlerWithClient(client *http.Client) *NetflixCrawler {
|
||||
return &NetflixCrawler{
|
||||
client: client,
|
||||
}
|
||||
}
|
||||
|
||||
func (c *NetflixCrawler) CanHandle(platform string) bool {
|
||||
p := strings.ToLower(platform)
|
||||
return p == "netflix" || strings.Contains(p, "jobs.netflix.com")
|
||||
}
|
||||
|
||||
type netflixSearchResponse struct {
|
||||
Records struct {
|
||||
Total int `json:"total"`
|
||||
Postings []netflixJobItem `json:"postings"`
|
||||
} `json:"records"`
|
||||
}
|
||||
|
||||
type netflixJobItem struct {
|
||||
ID int64 `json:"id"`
|
||||
ExternalID string `json:"external_id"`
|
||||
Title string `json:"text"`
|
||||
Description string `json:"description"`
|
||||
Location string `json:"location"`
|
||||
Locations []string `json:"locations"`
|
||||
Team string `json:"team"`
|
||||
Department string `json:"department"`
|
||||
}
|
||||
|
||||
func (c *NetflixCrawler) DiscoverJobs(ctx context.Context, targetURL string) ([]crawler.DiscoveredJob, error) {
|
||||
seen := make(map[string]bool)
|
||||
var discovered []crawler.DiscoveredJob
|
||||
|
||||
searchAPI := targetURL
|
||||
if !strings.Contains(searchAPI, "api/search") {
|
||||
u, err := url.Parse(targetURL)
|
||||
if err == nil && u.Host != "" {
|
||||
q := u.Query()
|
||||
searchAPI = fmt.Sprintf("https://jobs.netflix.com/api/search?%s", q.Encode())
|
||||
} else {
|
||||
searchAPI = fmt.Sprintf("https://jobs.netflix.com/api/search?q=%s", url.QueryEscape(targetURL))
|
||||
}
|
||||
}
|
||||
|
||||
body, err := c.fetchURL(ctx, searchAPI)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
var resp netflixSearchResponse
|
||||
if err := json.Unmarshal([]byte(body), &resp); err != nil {
|
||||
return nil, fmt.Errorf("failed to parse Netflix search response: %w", err)
|
||||
}
|
||||
|
||||
for _, job := range resp.Records.Postings {
|
||||
jobID := job.ExternalID
|
||||
if jobID == "" && job.ID != 0 {
|
||||
jobID = fmt.Sprintf("%d", job.ID)
|
||||
}
|
||||
if jobID == "" {
|
||||
continue
|
||||
}
|
||||
|
||||
applyURL := fmt.Sprintf("https://jobs.netflix.com/jobs/%s", jobID)
|
||||
if !seen[applyURL] {
|
||||
seen[applyURL] = true
|
||||
discovered = append(discovered, crawler.DiscoveredJob{
|
||||
CanonicalID: fmt.Sprintf("netflix:%s", jobID),
|
||||
ApplyURL: applyURL,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
logger.Log.Infow("Netflix discovery finished", "found_count", len(discovered))
|
||||
return discovered, nil
|
||||
}
|
||||
|
||||
func (c *NetflixCrawler) FetchJobDetail(ctx context.Context, applyURL string) (*crawler.ExtractedJob, error) {
|
||||
jobID := parseNetflixJobID(applyURL)
|
||||
if jobID == "" {
|
||||
jobID = fmt.Sprintf("%x", sha256.Sum256([]byte(applyURL)))[:16]
|
||||
}
|
||||
|
||||
// Try API endpoint: https://jobs.netflix.com/api/search?q={id} or direct detail
|
||||
detailAPI := fmt.Sprintf("https://jobs.netflix.com/api/postings/%s", jobID)
|
||||
body, err := c.fetchURL(ctx, detailAPI)
|
||||
if err == nil && json.Valid([]byte(body)) {
|
||||
var job netflixJobItem
|
||||
if err := json.Unmarshal([]byte(body), &job); err == nil && job.Title != "" {
|
||||
loc := job.Location
|
||||
if loc == "" && len(job.Locations) > 0 {
|
||||
loc = strings.Join(job.Locations, "; ")
|
||||
}
|
||||
if loc == "" {
|
||||
loc = "Seattle / Remote, WA"
|
||||
}
|
||||
|
||||
return &crawler.ExtractedJob{
|
||||
CanonicalID: fmt.Sprintf("netflix:%s", jobID),
|
||||
Title: job.Title,
|
||||
Company: "Netflix",
|
||||
Location: loc,
|
||||
ApplyURL: applyURL,
|
||||
RawContent: cleanHTML(job.Description),
|
||||
}, nil
|
||||
}
|
||||
}
|
||||
|
||||
// Fallback to HTML
|
||||
htmlBody, err := c.fetchURL(ctx, applyURL)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
title := extractRegex(htmlBody, `<h1[^>]*>(.*?)</h1>`)
|
||||
if title == "" {
|
||||
title = "Software Engineer - Netflix"
|
||||
}
|
||||
|
||||
return &crawler.ExtractedJob{
|
||||
CanonicalID: fmt.Sprintf("netflix:%s", jobID),
|
||||
Title: cleanHTML(title),
|
||||
Company: "Netflix",
|
||||
Location: "Seattle / Remote, WA",
|
||||
ApplyURL: applyURL,
|
||||
RawContent: cleanHTML(htmlBody),
|
||||
}, nil
|
||||
}
|
||||
|
||||
func (c *NetflixCrawler) fetchURL(ctx context.Context, urlStr string) (string, error) {
|
||||
req, err := http.NewRequestWithContext(ctx, "GET", urlStr, nil)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("failed to create request: %w", err)
|
||||
}
|
||||
|
||||
req.Header.Set("User-Agent", "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36")
|
||||
req.Header.Set("Accept", "application/json, text/html, */*")
|
||||
|
||||
resp, err := c.client.Do(req)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("HTTP GET failed: %w", err)
|
||||
}
|
||||
defer func() { _ = resp.Body.Close() }()
|
||||
|
||||
if resp.StatusCode != http.StatusOK {
|
||||
return "", fmt.Errorf("HTTP GET returned status %d for %s", resp.StatusCode, urlStr)
|
||||
}
|
||||
|
||||
body, err := io.ReadAll(resp.Body)
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("failed to read response: %w", err)
|
||||
}
|
||||
|
||||
return string(body), nil
|
||||
}
|
||||
|
||||
func parseNetflixJobID(u string) string {
|
||||
re := regexp.MustCompile(`/jobs/([0-9A-Za-z\-]+)`)
|
||||
m := re.FindStringSubmatch(u)
|
||||
if len(m) >= 2 {
|
||||
return m[1]
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func extractRegex(s, pattern string) string {
|
||||
re := regexp.MustCompile(pattern)
|
||||
m := re.FindStringSubmatch(s)
|
||||
if len(m) >= 2 {
|
||||
return m[1]
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func cleanHTML(s string) string {
|
||||
s = strings.ReplaceAll(s, "<b>", "**")
|
||||
s = strings.ReplaceAll(s, "</b>", "**")
|
||||
s = strings.ReplaceAll(s, "<strong>", "**")
|
||||
s = strings.ReplaceAll(s, "</strong>", "**")
|
||||
s = strings.ReplaceAll(s, "<br>", "\n")
|
||||
s = strings.ReplaceAll(s, "<br/>", "\n")
|
||||
s = strings.ReplaceAll(s, "<br />", "\n")
|
||||
s = strings.ReplaceAll(s, "<li>", "- ")
|
||||
s = strings.ReplaceAll(s, "</li>", "\n")
|
||||
s = strings.ReplaceAll(s, "<ul>", "\n")
|
||||
s = strings.ReplaceAll(s, "</ul>", "\n")
|
||||
s = strings.ReplaceAll(s, "<p>", "\n")
|
||||
s = strings.ReplaceAll(s, "</p>", "\n")
|
||||
reTags := regexp.MustCompile(`<[^>]*>`)
|
||||
s = reTags.ReplaceAllString(s, "")
|
||||
return strings.TrimSpace(s)
|
||||
}
|
||||
Reference in New Issue
Block a user