add spooldb client and look up spool location alongside weight

2026-05-31 13:50:37 -07:00
parent d3e9cc8e54
commit 2b4d2134b4
5 changed files with 378 additions and 2 deletions
@@ -3,11 +3,19 @@ module spoolweight
 go 1.26.2

 require (
+	github.com/chromedp/chromedp v0.15.1
 	github.com/makiuchi-d/gozxing v0.1.1
 	golang.org/x/image v0.41.0
 )

 require (
+	github.com/chromedp/cdproto v0.0.0-20260321001828-e3e3800016bc // indirect
+	github.com/chromedp/sysutil v1.1.0 // indirect
+	github.com/go-json-experiment/json v0.0.0-20260214004413-d219187c3433 // indirect
+	github.com/gobwas/httphead v0.1.0 // indirect
+	github.com/gobwas/pool v0.2.1 // indirect
+	github.com/gobwas/ws v1.4.0 // indirect
+	golang.org/x/sys v0.42.0 // indirect
 	golang.org/x/text v0.37.0 // indirect
 	golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 // indirect
 )
@@ -1,7 +1,28 @@
+github.com/chromedp/cdproto v0.0.0-20260321001828-e3e3800016bc h1:wkN/LMi5vc60pBRWx6qpbk/aEvq3/ZVNpnMvsw8PVVU=
+github.com/chromedp/cdproto v0.0.0-20260321001828-e3e3800016bc/go.mod h1:cbyjALe67vDvlvdiG9369P8w5U2w6IshwtyD2f2Tvag=
+github.com/chromedp/chromedp v0.15.1 h1:EJWiPm7BNqDqjYy6U0lTSL5wNH+iNt9GjC3a4gfjNyQ=
+github.com/chromedp/chromedp v0.15.1/go.mod h1:CdTHtUqD/dqaFw/cvFWtTydoEQS44wLBuwbMR9EkOY4=
+github.com/chromedp/sysutil v1.1.0 h1:PUFNv5EcprjqXZD9nJb9b/c9ibAbxiYo4exNWZyipwM=
+github.com/chromedp/sysutil v1.1.0/go.mod h1:WiThHUdltqCNKGc4gaU50XgYjwjYIhKWoHGPTUfWTJ8=
+github.com/go-json-experiment/json v0.0.0-20260214004413-d219187c3433 h1:vymEbVwYFP/L05h5TKQxvkXoKxNvTpjxYKdF1Nlwuao=
+github.com/go-json-experiment/json v0.0.0-20260214004413-d219187c3433/go.mod h1:tphK2c80bpPhMOI4v6bIc2xWywPfbqi1Z06+RcrMkDg=
+github.com/gobwas/httphead v0.1.0 h1:exrUm0f4YX0L7EBwZHuCF4GDp8aJfVeBrlLQrs6NqWU=
+github.com/gobwas/httphead v0.1.0/go.mod h1:O/RXo79gxV8G+RqlR/otEwx4Q36zl9rqC5u12GKvMCM=
+github.com/gobwas/pool v0.2.1 h1:xfeeEhW7pwmX8nuLVlqbzVc7udMDrwetjEv+TZIz1og=
+github.com/gobwas/pool v0.2.1/go.mod h1:q8bcK0KcYlCgd9e7WYLm9LpyS+YeLd8JVDW6WezmKEw=
+github.com/gobwas/ws v1.4.0 h1:CTaoG1tojrh4ucGPcoJFiAQUAsEWekEWvLy7GsVNqGs=
+github.com/gobwas/ws v1.4.0/go.mod h1:G3gNqMNtPppf5XUz7O4shetPpcZ1VJ7zt18dlUeakrc=
+github.com/ledongthuc/pdf v0.0.0-20220302134840-0c2507a12d80 h1:6Yzfa6GP0rIo/kULo2bwGEkFvCePZ3qHDDTC3/J9Swo=
+github.com/ledongthuc/pdf v0.0.0-20220302134840-0c2507a12d80/go.mod h1:imJHygn/1yfhB7XSJJKlFZKl/J+dCPAknuiaGOshXAs=
 github.com/makiuchi-d/gozxing v0.1.1 h1:xxqijhoedi+/lZlhINteGbywIrewVdVv2wl9r5O9S1I=
 github.com/makiuchi-d/gozxing v0.1.1/go.mod h1:eRIHbOjX7QWxLIDJoQuMLhuXg9LAuw6znsUtRkNw9DU=
+github.com/orisano/pixelmatch v0.0.0-20220722002657-fb0b55479cde h1:x0TT0RDC7UhAVbbWWBzr41ElhJx5tXPWkIHA2HWPRuw=
+github.com/orisano/pixelmatch v0.0.0-20220722002657-fb0b55479cde/go.mod h1:nZgzbfBr3hhjoZnS66nKrHmduYNpc34ny7RK4z5/HM0=
 golang.org/x/image v0.41.0 h1:8wS72eGJMJaBxK6okTzd4WaXumUlTVlb753MlsSvTCo=
 golang.org/x/image v0.41.0/go.mod h1:uIc348UZMSvS5Z65CVZ7iDPaNobNFEPeJ4kbqTOszmA=
+golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.42.0 h1:omrd2nAlyT5ESRdCLYdm3+fMfNFE/+Rf4bDIQImRJeo=
+golang.org/x/sys v0.42.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
 golang.org/x/text v0.37.0 h1:Cqjiwd9eSg8e0QAkyCaQTNHFIIzWtidPahFWR83rTrc=
 golang.org/x/text v0.37.0/go.mod h1:a5sjxXGs9hsn/AJVwuElvCAo9v8QYLzvavO5z2PiM38=
 golang.org/x/xerrors v0.0.0-20200804184101-5ec99f83aff1 h1:go1bK/D/BFZV2I8cIQd1NKEZ+0owSTG1fDTci4IqFcE=
@@ -2,6 +2,7 @@ package main

 import (
 	"bytes"
+	"context"
 	"encoding/base64"
 	"encoding/json"
 	"flag"
@@ -22,12 +23,14 @@ import (
 	"github.com/makiuchi-d/gozxing"
 	"github.com/makiuchi-d/gozxing/qrcode"
 	xdraw "golang.org/x/image/draw"
+	"spoolweight/spooldb"
 )

 type result struct {
 	Image            string    `json:"image"`
 	SpoolID          string    `json:"spool_id,omitempty"`
 	URL              string    `json:"url,omitempty"`
+	Location         string    `json:"location,omitempty"`
 	Weight           *float64  `json:"weight,omitempty"`
 	Unit             string    `json:"unit,omitempty"`
 	Confidence       *float64  `json:"confidence,omitempty"`
@@ -61,9 +64,12 @@ func main() {
 		log.Printf("auth: %s", auth.name)
 	}

+	locator := &spoolLocator{}
+	defer locator.close()
+
 	results := make([]result, 0, flag.NArg())
 	for _, path := range flag.Args() {
-		results = append(results, processImage(path, auth))
+		results = append(results, processImage(path, auth, locator))
 	}

 	enc := json.NewEncoder(os.Stdout)
@@ -71,9 +77,66 @@ func main() {
 	enc.Encode(results)
 }

+// spoolLocator lazily logs into spooldb on first use, so its (slow) browser
+// login overlaps with the first image's weight read rather than blocking it.
+// Location lookup is best-effort: any failure is logged and the location is
+// simply omitted from the output.
+type spoolLocator struct {
+	once   sync.Once
+	client *spooldb.Client
+	err    error
+}
+
+func (s *spoolLocator) login() (*spooldb.Client, error) {
+	s.once.Do(func() {
+		user, pass := os.Getenv("SPOOLDB_USER"), os.Getenv("SPOOLDB_PASS")
+		if user == "" || pass == "" {
+			s.err = fmt.Errorf("SPOOLDB_USER/SPOOLDB_PASS not set")
+			return
+		}
+		c, err := spooldb.New()
+		if err != nil {
+			s.err = err
+			return
+		}
+		ctx, cancel := context.WithTimeout(context.Background(), 90*time.Second)
+		defer cancel()
+		if err := c.Login(ctx, user, pass); err != nil {
+			c.Close()
+			s.err = fmt.Errorf("login: %w", err)
+			return
+		}
+		s.client = c
+	})
+	return s.client, s.err
+}
+
+// location returns the spool's storage location, or "" if it can't be looked up.
+func (s *spoolLocator) location(spoolID string) string {
+	client, err := s.login()
+	if err != nil {
+		log.Printf("spooldb: skipping location lookup: %v", err)
+		return ""
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), 60*time.Second)
+	defer cancel()
+	loc, err := client.SpoolLocation(ctx, spoolID)
+	if err != nil {
+		log.Printf("spooldb: location lookup for %s: %v", spoolID, err)
+		return ""
+	}
+	return loc
+}
+
+func (s *spoolLocator) close() {
+	if s.client != nil {
+		s.client.Close()
+	}
+}
+
 // processImage reads one photo, capturing any failure in the result's Error
 // field so a single bad image doesn't abort the whole batch.
-func processImage(path string, auth authInfo) result {
+func processImage(path string, auth authInfo, locator *spoolLocator) result {
 	r := result{Image: path}

 	img, err := loadImage(path)
@@ -94,7 +157,19 @@ func processImage(path string, auth authInfo) result {
 	r.SpoolID = spoolID(url)
 	r.URL = url

+	// Look up the spool's location concurrently with the (slower) weight read.
+	var loc string
+	var wg sync.WaitGroup
+	wg.Add(1)
+	go func() {
+		defer wg.Done()
+		loc = locator.location(r.SpoolID)
+	}()
+
 	w, err := readWeight(img, auth)
+	wg.Wait()
+	r.Location = loc
+
 	if err != nil {
 		r.Error = fmt.Sprintf("read weight: %v", err)
 		return r
@@ -0,0 +1,232 @@
+// Package spooldb is an isolated client for 3dfilamentprofiles.com (the site
+// behind the spooldb.com QR codes). The site has no public API and sits behind
+// Vercel's bot challenge, so a plain HTTP client can't reach it. This package
+// drives a headless Chromium (via chromedp) which solves the challenge
+// naturally, logs in, and reads/writes spool data. All site- and
+// browser-specific details are confined here.
+package spooldb
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"time"
+
+	"github.com/chromedp/chromedp"
+)
+
+const (
+	baseURL       = "https://3dfilamentprofiles.com"
+	challengeText = "Security Checkpoint"
+)
+
+// Client is a logged-in session against 3dfilamentprofiles.com. It owns a
+// headless browser; call Close when done. Methods are not safe for concurrent
+// use — the underlying browser tab is single-threaded.
+type Client struct {
+	browserCtx context.Context
+	cancels    []context.CancelFunc
+	loggedIn   bool
+}
+
+type config struct {
+	chromePath string
+	headless   bool
+}
+
+// Option configures a Client.
+type Option func(*config)
+
+// WithChromePath sets an explicit Chrome/Chromium executable path.
+func WithChromePath(p string) Option { return func(c *config) { c.chromePath = p } }
+
+// WithHeadful runs a visible browser window (useful for debugging).
+func WithHeadful() Option { return func(c *config) { c.headless = false } }
+
+// New launches a browser and returns a Client. It does not log in yet.
+func New(opts ...Option) (*Client, error) {
+	cfg := config{headless: true}
+	for _, o := range opts {
+		o(&cfg)
+	}
+	chromePath, err := resolveChrome(cfg.chromePath)
+	if err != nil {
+		return nil, err
+	}
+
+	execOpts := append(chromedp.DefaultExecAllocatorOptions[:],
+		chromedp.ExecPath(chromePath),
+		chromedp.Flag("disable-blink-features", "AutomationControlled"),
+		// A real-looking UA; the default headless UA advertises "HeadlessChrome".
+		chromedp.UserAgent("Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/149.0.0.0 Safari/537.36"),
+		chromedp.WindowSize(1280, 900),
+	)
+	if cfg.headless {
+		execOpts = append(execOpts, chromedp.Flag("headless", "new"))
+	} else {
+		execOpts = append(execOpts, chromedp.Flag("headless", false))
+	}
+
+	allocCtx, allocCancel := chromedp.NewExecAllocator(context.Background(), execOpts...)
+	browserCtx, browserCancel := chromedp.NewContext(allocCtx)
+
+	// Allocate the browser bound to the long-lived browserCtx. chromedp ties the
+	// Chrome process lifetime to the context of the first Run, so this must not
+	// be a short-lived per-call context (otherwise the browser dies after it).
+	if err := chromedp.Run(browserCtx, chromedp.Navigate("about:blank")); err != nil {
+		browserCancel()
+		allocCancel()
+		return nil, fmt.Errorf("start browser: %w", err)
+	}
+
+	return &Client{
+		browserCtx: browserCtx,
+		cancels:    []context.CancelFunc{browserCancel, allocCancel},
+	}, nil
+}
+
+// Close shuts down the browser.
+func (c *Client) Close() {
+	for _, cancel := range c.cancels {
+		cancel()
+	}
+}
+
+// run executes actions against the browser, bounded by timeout, and also
+// cancels if the caller's ctx is done.
+func (c *Client) run(ctx context.Context, timeout time.Duration, actions ...chromedp.Action) error {
+	runCtx, cancel := context.WithTimeout(c.browserCtx, timeout)
+	defer cancel()
+	stop := context.AfterFunc(ctx, cancel)
+	defer stop()
+	return chromedp.Run(runCtx, actions...)
+}
+
+// awaitChallenge waits until the Vercel checkpoint clears (the headless browser
+// solves it automatically by running the page's JavaScript).
+func (c *Client) awaitChallenge(ctx context.Context) error {
+	deadline := time.Now().Add(45 * time.Second)
+	for time.Now().Before(deadline) {
+		var title string
+		if err := c.run(ctx, 10*time.Second, chromedp.Title(&title)); err != nil {
+			return err
+		}
+		if !strings.Contains(title, challengeText) {
+			return nil
+		}
+		select {
+		case <-ctx.Done():
+			return ctx.Err()
+		case <-time.After(2 * time.Second):
+		}
+	}
+	return errors.New("vercel challenge did not clear in time")
+}
+
+// Login authenticates with email/password. Safe to call once per Client.
+func (c *Client) Login(ctx context.Context, email, password string) error {
+	if err := c.run(ctx, 45*time.Second, chromedp.Navigate(baseURL+"/login")); err != nil {
+		return fmt.Errorf("navigate to login: %w", err)
+	}
+	if err := c.awaitChallenge(ctx); err != nil {
+		return err
+	}
+	if err := c.run(ctx, 45*time.Second,
+		chromedp.WaitVisible("#email", chromedp.ByID),
+		chromedp.SendKeys("#email", email, chromedp.ByID),
+		chromedp.SendKeys("#password", password, chromedp.ByID),
+		chromedp.Click(`//button[normalize-space()='Sign In']`, chromedp.BySearch),
+	); err != nil {
+		return fmt.Errorf("submit login form: %w", err)
+	}
+
+	// Login succeeds once we navigate away from /login.
+	deadline := time.Now().Add(30 * time.Second)
+	for time.Now().Before(deadline) {
+		var loc string
+		if err := c.run(ctx, 10*time.Second, chromedp.Location(&loc)); err != nil {
+			return err
+		}
+		if !strings.Contains(loc, "/login") {
+			c.loggedIn = true
+			return nil
+		}
+		select {
+		case <-ctx.Done():
+			return ctx.Err()
+		case <-time.After(time.Second):
+		}
+	}
+	return errors.New("login did not complete (check credentials)")
+}
+
+// SpoolLocation returns the storage location assigned to a spool (e.g. "H"),
+// or "" if the spool has no location. spoolID is the code from the QR URL
+// (spooldb.com/s/<id>).
+func (c *Client) SpoolLocation(ctx context.Context, spoolID string) (string, error) {
+	if !c.loggedIn {
+		return "", errors.New("not logged in")
+	}
+	if err := c.run(ctx, 45*time.Second, chromedp.Navigate(baseURL+"/my/spool/"+spoolID)); err != nil {
+		return "", fmt.Errorf("navigate to spool: %w", err)
+	}
+	if err := c.awaitChallenge(ctx); err != nil {
+		return "", err
+	}
+
+	// The spool's status card has a panel header whose first line is the
+	// location (a box icon followed by the location name).
+	const js = `(() => {
+	  const hdr = [...document.querySelectorAll('div.bg-panel')].find(h => h.querySelector('div.font-medium'));
+	  if (!hdr) return null;
+	  return (hdr.querySelector('div.font-medium').textContent || '').trim();
+	})()`
+
+	var loc *string
+	deadline := time.Now().Add(20 * time.Second)
+	for time.Now().Before(deadline) {
+		if err := c.run(ctx, 10*time.Second, chromedp.Evaluate(js, &loc)); err != nil {
+			return "", err
+		}
+		if loc != nil {
+			return strings.TrimSpace(*loc), nil
+		}
+		select {
+		case <-ctx.Done():
+			return "", ctx.Err()
+		case <-time.After(time.Second):
+		}
+	}
+	return "", errors.New("spool page did not render (wrong id or not logged in?)")
+}
+
+// resolveChrome finds a Chrome/Chromium binary: explicit path, then $CHROME,
+// then a Chrome-for-Testing install, then common installed browsers.
+func resolveChrome(explicit string) (string, error) {
+	candidates := []string{explicit, os.Getenv("CHROME")}
+
+	if home, err := os.UserHomeDir(); err == nil {
+		pattern := filepath.Join(home, ".cache/chrome-for-testing/chrome/*/chrome-*/*.app/Contents/MacOS/*")
+		if m, _ := filepath.Glob(pattern); len(m) > 0 {
+			candidates = append(candidates, m[len(m)-1]) // newest-sorted last
+		}
+	}
+	candidates = append(candidates,
+		"/Applications/Google Chrome.app/Contents/MacOS/Google Chrome",
+		"/Applications/Chromium.app/Contents/MacOS/Chromium",
+		"/usr/bin/google-chrome",
+		"/usr/bin/chromium",
+	)
+	for _, p := range candidates {
+		if p == "" {
+			continue
+		}
+		if fi, err := os.Stat(p); err == nil && !fi.IsDir() {
+			return p, nil
+		}
+	}
+	return "", errors.New("no Chrome/Chromium found; install Chrome for Testing or pass WithChromePath")
+}
@@ -0,0 +1,40 @@
+package spooldb
+
+import (
+	"context"
+	"os"
+	"testing"
+	"time"
+)
+
+// TestSpoolLocation is a live integration test against 3dfilamentprofiles.com.
+// It is skipped unless SPOOLDB_USER and SPOOLDB_PASS are set. The spool to look
+// up defaults to the sample spool but can be overridden with SPOOL_ID.
+func TestSpoolLocation(t *testing.T) {
+	email, pass := os.Getenv("SPOOLDB_USER"), os.Getenv("SPOOLDB_PASS")
+	if email == "" || pass == "" {
+		t.Skip("set SPOOLDB_USER and SPOOLDB_PASS to run the live integration test")
+	}
+	spoolID := os.Getenv("SPOOL_ID")
+	if spoolID == "" {
+		spoolID = "fU9zkaRWB"
+	}
+
+	c, err := New()
+	if err != nil {
+		t.Fatalf("new client: %v", err)
+	}
+	defer c.Close()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 3*time.Minute)
+	defer cancel()
+
+	if err := c.Login(ctx, email, pass); err != nil {
+		t.Fatalf("login: %v", err)
+	}
+	loc, err := c.SpoolLocation(ctx, spoolID)
+	if err != nil {
+		t.Fatalf("spool location: %v", err)
+	}
+	t.Logf("spool %s location: %q", spoolID, loc)
+}