feat(listing): populate Tags and CategorizedTags from figure data-tags

FA's beta listing pages emit each submission's tag list on the figure's <img data-tags="..."> attribute, mixing prefixed system tags (s_/c_/a_/u_/t_) with the unprefixed keyword list. Reading it during gallery-page parse lets callers classify favorites/gallery/scraps/ browse/search/inbox items at scrape time, avoiding a /view/{id} round-trip per submission. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-06-02 21:53:56 +02:00
parent bc2d27f702
commit a2fc1b7e32
3 changed files with 146 additions and 3 deletions
--- a/gallery_parser.go
+++ b/gallery_parser.go
@@ -85,6 +85,15 @@ func parseGalleryFigure(sel *goquery.Selection, jsonData listingJSONMap) *Submis
 		}
 	}

+	// data-tags on the figure's <img> carries both the unprefixed keyword
+	// list and the prefixed system tags (s_/c_/a_/u_/t_). Splitting it lets
+	// callers classify listing items without an extra /view/ fetch.
+	if img := sel.Find("img[data-tags]").First(); img.Length() > 0 {
+		if raw, ok := img.Attr("data-tags"); ok {
+			applyListingDataTags(s, raw)
+		}
+	}
+
 	// JSON enrichment preferred sources for the fields it carries.
 	if jsonData != nil {
 		if entry, ok := jsonData[id]; ok {
@@ -105,3 +114,35 @@ func parseGalleryFigure(sel *goquery.Selection, jsonData listingJSONMap) *Submis

 	return s
 }
+
+// applyListingDataTags splits the whitespace-separated data-tags attribute
+// FA emits on listing-page <img> elements and routes each token to either
+// CategorizedTags (when the token has a known single-letter prefix
+// s_/c_/a_/u_/t_) or Tags (everything else).
+//
+// The prefix mapping mirrors the /view/ parser in submission_parser.go so a
+// listing-path Submission carries the same categorisation a /view/-path one
+// would, modulo tokens FA can't represent in this flat attribute (multi-word
+// tags, the a_ vs u_ distinction).
+func applyListingDataTags(s *Submission, raw string) {
+	for _, tok := range strings.Fields(raw) {
+		if len(tok) >= 3 && tok[1] == '_' {
+			name := tok[2:]
+			switch tok[0] {
+			case 's':
+				s.CategorizedTags.Species = append(s.CategorizedTags.Species, name)
+				continue
+			case 'c':
+				s.CategorizedTags.Characters = append(s.CategorizedTags.Characters, name)
+				continue
+			case 'a', 'u':
+				s.CategorizedTags.Artists = append(s.CategorizedTags.Artists, name)
+				continue
+			case 't':
+				s.CategorizedTags.Types = append(s.CategorizedTags.Types, name)
+				continue
+			}
+		}
+		s.Tags = append(s.Tags, tok)
+	}
+}
--- a/gallery_parser_test.go
+++ b/gallery_parser_test.go
@@ -62,6 +62,99 @@ func TestParseGalleryPage_Synthetic(t *testing.T) {
 	}
 }

+func TestParseGalleryFigure_DataTags(t *testing.T) {
+	const html = `<html><body>
+<figure id="sid-2001" class="t-image r-general">
+  <a href="/view/2001/" title="Mixed Tags">
+    <img data-tags="u_someartist c_artwork_digital t_all s_wolf wolf solo digital landscape" src="//d.example/thumb/2001.png"/>
+  </a>
+</figure>
+<figure id="sid-2002" class="t-image r-general">
+  <a href="/view/2002/" title="No Tags">
+    <img src="//d.example/thumb/2002.png"/>
+  </a>
+</figure>
+<figure id="sid-2003" class="t-image r-general">
+  <a href="/view/2003/" title="Only Keywords">
+    <img data-tags="wolf solo" src="//d.example/thumb/2003.png"/>
+  </a>
+</figure>
+</body></html>`
+	doc, err := goquery.NewDocumentFromReader(strings.NewReader(html))
+	if err != nil {
+		t.Fatalf("setup: %v", err)
+	}
+	items, _ := parseGalleryPage(doc, false)
+	if len(items) != 3 {
+		t.Fatalf("items = %d; want 3", len(items))
+	}
+
+	// Mixed prefixed + unprefixed.
+	mixed := items[0]
+	wantTags := []string{"wolf", "solo", "digital", "landscape"}
+	if !equalStrings(mixed.Tags, wantTags) {
+		t.Errorf("items[0].Tags = %v; want %v", mixed.Tags, wantTags)
+	}
+	if !equalStrings(mixed.CategorizedTags.Species, []string{"wolf"}) {
+		t.Errorf("items[0].Species = %v", mixed.CategorizedTags.Species)
+	}
+	if !equalStrings(mixed.CategorizedTags.Characters, []string{"artwork_digital"}) {
+		t.Errorf("items[0].Characters = %v", mixed.CategorizedTags.Characters)
+	}
+	if !equalStrings(mixed.CategorizedTags.Types, []string{"all"}) {
+		t.Errorf("items[0].Types = %v", mixed.CategorizedTags.Types)
+	}
+	if !equalStrings(mixed.CategorizedTags.Artists, []string{"someartist"}) {
+		t.Errorf("items[0].Artists = %v", mixed.CategorizedTags.Artists)
+	}
+
+	// Missing data-tags: both slices stay nil.
+	if items[1].Tags != nil {
+		t.Errorf("items[1].Tags = %v; want nil", items[1].Tags)
+	}
+	if items[1].CategorizedTags.Species != nil ||
+		items[1].CategorizedTags.Characters != nil ||
+		items[1].CategorizedTags.Artists != nil ||
+		items[1].CategorizedTags.Types != nil {
+		t.Errorf("items[1].CategorizedTags = %+v; want zero", items[1].CategorizedTags)
+	}
+
+	// Unprefixed-only: everything lands in Tags.
+	if !equalStrings(items[2].Tags, []string{"wolf", "solo"}) {
+		t.Errorf("items[2].Tags = %v", items[2].Tags)
+	}
+	if items[2].CategorizedTags.Species != nil {
+		t.Errorf("items[2].Species = %v; want nil", items[2].CategorizedTags.Species)
+	}
+}
+
+func TestParseGalleryPage_RealFixtureTags(t *testing.T) {
+	raw := loadFixture(t, "gallery_page1.html")
+	doc, err := goquery.NewDocumentFromReader(bytes.NewReader(raw))
+	if err != nil {
+		t.Fatalf("read doc: %v", err)
+	}
+	items, _ := parseGalleryPage(doc, false)
+	if len(items) == 0 {
+		t.Fatal("real fixture: no items parsed")
+	}
+	var withTags, withSpecies int
+	for _, it := range items {
+		if len(it.Tags) > 0 {
+			withTags++
+		}
+		if len(it.CategorizedTags.Species) > 0 {
+			withSpecies++
+		}
+	}
+	if withTags == 0 {
+		t.Error("no items got Tags populated from data-tags")
+	}
+	if withSpecies == 0 {
+		t.Error("no items got CategorizedTags.Species populated from data-tags")
+	}
+}
+
 func TestParseGalleryPage_RealFixture(t *testing.T) {
 	raw := loadFixture(t, "gallery_page1.html")
 	doc, err := goquery.NewDocumentFromReader(bytes.NewReader(raw))
--- a/submission.go
+++ b/submission.go
@@ -35,10 +35,19 @@ type Submission struct {
 	Gender          Gender
 	Description     string // raw HTML; sanitise before rendering to a browser
 	DescriptionText string // plaintext convenience
-	Tags            []string
+	// Tags holds the user-supplied keyword tags. On /view/-path Submissions
+	// these come from div.submission-tags anchors. On listing-path
+	// Submissions (Gallery/Scraps/Favorites/Browse/Search/SubmissionInbox)
+	// they come from the figure's data-tags attribute, which carries the
+	// same keywords FA renders on /view/ for that submission.
+	Tags []string
 	// CategorizedTags groups FA's prefixed system tags by category.
-	// FA emits these as tag-block entries inside div.submission-tags with
-	// prefixes s_ (species), c_ (character), a_/u_ (artist), and t_ (type).
+	// On /view/-path Submissions FA emits these as tag-block entries inside
+	// div.submission-tags with prefixes s_ (species), c_ (character),
+	// a_/u_ (artist), and t_ (type). On listing-path Submissions the same
+	// prefixed tokens are parsed out of the figure's data-tags attribute;
+	// the a_ vs u_ distinction is lost there because FA collapses both into
+	// u_ in that flat list.
 	CategorizedTags CategorizedTags
 	FileURL         string // absolute CDN URL; pass to Download
 	ThumbURL        string