feat(latest): extract per-site covers (#58)

backend/internal/latest/sites.go

@@ -1,6 +1,8 @@
 package latest
 
 import (
+	"encoding/json"
+	"html"
 	"net/url"
 	"regexp"
 	"strconv"
@@ -34,6 +36,18 @@ var demonicChapterRe = regexp.MustCompile(`chaptered\.php\?manga=\d+&(?:amp;)?ch
 // Only the id prefix is stable; the slug tail follows the title.
 var comixSlugRe = regexp.MustCompile(`/title/([^/?#]+)`)
 
+func comixSeriesID(seriesURL string) (string, bool) {
+	m := comixSlugRe.FindStringSubmatch(seriesURL)
+	if m == nil {
+		return "", false
+	}
+	id := m[1]
+	if i := strings.Index(id, "-"); i != -1 {
+		id = id[:i]
+	}
+	return id, true
+}
+
 // kaganeChapterRe matches the chapter numbers in a kagane API response. This
 // branch is fed by the browser fetcher, so the body is JSON rather than HTML —
 // there are no anchors to scan.
@@ -87,18 +101,14 @@ func latestChapterFrom(site, seriesURL, body string) (latestChapter, bool) {
 	case "demonic":
 		re = demonicChapterRe
 	case "comix":
-		m := comixSlugRe.FindStringSubmatch(seriesURL)
-		if m == nil {
+		id, ok := comixSeriesID(seriesURL)
+		if !ok {
 			return latestChapter{}, false
 		}
 		// comix ships an SPA: the served HTML carries a JSON state blob instead
 		// of chapter anchors, and latestChapterUrl is the only place the newest
 		// chapter appears. Scoping to this series' id prefix keeps a
 		// "recommended" strip's entries from winning the maximum.
-		id := m[1]
-		if i := strings.Index(id, "-"); i != -1 {
-			id = id[:i]
-		}
 		re = regexp.MustCompile(`"latestChapterUrl":"/title/` + regexp.QuoteMeta(id) + `-[^"]*-chapter-([0-9.]+)"`)
 	case "kagane":
 		re = kaganeChapterRe
@@ -146,3 +156,91 @@ func latestChapterFrom(site, seriesURL, body string) (latestChapter, bool) {
 	}
 	return best, found
 }
+
+var metaTagRe = regexp.MustCompile(`(?is)<meta\b[^>]*>`)
+var doubleQuotedMetaAttrRe = regexp.MustCompile(`(?is)([a-z][a-z0-9:_-]*)\s*=\s*"([^"]*)"`)
+var singleQuotedMetaAttrRe = regexp.MustCompile(`(?is)([a-z][a-z0-9:_-]*)\s*=\s*'([^']*)'`)
+
+// comix's server-rendered page embeds query data in this JSON script; parsing
+// the target detail entry avoids matching posters from recommended results.
+var comixInitialDataRe = regexp.MustCompile(`(?is)<script\b[^>]*\bid\s*=\s*["']initial-data["'][^>]*>(.*?)</script>`)
+
+// kagane's browser-fetched series response carries this published cover URL.
+// Decode the top-level field, not merely an image-shaped URL elsewhere in JSON.
+func kaganeCoverURL(body string) string {
+	var response struct {
+		Cover string `json:"cover"`
+	}
+	if err := json.Unmarshal([]byte(body), &response); err != nil {
+		return ""
+	}
+	return publishedCoverURL(response.Cover)
+}
+
+func comixCoverURL(seriesURL, body string) string {
+	id, ok := comixSeriesID(seriesURL)
+	if !ok {
+		return ""
+	}
+	data := comixInitialDataRe.FindStringSubmatch(body)
+	if data == nil {
+		return ""
+	}
+	var state struct {
+		Queries map[string]json.RawMessage `json:"queries"`
+	}
+	if err := json.Unmarshal([]byte(data[1]), &state); err != nil {
+		return ""
+	}
+	raw := state.Queries[`["manga","detail","`+id+`"]`]
+	if len(raw) == 0 {
+		return ""
+	}
+	var detail struct {
+		Poster struct {
+			Medium string `json:"medium"`
+		} `json:"poster"`
+	}
+	if err := json.Unmarshal(raw, &detail); err != nil {
+		return ""
+	}
+	return publishedCoverURL(detail.Poster.Medium)
+}
+
+func coverFrom(site, seriesURL, body string) (string, bool) {
+	var cover string
+	switch site {
+	case "asura", "demonic", "lightnovelworld":
+		cover = metaContent(body, "property", "og:image")
+	case "novelfull":
+		cover = metaContent(body, "name", "image")
+	case "comix":
+		cover = comixCoverURL(seriesURL, body)
+	case "kagane":
+		cover = kaganeCoverURL(body)
+	}
+	return cover, cover != ""
+}
+
+func metaContent(body, attrName, attrValue string) string {
+	for _, tag := range metaTagRe.FindAllString(body, -1) {
+		attrs := make(map[string]string)
+		for _, m := range doubleQuotedMetaAttrRe.FindAllStringSubmatch(tag, -1) {
+			attrs[strings.ToLower(m[1])] = m[2]
+		}
+		for _, m := range singleQuotedMetaAttrRe.FindAllStringSubmatch(tag, -1) {
+			attrs[strings.ToLower(m[1])] = m[2]
+		}
+		if strings.EqualFold(attrs[strings.ToLower(attrName)], attrValue) {
+			if cover := publishedCoverURL(attrs["content"]); cover != "" {
+				return cover
+			}
+		}
+	}
+	return ""
+}
+
+func publishedCoverURL(value string) string {
+	value = strings.TrimSpace(html.UnescapeString(value))
+	return strings.ReplaceAll(value, " ", "%20")
+}