feat: per-site latest-chapter extraction from series HTML

Ports latestChapterFromAnchors from the userscript for asura and
demonic. Asura's pattern is scoped to the series' own slug, which
subsumes the userscript's anchor-text check and also excludes chapter
links belonging to other series. Fixtures are trimmed from real pages.

backend/latest_sites.go

@@ -0,0 +1,72 @@
+package main
+
+import (
+	"regexp"
+	"strconv"
+	"strings"
+)
+
+// latestChapter is the newest chapter a series page advertises.
+type latestChapter struct {
+	Num   float64
+	Label string
+}
+
+// asuraSlugRe pulls the series slug out of a stored series_url.
+// Shape verified live 2026-07-26: https://asurascans.com/comics/<slug>, where
+// the slug carries a trailing hash-like suffix (e.g. "-f886a8af").
+var asuraSlugRe = regexp.MustCompile(`/comics/([^/?#]+)`)
+
+// demonicChapterRe matches the pre-redirect anchors demonic series pages link
+// through. Both the raw "&" and the HTML-escaped "&amp;" forms occur.
+var demonicChapterRe = regexp.MustCompile(`chaptered\.php\?manga=\d+&(?:amp;)?chapter=([0-9.]+)`)
+
+// latestChapterFrom returns the highest chapter number body advertises for this
+// series. ok is false when the body yields nothing usable — an unknown site, an
+// empty body, a Cloudflare challenge page, and a site redesign all land here,
+// and the caller treats all four identically.
+//
+// Ported from the userscript's latestChapterFromAnchors (asura L123-133,
+// demonic L183-193), including its reason for taking a maximum rather than a
+// first or last: neither site lists chapters in a dependable order.
+//
+// The userscript's asura rule additionally requires the anchor text to match
+// /Chapter\s+[\d.]+/i. That check exists only to skip the "First Chapter"
+// shortcut, which points at chapter/1 and therefore can never win a maximum, so
+// it is redundant here. Scoping the pattern to this series' own slug replaces it
+// with a stronger guarantee: a chapter link belonging to some other series
+// cannot contribute even if the page starts carrying them.
+func latestChapterFrom(site, seriesURL, body string) (latestChapter, bool) {
+	var re *regexp.Regexp
+	switch site {
+	case "asura":
+		m := asuraSlugRe.FindStringSubmatch(seriesURL)
+		if m == nil {
+			return latestChapter{}, false
+		}
+		// Compiled per call rather than cached: this runs once per fetch, which
+		// is at most a few times a minute, and the slug varies per series.
+		re = regexp.MustCompile(`/comics/` + regexp.QuoteMeta(m[1]) + `/chapter/([0-9.]+)`)
+	case "demonic":
+		re = demonicChapterRe
+	default:
+		return latestChapter{}, false
+	}
+
+	var best latestChapter
+	found := false
+	for _, m := range re.FindAllStringSubmatch(body, -1) {
+		// [0-9.]+ can swallow a trailing separator, e.g. "chapter/12." in a
+		// sentence; ParseFloat would reject the whole match.
+		raw := strings.Trim(m[1], ".")
+		num, err := strconv.ParseFloat(raw, 64)
+		if err != nil {
+			continue
+		}
+		if !found || num > best.Num {
+			best = latestChapter{Num: num, Label: "Chapter " + raw}
+			found = true
+		}
+	}
+	return best, found
+}