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.
2026-07-26 15:34:54 +07:00
parent 0a9042dc42
commit c38ed247df
2 changed files with 187 additions and 0 deletions
@@ -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
+}
@@ -0,0 +1,115 @@
+package main
+
+import "testing"
+
+// Trimmed from https://asurascans.com/comics/chronicles-of-the-demon-faction-f886a8af
+// fetched 2026-07-26. The first anchor is the "First Chapter" shortcut: it is a
+// real chapter link with no "Chapter N" text, and it must not be mistaken for
+// the latest just because it parses.
+const asuraSeriesFixture = `
+<a href="/comics/chronicles-of-the-demon-faction-f886a8af/chapter/1" class="py-3 rounded-md bg-[#E8E8E8]"><svg class="w-4 h-4"></svg>First Chapter</a>
+<a href="/comics/chronicles-of-the-demon-faction-f886a8af/chapter/179" data-astro-prefetch="hover" class="group flex"><span class="font-medium">Chapter 179</span></a>
+<a href="/comics/chronicles-of-the-demon-faction-f886a8af/chapter/181" data-astro-prefetch="hover" class="group flex"><span class="font-medium">Chapter 181</span></a>
+<a href="/comics/chronicles-of-the-demon-faction-f886a8af/chapter/180" data-astro-prefetch="hover" class="group flex"><span class="font-medium">Chapter 180</span></a>
+`
+
+// A chapter link belonging to a different series, of the kind a "you might also
+// like" strip would introduce. Slug scoping must exclude it.
+const asuraCrossSeriesFixture = asuraSeriesFixture + `
+<a href="/comics/some-other-series-aabbccdd/chapter/999" class="group flex"><span>Chapter 999</span></a>
+`
+
+// Trimmed from https://demonicscans.org/manga/Catastrophic-Necromancer fetched
+// 2026-07-26. Note the raw "&", the doubled space after <a, and the decimal
+// chapters, all as they appear live.
+const demonicSeriesFixture = `
+<a  href="/chaptered.php?manga=11799&chapter=0.5" class="chplinks" title="Catastrophic Necromancer 0.5">Chapter 0.5</a>
+<a  href="/chaptered.php?manga=11799&chapter=294" class="chplinks" title="Catastrophic Necromancer 294">Chapter 294</a>
+<a  href="/chaptered.php?manga=11799&amp;chapter=296" class="chplinks" title="Catastrophic Necromancer 296">Chapter 296</a>
+<a  href="/chaptered.php?manga=11799&chapter=295" class="chplinks" title="Catastrophic Necromancer 295">Chapter 295</a>
+`
+
+// What Cloudflare serves instead of the page when an IP's bot score flips.
+const challengeFixture = `<!DOCTYPE html><html><head><title>Just a moment...</title>
+<script src="/cdn-cgi/challenge-platform/h/b/orchestrate/chl_page/v1"></script></head>
+<body><div id="challenge-running">Checking your browser</div></body></html>`
+
+func TestLatestChapterFrom(t *testing.T) {
+	const asuraURL = "https://asurascans.com/comics/chronicles-of-the-demon-faction-f886a8af"
+	const demonicURL = "https://demonicscans.org/manga/Catastrophic-Necromancer"
+
+	tests := []struct {
+		name      string
+		site      string
+		seriesURL string
+		body      string
+		wantOK    bool
+		wantNum   float64
+		wantLabel string
+	}{
+		{
+			name: "asura takes the max, not the last listed",
+			site: "asura", seriesURL: asuraURL, body: asuraSeriesFixture,
+			wantOK: true, wantNum: 181, wantLabel: "Chapter 181",
+		},
+		{
+			name: "asura ignores another series' chapter links",
+			site: "asura", seriesURL: asuraURL, body: asuraCrossSeriesFixture,
+			wantOK: true, wantNum: 181, wantLabel: "Chapter 181",
+		},
+		{
+			name: "asura with an unparseable series url",
+			site: "asura", seriesURL: "https://asurascans.com/", body: asuraSeriesFixture,
+			wantOK: false,
+		},
+		{
+			name: "demonic takes the max across raw and escaped ampersands",
+			site: "demonic", seriesURL: demonicURL, body: demonicSeriesFixture,
+			wantOK: true, wantNum: 296, wantLabel: "Chapter 296",
+		},
+		{
+			name: "demonic keeps decimal chapters parseable",
+			site: "demonic", seriesURL: demonicURL,
+			body:   `<a href="/chaptered.php?manga=11799&chapter=0.5">Chapter 0.5</a>`,
+			wantOK: true, wantNum: 0.5, wantLabel: "Chapter 0.5",
+		},
+		{
+			name: "empty body",
+			site: "asura", seriesURL: asuraURL, body: "",
+			wantOK: false,
+		},
+		{
+			name: "cloudflare challenge page",
+			site: "asura", seriesURL: asuraURL, body: challengeFixture,
+			wantOK: false,
+		},
+		{
+			name: "demonic markup handed to the asura rule",
+			site: "asura", seriesURL: asuraURL, body: demonicSeriesFixture,
+			wantOK: false,
+		},
+		{
+			name: "unknown site",
+			site: "mangadex", seriesURL: "https://example.com/x", body: asuraSeriesFixture,
+			wantOK: false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, ok := latestChapterFrom(tt.site, tt.seriesURL, tt.body)
+			if ok != tt.wantOK {
+				t.Fatalf("ok = %v, want %v (got %+v)", ok, tt.wantOK, got)
+			}
+			if !tt.wantOK {
+				return
+			}
+			if got.Num != tt.wantNum {
+				t.Errorf("Num = %v, want %v", got.Num, tt.wantNum)
+			}
+			if got.Label != tt.wantLabel {
+				t.Errorf("Label = %q, want %q", got.Label, tt.wantLabel)
+			}
+		})
+	}
+}