feat: one registry entry per Site, derived browser route and gate (#94)
Collapse the six per-site comparison points into a sites map in sites.go: Latest Chapter parse, Cover parse, browser-backed list, fetcher route, host pins, and the browser payload read all become lookups into it. All six hosts are now pinned in fetchableSeriesURL; asura/demonic/comix were previously accepted on any https host.
This commit is contained in:
@@ -8,6 +8,8 @@ import (
|
||||
"regexp"
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"github.com/chromedp/chromedp"
|
||||
)
|
||||
|
||||
// latestChapter is the newest chapter a series page advertises.
|
||||
@@ -16,6 +18,40 @@ type latestChapter struct {
|
||||
Label string
|
||||
}
|
||||
|
||||
// site answers the fixed questions every series-page read asks of its Site
|
||||
// (ADR-0009): the host its addresses must carry, how to find the Latest
|
||||
// Chapter and the Cover address in a body, and — for a Site behind a
|
||||
// JavaScript challenge — how to read its payload from a cleared tab. One
|
||||
// entry describes everything about one Site, and nowhere else gets to compare
|
||||
// the site string.
|
||||
type site struct {
|
||||
// Host is the exact hostname a series_url for this Site must carry.
|
||||
Host string
|
||||
// LatestChapter finds the newest chapter in a fetched body.
|
||||
LatestChapter func(seriesURL, body string) (latestChapter, bool)
|
||||
// Cover finds the Cover address in a fetched body.
|
||||
Cover func(seriesURL, body string) (string, bool)
|
||||
// Browser reads this Site's payload from a cleared browser tab; nil
|
||||
// means the page is fetched over plain TLS.
|
||||
Browser *browserRead
|
||||
}
|
||||
|
||||
type browserRead struct {
|
||||
// Read builds the tab read for seriesURL, refusing (false) an address
|
||||
// this Site will not open in a browser — the per-Site half of the SSRF
|
||||
// gate, kept deliberately behind fetchableSeriesURL: a headless browser
|
||||
// executes JavaScript and carries cookies, and series_url is
|
||||
// client-supplied.
|
||||
Read func(seriesURL string, out *string) (chromedp.Action, bool)
|
||||
// Done reports whether the payload arrived.
|
||||
Done func(body string) bool
|
||||
// Fallback allows the plain-TLS fetcher when no browser is configured.
|
||||
// False skips the Site instead. kagane is false — a plain fetch would
|
||||
// only ever retrieve a challenge page — and novelfull is true, because
|
||||
// its challenge is a live time-varying fact (AGENTS.md).
|
||||
Fallback bool
|
||||
}
|
||||
|
||||
// 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 build-hash suffix (e.g. "-f886a8af") that
|
||||
@@ -66,7 +102,7 @@ var novelfullSlugRe = regexp.MustCompile(`^/([^/?#]+)\.html$`)
|
||||
// under several Chapter Slugs (measured 2026-08-11: a sampled novel serves
|
||||
// 1-99 under one slug and 100-423 under another), so no stored-slug pattern can
|
||||
// cover a Series' whole list. An unscoped match is safe because
|
||||
// latestChapterFrom truncates the body at the comment thread before scanning
|
||||
// lnwLatestChapter truncates the body at the comment thread before scanning
|
||||
// (lnwCommentMarker); without that, a visitor's comment could set the Latest
|
||||
// Chapter on the shared Series row.
|
||||
var lnwChapterRe = regexp.MustCompile(`lightnovelworld\.net/[a-z0-9-]+-chapter-([0-9.]+)/`)
|
||||
@@ -80,86 +116,16 @@ var lnwChapterRe = regexp.MustCompile(`lightnovelworld\.net/[a-z0-9-]+-chapter-(
|
||||
// body is skipped, never scanned whole.
|
||||
const lnwCommentMarker = "wpd-threads"
|
||||
|
||||
// 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.
|
||||
// maxChapter returns the highest chapter number the regex finds in body. A
|
||||
// maximum rather than a first or last, ported from the userscript's
|
||||
// latestChapterFromAnchors (asura L123-133, demonic L183-193): 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. For asura, 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. demonic has no
|
||||
// such guarantee — demonicChapterRe matches any chaptered.php?manga=<id> anchor
|
||||
// with no per-series scoping, because the stored series_id for demonic is a
|
||||
// slug, not the numeric id the URL carries, so it cannot easily be scoped.
|
||||
// lightnovelworld is unscoped and body-truncated instead — see lnwChapterRe.
|
||||
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
|
||||
}
|
||||
// Stored URLs predating a redeploy may carry a stale build hash;
|
||||
// chapter hrefs in the fetched body carry the current one. Strip to
|
||||
// the stable ID and make the hash optional in the pattern, so scoping
|
||||
// survives rotations.
|
||||
slug := asuraBuildHash.ReplaceAllString(m[1], "")
|
||||
// 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(slug) + `(?:-[0-9a-f]{8})?/chapter/([0-9.]+)`)
|
||||
case "demonic":
|
||||
re = demonicChapterRe
|
||||
case "comix":
|
||||
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.
|
||||
re = regexp.MustCompile(`"latestChapterUrl":"/title/` + regexp.QuoteMeta(id) + `-[^"]*-chapter-([0-9.]+)"`)
|
||||
case "kagane":
|
||||
re = kaganeChapterRe
|
||||
case "novelfull":
|
||||
u, err := url.Parse(seriesURL)
|
||||
if err != nil {
|
||||
return latestChapter{}, false
|
||||
}
|
||||
m := novelfullSlugRe.FindStringSubmatch(u.Path)
|
||||
if m == nil {
|
||||
return latestChapter{}, false
|
||||
}
|
||||
// Scoped to this series' slug for the same reason asura is: page 1
|
||||
// carries a "latest chapters" widget and a "you may also like" strip,
|
||||
// and neither may contribute to the maximum.
|
||||
re = regexp.MustCompile(`/` + regexp.QuoteMeta(m[1]) + `/chapter-([0-9.]+)`)
|
||||
case "lightnovelworld":
|
||||
// The comment thread below the chapter list is the one region of the
|
||||
// page any visitor can write to, so the scan never reads past it (see
|
||||
// lnwChapterRe). A body without the marker is skipped, never scanned
|
||||
// whole — a redesign must degrade into staleness, not into a wrong
|
||||
// shared value; the logged body length tells a markup change from a
|
||||
// body the size cap cut short.
|
||||
i := strings.Index(body, lnwCommentMarker)
|
||||
if i < 0 {
|
||||
log.Printf("latest poll %q: no %s marker in %d bytes", seriesURL, lnwCommentMarker, len(body))
|
||||
return latestChapter{}, false
|
||||
}
|
||||
body = body[:i]
|
||||
re = lnwChapterRe
|
||||
default:
|
||||
return latestChapter{}, false
|
||||
}
|
||||
|
||||
// shortcut, which points at chapter/1 and therefore can never win a maximum,
|
||||
// so it is redundant once a maximum is taken.
|
||||
func maxChapter(re *regexp.Regexp, body string) (latestChapter, bool) {
|
||||
var best latestChapter
|
||||
found := false
|
||||
for _, m := range re.FindAllStringSubmatch(body, -1) {
|
||||
@@ -178,6 +144,91 @@ func latestChapterFrom(site, seriesURL, body string) (latestChapter, bool) {
|
||||
return best, found
|
||||
}
|
||||
|
||||
// asuraLatestChapter scopes chapter links to this series' own slug, which
|
||||
// replaces the userscript's anchor-text check with a stronger guarantee: a
|
||||
// chapter link belonging to some other series cannot contribute even if the
|
||||
// page starts carrying them.
|
||||
func asuraLatestChapter(seriesURL, body string) (latestChapter, bool) {
|
||||
m := asuraSlugRe.FindStringSubmatch(seriesURL)
|
||||
if m == nil {
|
||||
return latestChapter{}, false
|
||||
}
|
||||
// Stored URLs predating a redeploy may carry a stale build hash; chapter
|
||||
// hrefs in the fetched body carry the current one. Strip to the stable ID
|
||||
// and make the hash optional in the pattern, so scoping survives
|
||||
// rotations.
|
||||
slug := asuraBuildHash.ReplaceAllString(m[1], "")
|
||||
// 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(slug) + `(?:-[0-9a-f]{8})?/chapter/([0-9.]+)`)
|
||||
return maxChapter(re, body)
|
||||
}
|
||||
|
||||
// demonicLatestChapter is not scoped: demonicChapterRe matches any
|
||||
// chaptered.php?manga=<id> anchor, because the stored series_id is a slug,
|
||||
// not the numeric id the URL carries, so it cannot be scoped.
|
||||
func demonicLatestChapter(_, body string) (latestChapter, bool) {
|
||||
return maxChapter(demonicChapterRe, body)
|
||||
}
|
||||
|
||||
// comixLatestChapter reads comix's 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.
|
||||
func comixLatestChapter(seriesURL, body string) (latestChapter, bool) {
|
||||
id, ok := comixSeriesID(seriesURL)
|
||||
if !ok {
|
||||
return latestChapter{}, false
|
||||
}
|
||||
re := regexp.MustCompile(`"latestChapterUrl":"/title/` + regexp.QuoteMeta(id) + `-[^"]*-chapter-([0-9.]+)"`)
|
||||
return maxChapter(re, body)
|
||||
}
|
||||
|
||||
func kaganeLatestChapter(_, body string) (latestChapter, bool) {
|
||||
return maxChapter(kaganeChapterRe, body)
|
||||
}
|
||||
|
||||
// novelfullLatestChapter is scoped to this series' slug for the same reason
|
||||
// asura is: page 1 carries a "latest chapters" widget and a "you may also
|
||||
// like" strip, and neither may contribute to the maximum.
|
||||
func novelfullLatestChapter(seriesURL, body string) (latestChapter, bool) {
|
||||
u, err := url.Parse(seriesURL)
|
||||
if err != nil {
|
||||
return latestChapter{}, false
|
||||
}
|
||||
m := novelfullSlugRe.FindStringSubmatch(u.Path)
|
||||
if m == nil {
|
||||
return latestChapter{}, false
|
||||
}
|
||||
re := regexp.MustCompile(`/` + regexp.QuoteMeta(m[1]) + `/chapter-([0-9.]+)`)
|
||||
return maxChapter(re, body)
|
||||
}
|
||||
|
||||
// lnwLatestChapter truncates the body at the comment thread before scanning:
|
||||
// it is the one region of the page any visitor can write to (see lnwChapterRe).
|
||||
// A body without the marker is skipped, never scanned whole — a redesign must
|
||||
// degrade into staleness, not into a wrong shared value; the logged body length
|
||||
// tells a markup change from a body the size cap cut short.
|
||||
func lnwLatestChapter(seriesURL, body string) (latestChapter, bool) {
|
||||
i := strings.Index(body, lnwCommentMarker)
|
||||
if i < 0 {
|
||||
log.Printf("latest poll %q: no %s marker in %d bytes", seriesURL, lnwCommentMarker, len(body))
|
||||
return latestChapter{}, false
|
||||
}
|
||||
return maxChapter(lnwChapterRe, body[:i])
|
||||
}
|
||||
|
||||
// latestChapterFrom returns the highest chapter number body advertises for this
|
||||
// series, via the Site's registry entry. 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.
|
||||
func latestChapterFrom(site, seriesURL, body string) (latestChapter, bool) {
|
||||
if fn := sites[site].LatestChapter; fn != nil {
|
||||
return fn(seriesURL, body)
|
||||
}
|
||||
return latestChapter{}, false
|
||||
}
|
||||
|
||||
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*'([^']*)'`)
|
||||
@@ -257,24 +308,40 @@ func comixCoverURL(seriesURL, body string) string {
|
||||
return publishedCoverURL(detail.Poster.Medium)
|
||||
}
|
||||
|
||||
// coverFrom reports false for unknown sites, challenge bodies, and pages with
|
||||
// no usable cover. Metadata extraction keeps scanning after an empty match so
|
||||
// a later published cover is not hidden by an empty tag.
|
||||
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)
|
||||
}
|
||||
// ogImageCover reads the og:image metadata shared by asura, demonic and
|
||||
// lightnovelworld.
|
||||
func ogImageCover(_, body string) (string, bool) {
|
||||
cover := metaContent(body, "property", "og:image")
|
||||
return cover, cover != ""
|
||||
}
|
||||
|
||||
func novelfullCoverEntry(_, body string) (string, bool) {
|
||||
cover := metaContent(body, "name", "image")
|
||||
return cover, cover != ""
|
||||
}
|
||||
|
||||
func comixCoverEntry(seriesURL, body string) (string, bool) {
|
||||
cover := comixCoverURL(seriesURL, body)
|
||||
return cover, cover != ""
|
||||
}
|
||||
|
||||
func kaganeCoverEntry(_, body string) (string, bool) {
|
||||
cover := kaganeCoverURL(body)
|
||||
return cover, cover != ""
|
||||
}
|
||||
|
||||
// coverFrom reports false for unknown sites, challenge bodies, and pages with
|
||||
// no usable cover, via the Site's registry entry.
|
||||
func coverFrom(site, seriesURL, body string) (string, bool) {
|
||||
if fn := sites[site].Cover; fn != nil {
|
||||
return fn(seriesURL, body)
|
||||
}
|
||||
return "", false
|
||||
}
|
||||
|
||||
// metaContent returns the content of the first <meta> whose attrName is
|
||||
// attrValue. It keeps scanning after an empty match so a later published cover
|
||||
// is not hidden by an empty tag.
|
||||
func metaContent(body, attrName, attrValue string) string {
|
||||
for _, tag := range metaTagRe.FindAllString(body, -1) {
|
||||
attrs := make(map[string]string)
|
||||
@@ -297,3 +364,68 @@ func publishedCoverURL(value string) string {
|
||||
value = strings.TrimSpace(html.UnescapeString(value))
|
||||
return strings.ReplaceAll(value, " ", "%20")
|
||||
}
|
||||
|
||||
// sites is the registry: one entry per Site, keyed by the stored site string.
|
||||
// Adding a Site means adding an entry here and nowhere else — the dispatch
|
||||
// functions above and the poller's route list are lookups into this map. An
|
||||
// unknown site string resolves to the zero entry, which fails the existing
|
||||
// not-fetchable and no-fetcher paths unchanged.
|
||||
var sites = map[string]site{
|
||||
"asura": {
|
||||
Host: "asurascans.com",
|
||||
LatestChapter: asuraLatestChapter,
|
||||
Cover: ogImageCover,
|
||||
},
|
||||
"demonic": {
|
||||
Host: "demonicscans.org",
|
||||
LatestChapter: demonicLatestChapter,
|
||||
Cover: ogImageCover,
|
||||
},
|
||||
"comix": {
|
||||
Host: "comix.to",
|
||||
LatestChapter: comixLatestChapter,
|
||||
Cover: comixCoverEntry,
|
||||
},
|
||||
"kagane": {
|
||||
Host: "kagane.to",
|
||||
LatestChapter: kaganeLatestChapter,
|
||||
Cover: kaganeCoverEntry,
|
||||
Browser: &browserRead{
|
||||
Read: kaganeRead,
|
||||
Done: func(body string) bool { return body != "" },
|
||||
// Never falls back: a plain fetch of a kagane page or cover would
|
||||
// only ever retrieve a challenge page (verified 2026-08-03).
|
||||
Fallback: false,
|
||||
},
|
||||
},
|
||||
"novelfull": {
|
||||
Host: "novelfull.com",
|
||||
LatestChapter: novelfullLatestChapter,
|
||||
Cover: novelfullCoverEntry,
|
||||
Browser: &browserRead{
|
||||
Read: novelfullRead,
|
||||
// The interstitial has a DOM too, so "the payload arrived" has to
|
||||
// exclude it explicitly.
|
||||
Done: func(body string) bool { return body != "" && !isInterstitial(body) },
|
||||
Fallback: true,
|
||||
},
|
||||
},
|
||||
"lightnovelworld": {
|
||||
Host: "lightnovelworld.net",
|
||||
LatestChapter: lnwLatestChapter,
|
||||
Cover: ogImageCover,
|
||||
},
|
||||
}
|
||||
|
||||
// browserBackedSites is derived from the registry: the Sites whose pages are
|
||||
// read through the browser sidecar, which are also the ones granted the longer
|
||||
// cooldown.
|
||||
func browserBackedSites() []string {
|
||||
out := make([]string, 0, len(sites))
|
||||
for name, s := range sites {
|
||||
if s.Browser != nil {
|
||||
out = append(out, name)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user