Files
SaveAny-Bot/parsers/native/kemono/kemono.go
T
Krau c2f8ab3c01 refactor: quality overhaul (#234)
* fix: prevent queue deadlock after cancelling tasks

Get no longer recurses while holding the mutex.
Cancelled queued tasks leave the map, making their IDs reusable.
Closed empty queues return ErrQueueClosed.

* fix: init task queue lazily and close on shutdown

AddTask is safe before Run by initializing the queue once.
Close unblocks workers waiting in Get.

* fix: make resource fingerprints deterministic

Sort map keys before hashing so Resource.ID is stable.

* fix: harden per-item processing tracking in tasks

Use the resource fingerprint as the dedup key on insert and delete.
Check and set processing entries atomically instead of TOCTOU.
Count only successful downloads.

* fix: honor IgnoreErrors in batch tasks

Element failures no longer cancel sibling elements or stop later groups.

* fix: report streamed upload bytes in batch tasks

Stream downloads report their byte count as the upload total.

* fix: validate i18n key parity across locales

geni18n fails when a language file misses any key.
Align the syncpeers completion key between en and zh-Hans.
Translate three untranslated parse keys in zh-Hans.

* refactor: share progress throttling helpers

Move size-tiered and count-based throttling into progressutil.
Localize hardcoded Chinese progress strings.
Drop five duplicated implementations and dead local copies.

* refactor: share unique filename logic

Storage backends use fsutil.UniquePath instead of local loops.

* fix: sanitize local storage paths

Reject absolute paths and dot-dot escapes in Save.
Check close errors and wrap creation failures.

* fix: preserve webdav error causes

Wrap mkdir and write failures with %w and drop dead error values.

* fix: kill rclone subprocess on reader close

Prevent cat processes from hanging after the pipe is closed.

* fix: fail alist init instead of exiting

Replace log.Fatalf with wrapped errors so a bad alist cannot kill the bot.
Cancel token refresh with the init context and re-login on 401.

* fix: enforce telegram album limits and track saved paths

Use tglimit.MaxAlbumItems for album batching and video splitting.
Exists now reports previously saved paths instead of always false.

* fix: guard storage registry maps

Protect Storages and UserStorages with mutexes and expose read accessors.

* fix: harden JS parser plugin runtime

Validate semver instead of panicking and require canHandle.
Recover plugin worker panics and time out CanHandle calls.
Return a copy from the registry and sanitize install filenames.

* fix: guard kemono parser against nil fields

Skip sparse preview and attachment entries instead of panicking.

* refactor: remove commented-out dead code

Drop unused kemono legacy types and commented response structs.

* test: cover invalid plugin version rejection

* fix: show all queued tasks in /task list

Render up to ten tasks and append the truncation note once.

* fix: guard callback data parsing

Reject malformed callback payloads before indexing split parts.

* fix: isolate media groups per user

Key pending groups by chat, user and group id.

* fix: require permission for callback handlers

* fix: initialize userbot context once

Replace the racy lazy init with sync.OnceValue.

* fix: avoid leaking raw errors in /dir reply

* fix: notify users on invalid update version

* fix: fail fast when API listen fails

Bind synchronously and surface errors instead of logging them.

* fix: add timeouts and backoff to webhook delivery

* refactor: remove dead code from api and bot

Drop the empty ProgressTracker shim, unused token context key and a redundant SetBotCommands call.

* fix: load remote config without local lookup

Skip the local file search after reading a config URL and add a timeout.

* refactor: drop unused hook config

* docs: document parser plugin config

* ci: fix BuildTime formatting and align checkout

Actions format does not format dates; pass the raw timestamp.

* chore: ignore cache directory

* fix: make cache init idempotent

* fix: upload only downloaded batch elements

Failed elements keep partial cache files and never reach the backend.
Successfully downloaded siblings still upload when one element fails.

* fix: record telegram saved paths only after upload

Skip-large returns a sentinel so skipped files are not marked as saved.

* fix: deduplicate alist token refreshes

Guard token access with a mutex and merge concurrent logins.
Reuse a recent refresh to avoid login storms.

* test: cover concurrent alist 401 retry

Ten parallel uploads share a single re-login under -race.

* fix: count parsed resources in progress text

* fix: localize storage lookup errors in /dir

Use the shared i18n key and escape the dynamic error.

* fix: deduplicate concurrent storage initialization

singleflight merges first-time inits so side effects are not duplicated.

* fix: guard nil progress trackers in api-created tasks

Batch, telegraph and transfer tasks run without a Telegram tracker
when created through the API; their callbacks must not panic.

* fix: keep album order when filtering failed batch items

Download results are stored by original index so surviving
elements keep their source order.

* test: cover nil-tracker task execution

* fix: report partial failure in batch done message

IgnoreErrors runs with failed elements show success and failed
counts instead of claiming every file completed.

* fix: skip login refresh for token-only alist storage

401 responses surface the auth error instead of sending a
credential-less login; the refresh window never exceeds TokenExp.

* test: cover alist refresh semantics

Concurrent refresh uses username/password; token-only storage
never attempts a login on 401.

* fix: call tracker from notifyProgress instead of recursing

The helper called itself, overflowing the stack on any batch
task with a progress tracker.

* fix: propagate cancellation past IgnoreErrors

Cancelled tasks must not be reported as successful: only
ordinary element failures are ignored.

* test: cover notifyProgress tracker call

* test: cover cancellation with IgnoreErrors

* fix: refresh alist token after startup 401s

The init login no longer satisfies the dedup window, so an
early 401 triggers a real refresh; later 401s reuse it.
Clarify that streaming uploads cannot replay their body.

* test: exercise the alist 401 refresh path

Concurrent uploads now reject the init token, share one
refresh and retry with the new token; token-only stays inert.

* style: trim verbose comments

Drop process-style explanations; keep one-line behavior notes.

* style: gofmt test files

* fix: drop unbounded saved-path cache in telegram storage

Telegram cannot reliably query remote file existence, so the
cache answered a question it could not answer and grew without
bound. Exists returns false again, as before.

* style: format codes
2026-08-17 19:10:03 +08:00

183 lines
5.0 KiB
Go

package kemono
import (
"context"
"encoding/json"
"errors"
"fmt"
"net/http"
"net/url"
"path"
"strings"
"github.com/charmbracelet/log"
"github.com/duke-git/lancet/v2/strutil"
"github.com/krau/SaveAny-Bot/common/utils/netutil"
"github.com/krau/SaveAny-Bot/pkg/parser"
)
type KemonoParser struct{}
var (
kemonoDomains = []string{
"kemono.su",
"kemono.cr",
}
ErrFailedToExtractInfo = errors.New("failed to extract download info from URL")
)
const (
kemonoApiBase = "https://kemono.cr/api/v1"
)
func (k *KemonoParser) CanHandle(text string) bool {
text = strings.TrimPrefix(text, "https://")
text = strings.TrimPrefix(text, "http://")
var matchesDomain bool
for _, domain := range kemonoDomains {
if strings.Contains(text, domain) {
matchesDomain = true
break
}
}
if !matchesDomain {
return false
}
var path string
for _, domain := range kemonoDomains {
if _, after, ok := strings.Cut(text, domain); ok {
remaining := after
if len(remaining) > 0 && remaining[0] == '/' {
path = remaining[1:]
}
break
}
}
if path == "" {
return false
}
parts := strings.Split(path, "/")
// servicename/user/id (user profile page)
// servicename/user/id/post/id (post page)
return len(parts) == 3 || (len(parts) == 5 && parts[3] == "post")
}
func (k *KemonoParser) Parse(ctx context.Context, u string) (*parser.Item, error) {
info := extractDownloadInfoFromURL(u)
if info == nil {
return nil, ErrFailedToExtractInfo
}
if info.PostID != "" {
return k.parseOne(ctx, info)
}
return k.parseUserPage(ctx, info)
}
func (k *KemonoParser) parseOne(ctx context.Context, info *DownloadInfo) (*parser.Item, error) {
client := netutil.DefaultParserHTTPClient()
endpoint := fmt.Sprintf("%s/%s/user/%s/post/%s", kemonoApiBase, info.ServiceName, info.UserID, info.PostID)
req, err := http.NewRequestWithContext(ctx, http.MethodGet, endpoint, nil)
if err != nil {
return nil, fmt.Errorf("failed to create request to Kemono API: %w", err)
}
req.Header.Set("Accept", "text/css")
resp, err := client.Do(req)
if err != nil {
return nil, fmt.Errorf("failed to fetch Kemono API: %w", err)
}
defer resp.Body.Close()
if resp.StatusCode != http.StatusOK {
return nil, fmt.Errorf("failed to fetch Kemono API, status code: %d", resp.StatusCode)
}
var postInfo PostInfo
if err := json.NewDecoder(resp.Body).Decode(&postInfo); err != nil {
return nil, fmt.Errorf("failed to decode Kemono API response: %w", err)
}
item := &parser.Item{
Site: "kemono",
Title: postInfo.Post.Title,
URL: fmt.Sprintf("https://kemono.cr/%s/user/%s/post/%s", info.ServiceName, info.UserID, info.PostID),
Author: postInfo.Post.User, // [TODO] request user profile
Description: postInfo.Post.Content,
Tags: func() []string {
if postInfo.Post.Tags != nil {
return *postInfo.Post.Tags
}
return nil
}(),
}
resources := make([]parser.Resource, 0)
for _, attachment := range postInfo.Attachments {
if attachment.Server == nil || attachment.Path == nil || attachment.Name == nil {
continue
}
var size int64
fileUrl := fmt.Sprintf("%s/data%s", *attachment.Server, *attachment.Path)
headReq, err := http.NewRequestWithContext(ctx, http.MethodHead, fileUrl, nil)
if err == nil {
resp, err := client.Do(headReq)
if err == nil {
size = resp.ContentLength
resp.Body.Close()
}
}
resources = append(resources, parser.Resource{
URL: fmt.Sprintf("%s/data%s", *attachment.Server, *attachment.Path),
Filename: *attachment.Name,
Size: size,
})
}
picCdnMap := make(map[string]string)
for _, preview := range postInfo.Previews {
if preview.Type == nil || *preview.Type != "thumbnail" {
continue
}
if preview.Path == nil || preview.Server == nil {
log.FromContext(ctx).Warnf("Skipping kemono preview with missing path or server: post %s", info.PostID)
continue
}
picCdnMap[*preview.Path] = *preview.Server
}
for _, attachment := range postInfo.Post.Attachments {
if attachment.Path == nil || attachment.Name == nil {
log.FromContext(ctx).Warnf("Skipping kemono post attachment with missing path or name: post %s", info.PostID)
continue
}
if !isImageExt(*attachment.Path) {
continue
}
picUrl, err := url.JoinPath(picCdnMap[*attachment.Path], "data", *attachment.Path)
if err != nil {
continue
}
var size int64
headReq, err := http.NewRequestWithContext(ctx, http.MethodHead, picUrl, nil)
if err == nil {
resp, err := client.Do(headReq)
if err == nil {
size = resp.ContentLength
resp.Body.Close()
}
}
resources = append(resources, parser.Resource{
URL: picUrl,
Filename: *attachment.Name,
Size: size,
})
}
item.Resources = resources
return item, nil
}
func (k *KemonoParser) parseUserPage(_ context.Context, _ *DownloadInfo) (*parser.Item, error) {
return nil, errors.New("kemono user page not implemented")
}
func isImageExt(attachmentPath string) bool {
return strutil.HasSuffixAny(path.Ext(strings.Split(attachmentPath, "?")[0]), []string{".jpg", ".jpeg", ".png", ".webp"})
}