chore: initial commit for asepharyana-hub-scraper
This commit is contained in:
@@ -0,0 +1,24 @@
|
|||||||
|
name: Notify Parent Repo
|
||||||
|
|
||||||
|
on:
|
||||||
|
push:
|
||||||
|
branches:
|
||||||
|
- main
|
||||||
|
|
||||||
|
jobs:
|
||||||
|
dispatch:
|
||||||
|
runs-on: ubuntu-latest
|
||||||
|
steps:
|
||||||
|
- name: Trigger root monorepo build
|
||||||
|
uses: peter-evans/repository-dispatch@v3
|
||||||
|
with:
|
||||||
|
token: ${{ secrets.DISPATCH_TOKEN }}
|
||||||
|
repository: MythEclipse/ultimate-asepharyana.tech
|
||||||
|
event-type: submodule-updated
|
||||||
|
client-payload: |
|
||||||
|
{
|
||||||
|
"service": "scraper-api",
|
||||||
|
"ref": "${{ github.ref }}",
|
||||||
|
"sha": "${{ github.sha }}",
|
||||||
|
"actor": "${{ github.actor }}"
|
||||||
|
}
|
||||||
+67
@@ -0,0 +1,67 @@
|
|||||||
|
apps/gmw/
|
||||||
|
# See https://docs.github.com/en/get-started/getting-started-with-git/ignoring-files for more about ignoring files.
|
||||||
|
|
||||||
|
# compiled output
|
||||||
|
dist
|
||||||
|
tmp
|
||||||
|
out-tsc
|
||||||
|
error.log
|
||||||
|
# dependencies
|
||||||
|
node_modules
|
||||||
|
.bun/**
|
||||||
|
.turbo/
|
||||||
|
# IDEs and editors
|
||||||
|
/.idea
|
||||||
|
.project
|
||||||
|
.classpath
|
||||||
|
.c9/
|
||||||
|
*.launch
|
||||||
|
.settings/
|
||||||
|
*.sublime-workspace
|
||||||
|
**/target/**
|
||||||
|
# IDE - VSCode
|
||||||
|
.vscode/*
|
||||||
|
!.vscode/settings.json
|
||||||
|
!.vscode/tasks.json
|
||||||
|
!.vscode/launch.json
|
||||||
|
!.vscode/extensions.json
|
||||||
|
|
||||||
|
# misc
|
||||||
|
/.sass-cache
|
||||||
|
/connect.lock
|
||||||
|
/coverage
|
||||||
|
/libpeerconnection.log
|
||||||
|
npm-debug.log
|
||||||
|
yarn-error.log
|
||||||
|
testem.log
|
||||||
|
/typings
|
||||||
|
|
||||||
|
# System Files
|
||||||
|
.DS_Store
|
||||||
|
Thumbs.db
|
||||||
|
.claude
|
||||||
|
# Next.js
|
||||||
|
.next
|
||||||
|
out
|
||||||
|
**/.codegraph/**
|
||||||
|
**/.claude/**
|
||||||
|
test-output
|
||||||
|
**/**.env
|
||||||
|
**/**.env.**
|
||||||
|
vite.config.*.timestamp*
|
||||||
|
vitest.config.*.timestamp*
|
||||||
|
|
||||||
|
|
||||||
|
storybook-static
|
||||||
|
~/.bun/**
|
||||||
|
docs/dependency-map.md
|
||||||
|
docs/handoff-log.jsonl
|
||||||
|
docs/observability.md
|
||||||
|
docs/quality-gates.json
|
||||||
|
docs/workflow-state.json
|
||||||
|
docs/todo.md
|
||||||
|
**/vendor/
|
||||||
|
|
||||||
|
# moonrepo
|
||||||
|
.moon/cache
|
||||||
|
.~moon**
|
||||||
@@ -0,0 +1,27 @@
|
|||||||
|
# AGENT.md - Universal AI Entry Point
|
||||||
|
|
||||||
|
This document serves as the unified entry point for all AI agents (Gemini, Claude, GPT, etc.) interacting with the **Scraping & CDN Service**.
|
||||||
|
|
||||||
|
## 🚀 Mission Statement
|
||||||
|
|
||||||
|
To provide a specialized, zero-bloat backend engine for high-concurrency web scraping and image persistent caching.
|
||||||
|
|
||||||
|
## 🛑 Global AI Protocols
|
||||||
|
|
||||||
|
As an AI agent, you **MUST** adhere to the following when working on this codebase:
|
||||||
|
|
||||||
|
1. **Professionalism**: Maintain a factual, technical, and objective tone.
|
||||||
|
2. **No Hyperbole**: Prohibited from using marketing-speak or exaggerated praise (e.g., "amazing", "powerful").
|
||||||
|
3. **Minimalism**: Prioritize the **Zero-Bloat Policy**. If a request adds unnecessary complexity or dependencies, challenge the user and suggest a leaner alternative.
|
||||||
|
4. **Zero Suppression**: Never use suppression flags (`#[allow]`, `@ts-ignore`) to bypass warnings. Fix the underlying logic or types.
|
||||||
|
5. **Observability**: Ensure critical business flows emit structured logs and request context where needed.
|
||||||
|
|
||||||
|
## 🔗 Technical Context
|
||||||
|
|
||||||
|
- **Architecture**: [GEMINI.md](file:///mnt/code/bp3/ultimate-asepharyana.tech/apps/scraper/GEMINI.md) (Logic flows, tech stack).
|
||||||
|
- **Maintenance**: [Development Guide](file:///mnt/code/bp3/ultimate-asepharyana.tech/apps/scraper/docs/development.md) (Coding standards).
|
||||||
|
- **Observability**: [Metrics Guide](file:///mnt/code/bp3/ultimate-asepharyana.tech/apps/scraper/docs/observability.md) (Standard telemetry).
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
*If you are an AI assistant, start by reading [GEMINI.md](file:///mnt/code/bp3/ultimate-asepharyana.tech/apps/scraper/GEMINI.md) for the full architectural context.*
|
||||||
@@ -0,0 +1,177 @@
|
|||||||
|
# CLAUDE.md
|
||||||
|
|
||||||
|
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
|
||||||
|
|
||||||
|
## Project Overview
|
||||||
|
|
||||||
|
Scraper service — a Rust/Axum backend for web scraping (anime/komik data extraction) and image proxy/CDN caching. Serves as the backend engine consumed by the `apps/solidjs` frontend.
|
||||||
|
|
||||||
|
## Commands
|
||||||
|
|
||||||
|
```bash
|
||||||
|
# Development
|
||||||
|
cargo run # Start server (binds 0.0.0.0:4091)
|
||||||
|
cargo test # Run all tests
|
||||||
|
cargo clippy -- -D warnings # Lint (warnings are errors)
|
||||||
|
cargo fmt # Auto-format all source files
|
||||||
|
|
||||||
|
# Release build (full LTO, single CGU, stripped)
|
||||||
|
cargo build --release
|
||||||
|
|
||||||
|
# PM2 production
|
||||||
|
pm2 start ecosystem.config.cjs --env production # Uses target/release/scraper
|
||||||
|
```
|
||||||
|
|
||||||
|
## Architecture
|
||||||
|
|
||||||
|
### Modular MVC + Service + Repository
|
||||||
|
|
||||||
|
Setiap module mengikuti arsitektur layered yang identik:
|
||||||
|
|
||||||
|
```
|
||||||
|
Request → Router (route.rs) → Controller → Service → Repository → Parser
|
||||||
|
│
|
||||||
|
├── Redis (L1 cache)
|
||||||
|
├── SeaORM/MySQL (L2, image_cache)
|
||||||
|
└── External HTTP (alqanime.si, picser CDN)
|
||||||
|
```
|
||||||
|
|
||||||
|
### Directory Layout
|
||||||
|
|
||||||
|
```
|
||||||
|
src/
|
||||||
|
├── main.rs # Entry point: builds Application, calls run()
|
||||||
|
├── lib.rs # Public module declarations
|
||||||
|
├── app.rs # Router assembly: modules + metrics + swagger + middleware layers
|
||||||
|
├── bootstrap/mod.rs # Application::build(): tracing, Redis, browser pool, DB, AppState
|
||||||
|
├── modules/ # Feature modules (vertical slices)
|
||||||
|
│ ├── anime/ # Otakudesu anime scraper
|
||||||
|
│ ├── anime2/ # Alqanime.si anime scraper
|
||||||
|
│ ├── komik/ # Komik scraper
|
||||||
|
│ └── proxy/ # Image proxy/cache/audit endpoints
|
||||||
|
└── shared/ # Cross-cutting infrastructure
|
||||||
|
├── config/ # Lazy-static AppConfig from env vars (fail-fast at startup)
|
||||||
|
├── state/ # AppState (redis_pool, db, semaphore, event_bus)
|
||||||
|
├── database/
|
||||||
|
│ ├── traits/ # ScrapingRepository, ImageCacheRepository (async_trait)
|
||||||
|
│ ├── repositories/ # SeaOrmImageCacheRepository (impl ImageCacheRepository)
|
||||||
|
│ └── persistence/ # SeaORM entities (image_cache)
|
||||||
|
├── services/images/ # ImageCache service + apply_cached_posters helper
|
||||||
|
├── errors/ # AppError enum → axum IntoResponse (500/404 by variant)
|
||||||
|
├── observability/ # Utoipa/Swagger OpenAPI doc
|
||||||
|
├── scheduler/ # Cron jobs (daily cache cleanup at 2 AM)
|
||||||
|
├── browser/ # Headless Chrome pool for JS-rendered scraping
|
||||||
|
├── scrapers/ # Site-specific scrapers (otakudesu)
|
||||||
|
├── utils/ # Cache helper, HTTP client, scraping helpers, retry, conversions
|
||||||
|
├── middlewares/ # Logging, rate limiting
|
||||||
|
├── events/ # EventBus for repair state updates
|
||||||
|
└── types/ # ApiResponse<T>, shared entity types (HasPoster trait, Pagination)
|
||||||
|
```
|
||||||
|
|
||||||
|
### Module Structure (identik untuk setiap module)
|
||||||
|
|
||||||
|
Setiap `src/modules/<name>/`:
|
||||||
|
|
||||||
|
| File | Peran | Pola |
|
||||||
|
|---|---|---|
|
||||||
|
| `route.rs` | Daftar endpoint, mapping URL → controller | `Router<Arc<AppState>>`, tidak ada logic |
|
||||||
|
| `controller.rs` | Extract State/Path/Query/Body, panggil service | `Result<Json<T>, AppError>` |
|
||||||
|
| `service.rs` | Business logic, caching, delegasi ke repository + parser | Struct dengan repo di-inject via constructor `new(repo: XRepository)` |
|
||||||
|
| `repository.rs` | HTTP fetching, URL builders, DB queries | Struct + `impl ScrapingRepository` trait |
|
||||||
|
| `parser.rs` | HTML parsing dengan `scraper` crate | Free functions → `Result<T, AppError>`, via `spawn_blocking` |
|
||||||
|
| `schema.rs` | Validasi query/path/body params | Struct `Deserialize` + `ToSchema` |
|
||||||
|
| `types.rs` | Response structs | `Serialize` + `ToSchema`, `impl HasPoster` jika punya poster |
|
||||||
|
|
||||||
|
### Dependency Injection
|
||||||
|
|
||||||
|
Semua service menerima dependency via constructor:
|
||||||
|
|
||||||
|
```rust
|
||||||
|
// Controller creates and injects dependencies
|
||||||
|
let repo = AnimeRepository::new();
|
||||||
|
let service = AnimeService::new(repo);
|
||||||
|
service.get_anime_index(app_state).await.map(Json)
|
||||||
|
|
||||||
|
// Service stores injected repo
|
||||||
|
pub struct AnimeService {
|
||||||
|
repository: AnimeRepository,
|
||||||
|
}
|
||||||
|
impl AnimeService {
|
||||||
|
pub fn new(repository: AnimeRepository) -> Self { Self { repository } }
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
### Image Caching Architecture
|
||||||
|
|
||||||
|
Single unified image cache system:
|
||||||
|
|
||||||
|
1. **Trait**: `ImageCacheRepository` (`shared/database/traits/image_cache.rs`) — Redis ops, DB ops, locks, cache invalidation
|
||||||
|
2. **Impl**: `SeaOrmImageCacheRepository` (`shared/database/repositories/image_cache.rs`)
|
||||||
|
3. **Service**: `ImageCache` struct (`shared/services/images/cache.rs`) — download, MIME-verify dengan `infer`, upload ke Picser CDN, verifikasi CDN URL (10 retry dengan backoff)
|
||||||
|
4. **Concurrency**: `Semaphore` (default 5 concurrent uploads) + request coalescing via `DashMap<broadcast::Sender>`
|
||||||
|
5. **Lazy batch helper**: `cache_image_urls_batch_lazy()` — Redis batch check → DB batch check → background spawn untuk misses
|
||||||
|
|
||||||
|
### HasPoster Trait & apply_cached_posters
|
||||||
|
|
||||||
|
`HasPoster` trait di `shared/types/entities/anime.rs` memungkinkan generic poster caching:
|
||||||
|
|
||||||
|
```rust
|
||||||
|
pub trait HasPoster {
|
||||||
|
fn poster(&self) -> &str;
|
||||||
|
fn set_poster(&mut self, url: String);
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
Semua item type dengan field `poster` mengimplementasikan trait ini (`OngoingAnimeItem`, `KomikItem`, `FilterAnimeItem`, `Recommendation`, dll).
|
||||||
|
|
||||||
|
`apply_cached_posters()` di `shared/services/images/cache.rs` menerima `&mut [T]` where `T: HasPoster`, menggantikan pola manual ~15 baris yang sebelumnya berulang di setiap service method.
|
||||||
|
|
||||||
|
### ScrapingRepository Trait
|
||||||
|
|
||||||
|
```rust
|
||||||
|
#[async_trait]
|
||||||
|
pub trait ScrapingRepository: Send + Sync {
|
||||||
|
async fn fetch_html(&self, url: &str) -> Result<String, AppError>;
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
Semua module repository (`AnimeRepository`, `Anime2Repository`, `KomikRepository`, `ProxyRepository`) mengimplementasikan trait ini.
|
||||||
|
|
||||||
|
### Error Handling
|
||||||
|
|
||||||
|
`AppError` enum di `src/shared/errors/app_error.rs` — derives `thiserror::Error` dan implements `IntoResponse` (404 untuk `NotFound`, 500 untuk lainnya).
|
||||||
|
|
||||||
|
**Kontrak error per layer:**
|
||||||
|
- **Parser** → `Result<T, AppError>`
|
||||||
|
- **Repository** → `Result<T, AppError>` (via `ScrapingRepository` trait)
|
||||||
|
- **Service** → `Result<T, AppError>` (tidak ada `Result<T, String>` atau `Box<dyn Error>`)
|
||||||
|
- **Controller** → `Result<Json<T>, AppError>` (kecuali proxy yang return raw `Response`)
|
||||||
|
|
||||||
|
### Configuration
|
||||||
|
|
||||||
|
`src/shared/config/mod.rs` — global `CONFIG` lazy-static loaded from:
|
||||||
|
1. `.env` file (dotenvy)
|
||||||
|
2. `config/default.toml` / `config/{RUN_MODE}.toml`
|
||||||
|
3. Environment variables (`APP__` prefix or legacy `DATABASE_URL`/`JWT_SECRET`/`REDIS_URL`)
|
||||||
|
|
||||||
|
Panics at startup if required config is missing — intentional fail-fast design.
|
||||||
|
|
||||||
|
## Constraints
|
||||||
|
|
||||||
|
- **No suppression flags**: `#[allow(...)]`, `#[ignore]`, `@ts-ignore` are prohibited. Fix the underlying issue.
|
||||||
|
- **Lint strictness**: `unsafe_code = "forbid"`, `panic = "deny"`, `todo = "deny"`, `unimplemented = "deny"`, `unwrap_used = "warn"`, `expect_used = "warn"`
|
||||||
|
- **Minimal dependencies**: Before adding a crate, evaluate if existing deps or std can handle it.
|
||||||
|
- **Dead code**: Remove unused functions, types, modules rather than leaving them.
|
||||||
|
- **Performance**: Use `spawn_blocking` for CPU-heavy work (HTML parsing).
|
||||||
|
- **No duplicate infrastructure**: Satu trait, satu impl. Jangan membuat trait/repository duplikat seperti `ImageRepository` dan `ImageCacheRepository` yang berbeda.
|
||||||
|
- **No thin wrappers**: Hindari wrapper tipis seperti `CacheImageUseCase` yang hanya meneruskan panggilan ke service lain.
|
||||||
|
|
||||||
|
## Useful Endpoints
|
||||||
|
|
||||||
|
- `GET /docs` — Swagger UI
|
||||||
|
- `GET /api-docs/openapi.json` — OpenAPI spec
|
||||||
|
- `POST /api/proxy/image-cache` — Cache an image URL
|
||||||
|
- `POST /api/proxy/image-cache/audit` — Audit/repair cached images
|
||||||
|
- `GET /api/anime/*` — Otakudesu scraping endpoints
|
||||||
|
- `GET /api/anime2/*` — Alqanime scraping endpoints
|
||||||
|
- `GET /api/komik/*` — Komik scraping endpoints
|
||||||
Generated
+5564
File diff suppressed because it is too large
Load Diff
+132
@@ -0,0 +1,132 @@
|
|||||||
|
|
||||||
|
[package]
|
||||||
|
name = "scraper-service"
|
||||||
|
version = "0.1.0"
|
||||||
|
edition = "2021"
|
||||||
|
description = "A batteries-included, production-ready Rust web framework built on Axum"
|
||||||
|
authors = ["Asep Haryana"]
|
||||||
|
license = "MIT"
|
||||||
|
repository = "https://github.com/MythEclipse/ultimate-asepharyana.tech"
|
||||||
|
keywords = ["web", "framework", "axum", "api", "rest"]
|
||||||
|
categories = ["web-programming::http-server", "web-programming::websocket"]
|
||||||
|
default-run = "scraper"
|
||||||
|
|
||||||
|
# Dependensi yang dibutuhkan saat aplikasi berjalan
|
||||||
|
[dependencies]
|
||||||
|
axum = { version = "0.8.8", features = ["ws", "multipart", "macros"] }
|
||||||
|
tokio = { version = "1.49.0", features = ["full"] }
|
||||||
|
serde = { version = "1.0", features = ["derive"] }
|
||||||
|
serde_json = "1.0"
|
||||||
|
dotenvy = "0.15"
|
||||||
|
tracing = "0.1"
|
||||||
|
tracing-subscriber = { version = "0.3", features = ["env-filter"] }
|
||||||
|
anyhow = "1.0"
|
||||||
|
# sqlx removed - SeaORM uses it internally via sqlx-postgres feature
|
||||||
|
sea-orm = { version = "1.1.19", features = ["sqlx-postgres", "runtime-tokio-rustls", "macros", "with-chrono", "with-uuid"] }
|
||||||
|
uuid = { version = "1.10.0", features = ["v4", "serde"] }
|
||||||
|
chrono = { version = "0.4", features = ["serde"] }
|
||||||
|
|
||||||
|
bytes = "1.11.0"
|
||||||
|
futures = "0.3"
|
||||||
|
reqwest = { version = "0.12.28", features = ["json", "stream", "multipart"] }
|
||||||
|
http = "1.4.0"
|
||||||
|
sha1 = "0.10.6"
|
||||||
|
data-url = "0.3.2"
|
||||||
|
base64 = "0.22.1"
|
||||||
|
tokio-util = { version = "0.7.18", features = ["codec"] }
|
||||||
|
async-trait = "0.1.89"
|
||||||
|
regex = "1.12.2"
|
||||||
|
infer = "0.19.0"
|
||||||
|
|
||||||
|
once_cell = "1.21.3"
|
||||||
|
urlencoding = "2.1"
|
||||||
|
|
||||||
|
url = "2.5.8"
|
||||||
|
rand = "0.8"
|
||||||
|
tempfile = "3.24.0"
|
||||||
|
mime_guess = "2.0.5"
|
||||||
|
|
||||||
|
tower-http = { version = "0.6.8", features = ["fs", "cors", "compression-gzip", "compression-br", "compression-zstd"] }
|
||||||
|
backoff = { version = "0.4", features = ["futures", "tokio"] }
|
||||||
|
dashmap = "6.1"
|
||||||
|
deadpool-redis = { version = "0.22.1", features = ["serde"] }
|
||||||
|
rayon = "1.11"
|
||||||
|
tl = "0.7.8"
|
||||||
|
tower = { version = "0.5", features = ["make"] }
|
||||||
|
scraper = "0.25.0"
|
||||||
|
flate2 = "1.1"
|
||||||
|
redis = { version = "0.32.7", features = ["tokio-rustls-comp", "safe_iterators"] }
|
||||||
|
thiserror = "2.0.18"
|
||||||
|
itertools = "0.14"
|
||||||
|
clap = { version = "4.5", features = ["derive"] }
|
||||||
|
config = { version = "0.15.19", features = ["toml"] }
|
||||||
|
governor = "0.10.4"
|
||||||
|
tokio-cron-scheduler = "0.15.1"
|
||||||
|
hex = "0.4.3"
|
||||||
|
hmac = "0.12.1"
|
||||||
|
sha2 = "0.10.9"
|
||||||
|
log = "0.4"
|
||||||
|
walkdir = "2.5"
|
||||||
|
utoipa = { version = "5.0", features = ["axum_extras"] }
|
||||||
|
utoipa-swagger-ui = { version = "9.0", features = ["axum"] }
|
||||||
|
utoipa-axum = "0.2.0"
|
||||||
|
|
||||||
|
# OpenTelemetry metrics
|
||||||
|
opentelemetry = { version = "0.27", features = ["metrics"] }
|
||||||
|
opentelemetry_sdk = { version = "0.27", features = ["metrics", "rt-tokio"] }
|
||||||
|
opentelemetry-otlp = { version = "0.27", features = ["metrics"] }
|
||||||
|
opentelemetry-semantic-conventions = "0.27"
|
||||||
|
|
||||||
|
|
||||||
|
# Dependensi yang hanya dibutuhkan untuk build script (build.rs)
|
||||||
|
|
||||||
|
# Dependensi yang hanya dibutuhkan untuk tes
|
||||||
|
[dev-dependencies]
|
||||||
|
sea-orm = { version = "1.1.19", features = ["sqlx-postgres", "runtime-tokio-rustls", "macros", "with-chrono", "with-uuid", "mock"] }
|
||||||
|
|
||||||
|
# Definisi targets secara eksplisit untuk menghindari peringatan cargo-chef (edition/plugin)
|
||||||
|
[lib]
|
||||||
|
name = "scraper_service"
|
||||||
|
path = "src/lib.rs"
|
||||||
|
|
||||||
|
[[bin]]
|
||||||
|
name = "scraper"
|
||||||
|
path = "src/main.rs"
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
[lints.rust]
|
||||||
|
unsafe_code = "forbid"
|
||||||
|
unused_variables = "deny"
|
||||||
|
unused_imports = "deny"
|
||||||
|
unused_must_use = "deny"
|
||||||
|
|
||||||
|
[lints.clippy]
|
||||||
|
unwrap_used = "warn"
|
||||||
|
expect_used = "warn"
|
||||||
|
panic = "deny"
|
||||||
|
todo = "deny"
|
||||||
|
unimplemented = "deny"
|
||||||
|
|
||||||
|
[features]
|
||||||
|
# default = ["ffmpeg"]
|
||||||
|
ffmpeg = []
|
||||||
|
|
||||||
|
# Profile optimasi untuk production - fokus pada performa runtime maksimal
|
||||||
|
[profile.release]
|
||||||
|
opt-level = 3 # Optimasi level maksimal
|
||||||
|
lto = "fat" # Full LTO untuk inlining maksimal dan binary optimal
|
||||||
|
codegen-units = 1 # Single codegen unit untuk optimasi maksimal (lebih lambat build, binary lebih cepat)
|
||||||
|
incremental = false # Disable incremental untuk optimasi penuh
|
||||||
|
debug = false # No debug info untuk binary lebih kecil
|
||||||
|
strip = true # Strip symbols untuk binary lebih kecil
|
||||||
|
panic = "abort" # Abort on panic (binary lebih kecil dan lebih cepat)
|
||||||
|
overflow-checks = false # Non-overflowing arithmetic for speed (disable in debug)
|
||||||
|
|
||||||
|
# Optimize dependencies too
|
||||||
|
[profile.dev]
|
||||||
|
opt-level = 0
|
||||||
|
|
||||||
|
[profile.bench]
|
||||||
|
opt-level = 3
|
||||||
|
lto = "fat"
|
||||||
@@ -0,0 +1,69 @@
|
|||||||
|
# GEMINI.md - Codebase Architecture & Structure
|
||||||
|
|
||||||
|
Internal technical overview of the **Scraping & CDN Service** (`apps/scraper`) for automated data extraction and image persistence.
|
||||||
|
|
||||||
|
## 🌍 Context
|
||||||
|
|
||||||
|
- **`apps/scraper`**: Specialized backend engine (Axum).
|
||||||
|
- **`apps/solidjs`**: Frontend consumer.
|
||||||
|
- **`packages/services`**: Shared logic.
|
||||||
|
|
||||||
|
## 🤖 AI Assistant Guidelines
|
||||||
|
|
||||||
|
AI assistants (like Claude, Gemini, GPT) interacting with this codebase **MUST** adhere to the following protocols defined in **[AGENT.md](file:///mnt/code/bp3/ultimate-asepharyana.tech/apps/scraper/AGENT.md)**:
|
||||||
|
|
||||||
|
1. **Professional Tone**: Maintain a cold, technical, and objective tone.
|
||||||
|
2. **No Hyperbole**: **PROHIBITED** from using marketing-speak or exaggerated praise (e.g., "amazing", "unparalleled", "powerful", "revolutionary").
|
||||||
|
3. **Technical Accuracy**: Focus purely on implementation facts, data structures, and performance metrics.
|
||||||
|
4. **Minimalist Adherence**: Always prioritize the **Zero-Bloat Policy**. If a request introduces unnecessary dependencies or logic, challenge the user and suggest a leaner alternative.
|
||||||
|
5. **Documentation Consistency**: Ensure any generated documentation follows the established professional and objective style of the `docs/` folder.
|
||||||
|
|
||||||
|
## 🦀 `apps/scraper` - Backend Service
|
||||||
|
|
||||||
|
An asynchronous service for scraping and image proxying. All secondary web framework features (Authentication, Social, GraphQL) have been removed to reduce complexity.
|
||||||
|
|
||||||
|
### 📊 Tech Stack
|
||||||
|
|
||||||
|
- **Framework**: [Axum](https://github.com/tokio-rs/axum) (0.8.8) - Asynchronous Rust HTTP.
|
||||||
|
- **ORM**: [SeaORM](https://www.sea-ql.org/SeaORM/) (MySQL) - Database abstraction.
|
||||||
|
- **Caching**: `deadpool-redis` & `redis` - In-memory cache mapping.
|
||||||
|
- **Observability**: Request ID tracing and structured logging.
|
||||||
|
- **Scraping**: `scraper` (CSS Selectors) & remote Chrome via HTTP.
|
||||||
|
|
||||||
|
### 📂 Directory Structure (`apps/scraper/src`)
|
||||||
|
|
||||||
|
Organized as a hybrid of Vertical Slice and Clean Architecture.
|
||||||
|
|
||||||
|
| Directory | Description |
|
||||||
|
| :--- | :--- |
|
||||||
|
| **`bin/`** | Binary entry points and CLI tools. |
|
||||||
|
| **`config/`** | Strongly-typed environment configuration. |
|
||||||
|
| **`entities/`** | **SeaORM Entities**. Database schema mapping. |
|
||||||
|
| **`routes/`** | **API Handlers**. Automatic routing system. |
|
||||||
|
| **`services/`** | Business logic (e.g., `ImageCache` service). |
|
||||||
|
| **`scraping/`** | Data extraction engines and parsers. |
|
||||||
|
| **`helpers/`** | Shared utilities and cache helpers. |
|
||||||
|
| **`middleware/`** | Axum layers (CORS, Compression). |
|
||||||
|
| **`events/`** | Internal event bus for repair state updates. |
|
||||||
|
| **`jobs/`** | Background task processing. |
|
||||||
|
| **`scheduler/`** | Periodic tasks (Daily CDN audit). |
|
||||||
|
| **`observability/`** | OpenAPI documentation, request ID tracing, and structured logging. |
|
||||||
|
|
||||||
|
### 🔑 Logic Flows
|
||||||
|
|
||||||
|
1. **Scraping**:
|
||||||
|
`Request` -> `Router` -> `Handler` -> `Scraper Engine` -> `Redis` -> `Response`.
|
||||||
|
2. **Image Proxy/CDN**:
|
||||||
|
`Request` -> `ImageCache` -> `Cache Lookup` -> `Picser Upload (on miss)` -> `CDN URL`.
|
||||||
|
|
||||||
|
### 📜 Commands
|
||||||
|
|
||||||
|
- **Standard Run**: `cargo run`
|
||||||
|
- **Optimized Build**: `cargo build --release`
|
||||||
|
- **External Audit**: `POST /api/proxy/image-cache/audit`
|
||||||
|
|
||||||
|
## 🏗 Maintenance Constraints
|
||||||
|
|
||||||
|
- **Minimalist Approach**: New dependencies require impact evaluation.
|
||||||
|
- **Lint Compliance**: Suppression flags (`#[allow]`) are prohibited.
|
||||||
|
- **Performance-First**: Use `spawn_blocking` for CPU-heavy work (HTML parsing).
|
||||||
@@ -0,0 +1,55 @@
|
|||||||
|
# Scraper API
|
||||||
|
|
||||||
|
Backend service berbasis Axum untuk scraping, image proxy/cache, dan endpoint API inti.
|
||||||
|
|
||||||
|
## Stack
|
||||||
|
|
||||||
|
- Rust + Axum
|
||||||
|
- SeaORM (MySQL)
|
||||||
|
- Redis (deadpool-redis)
|
||||||
|
- Utoipa + Swagger UI
|
||||||
|
|
||||||
|
## Quick Start
|
||||||
|
|
||||||
|
```bash
|
||||||
|
cargo run
|
||||||
|
```
|
||||||
|
|
||||||
|
Server bind ke `0.0.0.0:${PORT}` dengan default port `4091`.
|
||||||
|
|
||||||
|
## Required Environment Variables
|
||||||
|
|
||||||
|
```env
|
||||||
|
DATABASE_URL=mysql://asephs:hunterz@localhost:3306/sosmed
|
||||||
|
JWT_SECRET=change-me
|
||||||
|
REDIS_URL=redis://localhost:6379
|
||||||
|
```
|
||||||
|
|
||||||
|
Optional yang sering dipakai:
|
||||||
|
|
||||||
|
```env
|
||||||
|
RUST_LOG=info
|
||||||
|
EXTERNAL_BROWSERLESS_WS=
|
||||||
|
MINIO_ENDPOINT=
|
||||||
|
MINIO_BUCKET_NAME=
|
||||||
|
MINIO_ACCESS_KEY=
|
||||||
|
MINIO_SECRET_KEY=
|
||||||
|
```
|
||||||
|
|
||||||
|
## Useful Endpoints
|
||||||
|
|
||||||
|
- `GET /docs` - Swagger UI
|
||||||
|
- `GET /api-docs/openapi.json` - OpenAPI JSON
|
||||||
|
- `GET /api/anime2/*`
|
||||||
|
- `GET /api/komik/*`
|
||||||
|
- `POST /api/proxy/image-cache`
|
||||||
|
- `POST /api/proxy/image-cache/audit`
|
||||||
|
|
||||||
|
## Notes
|
||||||
|
|
||||||
|
- Database akan dicek/dibuat saat startup jika `DATABASE_URL` bertipe MySQL.
|
||||||
|
- Service ini juga menginisialisasi browser pool dan scheduler saat boot.
|
||||||
|
|
||||||
|
## License
|
||||||
|
|
||||||
|
MIT
|
||||||
Executable
+73
@@ -0,0 +1,73 @@
|
|||||||
|
#!/bin/bash
|
||||||
|
# Simple script to check image_cache database content
|
||||||
|
|
||||||
|
DATABASE_URL="mysql://asephs:hunterz@127.0.0.1:3306/sosmed"
|
||||||
|
|
||||||
|
echo "=== Checking Image Cache Database ==="
|
||||||
|
echo ""
|
||||||
|
echo "Attempting to connect via Rust binary..."
|
||||||
|
echo ""
|
||||||
|
|
||||||
|
cd "$(dirname "$0")"
|
||||||
|
|
||||||
|
# Create temporary Rust script
|
||||||
|
cat > /tmp/check_img_cache.rs << 'EOF'
|
||||||
|
use sea_orm::{Database, ConnectionTrait, Statement};
|
||||||
|
|
||||||
|
#[tokio::main]
|
||||||
|
async fn main() -> Result<(), Box<dyn std::error::Error>> {
|
||||||
|
let db = Database::connect("mysql://asephs:hunterz@127.0.0.1:3306/sosmed").await?;
|
||||||
|
|
||||||
|
println!("✓ Connected to database\n");
|
||||||
|
|
||||||
|
// Show all tables
|
||||||
|
println!("=== ALL TABLES ===");
|
||||||
|
let tables = db.query_all(Statement::from_string(
|
||||||
|
db.get_database_backend(),
|
||||||
|
"SHOW TABLES".to_owned()
|
||||||
|
)).await?;
|
||||||
|
for table in &tables {
|
||||||
|
println!(" - {:?}", table);
|
||||||
|
}
|
||||||
|
|
||||||
|
// Count image_cache records
|
||||||
|
println!("\n=== IMAGE_CACHE TABLE ===");
|
||||||
|
let count = db.query_one(Statement::from_string(
|
||||||
|
db.get_database_backend(),
|
||||||
|
"SELECT COUNT(*) as total FROM ImageCache".to_owned()
|
||||||
|
)).await?;
|
||||||
|
println!("Total records: {:?}", count);
|
||||||
|
|
||||||
|
// Show recent 10 records
|
||||||
|
println!("\n=== RECENT RECORDS (Last 10) ===");
|
||||||
|
let records = db.query_all(Statement::from_string(
|
||||||
|
db.get_database_backend(),
|
||||||
|
"SELECT id, originalUrl, cdnUrl, createdAt FROM ImageCache ORDER BY createdAt DESC LIMIT 10".to_owned()
|
||||||
|
)).await?;
|
||||||
|
|
||||||
|
for (i, record) in records.iter().enumerate() {
|
||||||
|
println!("\n[{}]", i + 1);
|
||||||
|
println!(" ID: {:?}", record.try_get::<String>("", "id"));
|
||||||
|
println!(" Original: {:?}", record.try_get::<String>("", "originalUrl"));
|
||||||
|
println!(" CDN URL: {:?}", record.try_get::<String>("", "cdnUrl"));
|
||||||
|
println!(" Created: {:?}", record.try_get::<chrono::DateTime<chrono::Utc>>("", "createdAt"));
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
|
EOF
|
||||||
|
|
||||||
|
echo "Running database check..."
|
||||||
|
rustc --edition 2021 /tmp/check_img_cache.rs -o /tmp/check_img_cache \
|
||||||
|
-L dependency=target/debug/deps \
|
||||||
|
--extern sea_orm=target/debug/deps/libsea_orm.rlib \
|
||||||
|
--extern tokio=target/debug/deps/libtokio.rlib \
|
||||||
|
--extern chrono=target/debug/deps/libchrono.rlib \
|
||||||
|
2>/dev/null
|
||||||
|
|
||||||
|
if [ $? -eq 0 ]; then
|
||||||
|
/tmp/check_img_cache
|
||||||
|
else
|
||||||
|
echo "Rust compilation failed, using cargo script instead..."
|
||||||
|
cargo script /tmp/check_img_cache.rs
|
||||||
|
fi
|
||||||
@@ -0,0 +1,167 @@
|
|||||||
|
# Clean-Modular Architecture Refactor Implementation Plan
|
||||||
|
|
||||||
|
> **For agentic workers:** REQUIRED SUB-SKILL: Use superpowers:subagent-driven-development (recommended) or superpowers:executing-plans to implement this plan task-by-task. Steps use checkbox (`- [ ]`) syntax for tracking.
|
||||||
|
|
||||||
|
**Goal:** Refactor the codebase into a rigid Clean-Modular architecture to improve maintainability and strictly enforce separation of concerns.
|
||||||
|
|
||||||
|
**Architecture:** A three-tier modular approach consisting of Presentation (API Handlers/DTOs), Core (Domain Models/Traits/Use Cases), and Infrastructure (Adapters/Repositories/Scrapers).
|
||||||
|
|
||||||
|
**Tech Stack:** Rust, Axum, SeaORM, Redis, reqwest.
|
||||||
|
|
||||||
|
---
|
||||||
|
|
||||||
|
### Task 1: Initialize Core Domain Models & Shared Errors
|
||||||
|
|
||||||
|
**Files:**
|
||||||
|
- Create: `src/shared/errors/mod.rs`
|
||||||
|
- Create: `src/core/models/image.rs`
|
||||||
|
- Create: `src/core/models/mod.rs`
|
||||||
|
- Create: `src/shared/mod.rs`
|
||||||
|
|
||||||
|
- [ ] **Step 1: Define shared application errors**
|
||||||
|
- [ ] **Step 2: Define pure domain models for ImageCache**
|
||||||
|
- [ ] **Step 3: Setup core and shared modules in `lib.rs`**
|
||||||
|
|
||||||
|
```rust
|
||||||
|
// src/shared/errors/mod.rs
|
||||||
|
use axum::{response::{IntoResponse, Response}, Json, http::StatusCode};
|
||||||
|
use serde_json::json;
|
||||||
|
use thiserror::Error;
|
||||||
|
|
||||||
|
#[derive(Error, Debug)]
|
||||||
|
pub enum AppError {
|
||||||
|
#[error("Not found: {0}")]
|
||||||
|
NotFound(String),
|
||||||
|
#[error("Internal error: {0}")]
|
||||||
|
Internal(String),
|
||||||
|
#[error("Validation error: {0}")]
|
||||||
|
Validation(String),
|
||||||
|
}
|
||||||
|
|
||||||
|
impl IntoResponse for AppError {
|
||||||
|
fn into_response(self) -> Response {
|
||||||
|
let (status, message) = match self {
|
||||||
|
AppError::NotFound(m) => (StatusCode::NOT_FOUND, m),
|
||||||
|
AppError::Internal(m) => (StatusCode::INTERNAL_SERVER_ERROR, m),
|
||||||
|
AppError::Validation(m) => (StatusCode::BAD_REQUEST, m),
|
||||||
|
};
|
||||||
|
(status, Json(json!({ "error": message }))).into_response()
|
||||||
|
}
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
- [ ] **Step 4: Commit changes**
|
||||||
|
```bash
|
||||||
|
git add src/shared/errors/mod.rs src/core/models/image.rs
|
||||||
|
git commit -m "feat: init core models and shared errors"
|
||||||
|
```
|
||||||
|
|
||||||
|
### Task 2: Define Core Repository Traits
|
||||||
|
|
||||||
|
**Files:**
|
||||||
|
- Create: `src/core/repositories/image_repository.rs`
|
||||||
|
- Create: `src/core/repositories/mod.rs`
|
||||||
|
|
||||||
|
- [ ] **Step 1: Define ImageRepository trait in `core`**
|
||||||
|
|
||||||
|
```rust
|
||||||
|
// src/core/repositories/image_repository.rs
|
||||||
|
use async_trait::async_trait;
|
||||||
|
use crate::core::models::image::ImageCache;
|
||||||
|
use crate::shared::errors::AppError;
|
||||||
|
|
||||||
|
#[async_trait]
|
||||||
|
pub trait ImageRepository: Send + Sync {
|
||||||
|
async fn find_by_original_url(&self, url: &str) -> Result<Option<ImageCache>, AppError>;
|
||||||
|
async fn save(&self, image: ImageCache) -> Result<(), AppError>;
|
||||||
|
async fn delete_by_original_url(&self, url: &str) -> Result<(), AppError>;
|
||||||
|
}
|
||||||
|
```
|
||||||
|
|
||||||
|
- [ ] **Step 2: Commit changes**
|
||||||
|
```bash
|
||||||
|
git add src/core/repositories/
|
||||||
|
git commit -m "feat: define core repository traits"
|
||||||
|
```
|
||||||
|
|
||||||
|
### Task 3: Migrate SeaORM Entities to Infrastructure
|
||||||
|
|
||||||
|
**Files:**
|
||||||
|
- Modify: `src/infra/mod.rs`
|
||||||
|
- Create: `src/infra/repositories/mysql_image_repository.rs`
|
||||||
|
|
||||||
|
- [ ] **Step 1: Implement ImageRepository for MySQL using SeaORM**
|
||||||
|
- [ ] **Step 2: Move `src/entities/image_cache.rs` logic into the new repository implementation**
|
||||||
|
- [ ] **Step 3: Update `src/infra/mod.rs` to expose repositories**
|
||||||
|
|
||||||
|
- [ ] **Step 4: Commit changes**
|
||||||
|
```bash
|
||||||
|
git add src/infra/repositories/
|
||||||
|
git commit -m "feat: implement mysql image repository in infra"
|
||||||
|
```
|
||||||
|
|
||||||
|
### Task 4: Implement Core Use Cases (Image Caching)
|
||||||
|
|
||||||
|
**Files:**
|
||||||
|
- Create: `src/core/use_cases/cache_image.rs`
|
||||||
|
- Create: `src/core/use_cases/mod.rs`
|
||||||
|
|
||||||
|
- [ ] **Step 1: Implement `CacheImageUseCase`**
|
||||||
|
- [ ] **Step 2: Orchestrate logic between repository, redis, and scraper/uploader**
|
||||||
|
|
||||||
|
- [ ] **Step 3: Commit changes**
|
||||||
|
```bash
|
||||||
|
git add src/core/use_cases/
|
||||||
|
git commit -m "feat: implement image caching use cases"
|
||||||
|
```
|
||||||
|
|
||||||
|
### Task 5: Refactor Scrapers into Infrastructure
|
||||||
|
|
||||||
|
**Files:**
|
||||||
|
- Create: `src/core/repositories/scraping_repository.rs`
|
||||||
|
- Create: `src/infra/scrapers/otakudesu.rs`
|
||||||
|
|
||||||
|
- [ ] **Step 1: Define Scraping traits in `core`**
|
||||||
|
- [ ] **Step 2: Implement site-specific scrapers in `infra`**
|
||||||
|
- [ ] **Step 3: Migrate existing logic from `src/scraping/`**
|
||||||
|
|
||||||
|
- [ ] **Step 4: Commit changes**
|
||||||
|
```bash
|
||||||
|
git add src/infra/scrapers/
|
||||||
|
git commit -m "feat: migrate scrapers to infra adapters"
|
||||||
|
```
|
||||||
|
|
||||||
|
### Task 6: Refactor Presentation Layer (API Handlers)
|
||||||
|
|
||||||
|
**Files:**
|
||||||
|
- Create: `src/presentation/api/anime_handler.rs`
|
||||||
|
- Create: `src/presentation/api/mod.rs`
|
||||||
|
- Create: `src/presentation/mod.rs`
|
||||||
|
|
||||||
|
- [ ] **Step 1: Migrate handlers from `src/routes/` to `presentation/api/`**
|
||||||
|
- [ ] **Step 2: Update handlers to use Use Cases instead of direct service/helper calls**
|
||||||
|
- [ ] **Step 3: Update global router in `src/main.rs` or `src/lib.rs`**
|
||||||
|
|
||||||
|
- [ ] **Step 4: Commit changes**
|
||||||
|
```bash
|
||||||
|
git add src/presentation/api/
|
||||||
|
git commit -m "feat: refactor presentation layer api handlers"
|
||||||
|
```
|
||||||
|
|
||||||
|
### Task 7: Global Cleanup & Verification
|
||||||
|
|
||||||
|
**Files:**
|
||||||
|
- Modify: `src/lib.rs`
|
||||||
|
- Delete: `src/helpers/` (partially merged into shared/infra)
|
||||||
|
- Delete: `src/services/` (merged into core/use_cases)
|
||||||
|
- Delete: `src/routes/` (merged into presentation)
|
||||||
|
|
||||||
|
- [ ] **Step 1: Update `lib.rs` to reflect new module structure**
|
||||||
|
- [ ] **Step 2: Remove old redundant directories**
|
||||||
|
- [ ] **Step 3: Run full test suite**
|
||||||
|
- [ ] **Step 4: Verify metrics endpoint**
|
||||||
|
|
||||||
|
- [ ] **Step 5: Final Commit**
|
||||||
|
```bash
|
||||||
|
git commit -m "refactor: complete clean-modular architecture overhaul"
|
||||||
|
```
|
||||||
@@ -0,0 +1,49 @@
|
|||||||
|
# Design Spec: Clean-Modular Architecture Refactor
|
||||||
|
|
||||||
|
**Date**: 2026-05-08
|
||||||
|
**Topic**: Refactor `apps/rust` from Hybrid to Clean-Modular Architecture.
|
||||||
|
|
||||||
|
## 1. Purpose
|
||||||
|
Standardize codebase structure for rigidity, maintainability, and clear separation of concerns (SOC) without violating the **Zero-Bloat Policy**.
|
||||||
|
|
||||||
|
## 2. Target Architecture
|
||||||
|
Moving from current structure to a three-tier modular design:
|
||||||
|
|
||||||
|
### A. Presentation Layer (`src/presentation/`)
|
||||||
|
- **API Handlers**: Pure Axum handlers.
|
||||||
|
- **DTOs**: Request/Response models for external communication.
|
||||||
|
- **Middleware**: Cross-cutting concerns (CORS, Metrics, Logging).
|
||||||
|
|
||||||
|
### B. Core Layer (`src/core/`) - The Domain
|
||||||
|
- **Models**: Pure data structures (Plain Rust Objects).
|
||||||
|
- **Repository Traits**: Abstract interfaces for data persistence.
|
||||||
|
- **Use Cases**: Orchestration of business logic (e.g., `ScrapeAnime`, `ProcessImage`).
|
||||||
|
- **Dependencies**: None (or minimal shared utils).
|
||||||
|
|
||||||
|
### C. Infrastructure Layer (`src/infra/`) - The Adapters
|
||||||
|
- **Repositories**: SeaORM & Redis implementations of Core traits.
|
||||||
|
- **Scrapers**: Site-specific parsing logic implementing Core scraping traits.
|
||||||
|
- **External Clients**: HTTP Client (reqwest), Browser Pool.
|
||||||
|
|
||||||
|
### D. Shared Layer (`src/shared/`)
|
||||||
|
- **Utils**: Low-level helpers (Date, JSON, String).
|
||||||
|
- **Config**: Application configuration.
|
||||||
|
- **Errors**: Centralized error handling.
|
||||||
|
|
||||||
|
## 3. Implementation Strategy
|
||||||
|
1. **Phase 1**: Scaffold new directory structure.
|
||||||
|
2. **Phase 2**: Migrate `models` and `entities` to `core/models` and `infra/repositories`.
|
||||||
|
3. **Phase 3**: Refactor `scraping` logic into `infra/scrapers` and define traits in `core`.
|
||||||
|
4. **Phase 4**: Move Axum handlers to `presentation/api` and update routing.
|
||||||
|
5. **Phase 5**: Cleanup `helpers` into `shared/utils`.
|
||||||
|
|
||||||
|
## 4. Constraints
|
||||||
|
- **Zero-Bloat**: No new heavy dependencies for the sake of abstraction.
|
||||||
|
- **Performance**: Maintain latency metrics as defined in `docs/development.md`.
|
||||||
|
- **SeaORM**: Entities stay in `infra/` to keep `core/` pure.
|
||||||
|
|
||||||
|
## 5. Success Criteria
|
||||||
|
- All tests pass.
|
||||||
|
- `/metrics` show no latency regression.
|
||||||
|
- Circular dependencies are eliminated.
|
||||||
|
- Folder structure matches this spec.
|
||||||
@@ -0,0 +1,26 @@
|
|||||||
|
// PM2 Ecosystem Configuration for Rust
|
||||||
|
module.exports = {
|
||||||
|
apps: [
|
||||||
|
{
|
||||||
|
name: 'ultimate-rust',
|
||||||
|
script: 'target/release/scraper',
|
||||||
|
cwd: process.env.VPS_TARGET_DIR
|
||||||
|
? `${process.env.VPS_TARGET_DIR}/apps/scraper`
|
||||||
|
: '/home/asephs/ultimate-asepharyana.cloud/apps/scraper',
|
||||||
|
interpreter: 'none',
|
||||||
|
exec_mode: 'fork',
|
||||||
|
autorestart: true,
|
||||||
|
watch: false,
|
||||||
|
max_memory_restart: '1G',
|
||||||
|
env_production: {
|
||||||
|
NODE_ENV: 'production',
|
||||||
|
PORT: 4091,
|
||||||
|
},
|
||||||
|
// Logging configuration
|
||||||
|
error_file: './logs/error.log',
|
||||||
|
out_file: './logs/out.log',
|
||||||
|
log_date_format: 'YYYY-MM-DD HH:mm:ss Z',
|
||||||
|
merge_logs: true,
|
||||||
|
},
|
||||||
|
],
|
||||||
|
};
|
||||||
@@ -0,0 +1,8 @@
|
|||||||
|
{
|
||||||
|
"name": "scraper",
|
||||||
|
"version": "0.1.0",
|
||||||
|
"private": true,
|
||||||
|
"scripts": {
|
||||||
|
"start": "./target/release/scraper"
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,15 @@
|
|||||||
|
# rustfmt configuration (stable features only)
|
||||||
|
|
||||||
|
max_width = 100
|
||||||
|
hard_tabs = false
|
||||||
|
tab_spaces = 4
|
||||||
|
newline_style = "Unix"
|
||||||
|
use_small_heuristics = "Default"
|
||||||
|
reorder_imports = true
|
||||||
|
reorder_modules = true
|
||||||
|
remove_nested_parens = true
|
||||||
|
edition = "2021"
|
||||||
|
merge_derives = true
|
||||||
|
use_try_shorthand = true
|
||||||
|
use_field_init_shorthand = true
|
||||||
|
force_explicit_abi = true
|
||||||
Binary file not shown.
Executable
+20
@@ -0,0 +1,20 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# Auto-fix warnings and lint Rust code
|
||||||
|
|
||||||
|
set -e
|
||||||
|
|
||||||
|
echo "🔧 Auto-fixing Rust warnings and linting..."
|
||||||
|
|
||||||
|
# Format code
|
||||||
|
echo "📝 Running rustfmt..."
|
||||||
|
cargo fmt
|
||||||
|
|
||||||
|
# Fix clippy warnings automatically
|
||||||
|
echo "🔍 Running clippy auto-fix..."
|
||||||
|
cargo clippy --fix --allow-dirty --allow-staged --all-targets
|
||||||
|
|
||||||
|
# Check for remaining issues
|
||||||
|
echo "✅ Running final check..."
|
||||||
|
cargo clippy --all-targets -- -D warnings
|
||||||
|
|
||||||
|
echo "✨ Done! Code is formatted and linted."
|
||||||
Executable
+84
@@ -0,0 +1,84 @@
|
|||||||
|
#!/usr/bin/env python3
|
||||||
|
"""Compare OpenAPI specifications for endpoint compatibility."""
|
||||||
|
|
||||||
|
import json
|
||||||
|
import sys
|
||||||
|
from pathlib import Path
|
||||||
|
|
||||||
|
|
||||||
|
def main():
|
||||||
|
if len(sys.argv) != 3:
|
||||||
|
print("Usage: compare-openapi.py <reference-openapi.json> <local-openapi.json>")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
ref_path = Path(sys.argv[1])
|
||||||
|
local_path = Path(sys.argv[2])
|
||||||
|
|
||||||
|
# Load reference OpenAPI
|
||||||
|
try:
|
||||||
|
ref_data = json.loads(ref_path.read_text())
|
||||||
|
except FileNotFoundError:
|
||||||
|
print(f"Error: Reference file not found: {ref_path}")
|
||||||
|
sys.exit(1)
|
||||||
|
except json.JSONDecodeError as e:
|
||||||
|
print(f"Error: Invalid JSON in reference file: {e}")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
# Load local OpenAPI
|
||||||
|
try:
|
||||||
|
local_data = json.loads(local_path.read_text())
|
||||||
|
except FileNotFoundError:
|
||||||
|
print(f"Error: Local file not found: {local_path}")
|
||||||
|
sys.exit(1)
|
||||||
|
except json.JSONDecodeError as e:
|
||||||
|
print(f"Error: Invalid JSON in local file: {e}")
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
ref_paths = ref_data.get("paths", {})
|
||||||
|
local_paths = local_data.get("paths", {})
|
||||||
|
|
||||||
|
http_methods = {"get", "put", "post", "delete", "options", "head", "patch", "trace"}
|
||||||
|
|
||||||
|
has_differences = False
|
||||||
|
|
||||||
|
# Check for missing paths
|
||||||
|
missing_paths = set(ref_paths.keys()) - set(local_paths.keys())
|
||||||
|
if missing_paths:
|
||||||
|
has_differences = True
|
||||||
|
for path in sorted(missing_paths):
|
||||||
|
print(f"Missing path: {path}")
|
||||||
|
|
||||||
|
# Check for extra paths
|
||||||
|
extra_paths = set(local_paths.keys()) - set(ref_paths.keys())
|
||||||
|
if extra_paths:
|
||||||
|
has_differences = True
|
||||||
|
for path in sorted(extra_paths):
|
||||||
|
print(f"Extra path: {path}")
|
||||||
|
|
||||||
|
# Check for method mismatches in common paths
|
||||||
|
common_paths = set(ref_paths.keys()) & set(local_paths.keys())
|
||||||
|
for path in sorted(common_paths):
|
||||||
|
ref_methods = set(method.lower() for method in ref_paths[path].keys() if method.lower() in http_methods)
|
||||||
|
local_methods = set(method.lower() for method in local_paths[path].keys() if method.lower() in http_methods)
|
||||||
|
|
||||||
|
missing_methods = ref_methods - local_methods
|
||||||
|
if missing_methods:
|
||||||
|
has_differences = True
|
||||||
|
for method in sorted(missing_methods):
|
||||||
|
print(f"Missing method {method.upper()} for path: {path}")
|
||||||
|
|
||||||
|
extra_methods = local_methods - ref_methods
|
||||||
|
if extra_methods:
|
||||||
|
has_differences = True
|
||||||
|
for method in sorted(extra_methods):
|
||||||
|
print(f"Extra method {method.upper()} for path: {path}")
|
||||||
|
|
||||||
|
if has_differences:
|
||||||
|
sys.exit(1)
|
||||||
|
|
||||||
|
print(f"OpenAPI paths/methods match: {len(ref_paths)} paths")
|
||||||
|
sys.exit(0)
|
||||||
|
|
||||||
|
|
||||||
|
if __name__ == "__main__":
|
||||||
|
main()
|
||||||
Executable
+15
@@ -0,0 +1,15 @@
|
|||||||
|
#!/bin/bash
|
||||||
|
# Script to run database migrations manually
|
||||||
|
|
||||||
|
echo "Running database migrations..."
|
||||||
|
cd "$(dirname "$0")/.."
|
||||||
|
|
||||||
|
# Build and run the migration binary
|
||||||
|
cargo run --bin migrate
|
||||||
|
|
||||||
|
if [ $? -eq 0 ]; then
|
||||||
|
echo "✅ Migration completed successfully."
|
||||||
|
else
|
||||||
|
echo "❌ Migration failed."
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
Executable
+19
@@ -0,0 +1,19 @@
|
|||||||
|
#!/usr/bin/env bash
|
||||||
|
# Pre-build hook to enforce best practices
|
||||||
|
|
||||||
|
set -e
|
||||||
|
|
||||||
|
echo "🔍 Running pre-build lint checks..."
|
||||||
|
|
||||||
|
# Format check
|
||||||
|
echo "📝 Checking code formatting..."
|
||||||
|
if ! cargo fmt -- --check; then
|
||||||
|
echo "❌ Code not formatted. Run: cargo fmt"
|
||||||
|
exit 1
|
||||||
|
fi
|
||||||
|
|
||||||
|
# Clippy check with denials
|
||||||
|
echo "🔧 Running clippy..."
|
||||||
|
cargo clippy --all-targets -- -D warnings
|
||||||
|
|
||||||
|
echo "✅ All lint checks passed!"
|
||||||
+51
@@ -0,0 +1,51 @@
|
|||||||
|
use std::sync::Arc;
|
||||||
|
|
||||||
|
use axum::Router;
|
||||||
|
use sea_orm::DatabaseConnection;
|
||||||
|
use tower_http::compression::{CompressionLayer, CompressionLevel};
|
||||||
|
use tower_http::cors::CorsLayer;
|
||||||
|
use utoipa::OpenApi;
|
||||||
|
use utoipa_swagger_ui::SwaggerUi;
|
||||||
|
|
||||||
|
use crate::shared::observability::openapi::ApiDoc;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
|
||||||
|
pub async fn build_router(
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
db: Arc<DatabaseConnection>,
|
||||||
|
) -> anyhow::Result<Router> {
|
||||||
|
init_scheduler(db).await?;
|
||||||
|
|
||||||
|
let mut openapi = ApiDoc::openapi();
|
||||||
|
openapi.merge(crate::shared::observability::openapi_modules::ModuleApiDoc::openapi());
|
||||||
|
|
||||||
|
let app = crate::modules::routes(Router::new())
|
||||||
|
.merge(SwaggerUi::new("/docs").url("/api-docs/openapi.json", openapi))
|
||||||
|
.with_state(app_state)
|
||||||
|
.layer(axum::middleware::from_fn(
|
||||||
|
crate::shared::observability::metrics::otel_metrics_middleware,
|
||||||
|
))
|
||||||
|
.layer(CompressionLayer::new().quality(CompressionLevel::Fastest))
|
||||||
|
.layer(CorsLayer::permissive());
|
||||||
|
|
||||||
|
Ok(app)
|
||||||
|
}
|
||||||
|
|
||||||
|
async fn init_scheduler(db: Arc<DatabaseConnection>) -> anyhow::Result<()> {
|
||||||
|
let scheduler = crate::shared::scheduler::Scheduler::new()
|
||||||
|
.await
|
||||||
|
.map_err(|e| anyhow::anyhow!("Failed to create scheduler: {}", e))?;
|
||||||
|
|
||||||
|
let cache_cleanup = crate::shared::scheduler::CleanupOldCache::new(db);
|
||||||
|
scheduler
|
||||||
|
.add(cache_cleanup)
|
||||||
|
.await
|
||||||
|
.map_err(|e| anyhow::anyhow!("Failed to add cache cleanup: {}", e))?;
|
||||||
|
|
||||||
|
scheduler
|
||||||
|
.start()
|
||||||
|
.await
|
||||||
|
.map_err(|e| anyhow::anyhow!("Failed to start scheduler: {}", e))?;
|
||||||
|
tracing::info!("✓ Scheduler started");
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
@@ -0,0 +1,117 @@
|
|||||||
|
use scraper::Selector;
|
||||||
|
use scraper_service::shared::utils::parse_html;
|
||||||
|
/// Capture html5ever tree_builder warning evidence by parsing problematic HTML.
|
||||||
|
///
|
||||||
|
/// Build with: cargo build --bin capture_warning
|
||||||
|
/// Run with: RUST_LOG=warn cargo run --bin capture_warning 2>&1
|
||||||
|
///
|
||||||
|
/// Evidence of the warning is captured through:
|
||||||
|
/// 1. HTML that triggers foster_parenting in html5ever::tree_builder
|
||||||
|
/// 2. Observable parsing behavior showing tree reconstruction
|
||||||
|
/// 3. The call path from src/helpers::parse_html () to html5ever
|
||||||
|
/// 4. Real endpoint context from /api/anime2/latest/{slug} route
|
||||||
|
use std::fs;
|
||||||
|
use tracing_subscriber::EnvFilter;
|
||||||
|
|
||||||
|
fn main() {
|
||||||
|
// Initialize logging to capture WARN output from html5ever
|
||||||
|
let env_filter = EnvFilter::from_default_env()
|
||||||
|
.add_directive("warn".parse().expect("valid directive"))
|
||||||
|
.add_directive("html5ever=warn".parse().expect("valid directive"));
|
||||||
|
|
||||||
|
tracing_subscriber::fmt()
|
||||||
|
.with_env_filter(env_filter)
|
||||||
|
.with_writer(std::io::stderr)
|
||||||
|
.init();
|
||||||
|
|
||||||
|
println!("=== HTML5ever Tree Builder Foster Parenting Evidence ===\n");
|
||||||
|
println!("Real Endpoint: GET /api/anime2/latest/{{slug}}");
|
||||||
|
println!("Handler: src/routes/api/anime2/latest/[slug].rs:124");
|
||||||
|
println!("Helper Path: src/helpers/web/scraping.rs::parse_html() -> Html::parse_document()\n");
|
||||||
|
|
||||||
|
// Load HTML fixture from shared test file
|
||||||
|
let fixture_path = "src/bin/test_fixtures/foster_parenting_minimal.html";
|
||||||
|
let test_html = fs::read_to_string(fixture_path)
|
||||||
|
.expect(&format!("Failed to read fixture from {}", fixture_path));
|
||||||
|
|
||||||
|
println!("Input Request:");
|
||||||
|
println!(" GET /api/anime2/latest/some-anime");
|
||||||
|
println!(" Body: HTML containing misplaced text in <table>");
|
||||||
|
println!(" Fixture: {}", fixture_path);
|
||||||
|
println!(" Test HTML: {}\n", test_html);
|
||||||
|
|
||||||
|
println!("Parsing through src/helpers::parse_html()...\n");
|
||||||
|
println!("--- BEGIN STDERR (logging output) ---");
|
||||||
|
|
||||||
|
// This parse_html() call routes through:
|
||||||
|
// src/helpers::parse_html()
|
||||||
|
// -> scraper crate Html::parse_document()
|
||||||
|
// -> html5ever::parse() [version 0.36.1]
|
||||||
|
// -> TreeBuilder::process_token()
|
||||||
|
// -> TreeBuilder::foster_parent_in_body() which emits:
|
||||||
|
// warn!("foster parenting not implemented")
|
||||||
|
let document = parse_html(&test_html);
|
||||||
|
|
||||||
|
println!("--- END STDERR (logging output) ---\n");
|
||||||
|
|
||||||
|
// Analyze the result
|
||||||
|
println!("Parse Output Evidence:\n");
|
||||||
|
|
||||||
|
// Check table structure
|
||||||
|
let table_sel = Selector::parse("table").expect("Valid CSS selector");
|
||||||
|
let tr_sel = Selector::parse("tr").expect("Valid CSS selector");
|
||||||
|
let td_sel = Selector::parse("td").expect("Valid CSS selector");
|
||||||
|
|
||||||
|
let tables: Vec<_> = document.select(&table_sel).collect();
|
||||||
|
println!(" ✓ Tables parsed: {}", tables.len());
|
||||||
|
|
||||||
|
let trs: Vec<_> = document.select(&tr_sel).collect();
|
||||||
|
println!(" ✓ Table rows found: {}", trs.len());
|
||||||
|
|
||||||
|
let tds: Vec<_> = document.select(&td_sel).collect();
|
||||||
|
println!(" ✓ Table cells found: {}", tds.len());
|
||||||
|
|
||||||
|
let body_sel = Selector::parse("body").expect("Valid CSS selector");
|
||||||
|
if let Some(body) = document.select(&body_sel).next() {
|
||||||
|
let body_text: String = body.text().collect();
|
||||||
|
let trimmed = body_text.trim();
|
||||||
|
println!("\n Body element text content:");
|
||||||
|
println!(" '{}'", trimmed);
|
||||||
|
|
||||||
|
if trimmed.contains("orphaned text") {
|
||||||
|
println!("\n ✓ EVIDENCE: 'orphaned text' moved OUT of <table>");
|
||||||
|
println!(" This proves foster_parenting occurred!");
|
||||||
|
}
|
||||||
|
if trimmed.contains("more text") {
|
||||||
|
println!(" ✓ EVIDENCE: 'more text' moved OUT of <table>");
|
||||||
|
println!(" This confirms the adoption agency algorithm ran!");
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
println!("\n=== Proven Call Path ===");
|
||||||
|
println!("Route: GET /api/anime2/latest/{{slug}}");
|
||||||
|
println!("Request Handler: src/routes/api/anime2/latest/[slug].rs");
|
||||||
|
println!(" -> latest() handler");
|
||||||
|
println!(" -> fetch_latest_anime()");
|
||||||
|
println!(" -> parse_latest_page(html, page)");
|
||||||
|
println!(" -> crate::shared::utils::parse_html(html) [line 124]\n");
|
||||||
|
|
||||||
|
println!("Helper Function: src/helpers/web/scraping.rs");
|
||||||
|
println!(" pub fn parse_html(html: &str) -> Html {{");
|
||||||
|
println!(" Html::parse_document(html) // Line 34");
|
||||||
|
println!(" }}\n");
|
||||||
|
|
||||||
|
println!("Call Stack to Warning:");
|
||||||
|
println!(" 1. crate::shared::utils::parse_html() [src/helpers/web/scraping.rs:34]");
|
||||||
|
println!(" 2. Html::parse_document() [scraper crate wrapper]");
|
||||||
|
println!(" 3. html5ever::parse() [Cargo.toml: version 0.36.1]");
|
||||||
|
println!(" 4. TreeBuilder::process_token()");
|
||||||
|
println!(" 5. TreeBuilder::process_chars_in_table()");
|
||||||
|
println!(" 6. TreeBuilder::foster_parent_in_body() [src/tree_builder/mod.rs:1227]");
|
||||||
|
println!(" 7. warn!(\"foster parenting not implemented\") ← EMITTED ABOVE\n");
|
||||||
|
|
||||||
|
println!("=== Fixture Source ===");
|
||||||
|
println!("Shared File: {}", fixture_path);
|
||||||
|
println!("HTML Content: {}", test_html);
|
||||||
|
println!("Expected Parsing Behavior: Text nodes are fostered out of table");
|
||||||
|
}
|
||||||
@@ -0,0 +1,132 @@
|
|||||||
|
/// Test: Verify parsed output for foster_parenting_minimal.html fixture
|
||||||
|
///
|
||||||
|
/// This binary contains tests and assertions that validate the expected behavior
|
||||||
|
/// when parsing HTML that triggers the html5ever::tree_builder::foster_parent_in_body() warning.
|
||||||
|
///
|
||||||
|
/// Uses shared fixture: src/bin/test_fixtures/foster_parenting_minimal.html
|
||||||
|
/// Uses shared parser: src/helpers::parse_html()
|
||||||
|
use scraper::Selector;
|
||||||
|
use scraper_service::shared::utils::parse_html;
|
||||||
|
use std::fs;
|
||||||
|
|
||||||
|
fn main() {
|
||||||
|
println!("Running foster parenting regression tests...\n");
|
||||||
|
|
||||||
|
// Load HTML fixture from shared test file
|
||||||
|
let fixture_path = "src/bin/test_fixtures/foster_parenting_minimal.html";
|
||||||
|
let foster_parenting_html = fs::read_to_string(fixture_path)
|
||||||
|
.expect(&format!("Failed to read fixture from {}", fixture_path));
|
||||||
|
|
||||||
|
test_foster_parenting_text_extraction(&foster_parenting_html);
|
||||||
|
println!("✓ test_foster_parenting_text_extraction passed");
|
||||||
|
|
||||||
|
test_foster_parenting_table_structure(&foster_parenting_html);
|
||||||
|
println!("✓ test_foster_parenting_table_structure passed");
|
||||||
|
|
||||||
|
test_expected_parsed_output_assertion(&foster_parenting_html);
|
||||||
|
println!("✓ test_expected_parsed_output_assertion passed");
|
||||||
|
|
||||||
|
println!("\n✓ All assertions passed (3/3)");
|
||||||
|
println!("\nFixture source: {}", fixture_path);
|
||||||
|
println!("Parser source: src/helpers/web/scraping.rs::parse_html()");
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Test: Text nodes in <table> are foster-parented to body
|
||||||
|
fn test_foster_parenting_text_extraction(html: &str) {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let body_sel = Selector::parse("body").expect("Valid CSS selector");
|
||||||
|
|
||||||
|
let body_text: String = document
|
||||||
|
.select(&body_sel)
|
||||||
|
.next()
|
||||||
|
.map(|el| el.text().collect())
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
assert!(
|
||||||
|
body_text.contains("orphaned text"),
|
||||||
|
"Text 'orphaned text' should be present in body (fostered from table)"
|
||||||
|
);
|
||||||
|
assert!(
|
||||||
|
body_text.contains("more text"),
|
||||||
|
"Text 'more text' should be present in body (fostered from table)"
|
||||||
|
);
|
||||||
|
assert!(
|
||||||
|
body_text.contains("cell content"),
|
||||||
|
"Cell content should still be present"
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
fn test_foster_parenting_table_structure(html: &str) {
|
||||||
|
let document = parse_html(html);
|
||||||
|
|
||||||
|
let table_sel = Selector::parse("table").expect("Valid CSS selector");
|
||||||
|
let tr_sel = Selector::parse("tr").expect("Valid CSS selector");
|
||||||
|
let td_sel = Selector::parse("td").expect("Valid CSS selector");
|
||||||
|
|
||||||
|
let tables: Vec<_> = document.select(&table_sel).collect();
|
||||||
|
assert_eq!(tables.len(), 1, "Should have exactly 1 table");
|
||||||
|
|
||||||
|
let rows: Vec<_> = document.select(&tr_sel).collect();
|
||||||
|
assert_eq!(rows.len(), 1, "Should have exactly 1 row");
|
||||||
|
|
||||||
|
let cells: Vec<_> = document.select(&td_sel).collect();
|
||||||
|
assert_eq!(cells.len(), 1, "Should have exactly 1 cell");
|
||||||
|
|
||||||
|
if let Some(cell) = cells.first() {
|
||||||
|
let cell_text: String = cell.text().collect();
|
||||||
|
assert_eq!(
|
||||||
|
cell_text.trim(),
|
||||||
|
"cell content",
|
||||||
|
"Cell content should be preserved"
|
||||||
|
);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
fn test_expected_parsed_output_assertion(html: &str) {
|
||||||
|
let document = parse_html(html);
|
||||||
|
|
||||||
|
let body_sel = Selector::parse("body").expect("Valid CSS selector");
|
||||||
|
let body = document
|
||||||
|
.select(&body_sel)
|
||||||
|
.next()
|
||||||
|
.expect("body should exist");
|
||||||
|
let full_text: String = body.text().collect();
|
||||||
|
|
||||||
|
let expected_pattern = "orphaned textmore textcell content";
|
||||||
|
assert!(
|
||||||
|
full_text.contains(&expected_pattern)
|
||||||
|
|| (full_text.contains("orphaned text")
|
||||||
|
&& full_text.contains("more text")
|
||||||
|
&& full_text.contains("cell content")),
|
||||||
|
"Parsed output should contain all text content in fostered form. Got: '{}'",
|
||||||
|
full_text
|
||||||
|
);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[cfg(test)]
|
||||||
|
mod tests {
|
||||||
|
use super::*;
|
||||||
|
|
||||||
|
fn load_fixture() -> String {
|
||||||
|
fs::read_to_string("src/bin/test_fixtures/foster_parenting_minimal.html")
|
||||||
|
.expect("Failed to load fixture")
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_foster_parenting_text_extraction_test() {
|
||||||
|
let html = load_fixture();
|
||||||
|
test_foster_parenting_text_extraction(&html);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_foster_parenting_table_structure_test() {
|
||||||
|
let html = load_fixture();
|
||||||
|
test_foster_parenting_table_structure(&html);
|
||||||
|
}
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_expected_parsed_output_assertion_test() {
|
||||||
|
let html = load_fixture();
|
||||||
|
test_expected_parsed_output_assertion(&html);
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,83 @@
|
|||||||
|
//! Complete API generator - combines model, migration, controller, service, repository
|
||||||
|
|
||||||
|
use anyhow::Result;
|
||||||
|
|
||||||
|
pub fn generate_full_api(name: &str, full: bool) -> Result<()> {
|
||||||
|
println!("📦 Generating model...");
|
||||||
|
let model_name = singularize(name);
|
||||||
|
super::model::generate_model(&model_name, true, true, false)?;
|
||||||
|
|
||||||
|
if full {
|
||||||
|
println!("🔧 Generating service...");
|
||||||
|
super::service::generate_service(name, Some(&model_name))?;
|
||||||
|
|
||||||
|
println!("💾 Generating repository...");
|
||||||
|
super::repository::generate_repository(name, &model_name)?;
|
||||||
|
}
|
||||||
|
|
||||||
|
println!("🎮 Generating CRUD controller...");
|
||||||
|
super::controller::generate_controller(name, true, Some(&model_name))?;
|
||||||
|
|
||||||
|
println!("\n✅ Complete API generated!");
|
||||||
|
println!("\n📋 Generated files:");
|
||||||
|
println!(
|
||||||
|
" - src/entities/{}.rs (SeaORM model)",
|
||||||
|
model_name.to_lowercase()
|
||||||
|
);
|
||||||
|
println!(
|
||||||
|
" - migrations/m*_create_{}.rs (migration)",
|
||||||
|
super::model::pluralize(&model_name)
|
||||||
|
);
|
||||||
|
|
||||||
|
if full {
|
||||||
|
println!(" - src/services/{}_service.rs (service layer)", name);
|
||||||
|
println!(" - src/repositories/{}_repository.rs (repository)", name);
|
||||||
|
}
|
||||||
|
|
||||||
|
println!(" - src/routes/api/{}/index.rs (list)", name);
|
||||||
|
println!(" - src/routes/api/{}/[id].rs (get)", name);
|
||||||
|
println!(" - src/routes/api/{}/create.rs (create)", name);
|
||||||
|
println!(" - src/routes/api/{}/[id]/update.rs (update)", name);
|
||||||
|
println!(" - src/routes/api/{}/[id]/delete.rs (delete)", name);
|
||||||
|
|
||||||
|
println!("\n🚀 Next steps:");
|
||||||
|
println!(" 1. Run 'cargo build' to compile");
|
||||||
|
println!(" 2. Run migrations: cargo run -- migration up");
|
||||||
|
println!(" 3. Start server: cargo run");
|
||||||
|
|
||||||
|
println!("\n📡 Available endpoints:");
|
||||||
|
println!(" GET /api/{} - List all", name);
|
||||||
|
println!(" GET /api/{}/{{id}} - Get one", name);
|
||||||
|
println!(" POST /api/{} - Create", name);
|
||||||
|
println!(" PUT /api/{}/{{id}} - Update", name);
|
||||||
|
println!(" DELETE /api/{}/{{id}} - Delete", name);
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
|
|
||||||
|
fn singularize(word: &str) -> String {
|
||||||
|
let lower = word.to_lowercase();
|
||||||
|
|
||||||
|
if lower.ends_with("ies") {
|
||||||
|
format!("{}y", &lower[..lower.len() - 3])
|
||||||
|
} else if lower.ends_with("es") {
|
||||||
|
lower[..lower.len() - 2].to_string()
|
||||||
|
} else if lower.ends_with('s') {
|
||||||
|
lower[..lower.len() - 1].to_string()
|
||||||
|
} else {
|
||||||
|
lower
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
#[cfg(test)]
|
||||||
|
mod tests {
|
||||||
|
use super::*;
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_singularize() {
|
||||||
|
assert_eq!(singularize("users"), "user");
|
||||||
|
assert_eq!(singularize("categories"), "category");
|
||||||
|
assert_eq!(singularize("posts"), "post");
|
||||||
|
assert_eq!(singularize("boxes"), "box");
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,287 @@
|
|||||||
|
//! API controller generator with CRUD operations
|
||||||
|
|
||||||
|
use anyhow::Result;
|
||||||
|
use std::fs;
|
||||||
|
use std::path::Path;
|
||||||
|
|
||||||
|
pub fn generate_controller(name: &str, crud: bool, model: Option<&str>) -> Result<()> {
|
||||||
|
let api_dir = Path::new("src/routes/api").join(name);
|
||||||
|
fs::create_dir_all(&api_dir)?;
|
||||||
|
|
||||||
|
let model_name = model.map(|s| s.to_string()).unwrap_or_else(|| {
|
||||||
|
// Singularize the resource name
|
||||||
|
let singular = name.trim_end_matches('s');
|
||||||
|
format!("{}{}", &singular[..1].to_uppercase(), &singular[1..])
|
||||||
|
});
|
||||||
|
|
||||||
|
if crud {
|
||||||
|
generate_crud_routes(&api_dir, name, &model_name)?;
|
||||||
|
} else {
|
||||||
|
generate_basic_controller(&api_dir, name);
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_crud_routes(api_dir: &Path, resource: &str, model: &str) -> Result<()> {
|
||||||
|
// List all
|
||||||
|
let index_content = generate_list_handler(resource, model);
|
||||||
|
fs::write(api_dir.join("index.rs"), index_content)?;
|
||||||
|
|
||||||
|
// Get by ID
|
||||||
|
let show_content = generate_show_handler(resource, model);
|
||||||
|
fs::write(api_dir.join("[id].rs"), show_content)?;
|
||||||
|
|
||||||
|
// Create
|
||||||
|
let create_content = generate_create_handler(resource, model);
|
||||||
|
fs::write(api_dir.join("create.rs"), create_content)?;
|
||||||
|
|
||||||
|
// Update & Delete in [id] subdirectory
|
||||||
|
fs::create_dir_all(api_dir.join("[id]"))?;
|
||||||
|
|
||||||
|
let update_content = generate_update_handler(resource, model);
|
||||||
|
fs::write(api_dir.join("[id]/update.rs"), update_content)?;
|
||||||
|
|
||||||
|
let delete_content = generate_delete_handler(resource, model);
|
||||||
|
fs::write(api_dir.join("[id]/delete.rs"), delete_content)?;
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_list_handler(resource: &str, model: &str) -> String {
|
||||||
|
format!(
|
||||||
|
r#"//! List all {resource}
|
||||||
|
|
||||||
|
use axum::{{Extension, Json, response::IntoResponse, Router}};
|
||||||
|
use sea_orm::{{DatabaseConnection, EntityTrait}};
|
||||||
|
use std::sync::Arc;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
use crate::entities::{model_low}::{{Entity as {model}, Model}};
|
||||||
|
|
||||||
|
pub async fn list(
|
||||||
|
Extension(db): Extension<DatabaseConnection>,
|
||||||
|
) -> impl IntoResponse {{
|
||||||
|
match {model}.find().all(&db).await {{
|
||||||
|
Ok(items) => Json(items).into_response(),
|
||||||
|
Err(e) => {{
|
||||||
|
eprintln!("Error listing {resource}: {{}}", e);
|
||||||
|
(axum::http::StatusCode::INTERNAL_SERVER_ERROR, "Failed to list {resource}").into_response()
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub fn register_routes(router: Router<Arc<AppState>>) -> Router<Arc<AppState>> {{
|
||||||
|
router
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
resource = resource,
|
||||||
|
model_low = model.to_lowercase(),
|
||||||
|
model = model
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_show_handler(resource: &str, model: &str) -> String {
|
||||||
|
let singular = resource.trim_end_matches('s');
|
||||||
|
format!(
|
||||||
|
r#"//! Get {singular} by ID
|
||||||
|
|
||||||
|
use axum::{{Extension, Json, extract::Path, response::IntoResponse, Router}};
|
||||||
|
use sea_orm::{{DatabaseConnection, EntityTrait}};
|
||||||
|
use std::sync::Arc;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
use crate::entities::{model_low}::{{Entity as {model}, Model}};
|
||||||
|
|
||||||
|
pub async fn show(
|
||||||
|
Path(id): Path<i32>,
|
||||||
|
Extension(db): Extension<DatabaseConnection>,
|
||||||
|
) -> impl IntoResponse {{
|
||||||
|
match {model}.find_by_id(id).one(&db).await {{
|
||||||
|
Ok(Some(item)) => Json(item).into_response(),
|
||||||
|
Ok(None) => (axum::http::StatusCode::NOT_FOUND, "{singular} not found").into_response(),
|
||||||
|
Err(e) => {{
|
||||||
|
eprintln!("Error getting {singular}: {{}}", e);
|
||||||
|
(axum::http::StatusCode::INTERNAL_SERVER_ERROR, "Failed to get {singular}").into_response()
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub fn register_routes(router: Router<Arc<AppState>>) -> Router<Arc<AppState>> {{
|
||||||
|
router
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
singular = singular,
|
||||||
|
model_low = model.to_lowercase(),
|
||||||
|
model = model,
|
||||||
|
resource = resource
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_create_handler(resource: &str, model: &str) -> String {
|
||||||
|
let singular = resource.trim_end_matches('s');
|
||||||
|
format!(
|
||||||
|
r#"//! Create new {singular}
|
||||||
|
|
||||||
|
use axum::{{Extension, Json, response::IntoResponse, Router}};
|
||||||
|
use sea_orm::{{ActiveModelTrait, DatabaseConnection, Set}};
|
||||||
|
use serde::{{Deserialize, Serialize}};
|
||||||
|
use std::sync::Arc;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
use crate::entities::{model_low}::{{ActiveModel, Model}};
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize)]
|
||||||
|
pub struct Create{model}Dto {{
|
||||||
|
pub name: String,
|
||||||
|
// Add your fields
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub async fn create(
|
||||||
|
Extension(db): Extension<DatabaseConnection>,
|
||||||
|
Json(data): Json<Create{model}Dto>,
|
||||||
|
) -> impl IntoResponse {{
|
||||||
|
let new_item = ActiveModel {{
|
||||||
|
name: Set(data.name),
|
||||||
|
..Default::default()
|
||||||
|
}};
|
||||||
|
|
||||||
|
match new_item.insert(&db).await {{
|
||||||
|
Ok(item) => (axum::http::StatusCode::CREATED, Json(item)).into_response(),
|
||||||
|
Err(e) => {{
|
||||||
|
eprintln!("Error creating {singular}: {{}}", e);
|
||||||
|
(axum::http::StatusCode::INTERNAL_SERVER_ERROR, "Failed to create {singular}").into_response()
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub fn register_routes(router: Router<Arc<AppState>>) -> Router<Arc<AppState>> {{
|
||||||
|
router
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
singular = singular,
|
||||||
|
model_low = model.to_lowercase(),
|
||||||
|
model = model,
|
||||||
|
resource = resource
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_update_handler(resource: &str, model: &str) -> String {
|
||||||
|
let singular = resource.trim_end_matches('s');
|
||||||
|
format!(
|
||||||
|
r#"//! Update {singular}
|
||||||
|
|
||||||
|
use axum::{{Extension, Json, extract::Path, response::IntoResponse, Router}};
|
||||||
|
use sea_orm::{{ActiveModelTrait, DatabaseConnection, EntityTrait, Set}};
|
||||||
|
use serde::{{Deserialize, Serialize}};
|
||||||
|
use std::sync::Arc;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
use crate::entities::{model_low}::{{ActiveModel, Entity as {model}, Model}};
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize)]
|
||||||
|
pub struct Update{model}Dto {{
|
||||||
|
pub name: Option<String>,
|
||||||
|
// Add your fields
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub async fn update(
|
||||||
|
Path(id): Path<i32>,
|
||||||
|
Extension(db): Extension<DatabaseConnection>,
|
||||||
|
Json(data): Json<Update{model}Dto>,
|
||||||
|
) -> impl IntoResponse {{
|
||||||
|
let item = match {model}.find_by_id(id).one(&db).await {{
|
||||||
|
Ok(Some(item)) => item,
|
||||||
|
Ok(None) => return (axum::http::StatusCode::NOT_FOUND, "{singular} not found").into_response(),
|
||||||
|
Err(e) => {{
|
||||||
|
eprintln!("Error finding {singular}: {{}}", e);
|
||||||
|
return (axum::http::StatusCode::INTERNAL_SERVER_ERROR, "Failed to find {singular}").into_response();
|
||||||
|
}}
|
||||||
|
}};
|
||||||
|
|
||||||
|
let mut active_model: ActiveModel = item.into();
|
||||||
|
if let Some(name) = data.name {{
|
||||||
|
active_model.name = Set(name);
|
||||||
|
}}
|
||||||
|
|
||||||
|
match active_model.update(&db).await {{
|
||||||
|
Ok(updated) => Json(updated).into_response(),
|
||||||
|
Err(e) => {{
|
||||||
|
eprintln!("Error updating {singular}: {{}}", e);
|
||||||
|
(axum::http::StatusCode::INTERNAL_SERVER_ERROR, "Failed to update {singular}").into_response()
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub fn register_routes(router: Router<Arc<AppState>>) -> Router<Arc<AppState>> {{
|
||||||
|
router
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
singular = singular,
|
||||||
|
model_low = model.to_lowercase(),
|
||||||
|
model = model,
|
||||||
|
resource = resource
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_delete_handler(resource: &str, model: &str) -> String {
|
||||||
|
let singular = resource.trim_end_matches('s');
|
||||||
|
format!(
|
||||||
|
r#"//! Delete {singular}
|
||||||
|
|
||||||
|
use axum::{{Extension, extract::Path, response::IntoResponse, Router}};
|
||||||
|
use sea_orm::{{ActiveModelTrait, DatabaseConnection, EntityTrait, IntoActiveModel}};
|
||||||
|
use std::sync::Arc;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
use crate::entities::{model_low}::{{Entity as {model}}};
|
||||||
|
|
||||||
|
pub async fn destroy(
|
||||||
|
Path(id): Path<i32>,
|
||||||
|
Extension(db): Extension<DatabaseConnection>,
|
||||||
|
) -> impl IntoResponse {{
|
||||||
|
let item = match {model}.find_by_id(id).one(&db).await {{
|
||||||
|
Ok(Some(item)) => item,
|
||||||
|
Ok(None) => return (axum::http::StatusCode::NOT_FOUND, "{singular} not found").into_response(),
|
||||||
|
Err(e) => {{
|
||||||
|
eprintln!("Error finding {singular}: {{}}", e);
|
||||||
|
return (axum::http::StatusCode::INTERNAL_SERVER_ERROR, "Failed to find {singular}").into_response();
|
||||||
|
}}
|
||||||
|
}};
|
||||||
|
|
||||||
|
match item.into_active_model().delete(&db).await {{
|
||||||
|
Ok(_) => axum::http::StatusCode::NO_CONTENT.into_response(),
|
||||||
|
Err(e) => {{
|
||||||
|
eprintln!("Error deleting {singular}: {{}}", e);
|
||||||
|
(axum::http::StatusCode::INTERNAL_SERVER_ERROR, "Failed to delete {singular}").into_response()
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub fn register_routes(router: Router<Arc<AppState>>) -> Router<Arc<AppState>> {{
|
||||||
|
router
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
singular = singular,
|
||||||
|
model_low = model.to_lowercase(),
|
||||||
|
model = model,
|
||||||
|
resource = resource
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_basic_controller(api_dir: &Path, resource: &str) {
|
||||||
|
let content = format!(
|
||||||
|
r#"//! {resource} controller
|
||||||
|
|
||||||
|
use axum::Router;
|
||||||
|
use std::sync::Arc;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
|
||||||
|
pub async fn index() -> &'static str {{
|
||||||
|
"{resource} endpoint"
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub fn register_routes(router: Router<Arc<AppState>>) -> Router<Arc<AppState>> {{
|
||||||
|
router
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
resource = resource
|
||||||
|
);
|
||||||
|
|
||||||
|
let _ = fs::write(api_dir.join("index.rs"), content);
|
||||||
|
}
|
||||||
@@ -0,0 +1,262 @@
|
|||||||
|
//! Database migration generator
|
||||||
|
|
||||||
|
use anyhow::{Context, Result};
|
||||||
|
use chrono::Local;
|
||||||
|
use std::fs;
|
||||||
|
use std::path::Path;
|
||||||
|
|
||||||
|
pub fn generate_migration(name: &str, table: Option<&str>) -> Result<()> {
|
||||||
|
let timestamp = Local::now().format("%Y%m%d%H%M%S");
|
||||||
|
let file_name = format!("m{}_{}.rs", timestamp, name);
|
||||||
|
|
||||||
|
let migrations_dir = Path::new("migrations");
|
||||||
|
fs::create_dir_all(migrations_dir)?;
|
||||||
|
|
||||||
|
let content = if let Some(table_name) = table {
|
||||||
|
generate_create_table_migration(table_name)
|
||||||
|
} else {
|
||||||
|
generate_empty_migration()
|
||||||
|
};
|
||||||
|
|
||||||
|
let migration_path = migrations_dir.join(&file_name);
|
||||||
|
fs::write(&migration_path, content)
|
||||||
|
.with_context(|| format!("Failed to write migration: {:?}", migration_path))?;
|
||||||
|
|
||||||
|
update_migrations_mod(&file_name)?;
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn generate_model_migration(table: &str, timestamps: bool, soft_delete: bool) -> Result<()> {
|
||||||
|
let timestamp = Local::now().format("%Y%m%d%H%M%S");
|
||||||
|
let name = format!("create_{}_table", table);
|
||||||
|
let file_name = format!("m{}_{}.rs", timestamp, name);
|
||||||
|
|
||||||
|
let migrations_dir = Path::new("migrations");
|
||||||
|
fs::create_dir_all(migrations_dir)?;
|
||||||
|
|
||||||
|
let content = generate_model_table_migration(table, timestamps, soft_delete);
|
||||||
|
|
||||||
|
let migration_path = migrations_dir.join(&file_name);
|
||||||
|
fs::write(&migration_path, content)?;
|
||||||
|
|
||||||
|
update_migrations_mod(&file_name)?;
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_create_table_migration(table: &str) -> String {
|
||||||
|
let struct_name = table
|
||||||
|
.split('_')
|
||||||
|
.map(|s| {
|
||||||
|
let mut c = s.chars();
|
||||||
|
match c.next() {
|
||||||
|
None => String::new(),
|
||||||
|
Some(f) => f.to_uppercase().chain(c).collect(),
|
||||||
|
}
|
||||||
|
})
|
||||||
|
.collect::<String>();
|
||||||
|
|
||||||
|
format!(
|
||||||
|
r#"use sea_orm_migration::prelude::*;
|
||||||
|
|
||||||
|
#[derive(DeriveMigrationName)]
|
||||||
|
pub struct Migration;
|
||||||
|
|
||||||
|
#[async_trait::async_trait]
|
||||||
|
impl MigrationTrait for Migration {{
|
||||||
|
async fn up(&self, manager: &SchemaManager) -> Result<(), DbErr> {{
|
||||||
|
manager
|
||||||
|
.create_table(
|
||||||
|
Table::create()
|
||||||
|
.table({table}::Table)
|
||||||
|
.if_not_exists()
|
||||||
|
.col(
|
||||||
|
ColumnDef::new({table}::Id)
|
||||||
|
.integer()
|
||||||
|
.not_null()
|
||||||
|
.auto_increment()
|
||||||
|
.primary_key(),
|
||||||
|
)
|
||||||
|
.col(ColumnDef::new({table}::Name).string().not_null())
|
||||||
|
.to_owned(),
|
||||||
|
)
|
||||||
|
.await
|
||||||
|
}}
|
||||||
|
|
||||||
|
async fn down(&self, manager: &SchemaManager) -> Result<(), DbErr> {{
|
||||||
|
manager
|
||||||
|
.drop_table(Table::drop().table({table}::Table).to_owned())
|
||||||
|
.await
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
|
||||||
|
#[derive(DeriveIden)]
|
||||||
|
enum {table} {{
|
||||||
|
Table,
|
||||||
|
Id,
|
||||||
|
Name,
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
table = struct_name
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_model_table_migration(table: &str, timestamps: bool, soft_delete: bool) -> String {
|
||||||
|
let table_pascal = table
|
||||||
|
.split('_')
|
||||||
|
.map(|s| {
|
||||||
|
let mut c = s.chars();
|
||||||
|
match c.next() {
|
||||||
|
None => String::new(),
|
||||||
|
Some(f) => f.to_uppercase().chain(c).collect(),
|
||||||
|
}
|
||||||
|
})
|
||||||
|
.collect::<String>();
|
||||||
|
|
||||||
|
let timestamp_cols = if timestamps {
|
||||||
|
format!(
|
||||||
|
r#"
|
||||||
|
.col(ColumnDef::new({}::CreatedAt).timestamp().null())
|
||||||
|
.col(ColumnDef::new({}::UpdatedAt).timestamp().null())"#,
|
||||||
|
table_pascal, table_pascal
|
||||||
|
)
|
||||||
|
} else {
|
||||||
|
String::new()
|
||||||
|
};
|
||||||
|
|
||||||
|
let soft_delete_col = if soft_delete {
|
||||||
|
format!(
|
||||||
|
r#"
|
||||||
|
.col(ColumnDef::new({}::DeletedAt).timestamp().null())"#,
|
||||||
|
table_pascal
|
||||||
|
)
|
||||||
|
} else {
|
||||||
|
String::new()
|
||||||
|
};
|
||||||
|
|
||||||
|
let enum_fields = if timestamps && soft_delete {
|
||||||
|
format!(" CreatedAt,\n UpdatedAt,\n DeletedAt,")
|
||||||
|
} else if timestamps {
|
||||||
|
format!(" CreatedAt,\n UpdatedAt,")
|
||||||
|
} else if soft_delete {
|
||||||
|
format!(" DeletedAt,")
|
||||||
|
} else {
|
||||||
|
String::new()
|
||||||
|
};
|
||||||
|
|
||||||
|
format!(
|
||||||
|
r#"use sea_orm_migration::prelude::*;
|
||||||
|
|
||||||
|
#[derive(DeriveMigrationName)]
|
||||||
|
pub struct Migration;
|
||||||
|
|
||||||
|
#[async_trait::async_trait]
|
||||||
|
impl MigrationTrait for Migration {{
|
||||||
|
async fn up(&self, manager: &SchemaManager) -> Result<(), DbErr> {{
|
||||||
|
manager
|
||||||
|
.create_table(
|
||||||
|
Table::create()
|
||||||
|
.table({table}::Table)
|
||||||
|
.if_not_exists()
|
||||||
|
.col(
|
||||||
|
ColumnDef::new({table}::Id)
|
||||||
|
.integer()
|
||||||
|
.not_null()
|
||||||
|
.auto_increment()
|
||||||
|
.primary_key(),
|
||||||
|
)
|
||||||
|
.col(ColumnDef::new({table}::Name).string().not_null()){timestamps}{soft_delete}
|
||||||
|
.to_owned(),
|
||||||
|
)
|
||||||
|
.await
|
||||||
|
}}
|
||||||
|
|
||||||
|
async fn down(&self, manager: &SchemaManager) -> Result<(), DbErr> {{
|
||||||
|
manager
|
||||||
|
.drop_table(Table::drop().table({table}::Table).to_owned())
|
||||||
|
.await
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
|
||||||
|
#[derive(DeriveIden)]
|
||||||
|
enum {table} {{
|
||||||
|
Table,
|
||||||
|
Id,
|
||||||
|
Name,
|
||||||
|
{enum_fields}
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
table = table_pascal,
|
||||||
|
timestamps = timestamp_cols,
|
||||||
|
soft_delete = soft_delete_col,
|
||||||
|
enum_fields = enum_fields
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_empty_migration() -> String {
|
||||||
|
format!(
|
||||||
|
r#"use sea_orm_migration::prelude::*;
|
||||||
|
|
||||||
|
#[derive(DeriveMigrationName)]
|
||||||
|
pub struct Migration;
|
||||||
|
|
||||||
|
#[async_trait::async_trait]
|
||||||
|
impl MigrationTrait for Migration {{
|
||||||
|
async fn up(&self, manager: &SchemaManager) -> Result<(), DbErr> {{
|
||||||
|
// Add your migration logic here
|
||||||
|
Ok(())
|
||||||
|
}}
|
||||||
|
|
||||||
|
async fn down(&self, manager: &SchemaManager) -> Result<(), DbErr> {{
|
||||||
|
// Add your rollback logic here
|
||||||
|
Ok(())
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
"#
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn update_migrations_mod(file_name: &str) -> Result<()> {
|
||||||
|
let mod_path = Path::new("migrations/mod.rs");
|
||||||
|
let module_name = file_name.trim_end_matches(".rs");
|
||||||
|
let module_line = format!("mod {};", module_name);
|
||||||
|
|
||||||
|
if mod_path.exists() {
|
||||||
|
let content = fs::read_to_string(mod_path)?;
|
||||||
|
if !content.contains(&module_line) {
|
||||||
|
// Find the vec![] and add migration
|
||||||
|
let new_content = if content.contains("vec![") {
|
||||||
|
content.replace(
|
||||||
|
"vec![",
|
||||||
|
&format!("vec![\n Box::new({}::Migration),", module_name),
|
||||||
|
)
|
||||||
|
} else {
|
||||||
|
format!("{}\n{}", content.trim(), module_line)
|
||||||
|
};
|
||||||
|
fs::write(mod_path, new_content)?;
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
let initial_content = format!(
|
||||||
|
r#"pub use sea_orm_migration::prelude::*;
|
||||||
|
|
||||||
|
{}
|
||||||
|
|
||||||
|
pub struct Migrator;
|
||||||
|
|
||||||
|
#[async_trait::async_trait]
|
||||||
|
impl MigratorTrait for Migrator {{
|
||||||
|
fn migrations() -> Vec<Box<dyn MigrationTrait>> {{
|
||||||
|
vec![
|
||||||
|
Box::new({}::Migration),
|
||||||
|
]
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
module_line, module_name
|
||||||
|
);
|
||||||
|
fs::write(mod_path, initial_content)?;
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
@@ -0,0 +1,7 @@
|
|||||||
|
// Module declarations for generators
|
||||||
|
pub mod api;
|
||||||
|
pub mod controller;
|
||||||
|
pub mod migration;
|
||||||
|
pub mod model;
|
||||||
|
pub mod repository;
|
||||||
|
pub mod service;
|
||||||
@@ -0,0 +1,125 @@
|
|||||||
|
//! SeaORM model generator
|
||||||
|
|
||||||
|
use anyhow::{Context, Result};
|
||||||
|
use std::fs;
|
||||||
|
use std::path::Path;
|
||||||
|
|
||||||
|
pub fn generate_model(
|
||||||
|
name: &str,
|
||||||
|
with_migration: bool,
|
||||||
|
timestamps: bool,
|
||||||
|
soft_delete: bool,
|
||||||
|
) -> Result<()> {
|
||||||
|
let table_name = pluralize(name);
|
||||||
|
|
||||||
|
// Create entities directory
|
||||||
|
let entities_dir = Path::new("src/entities");
|
||||||
|
fs::create_dir_all(entities_dir)?;
|
||||||
|
|
||||||
|
// Generate model file
|
||||||
|
let model_content = generate_model_content(name, &table_name, timestamps, soft_delete);
|
||||||
|
let model_path = entities_dir.join(format!("{}.rs", name.to_lowercase()));
|
||||||
|
fs::write(&model_path, model_content)
|
||||||
|
.with_context(|| format!("Failed to write model file: {:?}", model_path))?;
|
||||||
|
|
||||||
|
// Update entities/mod.rs
|
||||||
|
update_entities_mod(name)?;
|
||||||
|
|
||||||
|
// Generate migration if requested
|
||||||
|
if with_migration {
|
||||||
|
super::migration::generate_model_migration(&table_name, timestamps, soft_delete)?;
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_model_content(
|
||||||
|
name: &str,
|
||||||
|
table_name: &str,
|
||||||
|
timestamps: bool,
|
||||||
|
soft_delete: bool,
|
||||||
|
) -> String {
|
||||||
|
let timestamp_fields = if timestamps {
|
||||||
|
r#"
|
||||||
|
#[sea_orm(nullable)]
|
||||||
|
pub created_at: Option<DateTimeUtc>,
|
||||||
|
#[sea_orm(nullable)]
|
||||||
|
pub updated_at: Option<DateTimeUtc>,"#
|
||||||
|
} else {
|
||||||
|
""
|
||||||
|
};
|
||||||
|
|
||||||
|
let soft_delete_field = if soft_delete {
|
||||||
|
r#"
|
||||||
|
#[sea_orm(nullable)]
|
||||||
|
pub deleted_at: Option<DateTimeUtc>,"#
|
||||||
|
} else {
|
||||||
|
""
|
||||||
|
};
|
||||||
|
|
||||||
|
format!(
|
||||||
|
r#"//! {} entity
|
||||||
|
|
||||||
|
use sea_orm::entity::prelude::*;
|
||||||
|
use serde::{{Deserialize, Serialize}};
|
||||||
|
|
||||||
|
#[derive(Clone, Debug, PartialEq, DeriveEntityModel, Serialize, Deserialize)]
|
||||||
|
#[sea_orm(table_name = "{}")]
|
||||||
|
pub struct Model {{
|
||||||
|
#[sea_orm(primary_key)]
|
||||||
|
pub id: i32,
|
||||||
|
|
||||||
|
// Add your fields here
|
||||||
|
pub name: String,{}{}
|
||||||
|
}}
|
||||||
|
|
||||||
|
#[derive(Copy, Clone, Debug, EnumIter, DeriveRelation)]
|
||||||
|
pub enum Relation {{}}
|
||||||
|
|
||||||
|
impl ActiveModelBehavior for ActiveModel {{}}
|
||||||
|
"#,
|
||||||
|
name, table_name, timestamp_fields, soft_delete_field
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn update_entities_mod(name: &str) -> Result<()> {
|
||||||
|
let mod_path = Path::new("src/entities/mod.rs");
|
||||||
|
let module_line = format!("pub mod {};", name.to_lowercase());
|
||||||
|
|
||||||
|
if mod_path.exists() {
|
||||||
|
let content = fs::read_to_string(mod_path)?;
|
||||||
|
if !content.contains(&module_line) {
|
||||||
|
let new_content = format!("{}\n{}", content.trim(), module_line);
|
||||||
|
fs::write(mod_path, new_content)?;
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
fs::write(mod_path, format!("{}\n", module_line))?;
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn pluralize(word: &str) -> String {
|
||||||
|
let lower = word.to_lowercase();
|
||||||
|
|
||||||
|
if lower.ends_with('y') {
|
||||||
|
format!("{}ies", &lower[..lower.len() - 1])
|
||||||
|
} else if lower.ends_with('s') || lower.ends_with("ch") || lower.ends_with("sh") || lower.ends_with('x') {
|
||||||
|
format!("{}es", lower)
|
||||||
|
} else {
|
||||||
|
format!("{}s", lower)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
#[cfg(test)]
|
||||||
|
mod tests {
|
||||||
|
use super::*;
|
||||||
|
|
||||||
|
#[test]
|
||||||
|
fn test_pluralize() {
|
||||||
|
assert_eq!(pluralize("User"), "users");
|
||||||
|
assert_eq!(pluralize("Category"), "categories");
|
||||||
|
assert_eq!(pluralize("Post"), "posts");
|
||||||
|
assert_eq!(pluralize("Box"), "boxes");
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,112 @@
|
|||||||
|
//! Repository pattern generator
|
||||||
|
|
||||||
|
use anyhow::{Context, Result};
|
||||||
|
use std::fs;
|
||||||
|
use std::path::Path;
|
||||||
|
|
||||||
|
pub fn generate_repository(name: &str, model: &str) -> Result<()> {
|
||||||
|
let repos_dir = Path::new("src/repositories");
|
||||||
|
fs::create_dir_all(repos_dir)?;
|
||||||
|
|
||||||
|
let repo_content = generate_repository_content(name, model);
|
||||||
|
|
||||||
|
let repo_path = repos_dir.join(format!("{}_repository.rs", name.to_lowercase()));
|
||||||
|
fs::write(&repo_path, repo_content)
|
||||||
|
.with_context(|| format!("Failed to write repository: {:?}", repo_path))?;
|
||||||
|
|
||||||
|
update_repositories_mod(name)?;
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_repository_content(name: &str, model: &str) -> String {
|
||||||
|
format!(
|
||||||
|
r#"//! {} repository
|
||||||
|
|
||||||
|
use sea_orm::*;
|
||||||
|
use crate::entities::{}::{{Entity as {}, Model, ActiveModel, Column}};
|
||||||
|
|
||||||
|
#[derive(Clone)]
|
||||||
|
pub struct {}Repository {{
|
||||||
|
db: DatabaseConnection,
|
||||||
|
}}
|
||||||
|
|
||||||
|
impl {}Repository {{
|
||||||
|
pub fn new(db: DatabaseConnection) -> Self {{
|
||||||
|
Self {{ db }}
|
||||||
|
}}
|
||||||
|
|
||||||
|
/// Find all records
|
||||||
|
pub async fn find_all(&self) -> Result<Vec<Model>, DbErr> {{
|
||||||
|
{}.find().all(&self.db).await
|
||||||
|
}}
|
||||||
|
|
||||||
|
/// Find by ID
|
||||||
|
pub async fn find_by_id(&self, id: i32) -> Result<Option<Model>, DbErr> {{
|
||||||
|
{}.find_by_id(id).one(&self.db).await
|
||||||
|
}}
|
||||||
|
|
||||||
|
/// Find with pagination
|
||||||
|
pub async fn paginate(&self, page: u64, per_page: u64) -> Result<(Vec<Model>, u64), DbErr> {{
|
||||||
|
let paginator = {}.find()
|
||||||
|
.paginate(&self.db, per_page);
|
||||||
|
|
||||||
|
let total = paginator.num_items().await?;
|
||||||
|
let items = paginator.fetch_page(page).await?;
|
||||||
|
|
||||||
|
Ok((items, total))
|
||||||
|
}}
|
||||||
|
|
||||||
|
/// Create new record
|
||||||
|
pub async fn create(&self, data: ActiveModel) -> Result<Model, DbErr> {{
|
||||||
|
data.insert(&self.db).await
|
||||||
|
}}
|
||||||
|
|
||||||
|
/// Update existing record
|
||||||
|
pub async fn update(&self, data: ActiveModel) -> Result<Model, DbErr> {{
|
||||||
|
data.update(&self.db).await
|
||||||
|
}}
|
||||||
|
|
||||||
|
/// Delete by ID
|
||||||
|
pub async fn delete(&self, id: i32) -> Result<DeleteResult, DbErr> {{
|
||||||
|
{}.delete_by_id(id).exec(&self.db).await
|
||||||
|
}}
|
||||||
|
|
||||||
|
/// Find by custom condition
|
||||||
|
pub async fn find_by_name(&self, name: &str) -> Result<Vec<Model>, DbErr> {{
|
||||||
|
{}.find()
|
||||||
|
.filter(Column::Name.contains(name))
|
||||||
|
.all(&self.db)
|
||||||
|
.await
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
name,
|
||||||
|
model.to_lowercase(),
|
||||||
|
model,
|
||||||
|
model,
|
||||||
|
model,
|
||||||
|
model,
|
||||||
|
model,
|
||||||
|
model,
|
||||||
|
model,
|
||||||
|
model
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn update_repositories_mod(name: &str) -> Result<()> {
|
||||||
|
let mod_path = Path::new("src/repositories/mod.rs");
|
||||||
|
let module_line = format!("pub mod {}_repository;", name.to_lowercase());
|
||||||
|
|
||||||
|
if mod_path.exists() {
|
||||||
|
let content = fs::read_to_string(mod_path)?;
|
||||||
|
if !content.contains(&module_line) {
|
||||||
|
let new_content = format!("{}\n{}", content.trim(), module_line);
|
||||||
|
fs::write(mod_path, new_content)?;
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
fs::write(mod_path, format!("{}\n", module_line))?;
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
@@ -0,0 +1,86 @@
|
|||||||
|
//! Service layer generator
|
||||||
|
|
||||||
|
use anyhow::{Context, Result};
|
||||||
|
use std::fs;
|
||||||
|
use std::path::Path;
|
||||||
|
|
||||||
|
pub fn generate_service(name: &str, model: Option<&str>) -> Result<()> {
|
||||||
|
let services_dir = Path::new("src/services");
|
||||||
|
fs::create_dir_all(services_dir)?;
|
||||||
|
|
||||||
|
let model_name = model.unwrap_or(name);
|
||||||
|
let service_content = generate_service_content(name, model_name);
|
||||||
|
|
||||||
|
let service_path = services_dir.join(format!("{}_service.rs", name.to_lowercase()));
|
||||||
|
fs::write(&service_path, service_content)
|
||||||
|
.with_context(|| format!("Failed to write service: {:?}", service_path))?;
|
||||||
|
|
||||||
|
update_services_mod(name)?;
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
|
|
||||||
|
fn generate_service_content(name: &str, model: &str) -> String {
|
||||||
|
format!(
|
||||||
|
r#"//! {} service layer
|
||||||
|
|
||||||
|
use sea_orm::*;
|
||||||
|
use crate::entities::{}::{{Entity as {}, Model, ActiveModel}};
|
||||||
|
|
||||||
|
pub struct {}Service {{
|
||||||
|
db: DatabaseConnection,
|
||||||
|
}}
|
||||||
|
|
||||||
|
impl {}Service {{
|
||||||
|
pub fn new(db: DatabaseConnection) -> Self {{
|
||||||
|
Self {{ db }}
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub async fn find_all(&self) -> Result<Vec<Model>, DbErr> {{
|
||||||
|
{}.find().all(&self.db).await
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub async fn find_by_id(&self, id: i32) -> Result<Option<Model>, DbErr> {{
|
||||||
|
{}.find_by_id(id).one(&self.db).await
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub async fn create(&self, data: ActiveModel) -> Result<Model, DbErr> {{
|
||||||
|
data.insert(&self.db).await
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub async fn update(&self, id: i32, data: ActiveModel) -> Result<Model, DbErr> {{
|
||||||
|
data.update(&self.db).await
|
||||||
|
}}
|
||||||
|
|
||||||
|
pub async fn delete(&self, id: i32) -> Result<DeleteResult, DbErr> {{
|
||||||
|
{}.delete_by_id(id).exec(&self.db).await
|
||||||
|
}}
|
||||||
|
}}
|
||||||
|
"#,
|
||||||
|
name,
|
||||||
|
model.to_lowercase(),
|
||||||
|
model,
|
||||||
|
model,
|
||||||
|
model,
|
||||||
|
model,
|
||||||
|
model,
|
||||||
|
model
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
fn update_services_mod(name: &str) -> Result<()> {
|
||||||
|
let mod_path = Path::new("src/services/mod.rs");
|
||||||
|
let module_line = format!("pub mod {}_service;", name.to_lowercase());
|
||||||
|
|
||||||
|
if mod_path.exists() {
|
||||||
|
let content = fs::read_to_string(mod_path)?;
|
||||||
|
if !content.contains(&module_line) {
|
||||||
|
let new_content = format!("{}\n{}", content.trim(), module_line);
|
||||||
|
fs::write(mod_path, new_content)?;
|
||||||
|
}
|
||||||
|
} else {
|
||||||
|
fs::write(mod_path, format!("{}\n", module_line))?;
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
@@ -0,0 +1 @@
|
|||||||
|
<table>orphaned text<tr><td>cell content</td></tr>more text</table>
|
||||||
@@ -0,0 +1,118 @@
|
|||||||
|
use std::net::SocketAddr;
|
||||||
|
use std::sync::Arc;
|
||||||
|
use tokio::net::TcpListener;
|
||||||
|
|
||||||
|
use axum::Router;
|
||||||
|
use sea_orm::Database;
|
||||||
|
use tracing_subscriber::EnvFilter;
|
||||||
|
|
||||||
|
use crate::shared::config::CONFIG;
|
||||||
|
use crate::shared::database::get_redis_conn;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
|
||||||
|
pub struct Application {
|
||||||
|
pub port: u16,
|
||||||
|
router: Router,
|
||||||
|
listener: TcpListener,
|
||||||
|
}
|
||||||
|
|
||||||
|
impl Application {
|
||||||
|
pub async fn build() -> anyhow::Result<Self> {
|
||||||
|
// Initialize tracing. Default to warn/error globally unless RUST_LOG is explicitly set.
|
||||||
|
let env_filter = match std::env::var("RUST_LOG") {
|
||||||
|
Ok(filter) => EnvFilter::new(filter).add_directive("html5ever=error".parse()?),
|
||||||
|
Err(_) => EnvFilter::new("warn,html5ever=error"),
|
||||||
|
};
|
||||||
|
|
||||||
|
tracing_subscriber::fmt().with_env_filter(env_filter).init();
|
||||||
|
|
||||||
|
// Initialize OpenTelemetry metrics
|
||||||
|
crate::shared::observability::metrics::init_otel_metrics();
|
||||||
|
|
||||||
|
tracing::info!("🚀 Scraper starting up...");
|
||||||
|
tracing::info!(" Environment: {}", CONFIG.environment);
|
||||||
|
|
||||||
|
// Log thread configuration
|
||||||
|
let worker_threads = std::thread::available_parallelism()
|
||||||
|
.map(|n| n.get())
|
||||||
|
.unwrap_or(1);
|
||||||
|
tracing::info!(
|
||||||
|
" Tokio Worker Threads: (Defaulting to CPU cores: {})",
|
||||||
|
worker_threads
|
||||||
|
);
|
||||||
|
|
||||||
|
// Redis
|
||||||
|
let _ = get_redis_conn().await;
|
||||||
|
|
||||||
|
// Browser Pool
|
||||||
|
tracing::info!("Initializing browser pool...");
|
||||||
|
let browser_config = crate::shared::browser::BrowserPoolConfig::default();
|
||||||
|
match crate::shared::browser::pool::init_browser_pool(browser_config).await {
|
||||||
|
Ok(_) => tracing::info!("✓ Browser pool initialized"),
|
||||||
|
Err(e) => tracing::error!("⚠️ Failed to initialize browser pool: {}", e),
|
||||||
|
}
|
||||||
|
|
||||||
|
// Database
|
||||||
|
let mut opt = sea_orm::ConnectOptions::new(CONFIG.database_url.clone());
|
||||||
|
opt.max_connections(20)
|
||||||
|
.min_connections(1)
|
||||||
|
.connect_timeout(std::time::Duration::from_secs(
|
||||||
|
CONFIG.db.connect_timeout_seconds,
|
||||||
|
))
|
||||||
|
.idle_timeout(std::time::Duration::from_secs(
|
||||||
|
CONFIG.db.idle_timeout_seconds,
|
||||||
|
))
|
||||||
|
.acquire_timeout(std::time::Duration::from_secs(
|
||||||
|
CONFIG.db.acquire_timeout_seconds,
|
||||||
|
))
|
||||||
|
.max_lifetime(std::time::Duration::from_secs(
|
||||||
|
CONFIG.db.max_lifetime_seconds,
|
||||||
|
))
|
||||||
|
.sqlx_logging(CONFIG.log_level == "debug");
|
||||||
|
|
||||||
|
let db = Database::connect(opt)
|
||||||
|
.await
|
||||||
|
.map_err(|e| anyhow::anyhow!("Failed to connect to database: {}", e))?;
|
||||||
|
tracing::info!("✓ SeaORM database connection established");
|
||||||
|
|
||||||
|
// Schema & Seeding
|
||||||
|
if let Err(e) = crate::shared::database::setup::init(&db).await {
|
||||||
|
tracing::error!("Failed to init DB schema: {}", e);
|
||||||
|
}
|
||||||
|
|
||||||
|
// App State components
|
||||||
|
let db_arc = Arc::new(db);
|
||||||
|
let image_processing_semaphore = Arc::new(tokio::sync::Semaphore::new(
|
||||||
|
CONFIG.image_processing_concurrency,
|
||||||
|
));
|
||||||
|
let event_bus = Arc::new(crate::shared::events::bus::EventBus::new());
|
||||||
|
|
||||||
|
let redis_pool = crate::shared::database::redis_pool()
|
||||||
|
.map_err(|e| anyhow::anyhow!("Failed to init Redis pool: {}", e))?;
|
||||||
|
|
||||||
|
let app_state = Arc::new(AppState {
|
||||||
|
redis_pool,
|
||||||
|
db: db_arc.clone(),
|
||||||
|
image_processing_semaphore,
|
||||||
|
event_bus: event_bus.clone(),
|
||||||
|
});
|
||||||
|
|
||||||
|
let app = crate::app::build_router(app_state, db_arc.clone()).await?;
|
||||||
|
|
||||||
|
// Listener
|
||||||
|
let port = CONFIG.server_port;
|
||||||
|
let addr = SocketAddr::from(([0, 0, 0, 0], port));
|
||||||
|
let listener = TcpListener::bind(&addr).await?;
|
||||||
|
tracing::info!("Server listening on {}", listener.local_addr()?);
|
||||||
|
|
||||||
|
Ok(Self {
|
||||||
|
port,
|
||||||
|
router: app,
|
||||||
|
listener,
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn run(self) -> std::io::Result<()> {
|
||||||
|
axum::serve(self.listener, self.router.into_make_service()).await
|
||||||
|
}
|
||||||
|
}
|
||||||
+10
@@ -0,0 +1,10 @@
|
|||||||
|
// Library root - clean organized module structure
|
||||||
|
// All modules organized into logical folders
|
||||||
|
|
||||||
|
// ============================================================================
|
||||||
|
// Core Framework
|
||||||
|
// ============================================================================
|
||||||
|
pub mod app;
|
||||||
|
pub mod bootstrap;
|
||||||
|
pub mod modules;
|
||||||
|
pub mod shared;
|
||||||
+12
@@ -0,0 +1,12 @@
|
|||||||
|
#![doc = "Logging Setup"]
|
||||||
|
use scraper_service::bootstrap::Application;
|
||||||
|
|
||||||
|
#[tokio::main(flavor = "multi_thread")]
|
||||||
|
async fn main() -> anyhow::Result<()> {
|
||||||
|
// Application setup and server logic is now encapsulated in `startup.rs`
|
||||||
|
// This makes the main function clean and the app easier to integration test.
|
||||||
|
let app = Application::build().await?;
|
||||||
|
app.run().await?;
|
||||||
|
|
||||||
|
Ok(())
|
||||||
|
}
|
||||||
@@ -0,0 +1,236 @@
|
|||||||
|
use crate::modules::anime::repository::AnimeRepository;
|
||||||
|
use crate::modules::anime::service::AnimeService;
|
||||||
|
use crate::shared::errors::AppError;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
use axum::extract::{Path, State};
|
||||||
|
use axum::Json;
|
||||||
|
use std::sync::Arc;
|
||||||
|
use tracing::info;
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_index",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Handles GET requests for the /api/anime endpoint.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn anime_index(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::AnimeData>, AppError> {
|
||||||
|
info!("Handling request for anime index");
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service.get_anime_index(app_state).await.map(Json)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime/genre_list",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_genre_list",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Handles GET requests for the /api/anime/genre_list endpoint.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn genres(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::GenresResponse>, AppError> {
|
||||||
|
info!("Handling request for anime genres");
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service.get_genres(app_state).await.map(Json)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime/detail/{slug}",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_detail_slug",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific detail by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn detail_slug(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::DetailResponse>, AppError> {
|
||||||
|
info!("Starting request for detail slug: {}", slug);
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service.get_anime_detail(app_state, slug).await.map(Json)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime/complete_anime/{slug}",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_complete_anime_slug",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific complete_anime by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn complete_anime_slug(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::ListResponse>, AppError> {
|
||||||
|
info!("Starting request for complete_anime slug: {}", slug);
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service
|
||||||
|
.get_complete_anime_page(app_state, slug)
|
||||||
|
.await
|
||||||
|
.map(Json)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime/full/{slug}",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_full_slug",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves full episode details for a specific episode by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn full_slug(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::FullResponse>, AppError> {
|
||||||
|
info!("Starting request for full slug: {}", slug);
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service.get_anime_full(app_state, slug).await.map(Json)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime/ongoing_anime/{slug}",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_ongoing_anime_slug",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific ongoing_anime by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn ongoing_anime_slug(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::OngoingAnimeResponse>, AppError> {
|
||||||
|
info!("Starting request for ongoing_anime slug: {}", slug);
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service
|
||||||
|
.get_ongoing_anime_page(app_state, slug)
|
||||||
|
.await
|
||||||
|
.map(Json)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime/latest/{slug}",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_latest_slug",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific latest by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn latest_slug(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::LatestAnimeResponse>, AppError> {
|
||||||
|
info!("Starting request for latest slug: {}", slug);
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service
|
||||||
|
.get_latest_anime_page(app_state, slug)
|
||||||
|
.await
|
||||||
|
.map(Json)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime/search/{slug}",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_search_slug_index",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific search by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn search_slug_index(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::SearchResponse>, AppError> {
|
||||||
|
info!("Starting request for search slug: {}", slug);
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service
|
||||||
|
.get_search_anime_page(app_state, slug, "1".to_string())
|
||||||
|
.await
|
||||||
|
.map(Json)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime/search/{slug}/{page}",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_search_slug_page",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific search by slug and page.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn search_slug_page(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path((slug, page)): Path<(String, String)>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::SearchResponse>, AppError> {
|
||||||
|
info!("Starting request for search slug: {} page: {}", slug, page);
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service
|
||||||
|
.get_search_anime_page(app_state, slug, page)
|
||||||
|
.await
|
||||||
|
.map(Json)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime/genre/{slug}",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_genre_slug_index",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific genre by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn genre_slug_index(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::GenreListResponse>, AppError> {
|
||||||
|
info!("Starting request for genre slug: {}", slug);
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service
|
||||||
|
.get_genre_anime_page(app_state, slug, "1".to_string())
|
||||||
|
.await
|
||||||
|
.map(Json)
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime/genre/{slug}/{page}",
|
||||||
|
tag = "anime",
|
||||||
|
operation_id = "anime_genre_slug_page",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific genre by slug and page.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn genre_slug_page(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path((slug, page)): Path<(String, String)>,
|
||||||
|
) -> Result<Json<crate::modules::anime::types::GenreListResponse>, AppError> {
|
||||||
|
info!("Starting request for genre slug: {} page: {}", slug, page);
|
||||||
|
let service = AnimeService::new(AnimeRepository::new());
|
||||||
|
service
|
||||||
|
.get_genre_anime_page(app_state, slug, page)
|
||||||
|
.await
|
||||||
|
.map(Json)
|
||||||
|
}
|
||||||
@@ -0,0 +1,7 @@
|
|||||||
|
pub mod controller;
|
||||||
|
pub mod parser;
|
||||||
|
pub mod repository;
|
||||||
|
pub mod route;
|
||||||
|
pub mod schema;
|
||||||
|
pub mod service;
|
||||||
|
pub mod types;
|
||||||
@@ -0,0 +1,632 @@
|
|||||||
|
use crate::modules::anime::types::*;
|
||||||
|
use crate::shared::errors::AppError;
|
||||||
|
use crate::shared::utils::parse_html;
|
||||||
|
use crate::shared::utils::scraping::{
|
||||||
|
attr, attr_from, attr_from_or, extract_slug, selector, text, text_from_or,
|
||||||
|
};
|
||||||
|
|
||||||
|
pub fn parse_ongoing_anime(html: &str) -> Result<Vec<OngoingAnimeItem>, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut ongoing_anime = Vec::new();
|
||||||
|
|
||||||
|
let venz_selector = selector(".venz ul li").unwrap();
|
||||||
|
let title_selector = selector(".thumbz h2.jdlflm").unwrap();
|
||||||
|
let link_selector = selector("a").unwrap();
|
||||||
|
let img_selector = selector("img").unwrap();
|
||||||
|
let episode_selector = selector(".epz").unwrap();
|
||||||
|
|
||||||
|
for element in document.select(&venz_selector) {
|
||||||
|
let title = text_from_or(&element, &title_selector, "");
|
||||||
|
let href = attr_from(&element, &link_selector, "href").unwrap_or_default();
|
||||||
|
let slug = extract_slug(&href);
|
||||||
|
let poster = attr_from_or(&element, &img_selector, "src", "");
|
||||||
|
let current_episode = text_from_or(&element, &episode_selector, "N/A");
|
||||||
|
let anime_url = attr_from_or(&element, &link_selector, "href", "");
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
ongoing_anime.push(OngoingAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
current_episode,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
Ok(ongoing_anime)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_complete_anime(html: &str) -> Result<Vec<CompleteAnimeItem>, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut complete_anime = Vec::new();
|
||||||
|
|
||||||
|
let venz_selector = selector(".venz ul li").unwrap();
|
||||||
|
let title_selector = selector(".thumbz h2.jdlflm").unwrap();
|
||||||
|
let link_selector = selector("a").unwrap();
|
||||||
|
let img_selector = selector("img").unwrap();
|
||||||
|
let episode_selector = selector(".epz").unwrap();
|
||||||
|
|
||||||
|
for element in document.select(&venz_selector) {
|
||||||
|
let title = text_from_or(&element, &title_selector, "");
|
||||||
|
let href = attr_from(&element, &link_selector, "href").unwrap_or_default();
|
||||||
|
let slug = extract_slug(&href);
|
||||||
|
let poster = attr_from_or(&element, &img_selector, "src", "");
|
||||||
|
let episode_count = text_from_or(&element, &episode_selector, "N/A");
|
||||||
|
let anime_url = attr_from_or(&element, &link_selector, "href", "");
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
complete_anime.push(CompleteAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
episode_count,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
Ok(complete_anime)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_genres(html: &str) -> Result<Vec<Genre>, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut genres = Vec::new();
|
||||||
|
let genre_selector = selector(".genres li a, .genre-list a").unwrap();
|
||||||
|
|
||||||
|
for element in document.select(&genre_selector) {
|
||||||
|
let name = text(&element);
|
||||||
|
let url = attr(&element, "href").unwrap_or_default();
|
||||||
|
let slug = extract_slug(&url);
|
||||||
|
|
||||||
|
if !name.is_empty() && !slug.is_empty() {
|
||||||
|
genres.push(Genre { name, slug, url });
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(genres)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_anime_detail_document(html: &str) -> Result<AnimeDetailData, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
|
||||||
|
let info_selector = selector(".infozingle p").unwrap();
|
||||||
|
let poster_selector = selector(".fotoanime img").unwrap();
|
||||||
|
let synopsis_selector = selector(".sinopc").unwrap();
|
||||||
|
let genre_link_selector = selector("a").unwrap();
|
||||||
|
let episode_list_selector = selector(".episodelist ul li a").unwrap();
|
||||||
|
let recommendation_selector = selector("#recommend-anime-series .isi-anime").unwrap();
|
||||||
|
let recommendation_title_selector = selector(".judul-anime a").unwrap();
|
||||||
|
let recommendation_img_selector = selector("img").unwrap();
|
||||||
|
|
||||||
|
let mut title = String::new();
|
||||||
|
let mut alternative_title = String::new();
|
||||||
|
let mut r#type: Option<String> = None;
|
||||||
|
let mut status: Option<String> = None;
|
||||||
|
let mut release_date = String::new();
|
||||||
|
let mut studio = String::new();
|
||||||
|
let producers = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&info_selector) {
|
||||||
|
let text = text(&element);
|
||||||
|
if text.contains("Judul:") {
|
||||||
|
title = text.replace("Judul:", "").trim().to_string();
|
||||||
|
} else if text.contains("Japanese:") {
|
||||||
|
alternative_title = text.replace("Japanese:", "").trim().to_string();
|
||||||
|
} else if text.contains("Type:") {
|
||||||
|
let type_str = text.replace("Type:", "").trim().to_string();
|
||||||
|
if !type_str.is_empty() {
|
||||||
|
r#type = Some(type_str);
|
||||||
|
}
|
||||||
|
} else if text.contains("Status:") {
|
||||||
|
let status_str = text.replace("Status:", "").trim().to_string();
|
||||||
|
if !status_str.is_empty() {
|
||||||
|
status = Some(status_str);
|
||||||
|
}
|
||||||
|
} else if text.contains("Tanggal Rilis:") {
|
||||||
|
release_date = text.replace("Tanggal Rilis:", "").trim().to_string();
|
||||||
|
} else if text.contains("Studio:") {
|
||||||
|
studio = text.replace("Studio:", "").trim().to_string();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let poster = document
|
||||||
|
.select(&poster_selector)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("src"))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let synopsis = text_from_or(&document.root_element(), &synopsis_selector, "");
|
||||||
|
|
||||||
|
let mut genres = Vec::new();
|
||||||
|
if let Some(genres_element) = document
|
||||||
|
.select(&info_selector)
|
||||||
|
.find(|e| text(&e).contains("Genres:"))
|
||||||
|
{
|
||||||
|
for genre_link in genres_element.select(&genre_link_selector) {
|
||||||
|
let name = text(&genre_link);
|
||||||
|
let anime_url = attr(&genre_link, "href").unwrap_or_default();
|
||||||
|
let genre_slug = extract_slug(&anime_url);
|
||||||
|
genres.push(DetailGenre {
|
||||||
|
name,
|
||||||
|
slug: genre_slug,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let mut episode_lists = Vec::new();
|
||||||
|
for element in document.select(&episode_list_selector) {
|
||||||
|
let episode = text(&element);
|
||||||
|
let href = attr(&element, "href").unwrap_or_default();
|
||||||
|
let slug = extract_slug(&href);
|
||||||
|
episode_lists.push(EpisodeList { episode, slug });
|
||||||
|
}
|
||||||
|
|
||||||
|
let mut recommendations = Vec::new();
|
||||||
|
for element in document.select(&recommendation_selector) {
|
||||||
|
let title = text_from_or(&element, &recommendation_title_selector, "");
|
||||||
|
let poster = attr_from_or(&element, &recommendation_img_selector, "src", "");
|
||||||
|
let href = element
|
||||||
|
.select(&genre_link_selector)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("href"))
|
||||||
|
.unwrap_or("");
|
||||||
|
|
||||||
|
let slug = extract_slug(href);
|
||||||
|
|
||||||
|
recommendations.push(Recommendation {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
status: None,
|
||||||
|
r#type: None,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(AnimeDetailData {
|
||||||
|
title,
|
||||||
|
alternative_title,
|
||||||
|
poster,
|
||||||
|
r#type,
|
||||||
|
status,
|
||||||
|
release_date,
|
||||||
|
studio,
|
||||||
|
genres,
|
||||||
|
synopsis,
|
||||||
|
episode_lists,
|
||||||
|
batch: vec![],
|
||||||
|
producers,
|
||||||
|
recommendations,
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_anime_page(
|
||||||
|
html: &str,
|
||||||
|
slug: &str,
|
||||||
|
) -> Result<(Vec<CompleteAnimeListItem>, Pagination), AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut anime_list = Vec::new();
|
||||||
|
|
||||||
|
let item_selector = selector(".venz ul li").unwrap();
|
||||||
|
let title_selector = selector(".thumbz h2.jdlflm").unwrap();
|
||||||
|
let link_selector = selector("a").unwrap();
|
||||||
|
let img_selector = selector("img").unwrap();
|
||||||
|
let episode_selector = selector(".epz").unwrap();
|
||||||
|
let pagination_selector = selector(".pagenavix .page-numbers:not(.next)").unwrap();
|
||||||
|
let next_selector = selector(".pagenavix .next.page-numbers").unwrap();
|
||||||
|
|
||||||
|
for element in document.select(&item_selector) {
|
||||||
|
let title = text_from_or(&element, &title_selector, "");
|
||||||
|
let anime_url = attr_from_or(&element, &link_selector, "href", "");
|
||||||
|
let slug = extract_slug(&anime_url);
|
||||||
|
let poster = attr_from_or(&element, &img_selector, "src", "");
|
||||||
|
let episode_count = text_from_or(&element, &episode_selector, "N/A");
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
anime_list.push(CompleteAnimeListItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
episode_count,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let current_page = slug.parse::<u32>().unwrap_or(1);
|
||||||
|
let last_visible_page = document
|
||||||
|
.select(&pagination_selector)
|
||||||
|
.next_back()
|
||||||
|
.and_then(|e| e.text().collect::<String>().trim().parse::<u32>().ok())
|
||||||
|
.unwrap_or(1);
|
||||||
|
|
||||||
|
let has_next_page = document.select(&next_selector).next().is_some();
|
||||||
|
let next_page = if has_next_page {
|
||||||
|
Some(current_page + 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
let has_previous_page = current_page > 1;
|
||||||
|
let previous_page = if has_previous_page {
|
||||||
|
Some(current_page - 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
|
||||||
|
let pagination = Pagination {
|
||||||
|
current_page,
|
||||||
|
last_visible_page,
|
||||||
|
has_next_page,
|
||||||
|
next_page,
|
||||||
|
has_previous_page,
|
||||||
|
previous_page,
|
||||||
|
};
|
||||||
|
|
||||||
|
Ok((anime_list, pagination))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_ongoing_anime_document(
|
||||||
|
html: &str,
|
||||||
|
slug: &str,
|
||||||
|
) -> Result<(Vec<OngoingAnimeListItem>, Pagination), AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut anime_list = Vec::new();
|
||||||
|
|
||||||
|
let item_selector = selector(".venz ul li").unwrap();
|
||||||
|
let title_selector = selector(".thumbz h2.jdlflm").unwrap();
|
||||||
|
let link_selector = selector("a").unwrap();
|
||||||
|
let img_selector = selector("img").unwrap();
|
||||||
|
let score_selector = selector(".epz").unwrap();
|
||||||
|
let pagination_selector = selector(".pagenavix .page-numbers:not(.next)").unwrap();
|
||||||
|
let next_selector = selector(".pagenavix .next.page-numbers").unwrap();
|
||||||
|
|
||||||
|
for element in document.select(&item_selector) {
|
||||||
|
let title = text_from_or(&element, &title_selector, "");
|
||||||
|
let anime_url = attr_from_or(&element, &link_selector, "href", "");
|
||||||
|
let slug = extract_slug(&anime_url);
|
||||||
|
let poster = attr_from_or(&element, &img_selector, "src", "");
|
||||||
|
let score = text_from_or(&element, &score_selector, "N/A");
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
anime_list.push(OngoingAnimeListItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
score,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let current_page = slug.parse::<u32>().unwrap_or(1);
|
||||||
|
let last_visible_page = document
|
||||||
|
.select(&pagination_selector)
|
||||||
|
.next_back()
|
||||||
|
.and_then(|e| e.text().collect::<String>().trim().parse::<u32>().ok())
|
||||||
|
.unwrap_or(1);
|
||||||
|
|
||||||
|
let has_next_page = document.select(&next_selector).next().is_some();
|
||||||
|
let next_page = if has_next_page {
|
||||||
|
Some(current_page + 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
let has_previous_page = current_page > 1;
|
||||||
|
let previous_page = if has_previous_page {
|
||||||
|
Some(current_page - 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
|
||||||
|
let pagination = Pagination {
|
||||||
|
current_page,
|
||||||
|
last_visible_page,
|
||||||
|
has_next_page,
|
||||||
|
next_page,
|
||||||
|
has_previous_page,
|
||||||
|
previous_page,
|
||||||
|
};
|
||||||
|
|
||||||
|
Ok((anime_list, pagination))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_latest_anime_document(
|
||||||
|
html: &str,
|
||||||
|
slug: &str,
|
||||||
|
) -> Result<(Vec<LatestAnimeItem>, Pagination), AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut anime_list = Vec::new();
|
||||||
|
|
||||||
|
let item_selector = selector(".venz ul li").unwrap();
|
||||||
|
let title_selector = selector(".thumbz h2.jdlflm").unwrap();
|
||||||
|
let link_selector = selector("a").unwrap();
|
||||||
|
let img_selector = selector("img").unwrap();
|
||||||
|
let episode_selector = selector(".epz").unwrap();
|
||||||
|
let pagination_selector = selector(".pagenavix .page-numbers:not(.next)").unwrap();
|
||||||
|
let next_selector = selector(".pagenavix .next.page-numbers").unwrap();
|
||||||
|
|
||||||
|
for element in document.select(&item_selector) {
|
||||||
|
let title = text_from_or(&element, &title_selector, "");
|
||||||
|
let anime_url = attr_from_or(&element, &link_selector, "href", "");
|
||||||
|
let slug = extract_slug(&anime_url);
|
||||||
|
let poster = attr_from_or(&element, &img_selector, "src", "");
|
||||||
|
let episode = text_from_or(&element, &episode_selector, "N/A");
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
anime_list.push(LatestAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
episode,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let current_page = slug.parse::<u32>().unwrap_or(1);
|
||||||
|
let last_visible_page = document
|
||||||
|
.select(&pagination_selector)
|
||||||
|
.next_back()
|
||||||
|
.and_then(|e| e.text().collect::<String>().trim().parse::<u32>().ok())
|
||||||
|
.unwrap_or(1);
|
||||||
|
|
||||||
|
let has_next_page = document.select(&next_selector).next().is_some();
|
||||||
|
let next_page = if has_next_page {
|
||||||
|
Some(current_page + 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
let has_previous_page = current_page > 1;
|
||||||
|
let previous_page = if has_previous_page {
|
||||||
|
Some(current_page - 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
|
||||||
|
let pagination = Pagination {
|
||||||
|
current_page,
|
||||||
|
last_visible_page,
|
||||||
|
has_next_page,
|
||||||
|
next_page,
|
||||||
|
has_previous_page,
|
||||||
|
previous_page,
|
||||||
|
};
|
||||||
|
|
||||||
|
Ok((anime_list, pagination))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_search_anime_document(
|
||||||
|
html: &str,
|
||||||
|
slug: &str,
|
||||||
|
) -> Result<(Vec<SearchAnimeItem>, Pagination), AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut anime_list = Vec::new();
|
||||||
|
|
||||||
|
let item_selector = selector(".venz ul li").unwrap();
|
||||||
|
let title_selector = selector(".thumbz h2.jdlflm").unwrap();
|
||||||
|
let link_selector = selector("a").unwrap();
|
||||||
|
let img_selector = selector("img").unwrap();
|
||||||
|
let episode_selector = selector(".epz").unwrap();
|
||||||
|
let genre_selector = selector(".genre-tag").unwrap();
|
||||||
|
let status_selector = selector(".status").unwrap();
|
||||||
|
let rating_selector = selector(".rating").unwrap();
|
||||||
|
let pagination_selector = selector(".pagenavix .page-numbers:not(.next)").unwrap();
|
||||||
|
let next_selector = selector(".pagenavix .next.page-numbers").unwrap();
|
||||||
|
|
||||||
|
for element in document.select(&item_selector) {
|
||||||
|
let title = text_from_or(&element, &title_selector, "");
|
||||||
|
let anime_url = attr_from_or(&element, &link_selector, "href", "");
|
||||||
|
let slug = extract_slug(&anime_url);
|
||||||
|
let poster = attr_from_or(&element, &img_selector, "src", "");
|
||||||
|
let episode = text_from_or(&element, &episode_selector, "N/A");
|
||||||
|
|
||||||
|
let mut genres = Vec::new();
|
||||||
|
for genre_elem in element.select(&genre_selector) {
|
||||||
|
genres.push(text(&genre_elem));
|
||||||
|
}
|
||||||
|
|
||||||
|
let status = text_from_or(&element, &status_selector, "");
|
||||||
|
let rating = text_from_or(&element, &rating_selector, "");
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
anime_list.push(SearchAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
episode,
|
||||||
|
anime_url,
|
||||||
|
genres,
|
||||||
|
status,
|
||||||
|
rating,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let current_page = slug.parse::<u32>().unwrap_or(1);
|
||||||
|
let last_visible_page = document
|
||||||
|
.select(&pagination_selector)
|
||||||
|
.next_back()
|
||||||
|
.and_then(|e| e.text().collect::<String>().trim().parse::<u32>().ok())
|
||||||
|
.unwrap_or(1);
|
||||||
|
|
||||||
|
let has_next_page = document.select(&next_selector).next().is_some();
|
||||||
|
let next_page = if has_next_page {
|
||||||
|
Some(current_page + 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
let has_previous_page = current_page > 1;
|
||||||
|
let previous_page = if has_previous_page {
|
||||||
|
Some(current_page - 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
|
||||||
|
let pagination = Pagination {
|
||||||
|
current_page,
|
||||||
|
last_visible_page,
|
||||||
|
has_next_page,
|
||||||
|
next_page,
|
||||||
|
has_previous_page,
|
||||||
|
previous_page,
|
||||||
|
};
|
||||||
|
|
||||||
|
Ok((anime_list, pagination))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_genre_anime_document(
|
||||||
|
html: &str,
|
||||||
|
slug: &str,
|
||||||
|
) -> Result<(Vec<GenreAnimeItem>, Pagination), AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut anime_list = Vec::new();
|
||||||
|
|
||||||
|
let item_selector = selector(".venz ul li").unwrap();
|
||||||
|
let title_selector = selector(".thumbz h2.jdlflm").unwrap();
|
||||||
|
let link_selector = selector("a").unwrap();
|
||||||
|
let img_selector = selector("img").unwrap();
|
||||||
|
let episode_selector = selector(".epz").unwrap();
|
||||||
|
let pagination_selector = selector(".pagenavix .page-numbers:not(.next)").unwrap();
|
||||||
|
let next_selector = selector(".pagenavix .next.page-numbers").unwrap();
|
||||||
|
|
||||||
|
for element in document.select(&item_selector) {
|
||||||
|
let title = text_from_or(&element, &title_selector, "");
|
||||||
|
let anime_url = attr_from_or(&element, &link_selector, "href", "");
|
||||||
|
let slug = extract_slug(&anime_url);
|
||||||
|
let poster = attr_from_or(&element, &img_selector, "src", "");
|
||||||
|
let episode = text_from_or(&element, &episode_selector, "N/A");
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
anime_list.push(GenreAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
episode,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let current_page = slug.parse::<u32>().unwrap_or(1);
|
||||||
|
let last_visible_page = document
|
||||||
|
.select(&pagination_selector)
|
||||||
|
.next_back()
|
||||||
|
.and_then(|e| e.text().collect::<String>().trim().parse::<u32>().ok())
|
||||||
|
.unwrap_or(1);
|
||||||
|
|
||||||
|
let has_next_page = document.select(&next_selector).next().is_some();
|
||||||
|
let next_page = if has_next_page {
|
||||||
|
Some(current_page + 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
let has_previous_page = current_page > 1;
|
||||||
|
let previous_page = if has_previous_page {
|
||||||
|
Some(current_page - 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
|
||||||
|
let pagination = Pagination {
|
||||||
|
current_page,
|
||||||
|
last_visible_page,
|
||||||
|
has_next_page,
|
||||||
|
next_page,
|
||||||
|
has_previous_page,
|
||||||
|
previous_page,
|
||||||
|
};
|
||||||
|
|
||||||
|
Ok((anime_list, pagination))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_anime_full_document(html: &str, slug: &str) -> Result<AnimeFullData, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
|
||||||
|
let episode_title_selector = selector("h1.posttl").unwrap();
|
||||||
|
let image_selector = selector(".cukder img").unwrap();
|
||||||
|
let stream_selector = selector("#embed_holder iframe").unwrap();
|
||||||
|
let download_item_selector = selector(".download ul li").unwrap();
|
||||||
|
let resolution_selector = selector("strong").unwrap();
|
||||||
|
let link_selector = selector("a").unwrap();
|
||||||
|
let next_episode_selector = selector(".flir a[title*='Episode Selanjutnya']").unwrap();
|
||||||
|
let previous_episode_selector = selector(".flir a[title*='Episode Sebelumnya']").unwrap();
|
||||||
|
|
||||||
|
let episode = document
|
||||||
|
.select(&episode_title_selector)
|
||||||
|
.next()
|
||||||
|
.map(|e| text(&e))
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let episode_number = episode
|
||||||
|
.split("Episode")
|
||||||
|
.nth(1)
|
||||||
|
.map(|s| s.trim().to_string())
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let image_url = document
|
||||||
|
.select(&image_selector)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| attr(&e, "src"))
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let stream_url = document
|
||||||
|
.select(&stream_selector)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| attr(&e, "src"))
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let mut download_urls = std::collections::HashMap::new();
|
||||||
|
|
||||||
|
for element in document.select(&download_item_selector) {
|
||||||
|
let resolution = element
|
||||||
|
.select(&resolution_selector)
|
||||||
|
.next()
|
||||||
|
.map(|e| text(&e))
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let mut links = Vec::new();
|
||||||
|
for link_element in element.select(&link_selector) {
|
||||||
|
let server = text(&link_element);
|
||||||
|
let url = attr(&link_element, "href").unwrap_or_default();
|
||||||
|
links.push(DownloadLink { server, url });
|
||||||
|
}
|
||||||
|
|
||||||
|
if !resolution.is_empty() && !links.is_empty() {
|
||||||
|
download_urls.insert(resolution, links);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let next_episode_element = document.select(&next_episode_selector).next();
|
||||||
|
let previous_episode_element = document.select(&previous_episode_selector).next();
|
||||||
|
|
||||||
|
let next_episode_slug = next_episode_element
|
||||||
|
.and_then(|e| attr(&e, "href"))
|
||||||
|
.and_then(|href| {
|
||||||
|
href.split('/')
|
||||||
|
.nth(href.split('/').count().saturating_sub(2))
|
||||||
|
.map(|s| s.to_string() + "/")
|
||||||
|
});
|
||||||
|
|
||||||
|
let previous_episode_slug = previous_episode_element
|
||||||
|
.and_then(|e| attr(&e, "href"))
|
||||||
|
.and_then(|href| {
|
||||||
|
href.split('/')
|
||||||
|
.nth(href.split('/').count().saturating_sub(2))
|
||||||
|
.map(|s| s.to_string() + "/")
|
||||||
|
});
|
||||||
|
|
||||||
|
Ok(AnimeFullData {
|
||||||
|
episode,
|
||||||
|
episode_number,
|
||||||
|
anime: AnimeInfo {
|
||||||
|
slug: slug.to_string(),
|
||||||
|
},
|
||||||
|
has_next_episode: next_episode_slug.is_some(),
|
||||||
|
next_episode: next_episode_slug.map(|s| EpisodeInfo { slug: s }),
|
||||||
|
has_previous_episode: previous_episode_slug.is_some(),
|
||||||
|
previous_episode: previous_episode_slug.map(|s| EpisodeInfo { slug: s }),
|
||||||
|
stream_url,
|
||||||
|
download_urls,
|
||||||
|
image_url,
|
||||||
|
})
|
||||||
|
}
|
||||||
@@ -0,0 +1,199 @@
|
|||||||
|
use crate::modules::anime::parser;
|
||||||
|
use crate::modules::anime::types::*;
|
||||||
|
use crate::shared::database::traits::scraping_repository::ScrapingRepository;
|
||||||
|
use crate::shared::errors::AppError;
|
||||||
|
use crate::shared::utils::web::proxy_fetch::fetch_with_proxy;
|
||||||
|
use crate::shared::utils::web::scraping_urls::{get_otakudesu_url, OTAKUDESU_BASE_URL};
|
||||||
|
use crate::shared::utils::{default_backoff, fetch_html_with_retry, transient};
|
||||||
|
use async_trait::async_trait;
|
||||||
|
use backoff::future::retry;
|
||||||
|
use tracing::{info, warn};
|
||||||
|
|
||||||
|
pub struct AnimeRepository;
|
||||||
|
|
||||||
|
impl Default for AnimeRepository {
|
||||||
|
fn default() -> Self {
|
||||||
|
Self::new()
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
impl AnimeRepository {
|
||||||
|
pub fn new() -> Self {
|
||||||
|
Self
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
#[async_trait]
|
||||||
|
impl ScrapingRepository for AnimeRepository {
|
||||||
|
async fn fetch_html(&self, url: &str) -> Result<String, AppError> {
|
||||||
|
fetch_html_with_retry(url).await
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
impl AnimeRepository {
|
||||||
|
pub fn base_url(&self) -> String {
|
||||||
|
get_otakudesu_url()
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn index_urls(&self) -> (String, String) {
|
||||||
|
let base = self.base_url();
|
||||||
|
(
|
||||||
|
format!("{}/ongoing-anime/", base),
|
||||||
|
format!("{}/complete-anime/", base),
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn genres_url(&self) -> String {
|
||||||
|
format!("{}/genre-list/", self.base_url())
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn detail_url(&self, slug: &str) -> String {
|
||||||
|
format!("{}/anime/{}", OTAKUDESU_BASE_URL, slug)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn page_url(&self, category: &str, page: &str) -> String {
|
||||||
|
format!("{}/{}/page/{}/", OTAKUDESU_BASE_URL, category, page)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn search_url(&self, query: &str, page: &str) -> String {
|
||||||
|
if page == "1" {
|
||||||
|
format!("{}/search/{}/", self.base_url(), query)
|
||||||
|
} else {
|
||||||
|
format!("{}/search/{}/page/{}/", self.base_url(), query, page)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn genre_page_url(&self, genre_slug: &str, page: &str) -> String {
|
||||||
|
format!("{}/genre/{}/page/{}/", self.base_url(), genre_slug, page)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn full_episode_url(&self, slug: &str) -> String {
|
||||||
|
format!("{}/episode/{}", OTAKUDESU_BASE_URL, slug)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn fetch_anime_index(&self) -> Result<AnimeData, AppError> {
|
||||||
|
let (ongoing_url, complete_url) = self.index_urls();
|
||||||
|
|
||||||
|
let (ongoing_html, complete_html) = tokio::join!(
|
||||||
|
self.fetch_html(&ongoing_url),
|
||||||
|
self.fetch_html(&complete_url)
|
||||||
|
);
|
||||||
|
|
||||||
|
let ongoing_html = ongoing_html?;
|
||||||
|
let complete_html = complete_html?;
|
||||||
|
|
||||||
|
let ongoing_anime =
|
||||||
|
tokio::task::spawn_blocking(move || parser::parse_ongoing_anime(&ongoing_html))
|
||||||
|
.await??;
|
||||||
|
let complete_anime =
|
||||||
|
tokio::task::spawn_blocking(move || parser::parse_complete_anime(&complete_html))
|
||||||
|
.await??;
|
||||||
|
|
||||||
|
Ok(AnimeData {
|
||||||
|
ongoing_anime,
|
||||||
|
complete_anime,
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn fetch_genres(&self) -> Result<Vec<Genre>, AppError> {
|
||||||
|
let html = self.fetch_html(&self.genres_url()).await?;
|
||||||
|
tokio::task::spawn_blocking(move || parser::parse_genres(&html)).await?
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn fetch_anime_detail(&self, slug: &str) -> Result<AnimeDetailData, AppError> {
|
||||||
|
let url = self.detail_url(slug);
|
||||||
|
let html = self
|
||||||
|
.fetch_with_proxy_retry(&url)
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e.to_string()))?;
|
||||||
|
|
||||||
|
tokio::task::spawn_blocking(move || parser::parse_anime_detail_document(&html)).await?
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn fetch_complete_anime_page(
|
||||||
|
&self,
|
||||||
|
slug: &str,
|
||||||
|
) -> Result<(Vec<CompleteAnimeListItem>, Pagination), AppError> {
|
||||||
|
let url = self.page_url("complete-anime", slug);
|
||||||
|
let html = self.fetch_html(&url).await?;
|
||||||
|
let slug_owned = slug.to_string();
|
||||||
|
tokio::task::spawn_blocking(move || parser::parse_anime_page(&html, &slug_owned)).await?
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn fetch_ongoing_anime_page(
|
||||||
|
&self,
|
||||||
|
slug: &str,
|
||||||
|
) -> Result<(Vec<OngoingAnimeListItem>, Pagination), AppError> {
|
||||||
|
let url = self.page_url("ongoing-anime", slug);
|
||||||
|
let html = self.fetch_html(&url).await?;
|
||||||
|
let slug_owned = slug.to_string();
|
||||||
|
tokio::task::spawn_blocking(move || {
|
||||||
|
parser::parse_ongoing_anime_document(&html, &slug_owned)
|
||||||
|
})
|
||||||
|
.await?
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn fetch_latest_anime_page(
|
||||||
|
&self,
|
||||||
|
slug: &str,
|
||||||
|
) -> Result<(Vec<LatestAnimeItem>, Pagination), AppError> {
|
||||||
|
let url = self.page_url("latest-anime", slug);
|
||||||
|
let html = self.fetch_html(&url).await?;
|
||||||
|
let slug_owned = slug.to_string();
|
||||||
|
tokio::task::spawn_blocking(move || parser::parse_latest_anime_document(&html, &slug_owned))
|
||||||
|
.await?
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn fetch_search_anime_page(
|
||||||
|
&self,
|
||||||
|
slug: &str,
|
||||||
|
page: &str,
|
||||||
|
) -> Result<(Vec<SearchAnimeItem>, Pagination), AppError> {
|
||||||
|
let url = self.search_url(slug, page);
|
||||||
|
let html = self.fetch_html(&url).await?;
|
||||||
|
let page_owned = page.to_string();
|
||||||
|
tokio::task::spawn_blocking(move || parser::parse_search_anime_document(&html, &page_owned))
|
||||||
|
.await?
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn fetch_genre_anime_page(
|
||||||
|
&self,
|
||||||
|
genre_slug: &str,
|
||||||
|
page: &str,
|
||||||
|
) -> Result<(Vec<GenreAnimeItem>, Pagination), AppError> {
|
||||||
|
let url = self.genre_page_url(genre_slug, page);
|
||||||
|
let html = self.fetch_html(&url).await?;
|
||||||
|
let page_owned = page.to_string();
|
||||||
|
tokio::task::spawn_blocking(move || parser::parse_genre_anime_document(&html, &page_owned))
|
||||||
|
.await?
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn fetch_anime_full(&self, slug: &str) -> Result<AnimeFullData, AppError> {
|
||||||
|
let url = self.full_episode_url(slug);
|
||||||
|
let html = self.fetch_html(&url).await?;
|
||||||
|
let slug_owned = slug.to_string();
|
||||||
|
tokio::task::spawn_blocking(move || parser::parse_anime_full_document(&html, &slug_owned))
|
||||||
|
.await?
|
||||||
|
}
|
||||||
|
|
||||||
|
async fn fetch_with_proxy_retry(&self, url: &str) -> Result<String, AppError> {
|
||||||
|
let backoff = default_backoff();
|
||||||
|
let url_owned = url.to_string();
|
||||||
|
let fetch_op = || async {
|
||||||
|
info!("Fetching URL: {}", url_owned);
|
||||||
|
match fetch_with_proxy(&url_owned).await {
|
||||||
|
Ok(response) => {
|
||||||
|
info!("Successfully fetched URL: {}", url_owned);
|
||||||
|
Ok(response.data)
|
||||||
|
}
|
||||||
|
Err(e) => {
|
||||||
|
warn!("Failed to fetch URL: {}, error: {:?}", url_owned, e);
|
||||||
|
Err(transient(e))
|
||||||
|
}
|
||||||
|
}
|
||||||
|
};
|
||||||
|
retry(backoff, fetch_op)
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e.to_string()))
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,49 @@
|
|||||||
|
use crate::modules::anime::controller;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
use axum::Router;
|
||||||
|
use std::sync::Arc;
|
||||||
|
|
||||||
|
pub fn routes(router: Router<Arc<AppState>>) -> Router<Arc<AppState>> {
|
||||||
|
router
|
||||||
|
.route("/api/anime", axum::routing::get(controller::anime_index))
|
||||||
|
.route(
|
||||||
|
"/api/anime/genre_list",
|
||||||
|
axum::routing::get(controller::genres),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime/detail/{slug}",
|
||||||
|
axum::routing::get(controller::detail_slug),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime/complete_anime/{slug}",
|
||||||
|
axum::routing::get(controller::complete_anime_slug),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime/full/{slug}",
|
||||||
|
axum::routing::get(controller::full_slug),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime/ongoing_anime/{slug}",
|
||||||
|
axum::routing::get(controller::ongoing_anime_slug),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime/latest/{slug}",
|
||||||
|
axum::routing::get(controller::latest_slug),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime/search/{slug}",
|
||||||
|
axum::routing::get(controller::search_slug_index),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime/search/{slug}/{page}",
|
||||||
|
axum::routing::get(controller::search_slug_page),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime/genre/{slug}",
|
||||||
|
axum::routing::get(controller::genre_slug_index),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime/genre/{slug}/{page}",
|
||||||
|
axum::routing::get(controller::genre_slug_page),
|
||||||
|
)
|
||||||
|
}
|
||||||
@@ -0,0 +1,18 @@
|
|||||||
|
use serde::Deserialize;
|
||||||
|
use utoipa::ToSchema;
|
||||||
|
|
||||||
|
#[derive(Deserialize, ToSchema)]
|
||||||
|
pub struct SearchQuery {
|
||||||
|
pub q: Option<String>,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Deserialize, ToSchema)]
|
||||||
|
pub struct SlugPath {
|
||||||
|
pub slug: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Deserialize, ToSchema)]
|
||||||
|
pub struct SlugPagePath {
|
||||||
|
pub slug: String,
|
||||||
|
pub page: String,
|
||||||
|
}
|
||||||
@@ -0,0 +1,81 @@
|
|||||||
|
use crate::shared::types::entities::anime::HasPoster;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
use std::sync::Arc;
|
||||||
|
|
||||||
|
/// Cache poster URLs for a collection of anime items
|
||||||
|
/// This is a fire-and-forget operation that triggers lazy background caching
|
||||||
|
pub async fn cache_posters<T: HasPoster>(app_state: &Arc<AppState>, items: &[T]) {
|
||||||
|
let posters: Vec<String> = items.iter().map(|item| item.poster().to_string()).collect();
|
||||||
|
|
||||||
|
if posters.is_empty() {
|
||||||
|
return;
|
||||||
|
}
|
||||||
|
|
||||||
|
let db = app_state.db.clone();
|
||||||
|
let redis = app_state.redis_pool.clone();
|
||||||
|
|
||||||
|
crate::shared::services::images::cache::cache_image_urls_batch_lazy(
|
||||||
|
db,
|
||||||
|
&redis,
|
||||||
|
posters,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Cache poster URLs and update items with cached URLs
|
||||||
|
/// Returns the updated items with CDN URLs
|
||||||
|
pub async fn cache_and_update_posters<T: HasPoster + Clone>(
|
||||||
|
app_state: &Arc<AppState>,
|
||||||
|
mut items: Vec<T>,
|
||||||
|
) -> Vec<T> {
|
||||||
|
let posters: Vec<String> = items.iter().map(|item| item.poster().to_string()).collect();
|
||||||
|
|
||||||
|
if posters.is_empty() {
|
||||||
|
return items;
|
||||||
|
}
|
||||||
|
|
||||||
|
let db = app_state.db.clone();
|
||||||
|
let redis = app_state.redis_pool.clone();
|
||||||
|
|
||||||
|
let cached_posters = crate::shared::services::images::cache::cache_image_urls_batch_lazy(
|
||||||
|
db,
|
||||||
|
&redis,
|
||||||
|
posters,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
// Update items with cached URLs
|
||||||
|
for (i, item) in items.iter_mut().enumerate() {
|
||||||
|
if let Some(url) = cached_posters.get(i) {
|
||||||
|
item.set_poster(url.clone());
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
items
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Cache multiple collections of posters and update them
|
||||||
|
/// Useful when you have different types of items (e.g., ongoing and complete anime)
|
||||||
|
pub async fn cache_multiple_collections(
|
||||||
|
app_state: &Arc<AppState>,
|
||||||
|
collections: Vec<Vec<String>>,
|
||||||
|
) -> Vec<String> {
|
||||||
|
let all_posters: Vec<String> = collections.into_iter().flatten().collect();
|
||||||
|
|
||||||
|
if all_posters.is_empty() {
|
||||||
|
return Vec::new();
|
||||||
|
}
|
||||||
|
|
||||||
|
let db = app_state.db.clone();
|
||||||
|
let redis = app_state.redis_pool.clone();
|
||||||
|
|
||||||
|
crate::shared::services::images::cache::cache_image_urls_batch_lazy(
|
||||||
|
db,
|
||||||
|
&redis,
|
||||||
|
all_posters,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await
|
||||||
|
}
|
||||||
@@ -0,0 +1,295 @@
|
|||||||
|
use std::sync::Arc;
|
||||||
|
|
||||||
|
use crate::modules::anime::repository::AnimeRepository;
|
||||||
|
use crate::modules::anime::types::*;
|
||||||
|
use crate::shared::errors::AppError;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
use crate::shared::utils::Cache;
|
||||||
|
|
||||||
|
const INDEX_CACHE_TTL: u64 = 10;
|
||||||
|
const GENRE_LIST_CACHE_TTL: u64 = 3600;
|
||||||
|
const DEFAULT_CACHE_TTL: u64 = 300;
|
||||||
|
|
||||||
|
pub struct AnimeService {
|
||||||
|
repository: AnimeRepository,
|
||||||
|
}
|
||||||
|
|
||||||
|
impl AnimeService {
|
||||||
|
pub fn new(repository: AnimeRepository) -> Self {
|
||||||
|
Self { repository }
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn get_anime_index(&self, app_state: Arc<AppState>) -> Result<AnimeData, AppError> {
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set("anime:index:v2", INDEX_CACHE_TTL, || async {
|
||||||
|
let mut data = self
|
||||||
|
.repository
|
||||||
|
.fetch_anime_index()
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
|
||||||
|
if data.ongoing_anime.is_empty() && data.complete_anime.is_empty() {
|
||||||
|
return Err("Empty anime index — refusing to cache".to_string());
|
||||||
|
}
|
||||||
|
|
||||||
|
let mut posters: Vec<String> = data
|
||||||
|
.ongoing_anime
|
||||||
|
.iter()
|
||||||
|
.map(|item| item.poster.clone())
|
||||||
|
.collect();
|
||||||
|
posters.extend(data.complete_anime.iter().map(|item| item.poster.clone()));
|
||||||
|
|
||||||
|
let cached_posters =
|
||||||
|
crate::shared::services::images::cache::cache_image_urls_batch_lazy(
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
posters,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
let ongoing_len = data.ongoing_anime.len();
|
||||||
|
for (i, item) in data.ongoing_anime.iter_mut().enumerate() {
|
||||||
|
if let Some(url) = cached_posters.get(i) {
|
||||||
|
item.poster = url.clone();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
for (i, item) in data.complete_anime.iter_mut().enumerate() {
|
||||||
|
if let Some(url) = cached_posters.get(ongoing_len + i) {
|
||||||
|
item.poster = url.clone();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(data)
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn get_genres(&self, app_state: Arc<AppState>) -> Result<GenresResponse, AppError> {
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set("anime:genres:list", GENRE_LIST_CACHE_TTL, || async {
|
||||||
|
let genres = self
|
||||||
|
.repository
|
||||||
|
.fetch_genres()
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
Ok(GenresResponse {
|
||||||
|
status: "Ok".to_string(),
|
||||||
|
data: genres,
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn get_anime_detail(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
slug: String,
|
||||||
|
) -> Result<DetailResponse, AppError> {
|
||||||
|
let cache_key = format!("anime:detail:{}", slug);
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, DEFAULT_CACHE_TTL, || async {
|
||||||
|
let mut data = self
|
||||||
|
.repository
|
||||||
|
.fetch_anime_detail(&slug)
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
|
||||||
|
data.poster = crate::shared::services::images::cache::get_cached_or_original(
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
&data.poster,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
let rec_posters: Vec<String> = data
|
||||||
|
.recommendations
|
||||||
|
.iter()
|
||||||
|
.map(|r| r.poster.clone())
|
||||||
|
.collect();
|
||||||
|
let cached_rec_posters =
|
||||||
|
crate::shared::services::images::cache::cache_image_urls_batch_lazy(
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
rec_posters,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
for (i, rec) in data.recommendations.iter_mut().enumerate() {
|
||||||
|
if let Some(url) = cached_rec_posters.get(i) {
|
||||||
|
rec.poster = url.clone();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(DetailResponse {
|
||||||
|
status: Some("Ok".to_string()),
|
||||||
|
data,
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn get_complete_anime_page(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
slug: String,
|
||||||
|
) -> Result<ListResponse, AppError> {
|
||||||
|
let cache_key = format!("anime:complete:{}", slug);
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, DEFAULT_CACHE_TTL, || async {
|
||||||
|
let (anime_list, pagination) = self
|
||||||
|
.repository
|
||||||
|
.fetch_complete_anime_page(&slug)
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
let total = anime_list.len() as i64;
|
||||||
|
Ok(ListResponse {
|
||||||
|
message: "Success".to_string(),
|
||||||
|
data: anime_list,
|
||||||
|
total: Some(total),
|
||||||
|
pagination: Some(pagination),
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn get_ongoing_anime_page(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
slug: String,
|
||||||
|
) -> Result<OngoingAnimeResponse, AppError> {
|
||||||
|
let cache_key = format!("anime:ongoing:{}", slug);
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, DEFAULT_CACHE_TTL, || async {
|
||||||
|
let (anime_list, pagination) = self
|
||||||
|
.repository
|
||||||
|
.fetch_ongoing_anime_page(&slug)
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
Ok(OngoingAnimeResponse {
|
||||||
|
status: "Ok".to_string(),
|
||||||
|
data: anime_list,
|
||||||
|
pagination,
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn get_latest_anime_page(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
slug: String,
|
||||||
|
) -> Result<LatestAnimeResponse, AppError> {
|
||||||
|
let cache_key = format!("anime:latest:{}", slug);
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, DEFAULT_CACHE_TTL, || async {
|
||||||
|
let (anime_list, pagination) = self
|
||||||
|
.repository
|
||||||
|
.fetch_latest_anime_page(&slug)
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
Ok(LatestAnimeResponse {
|
||||||
|
status: "Ok".to_string(),
|
||||||
|
data: anime_list,
|
||||||
|
pagination,
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn get_search_anime_page(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
slug: String,
|
||||||
|
page: String,
|
||||||
|
) -> Result<SearchResponse, AppError> {
|
||||||
|
let cache_key = format!("anime:search:{}:{}", slug, page);
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, DEFAULT_CACHE_TTL, || async {
|
||||||
|
let (anime_list, pagination) = self
|
||||||
|
.repository
|
||||||
|
.fetch_search_anime_page(&slug, &page)
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
Ok(SearchResponse {
|
||||||
|
status: "Ok".to_string(),
|
||||||
|
data: anime_list,
|
||||||
|
pagination,
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn get_genre_anime_page(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
genre_slug: String,
|
||||||
|
page: String,
|
||||||
|
) -> Result<GenreListResponse, AppError> {
|
||||||
|
let cache_key = format!("anime:genre:{}:{}", genre_slug, page);
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, DEFAULT_CACHE_TTL, || async {
|
||||||
|
let (anime_list, pagination) = self
|
||||||
|
.repository
|
||||||
|
.fetch_genre_anime_page(&genre_slug, &page)
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
Ok(GenreListResponse {
|
||||||
|
status: "Ok".to_string(),
|
||||||
|
data: anime_list,
|
||||||
|
pagination,
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn get_anime_full(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
slug: String,
|
||||||
|
) -> Result<FullResponse, AppError> {
|
||||||
|
let cache_key = format!("anime:full:{}", slug);
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, DEFAULT_CACHE_TTL, || async {
|
||||||
|
let data = self
|
||||||
|
.repository
|
||||||
|
.fetch_anime_full(&slug)
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
Ok(FullResponse {
|
||||||
|
status: "Ok".to_string(),
|
||||||
|
data,
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| AppError::ScraperError(e))
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,231 @@
|
|||||||
|
use serde::{Deserialize, Serialize};
|
||||||
|
use utoipa::ToSchema;
|
||||||
|
|
||||||
|
// Index endpoint types
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct OngoingAnimeItem {
|
||||||
|
pub title: String,
|
||||||
|
pub slug: String,
|
||||||
|
pub poster: String,
|
||||||
|
pub current_episode: String,
|
||||||
|
pub anime_url: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct CompleteAnimeItem {
|
||||||
|
pub title: String,
|
||||||
|
pub slug: String,
|
||||||
|
pub poster: String,
|
||||||
|
pub episode_count: String,
|
||||||
|
pub anime_url: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct AnimeData {
|
||||||
|
pub ongoing_anime: Vec<OngoingAnimeItem>,
|
||||||
|
pub complete_anime: Vec<CompleteAnimeItem>,
|
||||||
|
}
|
||||||
|
|
||||||
|
// Genre list types
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct Genre {
|
||||||
|
pub name: String,
|
||||||
|
pub slug: String,
|
||||||
|
pub url: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct GenresResponse {
|
||||||
|
pub status: String,
|
||||||
|
pub data: Vec<Genre>,
|
||||||
|
}
|
||||||
|
|
||||||
|
// Detail endpoint types
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct DetailGenre {
|
||||||
|
pub name: String,
|
||||||
|
pub slug: String,
|
||||||
|
pub anime_url: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct EpisodeList {
|
||||||
|
pub episode: String,
|
||||||
|
pub slug: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct Recommendation {
|
||||||
|
pub title: String,
|
||||||
|
pub slug: String,
|
||||||
|
pub poster: String,
|
||||||
|
#[serde(skip_serializing_if = "Option::is_none")]
|
||||||
|
pub status: Option<String>,
|
||||||
|
#[serde(skip_serializing_if = "Option::is_none")]
|
||||||
|
pub r#type: Option<String>,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct AnimeDetailData {
|
||||||
|
pub title: String,
|
||||||
|
pub alternative_title: String,
|
||||||
|
pub poster: String,
|
||||||
|
#[serde(skip_serializing_if = "Option::is_none")]
|
||||||
|
pub r#type: Option<String>,
|
||||||
|
#[serde(skip_serializing_if = "Option::is_none")]
|
||||||
|
pub status: Option<String>,
|
||||||
|
pub release_date: String,
|
||||||
|
pub studio: String,
|
||||||
|
#[serde(skip_serializing_if = "Vec::is_empty")]
|
||||||
|
pub genres: Vec<DetailGenre>,
|
||||||
|
pub synopsis: String,
|
||||||
|
pub episode_lists: Vec<EpisodeList>,
|
||||||
|
#[serde(skip_serializing_if = "Vec::is_empty")]
|
||||||
|
pub batch: Vec<EpisodeList>,
|
||||||
|
#[serde(skip_serializing_if = "Vec::is_empty")]
|
||||||
|
pub producers: Vec<String>,
|
||||||
|
pub recommendations: Vec<Recommendation>,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct DetailResponse {
|
||||||
|
#[serde(skip_serializing_if = "Option::is_none")]
|
||||||
|
pub status: Option<String>,
|
||||||
|
pub data: AnimeDetailData,
|
||||||
|
}
|
||||||
|
|
||||||
|
// Complete anime list types
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct CompleteAnimeListItem {
|
||||||
|
pub title: String,
|
||||||
|
pub slug: String,
|
||||||
|
pub poster: String,
|
||||||
|
pub episode_count: String,
|
||||||
|
pub anime_url: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct Pagination {
|
||||||
|
pub current_page: u32,
|
||||||
|
pub last_visible_page: u32,
|
||||||
|
pub has_next_page: bool,
|
||||||
|
pub next_page: Option<u32>,
|
||||||
|
pub has_previous_page: bool,
|
||||||
|
pub previous_page: Option<u32>,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct ListResponse {
|
||||||
|
pub message: String,
|
||||||
|
pub data: Vec<CompleteAnimeListItem>,
|
||||||
|
pub total: Option<i64>,
|
||||||
|
pub pagination: Option<Pagination>,
|
||||||
|
}
|
||||||
|
|
||||||
|
// Full episode types
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct AnimeInfo {
|
||||||
|
pub slug: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct EpisodeInfo {
|
||||||
|
pub slug: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct DownloadLink {
|
||||||
|
pub server: String,
|
||||||
|
pub url: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct AnimeFullData {
|
||||||
|
pub episode: String,
|
||||||
|
pub episode_number: String,
|
||||||
|
pub anime: AnimeInfo,
|
||||||
|
pub has_next_episode: bool,
|
||||||
|
pub next_episode: Option<EpisodeInfo>,
|
||||||
|
pub has_previous_episode: bool,
|
||||||
|
pub previous_episode: Option<EpisodeInfo>,
|
||||||
|
pub stream_url: String,
|
||||||
|
pub download_urls: std::collections::HashMap<String, Vec<DownloadLink>>,
|
||||||
|
pub image_url: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct FullResponse {
|
||||||
|
pub status: String,
|
||||||
|
pub data: AnimeFullData,
|
||||||
|
}
|
||||||
|
|
||||||
|
// Ongoing anime list types
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct OngoingAnimeListItem {
|
||||||
|
pub title: String,
|
||||||
|
pub slug: String,
|
||||||
|
pub poster: String,
|
||||||
|
pub score: String,
|
||||||
|
pub anime_url: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct OngoingAnimeResponse {
|
||||||
|
pub status: String,
|
||||||
|
pub data: Vec<OngoingAnimeListItem>,
|
||||||
|
pub pagination: Pagination,
|
||||||
|
}
|
||||||
|
|
||||||
|
// Latest anime types
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct LatestAnimeItem {
|
||||||
|
pub title: String,
|
||||||
|
pub slug: String,
|
||||||
|
pub poster: String,
|
||||||
|
pub episode: String,
|
||||||
|
pub anime_url: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct LatestAnimeResponse {
|
||||||
|
pub status: String,
|
||||||
|
pub data: Vec<LatestAnimeItem>,
|
||||||
|
pub pagination: Pagination,
|
||||||
|
}
|
||||||
|
|
||||||
|
// Search types
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct SearchAnimeItem {
|
||||||
|
pub title: String,
|
||||||
|
pub slug: String,
|
||||||
|
pub poster: String,
|
||||||
|
pub episode: String,
|
||||||
|
pub anime_url: String,
|
||||||
|
pub genres: Vec<String>,
|
||||||
|
pub status: String,
|
||||||
|
pub rating: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct SearchResponse {
|
||||||
|
pub status: String,
|
||||||
|
pub data: Vec<SearchAnimeItem>,
|
||||||
|
pub pagination: Pagination,
|
||||||
|
}
|
||||||
|
|
||||||
|
// Genre list by slug types
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct GenreAnimeItem {
|
||||||
|
pub title: String,
|
||||||
|
pub slug: String,
|
||||||
|
pub poster: String,
|
||||||
|
pub episode: String,
|
||||||
|
pub anime_url: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Serialize, Deserialize, Debug, Clone, ToSchema)]
|
||||||
|
pub struct GenreListResponse {
|
||||||
|
pub status: String,
|
||||||
|
pub data: Vec<GenreAnimeItem>,
|
||||||
|
pub pagination: Pagination,
|
||||||
|
}
|
||||||
@@ -0,0 +1,276 @@
|
|||||||
|
use std::sync::Arc;
|
||||||
|
|
||||||
|
use axum::{
|
||||||
|
extract::{Path, Query, State},
|
||||||
|
Json,
|
||||||
|
};
|
||||||
|
|
||||||
|
use crate::modules::anime2::repository::Anime2Repository;
|
||||||
|
use crate::modules::anime2::schema::FilterQuery;
|
||||||
|
use crate::modules::anime2::service::Anime2Service;
|
||||||
|
use crate::shared::errors::AppError;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_index",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Handles GET requests for the /api/anime2 endpoint.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn index(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
) -> Result<Json<crate::modules::anime2::types::Anime2Response>, AppError> {
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(service.index(app_state).await?))
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2/genre_list",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_genre_list",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Handles GET requests for the /api/anime2/genre_list endpoint.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn genre_list(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
) -> Result<Json<crate::modules::anime2::types::GenresResponse>, AppError> {
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(service.genre_list(app_state).await?))
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2/filter",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_filter",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Handles GET requests for the /api/anime2/filter endpoint.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn filter(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Query(params): Query<FilterQuery>,
|
||||||
|
) -> Result<Json<crate::modules::anime2::types::FilterResponse>, AppError> {
|
||||||
|
let page = params.page.unwrap_or(1);
|
||||||
|
let genre = params.genre.clone();
|
||||||
|
let status = params.status.clone();
|
||||||
|
let anime_type = params.r#type.clone();
|
||||||
|
let order = params.order.clone().unwrap_or("update".to_string());
|
||||||
|
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(
|
||||||
|
service
|
||||||
|
.filter(app_state, page, genre, status, anime_type, order)
|
||||||
|
.await?,
|
||||||
|
))
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2/detail/{slug}",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_detail_slug",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific detail by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn detail_slug(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<Json<crate::modules::anime2::types::DetailResponse>, AppError> {
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(service.detail(app_state, slug).await?))
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2/genre/{slug}",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_genre_slug_index",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific genre by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn genre_slug_index(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<
|
||||||
|
Json<
|
||||||
|
crate::shared::types::ApiResponse<
|
||||||
|
Vec<crate::shared::types::entities::anime::GenreAnimeItem>,
|
||||||
|
>,
|
||||||
|
>,
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(service.genre_slug(app_state, slug, 1).await?))
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2/genre/{slug}/{page}",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_genre_slug_page",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Handles GET requests for the /api/anime2/genre/{slug}/{page} endpoint.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn genre_slug_page(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path((slug, page)): Path<(String, u32)>,
|
||||||
|
) -> Result<
|
||||||
|
Json<
|
||||||
|
crate::shared::types::ApiResponse<
|
||||||
|
Vec<crate::shared::types::entities::anime::GenreAnimeItem>,
|
||||||
|
>,
|
||||||
|
>,
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(service.genre_slug(app_state, slug, page).await?))
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2/search/{slug}",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_search_slug_index",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific search by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn search_slug_index(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<
|
||||||
|
Json<
|
||||||
|
crate::shared::types::ApiResponse<
|
||||||
|
Vec<crate::shared::types::entities::anime::SearchAnimeItem>,
|
||||||
|
>,
|
||||||
|
>,
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(service.search(app_state, slug, 1).await?))
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2/search/{slug}/{page}",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_search_slug_page",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Handles GET requests for the /api/anime2/search/{slug}/{page} endpoint.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn search_slug_page(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path((slug, page)): Path<(String, u32)>,
|
||||||
|
) -> Result<
|
||||||
|
Json<
|
||||||
|
crate::shared::types::ApiResponse<
|
||||||
|
Vec<crate::shared::types::entities::anime::SearchAnimeItem>,
|
||||||
|
>,
|
||||||
|
>,
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(service.search(app_state, slug, page).await?))
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2/latest/{slug}",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_latest_slug",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific latest by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn latest_slug(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<
|
||||||
|
Json<
|
||||||
|
crate::shared::types::ApiResponse<
|
||||||
|
Vec<crate::shared::types::entities::anime::LatestAnimeItem>,
|
||||||
|
>,
|
||||||
|
>,
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let page = slug
|
||||||
|
.parse::<u32>()
|
||||||
|
.map_err(|_| AppError::ScraperError(format!("Invalid page number: {}", slug)))?;
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(service.latest(app_state, page).await?))
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2/ongoing_anime/{slug}",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_ongoing_anime_slug",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific ongoing_anime by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn ongoing_anime_slug(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<
|
||||||
|
Json<
|
||||||
|
crate::shared::types::ApiResponse<
|
||||||
|
Vec<crate::shared::types::entities::anime::OngoingAnimeItemWithScore>,
|
||||||
|
>,
|
||||||
|
>,
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let page = slug
|
||||||
|
.parse::<u32>()
|
||||||
|
.map_err(|_| AppError::ScraperError(format!("Invalid page number: {}", slug)))?;
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(service.ongoing_anime(app_state, page).await?))
|
||||||
|
}
|
||||||
|
|
||||||
|
#[utoipa::path(
|
||||||
|
get,
|
||||||
|
path = "/api/anime2/complete_anime/{slug}",
|
||||||
|
tag = "anime2",
|
||||||
|
operation_id = "anime2_complete_anime_slug",
|
||||||
|
responses(
|
||||||
|
(status = 200, description = "Retrieves details for a specific complete_anime by slug.", body = serde_json::Value),
|
||||||
|
(status = 500, description = "Internal Server Error", body = String)
|
||||||
|
)
|
||||||
|
)]
|
||||||
|
pub async fn complete_anime_slug(
|
||||||
|
State(app_state): State<Arc<AppState>>,
|
||||||
|
Path(slug): Path<String>,
|
||||||
|
) -> Result<
|
||||||
|
Json<
|
||||||
|
crate::shared::types::ApiResponse<
|
||||||
|
Vec<crate::shared::types::entities::anime::CompleteAnimeItem>,
|
||||||
|
>,
|
||||||
|
>,
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let page = slug
|
||||||
|
.parse::<u32>()
|
||||||
|
.map_err(|_| AppError::ScraperError(format!("Invalid page number: {}", slug)))?;
|
||||||
|
let service = Anime2Service::new(Anime2Repository::new());
|
||||||
|
Ok(Json(service.complete_anime(app_state, page).await?))
|
||||||
|
}
|
||||||
@@ -0,0 +1,7 @@
|
|||||||
|
pub mod controller;
|
||||||
|
pub mod parser;
|
||||||
|
pub mod repository;
|
||||||
|
pub mod route;
|
||||||
|
pub mod schema;
|
||||||
|
pub mod service;
|
||||||
|
pub mod types;
|
||||||
@@ -0,0 +1,804 @@
|
|||||||
|
use crate::shared::errors::AppError;
|
||||||
|
use crate::shared::utils::parse_html;
|
||||||
|
use crate::shared::utils::scraping::{attr, extract_slug, selector, text, text_from_or};
|
||||||
|
use once_cell::sync::Lazy;
|
||||||
|
use regex::Regex;
|
||||||
|
use scraper::Selector;
|
||||||
|
|
||||||
|
static ITEM_SELECTOR: Lazy<Selector> = Lazy::new(|| Selector::parse("article.bs").unwrap());
|
||||||
|
static TITLE_SELECTOR: Lazy<Selector> = Lazy::new(|| Selector::parse(".tt h2").unwrap());
|
||||||
|
static IMG_SELECTOR: Lazy<Selector> = Lazy::new(|| Selector::parse("img").unwrap());
|
||||||
|
static SCORE_SELECTOR: Lazy<Selector> = Lazy::new(|| Selector::parse(".numscore").unwrap());
|
||||||
|
static STATUS_SELECTOR: Lazy<Selector> = Lazy::new(|| Selector::parse(".status").unwrap());
|
||||||
|
static TYPE_SELECTOR: Lazy<Selector> = Lazy::new(|| Selector::parse(".type").unwrap());
|
||||||
|
static LINK_SELECTOR: Lazy<Selector> = Lazy::new(|| Selector::parse("a").unwrap());
|
||||||
|
static PAGINATION_SELECTOR: Lazy<Selector> =
|
||||||
|
Lazy::new(|| Selector::parse(".pagination .page-numbers:not(.next)").unwrap());
|
||||||
|
static NEXT_SELECTOR: Lazy<Selector> = Lazy::new(|| Selector::parse(".pagination .next").unwrap());
|
||||||
|
static SLUG_REGEX: Lazy<Regex> = Lazy::new(|| Regex::new(r"/([^/]+)/?$").unwrap());
|
||||||
|
static GENRE_SLUG_REGEX: Lazy<Regex> = Lazy::new(|| Regex::new(r"genre-(.+)$").unwrap());
|
||||||
|
pub fn parse_ongoing_anime(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<crate::shared::types::entities::anime::OngoingAnimeItem>, AppError> {
|
||||||
|
let items = parse_ongoing_anime_with_score(html)?;
|
||||||
|
Ok(items
|
||||||
|
.into_iter()
|
||||||
|
.map(
|
||||||
|
|item| crate::shared::types::entities::anime::OngoingAnimeItem {
|
||||||
|
title: item.title,
|
||||||
|
slug: item.slug,
|
||||||
|
poster: item.poster,
|
||||||
|
current_episode: item.score,
|
||||||
|
anime_url: item.anime_url,
|
||||||
|
},
|
||||||
|
)
|
||||||
|
.collect())
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_complete_anime(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<crate::shared::types::entities::anime::CompleteAnimeItem>, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut complete_anime = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&ITEM_SELECTOR) {
|
||||||
|
let title = element
|
||||||
|
.select(&TITLE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or_default();
|
||||||
|
let poster = element
|
||||||
|
.select(&IMG_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("src").or(e.value().attr("data-src")))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
let anime_url = element
|
||||||
|
.select(&LINK_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("href"))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
let slug = SLUG_REGEX
|
||||||
|
.captures(&anime_url)
|
||||||
|
.and_then(|cap| cap.get(1))
|
||||||
|
.map(|m| m.as_str())
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
let episode_count = text_from_or(&element, &STATUS_SELECTOR, "N/A");
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
complete_anime.push(crate::shared::types::entities::anime::CompleteAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
episode_count,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(complete_anime)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_genres(html: &str) -> Result<Vec<crate::modules::anime2::types::Genre>, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut genres = Vec::new();
|
||||||
|
let genre_label_selector = selector("label[for^=\"genre-\"]").ok_or_else(|| {
|
||||||
|
AppError::ScraperError("Invalid selector: label[for^=\"genre-\"]".to_string())
|
||||||
|
})?;
|
||||||
|
|
||||||
|
for element in document.select(&genre_label_selector) {
|
||||||
|
let name = text(&element).trim().to_string();
|
||||||
|
let for_attr = attr(&element, "for").unwrap_or_default();
|
||||||
|
|
||||||
|
let slug = GENRE_SLUG_REGEX
|
||||||
|
.captures(&for_attr)
|
||||||
|
.and_then(|cap| cap.get(1))
|
||||||
|
.map(|m| m.as_str())
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
if !name.is_empty() && !slug.is_empty() {
|
||||||
|
genres.push(crate::modules::anime2::types::Genre { name, slug });
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(genres)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_filter_page(
|
||||||
|
html: &str,
|
||||||
|
current_page: u32,
|
||||||
|
) -> Result<
|
||||||
|
(
|
||||||
|
Vec<crate::shared::types::entities::anime::FilterAnimeItem>,
|
||||||
|
crate::shared::types::entities::anime::Pagination,
|
||||||
|
),
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut anime_list = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&ITEM_SELECTOR) {
|
||||||
|
let title = element
|
||||||
|
.select(&TITLE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let poster = element
|
||||||
|
.select(&IMG_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("src").or(e.value().attr("data-src")))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let score = element
|
||||||
|
.select(&SCORE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or("N/A".to_string());
|
||||||
|
|
||||||
|
let status = element
|
||||||
|
.select(&STATUS_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or("Unknown".to_string());
|
||||||
|
|
||||||
|
let anime_type = element
|
||||||
|
.select(&TYPE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or("Unknown".to_string());
|
||||||
|
|
||||||
|
let anime_url = element
|
||||||
|
.select(&LINK_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("href"))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let slug = SLUG_REGEX
|
||||||
|
.captures(&anime_url)
|
||||||
|
.and_then(|cap| cap.get(1))
|
||||||
|
.map(|m| m.as_str())
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
anime_list.push(crate::shared::types::entities::anime::FilterAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
score,
|
||||||
|
status,
|
||||||
|
r#type: anime_type,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let last_visible_page = document
|
||||||
|
.select(&PAGINATION_SELECTOR)
|
||||||
|
.next_back()
|
||||||
|
.map(|e| {
|
||||||
|
e.text()
|
||||||
|
.collect::<String>()
|
||||||
|
.trim()
|
||||||
|
.parse::<u32>()
|
||||||
|
.unwrap_or(1)
|
||||||
|
})
|
||||||
|
.unwrap_or(1);
|
||||||
|
|
||||||
|
let has_next_page = document.select(&NEXT_SELECTOR).next().is_some();
|
||||||
|
let pagination = crate::shared::types::entities::anime::Pagination {
|
||||||
|
current_page,
|
||||||
|
last_visible_page,
|
||||||
|
has_next_page,
|
||||||
|
next_page: if has_next_page {
|
||||||
|
Some(current_page + 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
},
|
||||||
|
has_previous_page: current_page > 1,
|
||||||
|
previous_page: if current_page > 1 {
|
||||||
|
Some(current_page - 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
},
|
||||||
|
};
|
||||||
|
|
||||||
|
Ok((anime_list, pagination))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_genre_anime(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<crate::shared::types::entities::anime::GenreAnimeItem>, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut anime_list = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&ITEM_SELECTOR) {
|
||||||
|
let title = element
|
||||||
|
.select(&TITLE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let poster = element
|
||||||
|
.select(&IMG_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("src").or(e.value().attr("data-src")))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let score = element
|
||||||
|
.select(&SCORE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or("N/A".to_string());
|
||||||
|
|
||||||
|
let status = element
|
||||||
|
.select(&STATUS_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or("Unknown".to_string());
|
||||||
|
|
||||||
|
let anime_url = element
|
||||||
|
.select(&LINK_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("href"))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let slug = SLUG_REGEX
|
||||||
|
.captures(&anime_url)
|
||||||
|
.and_then(|cap| cap.get(1))
|
||||||
|
.map(|m| m.as_str())
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
anime_list.push(crate::shared::types::entities::anime::GenreAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
score,
|
||||||
|
status,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(anime_list)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_search_anime(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<crate::shared::types::entities::anime::SearchAnimeItem>, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut anime_list = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&ITEM_SELECTOR) {
|
||||||
|
let title = element
|
||||||
|
.select(&TITLE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let poster = element
|
||||||
|
.select(&IMG_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("src").or(e.value().attr("data-src")))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let anime_url = element
|
||||||
|
.select(&LINK_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("href"))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let slug = SLUG_REGEX
|
||||||
|
.captures(&anime_url)
|
||||||
|
.and_then(|cap| cap.get(1))
|
||||||
|
.map(|m| m.as_str())
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
anime_list.push(crate::shared::types::entities::anime::SearchAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
description: String::new(),
|
||||||
|
anime_url,
|
||||||
|
genres: Vec::new(),
|
||||||
|
rating: "N/A".to_string(),
|
||||||
|
r#type: "Unknown".to_string(),
|
||||||
|
season: "Unknown".to_string(),
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(anime_list)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_latest_anime(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<crate::shared::types::entities::anime::LatestAnimeItem>, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut anime_list = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&ITEM_SELECTOR) {
|
||||||
|
let title = element
|
||||||
|
.select(&TITLE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let poster = element
|
||||||
|
.select(&IMG_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("src").or(e.value().attr("data-src")))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let score = element
|
||||||
|
.select(&SCORE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or("N/A".to_string());
|
||||||
|
|
||||||
|
let anime_url = element
|
||||||
|
.select(&LINK_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("href"))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let slug = SLUG_REGEX
|
||||||
|
.captures(&anime_url)
|
||||||
|
.and_then(|cap| cap.get(1))
|
||||||
|
.map(|m| m.as_str())
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
anime_list.push(crate::shared::types::entities::anime::LatestAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
current_episode: "N/A".to_string(),
|
||||||
|
score,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(anime_list)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_ongoing_anime_with_score(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<crate::shared::types::entities::anime::OngoingAnimeItemWithScore>, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let mut anime_list = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&ITEM_SELECTOR) {
|
||||||
|
let title = element
|
||||||
|
.select(&TITLE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let poster = element
|
||||||
|
.select(&IMG_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("src").or(e.value().attr("data-src")))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let score = element
|
||||||
|
.select(&SCORE_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.map(|e| e.text().collect::<String>().trim().to_string())
|
||||||
|
.unwrap_or("N/A".to_string());
|
||||||
|
|
||||||
|
let anime_url = element
|
||||||
|
.select(&LINK_SELECTOR)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| e.value().attr("href"))
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
let slug = SLUG_REGEX
|
||||||
|
.captures(&anime_url)
|
||||||
|
.and_then(|cap| cap.get(1))
|
||||||
|
.map(|m| m.as_str())
|
||||||
|
.unwrap_or("")
|
||||||
|
.to_string();
|
||||||
|
|
||||||
|
if !title.is_empty() {
|
||||||
|
anime_list.push(
|
||||||
|
crate::shared::types::entities::anime::OngoingAnimeItemWithScore {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
score,
|
||||||
|
anime_url,
|
||||||
|
},
|
||||||
|
);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(anime_list)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_pagination(
|
||||||
|
document: &scraper::Html,
|
||||||
|
current_page: u32,
|
||||||
|
) -> Result<crate::shared::types::entities::anime::Pagination, String> {
|
||||||
|
let last_visible_page = document
|
||||||
|
.select(&PAGINATION_SELECTOR)
|
||||||
|
.next_back()
|
||||||
|
.map(|e| {
|
||||||
|
e.text()
|
||||||
|
.collect::<String>()
|
||||||
|
.trim()
|
||||||
|
.parse::<u32>()
|
||||||
|
.unwrap_or(1)
|
||||||
|
})
|
||||||
|
.unwrap_or(1);
|
||||||
|
|
||||||
|
let has_next_page = document.select(&NEXT_SELECTOR).next().is_some();
|
||||||
|
let pagination = crate::shared::types::entities::anime::Pagination {
|
||||||
|
current_page,
|
||||||
|
last_visible_page,
|
||||||
|
has_next_page,
|
||||||
|
next_page: if has_next_page {
|
||||||
|
Some(current_page + 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
},
|
||||||
|
has_previous_page: current_page > 1,
|
||||||
|
previous_page: if current_page > 1 {
|
||||||
|
Some(current_page - 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
},
|
||||||
|
};
|
||||||
|
|
||||||
|
Ok(pagination)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_pagination_with_string(
|
||||||
|
document: &scraper::Html,
|
||||||
|
current_page: u32,
|
||||||
|
) -> Result<crate::shared::types::entities::anime::PaginationWithStringPages, String> {
|
||||||
|
let last_visible_page = document
|
||||||
|
.select(&PAGINATION_SELECTOR)
|
||||||
|
.next_back()
|
||||||
|
.map(|e| {
|
||||||
|
e.text()
|
||||||
|
.collect::<String>()
|
||||||
|
.trim()
|
||||||
|
.parse::<u32>()
|
||||||
|
.unwrap_or(1)
|
||||||
|
})
|
||||||
|
.unwrap_or(1);
|
||||||
|
|
||||||
|
let has_next_page = document.select(&NEXT_SELECTOR).next().is_some();
|
||||||
|
let pagination = crate::shared::types::entities::anime::PaginationWithStringPages {
|
||||||
|
current_page,
|
||||||
|
last_visible_page,
|
||||||
|
has_next_page,
|
||||||
|
next_page: if has_next_page {
|
||||||
|
Some((current_page + 1).to_string())
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
},
|
||||||
|
has_previous_page: current_page > 1,
|
||||||
|
previous_page: if current_page > 1 {
|
||||||
|
Some((current_page - 1).to_string())
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
},
|
||||||
|
};
|
||||||
|
|
||||||
|
Ok(pagination)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_anime_detail(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<crate::modules::anime2::types::AnimeDetailData, AppError> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
|
||||||
|
let title_selector = selector(".entry-title")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .entry-title".to_string()))?;
|
||||||
|
let alt_title_selector = selector(".alter")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .alter".to_string()))?;
|
||||||
|
let poster_selector = selector(".thumb img, .thumbook img, .wp-post-image, .ts-post-image")
|
||||||
|
.ok_or_else(|| {
|
||||||
|
AppError::ScraperError(
|
||||||
|
"Invalid selector: .thumb img, .thumbook img, .wp-post-image, .ts-post-image"
|
||||||
|
.to_string(),
|
||||||
|
)
|
||||||
|
})?;
|
||||||
|
let poster2_selector = selector(".bigcover img, .bixbox.animefull .bigcover .ime img")
|
||||||
|
.ok_or_else(|| {
|
||||||
|
AppError::ScraperError(
|
||||||
|
"Invalid selector: .bigcover img, .bixbox.animefull .bigcover .ime img".to_string(),
|
||||||
|
)
|
||||||
|
})?;
|
||||||
|
let spe_span_selector = selector(".info-content .spe span").ok_or_else(|| {
|
||||||
|
AppError::ScraperError("Invalid selector: .info-content .spe span".to_string())
|
||||||
|
})?;
|
||||||
|
let a_selector =
|
||||||
|
selector("a").ok_or_else(|| AppError::ScraperError("Invalid selector: a".to_string()))?;
|
||||||
|
let synopsis_selector = selector(".entry-content p")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .entry-content p".to_string()))?;
|
||||||
|
let genre_selector = selector(".genxed a")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .genxed a".to_string()))?;
|
||||||
|
let download_container_selector = selector(".soraddl.dlone")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .soraddl.dlone".to_string()))?;
|
||||||
|
let resolution_selector = selector(".res")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .res".to_string()))?;
|
||||||
|
let link_selector = selector(".slink a")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .slink a".to_string()))?;
|
||||||
|
let h3_selector =
|
||||||
|
selector("h3").ok_or_else(|| AppError::ScraperError("Invalid selector: h3".to_string()))?;
|
||||||
|
let recommendation_selector = selector(".listupd .bs")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .listupd .bs".to_string()))?;
|
||||||
|
let rec_title_selector = selector(".ntitle")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .ntitle".to_string()))?;
|
||||||
|
let rec_img_selector = selector("img")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: img".to_string()))?;
|
||||||
|
let status_selector = selector(".status")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .status".to_string()))?;
|
||||||
|
let type_selector = selector(".typez")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: .typez".to_string()))?;
|
||||||
|
|
||||||
|
let title = text_from_or(&document.root_element(), &title_selector, "");
|
||||||
|
let alternative_title = text_from_or(&document.root_element(), &alt_title_selector, "");
|
||||||
|
|
||||||
|
let poster = document
|
||||||
|
.select(&poster_selector)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| {
|
||||||
|
attr(&e, "src")
|
||||||
|
.or_else(|| attr(&e, "data-src"))
|
||||||
|
.or_else(|| attr(&e, "data-lazy-src"))
|
||||||
|
})
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let poster2 = document
|
||||||
|
.select(&poster2_selector)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| {
|
||||||
|
attr(&e, "src")
|
||||||
|
.or_else(|| attr(&e, "data-src"))
|
||||||
|
.or_else(|| attr(&e, "data-lazy-src"))
|
||||||
|
})
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let r#type = document
|
||||||
|
.select(&spe_span_selector)
|
||||||
|
.find(|e| text(&e).contains("Tipe:"))
|
||||||
|
.and_then(|span| span.select(&a_selector).next())
|
||||||
|
.map(|e| text(&e))
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let release_date = document
|
||||||
|
.select(&spe_span_selector)
|
||||||
|
.find(|e| text(&e).contains("Dirilis:"))
|
||||||
|
.map(|e| text(&e))
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let status = document
|
||||||
|
.select(&spe_span_selector)
|
||||||
|
.find(|e| text(&e).contains("Status:"))
|
||||||
|
.map(|e| text(&e))
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let synopsis = text_from_or(&document.root_element(), &synopsis_selector, "");
|
||||||
|
|
||||||
|
let studio = document
|
||||||
|
.select(&spe_span_selector)
|
||||||
|
.find(|e| text(&e).contains("Studio:"))
|
||||||
|
.and_then(|span| span.select(&a_selector).next())
|
||||||
|
.map(|e| text(&e))
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let mut genres = Vec::new();
|
||||||
|
for element in document.select(&genre_selector) {
|
||||||
|
let name = text(&element);
|
||||||
|
let anime_url = attr(&element, "href").unwrap_or_default();
|
||||||
|
let genre_slug = extract_slug(&anime_url);
|
||||||
|
genres.push(crate::modules::anime2::types::DetailGenre {
|
||||||
|
name,
|
||||||
|
slug: genre_slug,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
let mut batch = Vec::new();
|
||||||
|
let mut ova = Vec::new();
|
||||||
|
let mut downloads = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&download_container_selector) {
|
||||||
|
let title = element
|
||||||
|
.select(&h3_selector)
|
||||||
|
.next()
|
||||||
|
.map(|e| text(&e))
|
||||||
|
.unwrap_or_else(|| "Unknown".to_string());
|
||||||
|
|
||||||
|
let category = title.to_lowercase();
|
||||||
|
let is_batch = category.contains("batch");
|
||||||
|
let is_ova = category.contains("ova");
|
||||||
|
|
||||||
|
let mut all_links = Vec::new();
|
||||||
|
|
||||||
|
let row_selector = selector("table tr")
|
||||||
|
.ok_or_else(|| AppError::ScraperError("Invalid selector: table tr".to_string()))?;
|
||||||
|
for row in element.select(&row_selector) {
|
||||||
|
let resolution = text_from_or(&row, &resolution_selector, "");
|
||||||
|
|
||||||
|
for link_element in row.select(&link_selector) {
|
||||||
|
let provider = text(&link_element);
|
||||||
|
let url = attr(&link_element, "href").unwrap_or_default();
|
||||||
|
|
||||||
|
let name = if !resolution.is_empty() {
|
||||||
|
format!("{} - {}", resolution, provider)
|
||||||
|
} else {
|
||||||
|
provider
|
||||||
|
};
|
||||||
|
|
||||||
|
all_links.push(crate::modules::anime2::types::Link { name, url });
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let download_item = crate::modules::anime2::types::DownloadItem {
|
||||||
|
resolution: title,
|
||||||
|
links: all_links,
|
||||||
|
};
|
||||||
|
|
||||||
|
if is_batch {
|
||||||
|
batch.push(download_item);
|
||||||
|
} else if is_ova {
|
||||||
|
ova.push(download_item);
|
||||||
|
} else {
|
||||||
|
downloads.push(download_item);
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
let mut recommendations = Vec::new();
|
||||||
|
for element in document.select(&recommendation_selector) {
|
||||||
|
let title = text_from_or(&element, &rec_title_selector, "");
|
||||||
|
|
||||||
|
let anime_url = element
|
||||||
|
.select(&a_selector)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| attr(&e, "href"))
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let rec_slug = extract_slug(&anime_url);
|
||||||
|
|
||||||
|
let poster = element
|
||||||
|
.select(&rec_img_selector)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| attr(&e, "data-src").or_else(|| attr(&e, "src")))
|
||||||
|
.unwrap_or_default();
|
||||||
|
|
||||||
|
let status = text_from_or(&element, &status_selector, "");
|
||||||
|
|
||||||
|
let r#type = text_from_or(&element, &type_selector, "");
|
||||||
|
|
||||||
|
recommendations.push(crate::modules::anime2::types::Recommendation {
|
||||||
|
title,
|
||||||
|
slug: rec_slug,
|
||||||
|
poster,
|
||||||
|
status,
|
||||||
|
r#type,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(crate::modules::anime2::types::AnimeDetailData {
|
||||||
|
title,
|
||||||
|
alternative_title,
|
||||||
|
poster,
|
||||||
|
poster2,
|
||||||
|
r#type,
|
||||||
|
release_date,
|
||||||
|
status,
|
||||||
|
synopsis,
|
||||||
|
studio,
|
||||||
|
genres,
|
||||||
|
producers: vec![],
|
||||||
|
recommendations,
|
||||||
|
batch,
|
||||||
|
ova,
|
||||||
|
downloads,
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_genre_page(
|
||||||
|
html: &str,
|
||||||
|
current_page: u32,
|
||||||
|
) -> Result<
|
||||||
|
(
|
||||||
|
Vec<crate::shared::types::entities::anime::GenreAnimeItem>,
|
||||||
|
crate::shared::types::entities::anime::Pagination,
|
||||||
|
),
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let anime_list = parse_genre_anime(html)?;
|
||||||
|
let pagination = parse_pagination(&document, current_page)?;
|
||||||
|
Ok((anime_list, pagination))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_search_page(
|
||||||
|
html: &str,
|
||||||
|
current_page: u32,
|
||||||
|
) -> Result<
|
||||||
|
(
|
||||||
|
Vec<crate::shared::types::entities::anime::SearchAnimeItem>,
|
||||||
|
crate::shared::types::entities::anime::PaginationWithStringPages,
|
||||||
|
),
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let data = parse_search_anime(html)?;
|
||||||
|
let pagination = parse_pagination_with_string(&document, current_page)?;
|
||||||
|
Ok((data, pagination))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_latest_page(
|
||||||
|
html: &str,
|
||||||
|
current_page: u32,
|
||||||
|
) -> Result<
|
||||||
|
(
|
||||||
|
Vec<crate::shared::types::entities::anime::LatestAnimeItem>,
|
||||||
|
crate::shared::types::entities::anime::Pagination,
|
||||||
|
),
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let anime_list = parse_latest_anime(html)?;
|
||||||
|
let pagination = parse_pagination(&document, current_page)?;
|
||||||
|
Ok((anime_list, pagination))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_ongoing_page(
|
||||||
|
html: &str,
|
||||||
|
current_page: u32,
|
||||||
|
) -> Result<
|
||||||
|
(
|
||||||
|
Vec<crate::shared::types::entities::anime::OngoingAnimeItemWithScore>,
|
||||||
|
crate::shared::types::entities::anime::Pagination,
|
||||||
|
),
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let anime_list = parse_ongoing_anime_with_score(html)?;
|
||||||
|
let pagination = parse_pagination(&document, current_page)?;
|
||||||
|
Ok((anime_list, pagination))
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn parse_complete_page(
|
||||||
|
html: &str,
|
||||||
|
current_page: u32,
|
||||||
|
) -> Result<
|
||||||
|
(
|
||||||
|
Vec<crate::shared::types::entities::anime::CompleteAnimeItem>,
|
||||||
|
crate::shared::types::entities::anime::Pagination,
|
||||||
|
),
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let anime_list = parse_complete_anime(html)?;
|
||||||
|
let pagination = parse_pagination(&document, current_page)?;
|
||||||
|
Ok((anime_list, pagination))
|
||||||
|
}
|
||||||
@@ -0,0 +1,102 @@
|
|||||||
|
use crate::shared::database::traits::scraping_repository::ScrapingRepository;
|
||||||
|
use crate::shared::errors::AppError;
|
||||||
|
use crate::shared::utils::web::proxy_fetch::fetch_with_proxy_only;
|
||||||
|
use async_trait::async_trait;
|
||||||
|
use tracing::warn;
|
||||||
|
|
||||||
|
const BASE_URL: &str = "https://alqanime.si";
|
||||||
|
const BASE_DETAIL_URL: &str = "https://alqanime.net";
|
||||||
|
|
||||||
|
pub struct Anime2Repository;
|
||||||
|
|
||||||
|
impl Default for Anime2Repository {
|
||||||
|
fn default() -> Self {
|
||||||
|
Self::new()
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
impl Anime2Repository {
|
||||||
|
pub fn new() -> Self {
|
||||||
|
Self
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn index_ongoing_url(&self) -> String {
|
||||||
|
format!("{}/anime/?status=ongoing&type=&order=update", BASE_URL)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn index_complete_url(&self) -> String {
|
||||||
|
format!("{}/anime/?status=completed&type=&order=update", BASE_URL)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn genre_list_url(&self) -> String {
|
||||||
|
format!("{}/anime/", BASE_URL)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn filter_url(&self, page: u32, order: &str) -> String {
|
||||||
|
if page > 1 {
|
||||||
|
format!("{}/anime/page/{}/?order={}", BASE_URL, page, order)
|
||||||
|
} else {
|
||||||
|
format!("{}/anime/?order={}", BASE_URL, order)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn detail_url(&self, slug: &str) -> String {
|
||||||
|
format!("{}/{}/", BASE_DETAIL_URL, slug)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn detail_image_url(&self, slug: &str) -> String {
|
||||||
|
format!("{}/anime/{}/", BASE_URL, slug)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn genre_page_url(&self, genre_slug: &str, page: u32) -> String {
|
||||||
|
if page > 1 {
|
||||||
|
format!(
|
||||||
|
"{}/anime/page/{}/?genre[]={}&order=update",
|
||||||
|
BASE_URL, page, genre_slug
|
||||||
|
)
|
||||||
|
} else {
|
||||||
|
format!("{}/anime/?genre[]={}&order=update", BASE_URL, genre_slug)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn search_url(&self, query: &str, page: u32) -> String {
|
||||||
|
let encoded = urlencoding::encode(query);
|
||||||
|
if page == 1 {
|
||||||
|
format!("{}/?s={}", BASE_URL, encoded)
|
||||||
|
} else {
|
||||||
|
format!("{}/page/{}/?s={}", BASE_URL, page, encoded)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn latest_url(&self, page: u32) -> String {
|
||||||
|
format!(
|
||||||
|
"{}/anime/page/{}/?status=&type=&order=latest",
|
||||||
|
BASE_URL, page
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn ongoing_url(&self, page: u32) -> String {
|
||||||
|
format!(
|
||||||
|
"{}/anime/page/{}/?status=ongoing&type=&order=update",
|
||||||
|
BASE_URL, page
|
||||||
|
)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub fn complete_url(&self, page: u32) -> String {
|
||||||
|
format!(
|
||||||
|
"{}/anime/page/{}/?status=completed&order=update",
|
||||||
|
BASE_URL, page
|
||||||
|
)
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
#[async_trait]
|
||||||
|
impl ScrapingRepository for Anime2Repository {
|
||||||
|
async fn fetch_html(&self, url: &str) -> Result<String, AppError> {
|
||||||
|
let response = fetch_with_proxy_only(url).await?;
|
||||||
|
if response.data.trim().is_empty() {
|
||||||
|
warn!("Anime2 browserless fetch returned empty body for {}", url);
|
||||||
|
}
|
||||||
|
Ok(response.data)
|
||||||
|
}
|
||||||
|
}
|
||||||
@@ -0,0 +1,39 @@
|
|||||||
|
use std::sync::Arc;
|
||||||
|
|
||||||
|
use axum::{routing::get, Router};
|
||||||
|
|
||||||
|
use crate::modules::anime2::controller;
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
|
||||||
|
pub fn routes(router: Router<Arc<AppState>>) -> Router<Arc<AppState>> {
|
||||||
|
router
|
||||||
|
.route("/api/anime2", get(controller::index))
|
||||||
|
.route(
|
||||||
|
"/api/anime2/complete_anime/{slug}",
|
||||||
|
get(controller::complete_anime_slug),
|
||||||
|
)
|
||||||
|
.route("/api/anime2/detail/{slug}", get(controller::detail_slug))
|
||||||
|
.route("/api/anime2/filter", get(controller::filter))
|
||||||
|
.route("/api/anime2/genre_list", get(controller::genre_list))
|
||||||
|
.route(
|
||||||
|
"/api/anime2/genre/{slug}",
|
||||||
|
get(controller::genre_slug_index),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime2/genre/{slug}/{page}",
|
||||||
|
get(controller::genre_slug_page),
|
||||||
|
)
|
||||||
|
.route("/api/anime2/latest/{slug}", get(controller::latest_slug))
|
||||||
|
.route(
|
||||||
|
"/api/anime2/ongoing_anime/{slug}",
|
||||||
|
get(controller::ongoing_anime_slug),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime2/search/{slug}",
|
||||||
|
get(controller::search_slug_index),
|
||||||
|
)
|
||||||
|
.route(
|
||||||
|
"/api/anime2/search/{slug}/{page}",
|
||||||
|
get(controller::search_slug_page),
|
||||||
|
)
|
||||||
|
}
|
||||||
@@ -0,0 +1,34 @@
|
|||||||
|
use serde::Deserialize;
|
||||||
|
use utoipa::ToSchema;
|
||||||
|
|
||||||
|
#[derive(Debug, Clone, Deserialize, ToSchema)]
|
||||||
|
pub struct SlugPath {
|
||||||
|
pub slug: String,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Debug, Clone, Deserialize, ToSchema)]
|
||||||
|
pub struct SlugPagePath {
|
||||||
|
pub slug: String,
|
||||||
|
pub page: u32,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Deserialize, ToSchema)]
|
||||||
|
pub struct FilterQuery {
|
||||||
|
pub page: Option<u32>,
|
||||||
|
pub genre: Option<String>,
|
||||||
|
pub status: Option<String>,
|
||||||
|
pub r#type: Option<String>,
|
||||||
|
pub order: Option<String>,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Deserialize, ToSchema)]
|
||||||
|
pub struct GenreQuery {
|
||||||
|
pub page: Option<u32>,
|
||||||
|
pub status: Option<String>,
|
||||||
|
pub order: Option<String>,
|
||||||
|
}
|
||||||
|
|
||||||
|
#[derive(Deserialize, ToSchema)]
|
||||||
|
pub struct SearchQuery {
|
||||||
|
pub q: Option<String>,
|
||||||
|
}
|
||||||
@@ -0,0 +1,359 @@
|
|||||||
|
use crate::shared::types::entities::anime::*;
|
||||||
|
use crate::shared::utils::parse_html;
|
||||||
|
use crate::shared::utils::scraping::{
|
||||||
|
attr, attr_from, attr_from_or, extract_slug, selector, text, text_from_or,
|
||||||
|
};
|
||||||
|
use scraper::{Html, Selector};
|
||||||
|
|
||||||
|
// ============================================================================
|
||||||
|
// SELECTORS
|
||||||
|
// ============================================================================
|
||||||
|
|
||||||
|
/// Common selectors used across anime parsing
|
||||||
|
pub struct AnimeSelectors {
|
||||||
|
pub item: Selector,
|
||||||
|
pub title: Selector,
|
||||||
|
pub link: Selector,
|
||||||
|
pub img: Selector,
|
||||||
|
pub episode: Selector,
|
||||||
|
pub score: Selector,
|
||||||
|
pub status: Selector,
|
||||||
|
pub genre: Selector,
|
||||||
|
pub rating: Selector,
|
||||||
|
pub type_sel: Selector,
|
||||||
|
pub season: Selector,
|
||||||
|
pub desc: Selector,
|
||||||
|
}
|
||||||
|
|
||||||
|
impl AnimeSelectors {
|
||||||
|
pub fn new() -> Result<Self, String> {
|
||||||
|
Ok(Self {
|
||||||
|
item: selector("article.bs").ok_or("Invalid selector: article.bs")?,
|
||||||
|
title: selector(".tt h2").ok_or("Invalid selector: .tt h2")?,
|
||||||
|
link: selector("a").ok_or("Invalid selector: a")?,
|
||||||
|
img: selector("img").ok_or("Invalid selector: img")?,
|
||||||
|
episode: selector(".epx").ok_or("Invalid selector: .epx")?,
|
||||||
|
score: selector(".numscore").ok_or("Invalid selector: .numscore")?,
|
||||||
|
status: selector(".status").ok_or("Invalid selector: .status")?,
|
||||||
|
genre: selector(".genres a").ok_or("Invalid selector: .genres a")?,
|
||||||
|
rating: selector(".score").ok_or("Invalid selector: .score")?,
|
||||||
|
type_sel: selector(".typez").ok_or("Invalid selector: .typez")?,
|
||||||
|
season: selector(".season").ok_or("Invalid selector: .season")?,
|
||||||
|
desc: selector(".data .typez").ok_or("Invalid selector: .data .typez")?,
|
||||||
|
})
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
impl Default for AnimeSelectors {
|
||||||
|
fn default() -> Self {
|
||||||
|
Self::new().expect("Valid CSS selectors")
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
// Global lazy static instance for selectors to avoid reallocation per parse
|
||||||
|
use once_cell::sync::Lazy;
|
||||||
|
static ANIME_SELECTORS: Lazy<Result<AnimeSelectors, String>> =
|
||||||
|
Lazy::new(|| AnimeSelectors::new().map_err(|e| format!("Failed to create selectors: {}", e)));
|
||||||
|
|
||||||
|
// ============================================================================
|
||||||
|
// HELPER FUNCTIONS
|
||||||
|
// ============================================================================
|
||||||
|
|
||||||
|
/// Extract poster URL from an element, checking both src and data-src attributes
|
||||||
|
pub fn extract_poster(element: &scraper::ElementRef, img_selector: &Selector) -> String {
|
||||||
|
element
|
||||||
|
.select(img_selector)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| attr(&e, "src").or(attr(&e, "data-src")))
|
||||||
|
.unwrap_or_default()
|
||||||
|
}
|
||||||
|
|
||||||
|
// ============================================================================
|
||||||
|
// ANIME PARSERS
|
||||||
|
// ============================================================================
|
||||||
|
|
||||||
|
/// Parse ongoing anime items from HTML
|
||||||
|
pub fn parse_ongoing_anime(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<OngoingAnimeItem>, Box<dyn std::error::Error + Send + Sync>> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let selectors = ANIME_SELECTORS.as_ref().map_err(|e| e.clone())?;
|
||||||
|
let mut items = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&selectors.item) {
|
||||||
|
let title = text_from_or(&element, &selectors.title, "");
|
||||||
|
if title.is_empty() {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
|
||||||
|
let href = attr_from_or(&element, &selectors.link, "href", "");
|
||||||
|
let slug = extract_slug(&href);
|
||||||
|
let poster = extract_poster(&element, &selectors.img);
|
||||||
|
let current_episode = text_from_or(&element, &selectors.episode, "N/A");
|
||||||
|
let anime_url = attr_from_or(&element, &selectors.link, "href", "");
|
||||||
|
|
||||||
|
items.push(OngoingAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
current_episode,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(items)
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Parse ongoing anime items with score from HTML
|
||||||
|
pub fn parse_ongoing_anime_with_score(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<OngoingAnimeItemWithScore>, Box<dyn std::error::Error + Send + Sync>> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let selectors = ANIME_SELECTORS.as_ref().map_err(|e| e.clone())?;
|
||||||
|
let mut items = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&selectors.item) {
|
||||||
|
let title = text_from_or(&element, &selectors.title, "");
|
||||||
|
if title.is_empty() {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
|
||||||
|
let poster = extract_poster(&element, &selectors.img);
|
||||||
|
let score = text_from_or(&element, &selectors.score, "N/A");
|
||||||
|
let anime_url = attr_from_or(&element, &selectors.link, "href", "");
|
||||||
|
let slug = extract_slug(&anime_url);
|
||||||
|
|
||||||
|
items.push(OngoingAnimeItemWithScore {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
score,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(items)
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Parse complete anime items from HTML
|
||||||
|
pub fn parse_complete_anime(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<CompleteAnimeItem>, Box<dyn std::error::Error + Send + Sync>> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let selectors = ANIME_SELECTORS.as_ref().map_err(|e| e.clone())?;
|
||||||
|
let mut items = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&selectors.item) {
|
||||||
|
let title = text_from_or(&element, &selectors.title, "");
|
||||||
|
if title.is_empty() {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
|
||||||
|
let href = attr_from_or(&element, &selectors.link, "href", "");
|
||||||
|
let slug = extract_slug(&href);
|
||||||
|
let poster = extract_poster(&element, &selectors.img);
|
||||||
|
let episode_count = text_from_or(&element, &selectors.episode, "N/A");
|
||||||
|
let anime_url = attr_from_or(&element, &selectors.link, "href", "");
|
||||||
|
|
||||||
|
items.push(CompleteAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
episode_count,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(items)
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Parse latest anime items from HTML
|
||||||
|
pub fn parse_latest_anime(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<LatestAnimeItem>, Box<dyn std::error::Error + Send + Sync>> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let selectors = ANIME_SELECTORS.as_ref().map_err(|e| e.clone())?;
|
||||||
|
let mut items = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&selectors.item) {
|
||||||
|
let title = text_from_or(&element, &selectors.title, "");
|
||||||
|
if title.is_empty() {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
|
||||||
|
let poster = extract_poster(&element, &selectors.img);
|
||||||
|
let current_episode = text_from_or(&element, &selectors.episode, "N/A");
|
||||||
|
let score = text_from_or(&element, &selectors.score, "N/A");
|
||||||
|
let anime_url = attr_from_or(&element, &selectors.link, "href", "");
|
||||||
|
let slug = extract_slug(&anime_url);
|
||||||
|
|
||||||
|
items.push(LatestAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
current_episode,
|
||||||
|
score,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(items)
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Parse search results from HTML
|
||||||
|
pub fn parse_search_anime(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<SearchAnimeItem>, Box<dyn std::error::Error + Send + Sync>> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let selectors = ANIME_SELECTORS.as_ref().map_err(|e| e.clone())?;
|
||||||
|
let mut items = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&selectors.item) {
|
||||||
|
let title = text_from_or(&element, &selectors.title, "");
|
||||||
|
if title.is_empty() {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
|
||||||
|
let href = attr_from(&element, &selectors.link, "href").unwrap_or_default();
|
||||||
|
let slug = extract_slug(&href);
|
||||||
|
let poster = extract_poster(&element, &selectors.img);
|
||||||
|
let description = text_from_or(&element, &selectors.desc, "");
|
||||||
|
let anime_url = attr_from_or(&element, &selectors.link, "href", "");
|
||||||
|
let genres = element.select(&selectors.genre).map(|e| text(&e)).collect();
|
||||||
|
let rating = text_from_or(&element, &selectors.rating, "");
|
||||||
|
let r#type = text_from_or(&element, &selectors.type_sel, "");
|
||||||
|
let season = text_from_or(&element, &selectors.season, "");
|
||||||
|
|
||||||
|
items.push(SearchAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
description,
|
||||||
|
anime_url,
|
||||||
|
genres,
|
||||||
|
rating,
|
||||||
|
r#type,
|
||||||
|
season,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(items)
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Parse genre-filtered anime items from HTML
|
||||||
|
pub fn parse_genre_anime(
|
||||||
|
html: &str,
|
||||||
|
) -> Result<Vec<GenreAnimeItem>, Box<dyn std::error::Error + Send + Sync>> {
|
||||||
|
let document = parse_html(html);
|
||||||
|
let selectors = ANIME_SELECTORS.as_ref().map_err(|e| e.clone())?;
|
||||||
|
let mut items = Vec::new();
|
||||||
|
|
||||||
|
for element in document.select(&selectors.item) {
|
||||||
|
let title = text_from_or(&element, &selectors.title, "");
|
||||||
|
if title.is_empty() {
|
||||||
|
continue;
|
||||||
|
}
|
||||||
|
|
||||||
|
let poster = extract_poster(&element, &selectors.img);
|
||||||
|
let score = text_from_or(&element, &selectors.score, "N/A");
|
||||||
|
let status = text_from_or(&element, &selectors.status, "Unknown");
|
||||||
|
let anime_url = attr_from_or(&element, &selectors.link, "href", "");
|
||||||
|
let slug = extract_slug(&anime_url);
|
||||||
|
|
||||||
|
items.push(GenreAnimeItem {
|
||||||
|
title,
|
||||||
|
slug,
|
||||||
|
poster,
|
||||||
|
score,
|
||||||
|
status,
|
||||||
|
anime_url,
|
||||||
|
});
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(items)
|
||||||
|
}
|
||||||
|
|
||||||
|
// ============================================================================
|
||||||
|
// PAGINATION PARSERS
|
||||||
|
// ============================================================================
|
||||||
|
|
||||||
|
/// Parse pagination from HTML document
|
||||||
|
pub fn parse_pagination(document: &Html, current_page: u32) -> Result<Pagination, String> {
|
||||||
|
let pagination_selector =
|
||||||
|
selector(".pagination .page-numbers:not(.next)").ok_or("Invalid selector")?;
|
||||||
|
let next_selector = selector(".pagination .next").ok_or("Invalid selector")?;
|
||||||
|
|
||||||
|
let last_visible_page = document
|
||||||
|
.select(&pagination_selector)
|
||||||
|
.next_back()
|
||||||
|
.and_then(|e| text(&e).trim().parse::<u32>().ok())
|
||||||
|
.unwrap_or(current_page);
|
||||||
|
|
||||||
|
let has_next_page = document.select(&next_selector).next().is_some();
|
||||||
|
let next_page = if has_next_page {
|
||||||
|
Some(current_page + 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
|
||||||
|
let has_previous_page = current_page > 1;
|
||||||
|
let previous_page = if has_previous_page {
|
||||||
|
Some(current_page - 1)
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
|
||||||
|
Ok(Pagination {
|
||||||
|
current_page,
|
||||||
|
last_visible_page,
|
||||||
|
has_next_page,
|
||||||
|
next_page,
|
||||||
|
has_previous_page,
|
||||||
|
previous_page,
|
||||||
|
})
|
||||||
|
}
|
||||||
|
|
||||||
|
/// Parse pagination with string-based page numbers (for search results)
|
||||||
|
pub fn parse_pagination_with_string(
|
||||||
|
document: &Html,
|
||||||
|
current_page: u32,
|
||||||
|
) -> Result<PaginationWithStringPages, String> {
|
||||||
|
let pagination_selector =
|
||||||
|
selector(".pagination .page-numbers:not(.next)").ok_or("Invalid selector")?;
|
||||||
|
let next_selector = selector(".pagination .next").ok_or("Invalid selector")?;
|
||||||
|
|
||||||
|
let last_visible_page = document
|
||||||
|
.select(&pagination_selector)
|
||||||
|
.last()
|
||||||
|
.and_then(|e| text(&e).trim().parse::<u32>().ok())
|
||||||
|
.unwrap_or(current_page);
|
||||||
|
|
||||||
|
let has_next_page = document.select(&next_selector).next().is_some();
|
||||||
|
|
||||||
|
let next_page = if has_next_page {
|
||||||
|
document
|
||||||
|
.select(&next_selector)
|
||||||
|
.next()
|
||||||
|
.and_then(|e| attr(&e, "href"))
|
||||||
|
.and_then(|href| href.split("/page/").nth(1).map(|s| s.to_string()))
|
||||||
|
.and_then(|s| s.split('/').next().map(|s| s.to_string()))
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
|
||||||
|
let has_previous_page = current_page > 1;
|
||||||
|
let previous_page = if has_previous_page {
|
||||||
|
Some((current_page - 1).to_string())
|
||||||
|
} else {
|
||||||
|
None
|
||||||
|
};
|
||||||
|
|
||||||
|
Ok(PaginationWithStringPages {
|
||||||
|
current_page,
|
||||||
|
last_visible_page,
|
||||||
|
has_next_page,
|
||||||
|
next_page,
|
||||||
|
has_previous_page,
|
||||||
|
previous_page,
|
||||||
|
})
|
||||||
|
}
|
||||||
@@ -0,0 +1,453 @@
|
|||||||
|
use std::sync::Arc;
|
||||||
|
|
||||||
|
use crate::modules::anime2::parser;
|
||||||
|
use crate::modules::anime2::repository::Anime2Repository;
|
||||||
|
use crate::modules::anime2::types::{DetailResponse, GenresResponse};
|
||||||
|
use crate::shared::database::traits::scraping_repository::ScrapingRepository;
|
||||||
|
use crate::shared::errors::AppError;
|
||||||
|
use crate::shared::services::images::cache::{
|
||||||
|
apply_cached_posters, cache_image_urls_batch_lazy, get_cached_or_original,
|
||||||
|
};
|
||||||
|
use crate::shared::state::AppState;
|
||||||
|
use crate::shared::types::ApiResponse;
|
||||||
|
use crate::shared::utils::Cache;
|
||||||
|
|
||||||
|
const INDEX_CACHE_TTL: u64 = 300;
|
||||||
|
const GENRE_LIST_CACHE_TTL: u64 = 3600;
|
||||||
|
const FILTER_CACHE_TTL: u64 = 300;
|
||||||
|
const DETAIL_CACHE_TTL: u64 = 300;
|
||||||
|
const GENRE_CACHE_TTL: u64 = 300;
|
||||||
|
const SEARCH_CACHE_TTL: u64 = 300;
|
||||||
|
const LATEST_CACHE_TTL: u64 = 120;
|
||||||
|
const ONGOING_CACHE_TTL: u64 = 300;
|
||||||
|
const COMPLETE_CACHE_TTL: u64 = 300;
|
||||||
|
|
||||||
|
pub struct Anime2Service {
|
||||||
|
repository: Anime2Repository,
|
||||||
|
}
|
||||||
|
|
||||||
|
impl Anime2Service {
|
||||||
|
pub fn new(repository: Anime2Repository) -> Self {
|
||||||
|
Self { repository }
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn index(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
) -> Result<crate::modules::anime2::types::Anime2Response, AppError> {
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set("anime2:index", INDEX_CACHE_TTL, || async {
|
||||||
|
let ongoing_html = self
|
||||||
|
.repository
|
||||||
|
.fetch_html(&self.repository.index_ongoing_url())
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
let complete_html = self
|
||||||
|
.repository
|
||||||
|
.fetch_html(&self.repository.index_complete_url())
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
|
||||||
|
let mut data = tokio::task::spawn_blocking(move || {
|
||||||
|
Ok::<_, String>((
|
||||||
|
parser::parse_ongoing_anime(&ongoing_html).map_err(|e| e.to_string())?,
|
||||||
|
parser::parse_complete_anime(&complete_html).map_err(|e| e.to_string())?,
|
||||||
|
))
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())??;
|
||||||
|
|
||||||
|
let mut posters: Vec<String> =
|
||||||
|
data.0.iter().map(|item| item.poster.clone()).collect();
|
||||||
|
posters.extend(data.1.iter().map(|item| item.poster.clone()));
|
||||||
|
|
||||||
|
let cached_posters = cache_image_urls_batch_lazy(
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
posters,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
let ongoing_len = data.0.len();
|
||||||
|
for (i, item) in data.0.iter_mut().enumerate() {
|
||||||
|
if let Some(url) = cached_posters.get(i) {
|
||||||
|
item.poster = url.clone();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
for (i, item) in data.1.iter_mut().enumerate() {
|
||||||
|
if let Some(url) = cached_posters.get(ongoing_len + i) {
|
||||||
|
item.poster = url.clone();
|
||||||
|
}
|
||||||
|
}
|
||||||
|
|
||||||
|
Ok(crate::modules::anime2::types::Anime2Response {
|
||||||
|
status: "Ok".to_string(),
|
||||||
|
data: crate::modules::anime2::types::Anime2Data {
|
||||||
|
ongoing_anime: data.0,
|
||||||
|
complete_anime: data.1,
|
||||||
|
},
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(AppError::ScraperError)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn genre_list(&self, app_state: Arc<AppState>) -> Result<GenresResponse, AppError> {
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set("anime2:genres:list:v3", GENRE_LIST_CACHE_TTL, || async {
|
||||||
|
let html = self
|
||||||
|
.repository
|
||||||
|
.fetch_html(&self.repository.genre_list_url())
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
|
||||||
|
let genres = tokio::task::spawn_blocking(move || {
|
||||||
|
parser::parse_genres(&html).map_err(|e| e.to_string())
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())??;
|
||||||
|
|
||||||
|
Ok(GenresResponse {
|
||||||
|
status: "Ok".to_string(),
|
||||||
|
data: genres,
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(AppError::ScraperError)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn filter(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
page: u32,
|
||||||
|
genre: Option<String>,
|
||||||
|
status: Option<String>,
|
||||||
|
anime_type: Option<String>,
|
||||||
|
order: String,
|
||||||
|
) -> Result<crate::modules::anime2::types::FilterResponse, AppError> {
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
let cache_key = format!(
|
||||||
|
"anime2:filter:{}:{:?}:{:?}:{:?}:{}",
|
||||||
|
page, genre, status, anime_type, order
|
||||||
|
);
|
||||||
|
let genre_clone = genre.clone();
|
||||||
|
let status_clone = status.clone();
|
||||||
|
let anime_type_clone = anime_type.clone();
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, FILTER_CACHE_TTL, || async {
|
||||||
|
let mut url = self.repository.filter_url(page, &order);
|
||||||
|
|
||||||
|
if let Some(g) = &genre {
|
||||||
|
for genre_item in g.split(',') {
|
||||||
|
url.push_str(&format!("&genre[]={}", genre_item.trim()));
|
||||||
|
}
|
||||||
|
}
|
||||||
|
if let Some(s) = &status {
|
||||||
|
url.push_str(&format!("&status={}", s));
|
||||||
|
}
|
||||||
|
if let Some(t) = &anime_type {
|
||||||
|
url.push_str(&format!("&type={}", t));
|
||||||
|
}
|
||||||
|
|
||||||
|
let html = self
|
||||||
|
.repository
|
||||||
|
.fetch_html(&url)
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
let (data, pagination) = tokio::task::spawn_blocking(move || {
|
||||||
|
parser::parse_filter_page(&html, page).map_err(|e| e.to_string())
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())??;
|
||||||
|
|
||||||
|
let mut final_data = data;
|
||||||
|
apply_cached_posters(
|
||||||
|
&mut final_data,
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
Ok(crate::modules::anime2::types::FilterResponse {
|
||||||
|
success: true,
|
||||||
|
data: final_data,
|
||||||
|
pagination,
|
||||||
|
filters_applied: crate::modules::anime2::types::FiltersApplied {
|
||||||
|
genre: genre_clone,
|
||||||
|
status: status_clone,
|
||||||
|
r#type: anime_type_clone,
|
||||||
|
order: order.clone(),
|
||||||
|
},
|
||||||
|
status: "Ok".to_string(),
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(AppError::ScraperError)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn detail(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
slug: String,
|
||||||
|
) -> Result<DetailResponse, AppError> {
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
let cache_key = format!("anime2:detail:{}", slug);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, DETAIL_CACHE_TTL, || async {
|
||||||
|
let detail_url = self.repository.detail_url(&slug);
|
||||||
|
let image_url = self.repository.detail_image_url(&slug);
|
||||||
|
let (detail_html, image_html) = tokio::join!(
|
||||||
|
self.repository.fetch_html(&detail_url),
|
||||||
|
self.repository.fetch_html(&image_url)
|
||||||
|
);
|
||||||
|
let detail_html = detail_html.map_err(|e| e.to_string())?;
|
||||||
|
let image_html = image_html.ok();
|
||||||
|
|
||||||
|
let mut data = tokio::task::spawn_blocking(move || {
|
||||||
|
let mut data =
|
||||||
|
parser::parse_anime_detail(&detail_html).map_err(|e| e.to_string())?;
|
||||||
|
if let Some(image_html) = image_html {
|
||||||
|
if let Ok(image_data) = parser::parse_anime_detail(&image_html) {
|
||||||
|
if !image_data.poster.is_empty() {
|
||||||
|
data.poster = image_data.poster;
|
||||||
|
}
|
||||||
|
if !image_data.poster2.is_empty() {
|
||||||
|
data.poster2 = image_data.poster2;
|
||||||
|
}
|
||||||
|
data.recommendations = image_data.recommendations;
|
||||||
|
}
|
||||||
|
}
|
||||||
|
Ok::<_, String>(data)
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())??;
|
||||||
|
|
||||||
|
data.poster = get_cached_or_original(
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
&data.poster,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
data.poster2 = get_cached_or_original(
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
&data.poster2,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
apply_cached_posters(
|
||||||
|
&mut data.recommendations,
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
Ok(DetailResponse {
|
||||||
|
status: "Ok".to_string(),
|
||||||
|
data,
|
||||||
|
})
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(AppError::ScraperError)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn genre_slug(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
genre_slug: String,
|
||||||
|
page: u32,
|
||||||
|
) -> Result<ApiResponse<Vec<crate::shared::types::entities::anime::GenreAnimeItem>>, AppError>
|
||||||
|
{
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
let cache_key = format!("anime2:genre:{}:{}", genre_slug, page);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, GENRE_CACHE_TTL, || async {
|
||||||
|
let html = self
|
||||||
|
.repository
|
||||||
|
.fetch_html(&self.repository.genre_page_url(&genre_slug, page))
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
let (data, _pagination) = tokio::task::spawn_blocking(move || {
|
||||||
|
parser::parse_genre_page(&html, page).map_err(|e| e.to_string())
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())??;
|
||||||
|
|
||||||
|
let mut final_data = data;
|
||||||
|
apply_cached_posters(
|
||||||
|
&mut final_data,
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
Ok(ApiResponse::success(final_data))
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(AppError::ScraperError)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn search(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
query: String,
|
||||||
|
page: u32,
|
||||||
|
) -> Result<ApiResponse<Vec<crate::shared::types::entities::anime::SearchAnimeItem>>, AppError>
|
||||||
|
{
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
let cache_key = format!("anime2:search:{}:{}", query, page);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, SEARCH_CACHE_TTL, || async {
|
||||||
|
let html = self
|
||||||
|
.repository
|
||||||
|
.fetch_html(&self.repository.search_url(&query, page))
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
let (data, _pagination) = tokio::task::spawn_blocking(move || {
|
||||||
|
parser::parse_search_page(&html, page).map_err(|e| e.to_string())
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())??;
|
||||||
|
|
||||||
|
let mut final_data = data;
|
||||||
|
apply_cached_posters(
|
||||||
|
&mut final_data,
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
Ok(ApiResponse::success(final_data))
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(AppError::ScraperError)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn latest(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
page: u32,
|
||||||
|
) -> Result<ApiResponse<Vec<crate::shared::types::entities::anime::LatestAnimeItem>>, AppError>
|
||||||
|
{
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
let cache_key = format!("anime2:latest:{}", page);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, LATEST_CACHE_TTL, || async {
|
||||||
|
let html = self
|
||||||
|
.repository
|
||||||
|
.fetch_html(&self.repository.latest_url(page))
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
let (data, _pagination) = tokio::task::spawn_blocking(move || {
|
||||||
|
parser::parse_latest_page(&html, page).map_err(|e| e.to_string())
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())??;
|
||||||
|
|
||||||
|
let mut final_data = data;
|
||||||
|
apply_cached_posters(
|
||||||
|
&mut final_data,
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
Ok(ApiResponse::success(final_data))
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(AppError::ScraperError)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn ongoing_anime(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
page: u32,
|
||||||
|
) -> Result<
|
||||||
|
ApiResponse<Vec<crate::shared::types::entities::anime::OngoingAnimeItemWithScore>>,
|
||||||
|
AppError,
|
||||||
|
> {
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
let cache_key = format!("anime2:ongoing:{}", page);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, ONGOING_CACHE_TTL, || async {
|
||||||
|
let html = self
|
||||||
|
.repository
|
||||||
|
.fetch_html(&self.repository.ongoing_url(page))
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
let (data, _pagination) = tokio::task::spawn_blocking(move || {
|
||||||
|
parser::parse_ongoing_page(&html, page).map_err(|e| e.to_string())
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())??;
|
||||||
|
|
||||||
|
let mut final_data = data;
|
||||||
|
apply_cached_posters(
|
||||||
|
&mut final_data,
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
Ok(ApiResponse::success(final_data))
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(AppError::ScraperError)
|
||||||
|
}
|
||||||
|
|
||||||
|
pub async fn complete_anime(
|
||||||
|
&self,
|
||||||
|
app_state: Arc<AppState>,
|
||||||
|
page: u32,
|
||||||
|
) -> Result<ApiResponse<Vec<crate::shared::types::entities::anime::CompleteAnimeItem>>, AppError>
|
||||||
|
{
|
||||||
|
let cache = Cache::new(&app_state.redis_pool);
|
||||||
|
let cache_key = format!("anime2:complete:{}", page);
|
||||||
|
|
||||||
|
cache
|
||||||
|
.get_or_set(&cache_key, COMPLETE_CACHE_TTL, || async {
|
||||||
|
let html = self
|
||||||
|
.repository
|
||||||
|
.fetch_html(&self.repository.complete_url(page))
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())?;
|
||||||
|
let (data, _pagination) = tokio::task::spawn_blocking(move || {
|
||||||
|
parser::parse_complete_page(&html, page).map_err(|e| e.to_string())
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(|e| e.to_string())??;
|
||||||
|
|
||||||
|
let mut final_data = data;
|
||||||
|
apply_cached_posters(
|
||||||
|
&mut final_data,
|
||||||
|
app_state.db.clone(),
|
||||||
|
&app_state.redis_pool,
|
||||||
|
Some(app_state.image_processing_semaphore.clone()),
|
||||||
|
)
|
||||||
|
.await;
|
||||||
|
|
||||||
|
Ok(ApiResponse::success(final_data))
|
||||||
|
})
|
||||||
|
.await
|
||||||
|
.map_err(AppError::ScraperError)
|
||||||
|
}
|
||||||
|
}
|
||||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user