moviefinder-cli 0.1.0__tar.gz

moviefinder_cli-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,27 @@
+name: Publish to PyPI
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  pypi-publish:
+    name: Build & Publish Release to PyPI
+    runs-on: ubuntu-latest
+
+    permissions:
+      id-token: write
+      contents: read
+
+    steps:
+      - name: Checkout target repository
+        uses: actions/checkout@v4
+
+      - name: Install the latest version of uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Build package
+        run: uv build
+
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1

moviefinder_cli-0.1.0/.gitignore

@@ -0,0 +1,8 @@
+__pycache__/
+*.py[cod]
+.venv/
+data/
+.pytest_cache/
+*.egg-info/
+build/
+dist/

moviefinder_cli-0.1.0/CHANGELOG.md

@@ -0,0 +1,9 @@
+# Changelog
+
+## 0.1.0 - 2026-05-30
+
+- Initial PyPI-ready release.
+- Add `moviefinder` CLI with Markdown and JSON output.
+- Add SQLite search/detail caching with stale-cache fallback.
+- Add `moviefinder-mcp` entrypoint for Agent/MCP clients.
+- Parse rrdynb search results, movie synopsis, Douban score, IMDB score, and cloud-drive resource links.

moviefinder_cli-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Han Zhang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

moviefinder_cli-0.1.0/PKG-INFO

@@ -0,0 +1,211 @@
+Metadata-Version: 2.4
+Name: moviefinder-cli
+Version: 0.1.0
+Summary: MovieFinder CLI and MCP server for searching cached rrdynb movie resources.
+Author: Han Zhang
+License: MIT
+License-File: LICENSE
+Keywords: cli,markdown,mcp,movie,movie-search,rrdynb
+Requires-Python: >=3.10
+Requires-Dist: beautifulsoup4>=4.12
+Requires-Dist: fastmcp>=0.1.0
+Requires-Dist: requests>=2.31
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+# moviefinder-cli
+
+MovieFinder 会搜索 `https://www.rrdynb.com`，抓取搜索结果页和影片详情页，把结果缓存到本地 SQLite，并以 Markdown/JSON 返回给 CLI 或 Agent。
+
+返回字段包括：
+
+- 影片标题、详情页地址、分类、发布日期、海报
+- 简介、豆瓣评分、IMDB 评分、IMDb ID
+- 详情页中识别到的所有网盘地址，包括夸克、阿里、迅雷、百度等
+- 提取码和 URL 中的 `pwd` 参数
+
+## Agent / MCP 使用
+
+发布到 PyPI 后，可以在 Claude Desktop 等 MCP 客户端中直接通过 `uvx` 启动：
+
+```json
+{
+  "mcpServers": {
+    "moviefinder": {
+      "command": "uvx",
+      "args": [
+        "--refresh",
+        "--from",
+        "moviefinder-cli",
+        "moviefinder-mcp"
+      ]
+    }
+  }
+}
+```
+
+可用 MCP Tools：
+
+- `search_movies(query, limit=5, refresh=false, output_format="markdown")`
+- `movie_cache_stats(output_format="markdown")`
+
+## 安装
+
+需要 Python 3.10+。
+
+### 使用 uv 安装（推荐）
+
+```bash
+uv tool install moviefinder-cli
+```
+
+安装后即可使用：
+
+```bash
+moviefinder search 一一 --limit 3
+```
+
+### 使用 pip 安装
+
+```bash
+pip install moviefinder-cli
+```
+
+### 源码安装（本地开发）
+
+```bash
+python3 -m pip install -e .
+```
+
+## 命令行搜索
+
+默认输出 Markdown：
+
+```bash
+moviefinder search 一一 --limit 3
+```
+
+也可以不安装，直接通过模块方式运行：
+
+```bash
+python3 -m moviefinder_cli search 一一 --limit 3
+```
+
+强制刷新缓存：
+
+```bash
+moviefinder search 一一 --limit 3 --refresh
+```
+
+保留 JSON 输出：
+
+```bash
+moviefinder search 一一 --limit 3 --format json
+```
+
+查看缓存统计：
+
+```bash
+moviefinder cache-stats
+```
+
+## HTTP API
+
+启动服务：
+
+```bash
+python3 -m moviefinder_cli serve --host 127.0.0.1 --port 8000
+```
+
+搜索：
+
+```bash
+curl 'http://127.0.0.1:8000/search?q=一一&limit=3'
+```
+
+强制刷新：
+
+```bash
+curl 'http://127.0.0.1:8000/search?q=一一&limit=3&refresh=1'
+```
+
+健康检查：
+
+```bash
+curl 'http://127.0.0.1:8000/health'
+```
+
+缓存统计：
+
+```bash
+curl 'http://127.0.0.1:8000/cache/stats'
+```
+
+## 缓存
+
+默认缓存文件是 `data/moviefinder.sqlite3`，可以通过环境变量覆盖：
+
+```bash
+MOVIEFINDER_DB_PATH=/tmp/moviefinder.sqlite3 moviefinder search 一一
+```
+
+缓存策略：
+
+- 搜索结果缓存 1 小时
+- 影片详情缓存 7 天
+- 搜索结果会复用影片详情缓存，避免同一详情页被重复抓取
+- 如果远端临时返回 403/网络错误，CLI 会优先用同关键词缓存兜底，并在 Markdown/JSON 中标注 `warning`
+
+## 返回示例
+
+```markdown
+# 搜索结果：一一
+
+- 来源：rrdynb
+- 搜索页：[打开](https://www.rrdynb.com/plus/search.php?q=...)
+- 结果数：1
+- 缓存：命中
+
+## 1. 《一一》百度云网盘下载.阿里云盘.国语中字.(2000)
+
+| 字段 | 值 |
+| --- | --- |
+| 分类 | movie |
+| 发布日期 | 2026-05-29 |
+| 豆瓣评分 | 9.0 |
+| IMDB 评分 | 8.1 |
+| IMDb ID | tt0244316 |
+| 详情页 | [打开](https://www.rrdynb.com/movie/2019/0216/3035.html) |
+
+### 简介
+
+电影《一一》讲述了...
+
+### 网盘资源
+
+| 平台 | 地址 | 提取码 | URL 密码 |
+| --- | --- | --- | --- |
+| 夸克网盘 | [打开](https://pan.quark.cn/s/...) | - | - |
+```
+
+## 测试
+
+```bash
+PYTHONPATH=src python3 -m unittest discover -s tests
+```
+
+## 发布
+
+项目使用与 `getnotes-cli` 类似的发布模式：
+
+```bash
+uv build
+uv publish
+```
+
+如果使用 GitHub Release 发布，则 `.github/workflows/publish.yml` 会通过 PyPI Trusted Publisher 自动发布。
+
+## 注意
+
+这个项目只读取公开页面并返回元数据和页面公开展示的网盘链接，不做登录绕过、验证码绕过或资源批量下载。

moviefinder_cli-0.1.0/README.md

@@ -0,0 +1,195 @@
+# moviefinder-cli
+
+MovieFinder 会搜索 `https://www.rrdynb.com`，抓取搜索结果页和影片详情页，把结果缓存到本地 SQLite，并以 Markdown/JSON 返回给 CLI 或 Agent。
+
+返回字段包括：
+
+- 影片标题、详情页地址、分类、发布日期、海报
+- 简介、豆瓣评分、IMDB 评分、IMDb ID
+- 详情页中识别到的所有网盘地址，包括夸克、阿里、迅雷、百度等
+- 提取码和 URL 中的 `pwd` 参数
+
+## Agent / MCP 使用
+
+发布到 PyPI 后，可以在 Claude Desktop 等 MCP 客户端中直接通过 `uvx` 启动：
+
+```json
+{
+  "mcpServers": {
+    "moviefinder": {
+      "command": "uvx",
+      "args": [
+        "--refresh",
+        "--from",
+        "moviefinder-cli",
+        "moviefinder-mcp"
+      ]
+    }
+  }
+}
+```
+
+可用 MCP Tools：
+
+- `search_movies(query, limit=5, refresh=false, output_format="markdown")`
+- `movie_cache_stats(output_format="markdown")`
+
+## 安装
+
+需要 Python 3.10+。
+
+### 使用 uv 安装（推荐）
+
+```bash
+uv tool install moviefinder-cli
+```
+
+安装后即可使用：
+
+```bash
+moviefinder search 一一 --limit 3
+```
+
+### 使用 pip 安装
+
+```bash
+pip install moviefinder-cli
+```
+
+### 源码安装（本地开发）
+
+```bash
+python3 -m pip install -e .
+```
+
+## 命令行搜索
+
+默认输出 Markdown：
+
+```bash
+moviefinder search 一一 --limit 3
+```
+
+也可以不安装，直接通过模块方式运行：
+
+```bash
+python3 -m moviefinder_cli search 一一 --limit 3
+```
+
+强制刷新缓存：
+
+```bash
+moviefinder search 一一 --limit 3 --refresh
+```
+
+保留 JSON 输出：
+
+```bash
+moviefinder search 一一 --limit 3 --format json
+```
+
+查看缓存统计：
+
+```bash
+moviefinder cache-stats
+```
+
+## HTTP API
+
+启动服务：
+
+```bash
+python3 -m moviefinder_cli serve --host 127.0.0.1 --port 8000
+```
+
+搜索：
+
+```bash
+curl 'http://127.0.0.1:8000/search?q=一一&limit=3'
+```
+
+强制刷新：
+
+```bash
+curl 'http://127.0.0.1:8000/search?q=一一&limit=3&refresh=1'
+```
+
+健康检查：
+
+```bash
+curl 'http://127.0.0.1:8000/health'
+```
+
+缓存统计：
+
+```bash
+curl 'http://127.0.0.1:8000/cache/stats'
+```
+
+## 缓存
+
+默认缓存文件是 `data/moviefinder.sqlite3`，可以通过环境变量覆盖：
+
+```bash
+MOVIEFINDER_DB_PATH=/tmp/moviefinder.sqlite3 moviefinder search 一一
+```
+
+缓存策略：
+
+- 搜索结果缓存 1 小时
+- 影片详情缓存 7 天
+- 搜索结果会复用影片详情缓存，避免同一详情页被重复抓取
+- 如果远端临时返回 403/网络错误，CLI 会优先用同关键词缓存兜底，并在 Markdown/JSON 中标注 `warning`
+
+## 返回示例
+
+```markdown
+# 搜索结果：一一
+
+- 来源：rrdynb
+- 搜索页：[打开](https://www.rrdynb.com/plus/search.php?q=...)
+- 结果数：1
+- 缓存：命中
+
+## 1. 《一一》百度云网盘下载.阿里云盘.国语中字.(2000)
+
+| 字段 | 值 |
+| --- | --- |
+| 分类 | movie |
+| 发布日期 | 2026-05-29 |
+| 豆瓣评分 | 9.0 |
+| IMDB 评分 | 8.1 |
+| IMDb ID | tt0244316 |
+| 详情页 | [打开](https://www.rrdynb.com/movie/2019/0216/3035.html) |
+
+### 简介
+
+电影《一一》讲述了...
+
+### 网盘资源
+
+| 平台 | 地址 | 提取码 | URL 密码 |
+| --- | --- | --- | --- |
+| 夸克网盘 | [打开](https://pan.quark.cn/s/...) | - | - |
+```
+
+## 测试
+
+```bash
+PYTHONPATH=src python3 -m unittest discover -s tests
+```
+
+## 发布
+
+项目使用与 `getnotes-cli` 类似的发布模式：
+
+```bash
+uv build
+uv publish
+```
+
+如果使用 GitHub Release 发布，则 `.github/workflows/publish.yml` 会通过 PyPI Trusted Publisher 自动发布。
+
+## 注意
+
+这个项目只读取公开页面并返回元数据和页面公开展示的网盘链接，不做登录绕过、验证码绕过或资源批量下载。

moviefinder_cli-0.1.0/pyproject.toml

@@ -0,0 +1,35 @@
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"
+
+[project]
+name = "moviefinder-cli"
+version = "0.1.0"
+description = "MovieFinder CLI and MCP server for searching cached rrdynb movie resources."
+readme = "README.md"
+license = {text = "MIT"}
+authors = [
+  { name = "Han Zhang" }
+]
+requires-python = ">=3.10"
+keywords = ["movie", "movie-search", "rrdynb", "cli", "markdown", "mcp"]
+dependencies = [
+  "beautifulsoup4>=4.12",
+  "requests>=2.31",
+  "fastmcp>=0.1.0",
+]
+
+[project.scripts]
+moviefinder = "moviefinder_cli.cli:main"
+moviefinder-mcp = "moviefinder_cli.mcp.server:main"
+
+[project.optional-dependencies]
+dev = [
+  "pytest>=7.0",
+]
+
+[tool.hatch.build.targets.wheel]
+packages = ["src/moviefinder_cli"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]

moviefinder_cli-0.1.0/requirements.txt

@@ -0,0 +1,3 @@
+beautifulsoup4>=4.12
+requests>=2.31
+fastmcp>=0.1.0

moviefinder_cli-0.1.0/src/moviefinder_cli/__init__.py

@@ -0,0 +1,5 @@
+"""MovieFinder package."""
+
+__all__ = ["__version__"]
+
+__version__ = "0.1.0"

moviefinder_cli-0.1.0/src/moviefinder_cli/__main__.py

@@ -0,0 +1,5 @@
+from .cli import main
+
+
+if __name__ == "__main__":
+    main()

moviefinder_cli-0.1.0/src/moviefinder_cli/cache.py

@@ -0,0 +1,125 @@
+import json
+import sqlite3
+import time
+from pathlib import Path
+from typing import Any, Dict, List, Optional, Tuple
+
+
+class SqliteCache:
+    def __init__(self, db_path: str = "data/moviefinder.sqlite3") -> None:
+        self.db_path = Path(db_path)
+        self.db_path.parent.mkdir(parents=True, exist_ok=True)
+        self._ensure_schema()
+
+    def _connect(self) -> sqlite3.Connection:
+        connection = sqlite3.connect(str(self.db_path))
+        connection.row_factory = sqlite3.Row
+        return connection
+
+    def _ensure_schema(self) -> None:
+        with self._connect() as connection:
+            connection.execute(
+                """
+                CREATE TABLE IF NOT EXISTS cache_entries (
+                    namespace TEXT NOT NULL,
+                    cache_key TEXT NOT NULL,
+                    payload TEXT NOT NULL,
+                    created_at REAL NOT NULL,
+                    expires_at REAL NOT NULL,
+                    PRIMARY KEY (namespace, cache_key)
+                )
+                """
+            )
+            connection.execute(
+                """
+                CREATE INDEX IF NOT EXISTS idx_cache_entries_expires_at
+                ON cache_entries(expires_at)
+                """
+            )
+
+    def get_json(self, namespace: str, cache_key: str) -> Tuple[Optional[Any], bool]:
+        payload, hit, _expired = self.get_json_with_meta(namespace, cache_key)
+        return payload, hit
+
+    def get_json_with_meta(
+        self, namespace: str, cache_key: str, allow_expired: bool = False
+    ) -> Tuple[Optional[Any], bool, bool]:
+        now = time.time()
+        with self._connect() as connection:
+            row = connection.execute(
+                """
+                SELECT payload, expires_at
+                FROM cache_entries
+                WHERE namespace = ? AND cache_key = ?
+                """,
+                (namespace, cache_key),
+            ).fetchone()
+            if row is None:
+                return None, False, False
+            expired = float(row["expires_at"]) < now
+            if expired and not allow_expired:
+                return None, False, True
+            return json.loads(row["payload"]), True, expired
+
+    def set_json(
+        self, namespace: str, cache_key: str, value: Any, ttl_seconds: int
+    ) -> None:
+        now = time.time()
+        with self._connect() as connection:
+            connection.execute(
+                """
+                INSERT INTO cache_entries
+                    (namespace, cache_key, payload, created_at, expires_at)
+                VALUES (?, ?, ?, ?, ?)
+                ON CONFLICT(namespace, cache_key) DO UPDATE SET
+                    payload = excluded.payload,
+                    created_at = excluded.created_at,
+                    expires_at = excluded.expires_at
+                """,
+                (
+                    namespace,
+                    cache_key,
+                    json.dumps(value, ensure_ascii=False),
+                    now,
+                    now + ttl_seconds,
+                ),
+            )
+
+    def iter_json(
+        self, namespace: str, allow_expired: bool = False
+    ) -> List[Tuple[str, Any, bool]]:
+        now = time.time()
+        with self._connect() as connection:
+            rows = connection.execute(
+                """
+                SELECT cache_key, payload, expires_at
+                FROM cache_entries
+                WHERE namespace = ?
+                ORDER BY created_at DESC
+                """,
+                (namespace,),
+            ).fetchall()
+
+        entries: List[Tuple[str, Any, bool]] = []
+        for row in rows:
+            expired = float(row["expires_at"]) < now
+            if expired and not allow_expired:
+                continue
+            entries.append((str(row["cache_key"]), json.loads(row["payload"]), expired))
+        return entries
+
+    def clear(self) -> None:
+        with self._connect() as connection:
+            connection.execute("DELETE FROM cache_entries")
+
+    def stats(self) -> Dict[str, int]:
+        with self._connect() as connection:
+            rows = connection.execute(
+                """
+                SELECT namespace, COUNT(*) AS count
+                FROM cache_entries
+                GROUP BY namespace
+                ORDER BY namespace
+                """
+            ).fetchall()
+        return {str(row["namespace"]): int(row["count"]) for row in rows}