mdengine 0.3.0__tar.gz → 0.5.0__tar.gz

{mdengine-0.3.0 → mdengine-0.5.0}/PKG-INFO

@@ -1,13 +1,13 @@
 Metadata-Version: 2.4
 Name: mdengine
-Version: 0.3.0
+Version: 0.5.0
 Summary: Convert PDF, Office, images, audio, video, text/JSON/XML, ZIP archives, and web URLs to Markdown.
 Author: mdengine contributors
 License-Expression: MIT
 Project-URL: Homepage, https://github.com/vishal7090/md-generator
 Project-URL: Repository, https://github.com/vishal7090/md-generator
 Project-URL: Issues, https://github.com/vishal7090/md-generator/issues
-Keywords: markdown,pdf,docx,pptx,xlsx,ocr,zip,url,html
+Keywords: markdown,pdf,docx,pptx,xlsx,ocr,zip,url,html,youtube,playwright,database
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3 :: Only
 Classifier: Topic :: Text Processing :: Markup :: Markdown
@@ -74,6 +74,31 @@ Requires-Dist: imageio-ffmpeg>=0.5.1; extra == "audio"
 Provides-Extra: video
 Requires-Dist: openai-whisper>=20231117; extra == "video"
 Requires-Dist: imageio-ffmpeg>=0.5.1; extra == "video"
+Provides-Extra: youtube
+Requires-Dist: youtube-transcript-api>=0.6.0; extra == "youtube"
+Requires-Dist: httpx>=0.27.0; extra == "youtube"
+Requires-Dist: beautifulsoup4>=4.12.0; extra == "youtube"
+Requires-Dist: lxml>=5.0.0; extra == "youtube"
+Provides-Extra: playwright
+Requires-Dist: playwright>=1.49.0; extra == "playwright"
+Requires-Dist: httpx>=0.27.0; extra == "playwright"
+Requires-Dist: beautifulsoup4>=4.12.0; extra == "playwright"
+Requires-Dist: lxml>=5.0.0; extra == "playwright"
+Requires-Dist: markdownify>=0.14.0; extra == "playwright"
+Requires-Dist: readability-lxml>=0.8.1; extra == "playwright"
+Requires-Dist: Pillow>=10.0.0; extra == "playwright"
+Provides-Extra: db
+Requires-Dist: sqlalchemy>=2.0.0; extra == "db"
+Requires-Dist: pyyaml>=6.0.0; extra == "db"
+Requires-Dist: psycopg2-binary>=2.9.9; extra == "db"
+Requires-Dist: pymysql>=1.1.0; extra == "db"
+Requires-Dist: oracledb>=2.0.0; extra == "db"
+Requires-Dist: pymongo>=4.6.0; extra == "db"
+Requires-Dist: mermaid-py>=0.8.0; extra == "db"
+Provides-Extra: graph
+Requires-Dist: networkx>=3.2.0; extra == "graph"
+Requires-Dist: neo4j>=5.14.0; extra == "graph"
+Requires-Dist: pyyaml>=6.0.0; extra == "graph"
 Provides-Extra: api
 Requires-Dist: fastapi>=0.115.0; extra == "api"
 Requires-Dist: uvicorn[standard]>=0.32.0; extra == "api"
@@ -86,9 +111,15 @@ Requires-Dist: fastmcp>=2.3.0; extra == "mcp"
 Provides-Extra: dev
 Requires-Dist: pytest>=8.0.0; extra == "dev"
 Requires-Dist: httpx>=0.27.0; extra == "dev"
+Requires-Dist: beautifulsoup4>=4.12.0; extra == "dev"
+Requires-Dist: lxml>=5.0.0; extra == "dev"
+Requires-Dist: youtube-transcript-api>=0.6.0; extra == "dev"
 Requires-Dist: mdengine[api]; extra == "dev"
 Requires-Dist: mdengine[mcp]; extra == "dev"
 Requires-Dist: mdengine[url]; extra == "dev"
+Requires-Dist: mdengine[playwright]; extra == "dev"
+Requires-Dist: mdengine[db]; extra == "dev"
+Requires-Dist: mdengine[graph]; extra == "dev"
 Provides-Extra: all
 Requires-Dist: pymupdf>=1.24.0; extra == "all"
 Requires-Dist: pdfplumber>=0.11.0; extra == "all"
@@ -114,11 +145,12 @@ Requires-Dist: fastmcp>=2.3.0; extra == "all"
 Requires-Dist: beautifulsoup4>=4.12.0; extra == "all"
 Requires-Dist: lxml_html_clean>=0.4.0; extra == "all"
 Requires-Dist: readability-lxml>=0.8.1; extra == "all"
+Requires-Dist: youtube-transcript-api>=0.6.0; extra == "all"
 Dynamic: license-file
 
 # mdengine
 
-Single Python distribution for converting **PDF**, **Word (.docx)**, **PowerPoint (.pptx)**, **Excel (.xlsx/.xlsm)**, **images** (OCR), **plain text / JSON / XML**, **ZIP archives**, and **audio / video** (Whisper transcription → Markdown) into **Markdown** (and related assets). Install only the extras you need; everything imports under the **`md_generator`** package.
+Single Python distribution for converting **PDF**, **Word (.docx)**, **PowerPoint (.pptx)**, **Excel (.xlsx/.xlsm)**, **images** (OCR), **plain text / JSON / XML**, **ZIP archives**, **audio / video** (Whisper transcription → Markdown), **database metadata** (SQL + Mongo), and **graphs** (Neo4j / NetworkX → Markdown) into **Markdown** (and related assets). Install only the extras you need; everything imports under the **`md_generator`** package.
 
 - **PyPI name:** `mdengine` (import package: `md_generator`)
 - **Source:** [github.com/vishal7090/md-generator](https://github.com/vishal7090/md-generator)
@@ -196,6 +228,7 @@ pip install "mdengine[all]"
 | `video` | **Video → Markdown** (ffmpeg extracts mono 16 kHz WAV, then same Whisper stack as `audio`) |
 | `api` | FastAPI, uvicorn, httpx, pydantic-settings |
 | `mcp` | MCP servers (`mcp`, `fastmcp` where used) |
+| `graph` | **Graph → Markdown** (Neo4j Bolt + NetworkX GraphML/GML): `networkx`, `neo4j`, `pyyaml` |
 | `dev` | pytest + API/MCP test helpers |
 | `all` | Large superset of dependencies (use only if you need everything) |
 
@@ -210,7 +243,7 @@ All converters can be run from a terminal after you install the package (with th
 ### 1. Install (once)
 
 ```bash
-pip install "mdengine[pdf,word]"          # adjust extras: ppt, xlsx, image, archive, text, …
+pip install "mdengine[pdf,word]"          # adjust extras: ppt, xlsx, image, archive, text, db, graph, …
 # or from a clone:
 pip install -e ".[pdf,word,archive]"
 ```
@@ -238,10 +271,26 @@ If the shell reports “command not found”, ensure the Python **Scripts** dire
 | `md-url` | `md_generator.url.converter:main` | `md-url https://example.com/doc ./web-out --artifact-layout` |
 | `md-audio` | `md_generator.media.audio.converter:main` | `md-audio clip.mp3 transcript.md --model base` |
 | `md-video` | `md_generator.media.video.converter:main` | `md-video clip.mp4 transcript.md --model base` |
+| `md-youtube` | `md_generator.media.youtube.converter:main` | `md-youtube "https://youtu.be/…" out.md --transcript-lang en` |
 | `md-audio-api` | `md_generator.media.audio.api.run:main` | REST + MCP on port **8011** (see [Audio and video to Markdown](#audio-and-video-to-markdown)) |
 | `md-video-api` | `md_generator.media.video.api.run:main` | REST + MCP on port **8012** |
+| `md-youtube-api` | `md_generator.media.youtube.api.run:main` | REST + MCP on port **8013** (JSON `url` body; see same section) |
 | `md-audio-mcp` | `md_generator.media.audio.api.mcp_server:main` | Standalone MCP (`--transport stdio` \| `sse` \| `streamable-http`) |
 | `md-video-mcp` | `md_generator.media.video.api.mcp_server:main` | Same for video |
+| `md-youtube-mcp` | `md_generator.media.youtube.api.mcp_server:main` | Same for YouTube (`youtube_url_to_markdown`) |
+| `md-db` | `md_generator.db.cli.main:main` | `pip install "mdengine[db]"` then `md-db --config db.yaml` (or `mdengine db-to-md …`) |
+| `md-db-api` | `md_generator.db.api.run:main` | FastAPI on port **8010** (`DB_TO_MD_PORT`): `POST /db-to-md/run`, `/db-to-md/job`, SSE `/db-to-md/job/{id}/events` |
+| `md-db-mcp` | `md_generator.db.api.mcp_server:main` | Standalone MCP for metadata export tools |
+| `md-graph` | `md_generator.graph.cli.main:main` | `pip install "mdengine[graph]"` then `md-graph --source neo4j --uri bolt://…` (or `mdengine graph-to-md …`) |
+| `md-graph-api` | `md_generator.graph.api.run:main` | FastAPI on port **8012** (`GRAPH_TO_MD_PORT`): `POST /graph-to-md/run`, `/graph-to-md/job`, SSE `/graph-to-md/job/{id}/events` |
+| `md-graph-mcp` | `md_generator.graph.api.mcp_server:main` | Standalone MCP for graph export tools |
+| `mdengine` | `md_generator.engine_cli:main` | `mdengine db-to-md …` / `mdengine graph-to-md …` (delegates to `md-db` / `md-graph`) |
+
+**db-to-md ER diagrams:** add **`erd`** to the export feature list (YAML `features.include`, API body, or CLI `--include …,erd`). **Preferred:** **Graphviz** (`dot` on `PATH`, or **`GRAPHVIZ_DOT`**) produces `erd/*.dot`, `erd/*.png`, and `erd/*.svg`. **If Graphviz is missing,** the exporter falls back to **Mermaid** (`erDiagram`): it writes `erd/*.mermaid` plus a fenced **`erd/*.md`** for GitHub-style preview. With **`mermaid-py`** (included in `mdengine[db]`), it also requests **PNG/SVG** via mermaid.ink (requires network unless you self-host mermaid.ink and set **`MERMAID_INK_SERVER`** per [mermaid-py](https://pypi.org/project/mermaid-py/)). Tune **`erd.max_tables`** (default 100) and **`erd.scope`** (`full` \| `per_schema` \| `per_table`) under `erd:` in YAML; CLI: `--erd-max-tables`, `--erd-scope`. Async job SSE uses `progress_update` with `current` starting with `erd:`.
+
+**db-to-md split exports and README merge:** with **`output.split_files: true`**, set **`output.write_combined_feature_markdown: true`** to also write root-level combined Markdown (for example `tables.md`, `functions.md`, `indexes.md`, and feature-specific paths such as `oracle/packages.md` or `mongodb/collections.md` when those features run). Set **`output.readme_feature_merge`** to **`inline`** (append full bundle bodies into `README.md`) or **`toc`** (append a linked list to those files). If merge is not **`none`** and split files are on, combined bundle writes are turned on automatically when loading config. CLI: `--write-combined-feature-markdown`, `--readme-feature-merge none|inline|toc`.
+
+**graph-to-md (Neo4j + NetworkX):** library lives under [`md_generator/graph/`](src/md_generator/graph/). **Sources:** **`networkx`** (GraphML/GML via `graph.graph_file` or `--graph-file`) or **`neo4j`** (`graph.uri`, `graph.user`, `graph.password`, optional `graph.database` for `session(database=…)`). **Output layout:** by default **`output.combine_markdown: true`** writes **`nodes.md`**, **`relationship.md`**, and **`graph_summary.md`** (summary plus embedded nodes and relationships). Set **`combine_markdown: false`** or CLI **`--individual` / `--markdown-layout individual`** for per-entity files under **`nodes/`** and **`relationships/`**. **Diagrams:** **`viz.mermaid: true`** (default) writes **`graph/graph.mmd`** and embeds a fenced Mermaid block in the export **`README.md`** (no Graphviz required). **`viz.enabled: true`** or CLI **`--viz`** also writes **`graph/graph.dot`** and runs **`dot`** for PNG/SVG/PDF when Graphviz is on `PATH` (or **`GRAPHVIZ_DOT`**). CLI **`--no-mermaid`** disables Mermaid; **`--depth`**, **`--start-node`**, **`--max-nodes`**, **`--max-edges`** bound traversal. Packaged defaults: [`src/md_generator/graph/config/default.yaml`](src/md_generator/graph/config/default.yaml). Tests: **`graph-to-md/tests/`**; API image: [`graph-to-md/Dockerfile.api`](graph-to-md/Dockerfile.api).
 
 Every command accepts **`-h` / `--help`** for full flags (artifact layout, OCR, ZIP options, etc.).
 
@@ -261,6 +310,7 @@ md-zip archive.zip ./unzipped-md
 md-url https://example.com/page ./page-bundle --artifact-layout
 md-audio ./voice.mp3 ./voice.md --model tiny
 md-video ./screen.mp4 ./screen.md --model base
+pip install "mdengine[graph]" && md-graph --source neo4j --uri neo4j://localhost:7687 --user neo4j --password secret --database neo4j --output ./graph-out --viz
 ```
 
 **Windows PowerShell** (same commands; use backslashes for paths if you prefer)
@@ -271,6 +321,8 @@ md-zip .\archive.zip .\zip-out
 md-url https://example.com/page .\page-bundle --artifact-layout
 md-audio .\voice.mp3 .\voice.md --model tiny
 md-video .\screen.mp4 .\screen.md --model base
+pip install "mdengine[graph]"
+md-graph --source neo4j --uri neo4j://localhost:7687 --user neo4j --password secret --database neo4j --output .\graph-out --viz
 ```
 
 **Windows CMD**
@@ -455,6 +507,7 @@ Library code lives under **`md_generator.media`**: shared probing in [`document_
 ```bash
 pip install "mdengine[audio,api,mcp]"    # audio CLI + HTTP + MCP
 pip install "mdengine[video,api,mcp]"   # video CLI + HTTP + MCP (same ML stack as audio)
+pip install "mdengine[youtube,api,mcp]" # YouTube URL → Markdown (captions + metadata; optional Whisper fallback)
 ```
 
 ### Python library
@@ -483,6 +536,18 @@ md = svc.to_markdown(Path("input.mp4"), title=None)
 svc.write_markdown(Path("input.mp4"), Path("out/transcript.md"))
 ```
 
+**YouTube** — captions API + page metadata (BeautifulSoup / oEmbed); optional **yt-dlp + Whisper** when captions are missing (`mdengine[audio]` and `yt-dlp` on `PATH`, or `MD_YOUTUBE_YTDLP`):
+
+```python
+from md_generator.media.youtube import YouTubeToMarkdownService
+
+svc = YouTubeToMarkdownService(whisper_model="base")
+md = svc.to_markdown("https://www.youtube.com/watch?v=VIDEO_ID", transcript_languages=["en"])
+svc.write_markdown("https://youtu.be/VIDEO_ID", Path("out/youtube.md"))
+```
+
+For file-based pipelines, [`YouTubeConverter`](src/md_generator/media/youtube/converter.py) reads a `.url` / `.yturl` / `.youtube` file (or a `.txt` whose first non-comment line is a YouTube URL) and implements [`DocumentConverter`](src/md_generator/media/document_converter.py).
+
 Public symbols are also re-exported from [`md_generator.media`](src/md_generator/media/__init__.py) for ffprobe helpers (`ffprobe_json`, `VideoProbeResult`, …).
 
 ### REST API (FastAPI)
@@ -497,13 +562,15 @@ Each service exposes the same job pattern as other converters:
 | `GET /convert/jobs/{job_id}/download` | Markdown when `done`; workspace removed after download. |
 
 **Audio** defaults: `MD_AUDIO_MAX_UPLOAD_MB=200`, `MD_AUDIO_MAX_SYNC_UPLOAD_MB=40`, `MD_AUDIO_API_PORT=8011`.  
-**Video** defaults: `MD_VIDEO_MAX_UPLOAD_MB=500`, `MD_VIDEO_MAX_SYNC_UPLOAD_MB=80`, `MD_VIDEO_API_PORT=8012`.
+**Video** defaults: `MD_VIDEO_MAX_UPLOAD_MB=500`, `MD_VIDEO_MAX_SYNC_UPLOAD_MB=80`, `MD_VIDEO_API_PORT=8012`.  
+**YouTube** uses **JSON** (not multipart): `POST /convert/sync` and `POST /convert/jobs` accept `{"url":"https://www.youtube.com/watch?v=…","title":null,"transcript_languages":["en"],"enable_audio_fallback":true,"whisper_model":"base","language":null}`. Defaults: `MD_YOUTUBE_API_PORT=8013`, `MD_YOUTUBE_JOB_TTL_SECONDS`, `MD_YOUTUBE_CORS_ORIGINS`, `MD_YOUTUBE_TEMP_DIR`.
 
 Run with the bundled runners (each call builds the app with **`factory=True`** for a clean MCP session manager):
 
 ```bash
 md-audio-api --host 127.0.0.1 --port 8011
 md-video-api --host 127.0.0.1 --port 8012
+md-youtube-api --host 127.0.0.1 --port 8013
 ```
 
 Or with Uvicorn directly (the ASGI app is built by **`create_app()`** so each worker gets its own MCP session manager):
@@ -511,6 +578,7 @@ Or with Uvicorn directly (the ASGI app is built by **`create_app()`** so each wo
 ```bash
 uvicorn md_generator.media.audio.api.main:create_app --factory --host 127.0.0.1 --port 8011
 uvicorn md_generator.media.video.api.main:create_app --factory --host 127.0.0.1 --port 8012
+uvicorn md_generator.media.youtube.api.main:create_app --factory --host 127.0.0.1 --port 8013
 ```
 
 The module also defines **`app = create_app()`** for a single-process target: `uvicorn md_generator.media.audio.api.main:app` (no `--factory`).
@@ -519,7 +587,7 @@ Swagger is at **`/docs`** when the app is running.
 
 ### MCP (stdio, SSE, streamable HTTP)
 
-1. **With FastAPI** — start `md-audio-api` or `md-video-api`; mount Streamable HTTP MCP at **`http://<host>:<port>/mcp`** (same host as REST).
+1. **With FastAPI** — start `md-audio-api`, `md-video-api`, or `md-youtube-api`; mount Streamable HTTP MCP at **`http://<host>:<port>/mcp`** (same host as REST).
 2. **Standalone** — process speaks MCP only:
 
 ```bash
@@ -527,16 +595,18 @@ md-audio-mcp --transport stdio
 md-audio-mcp --transport sse
 md-audio-mcp --transport streamable-http
 md-video-mcp --transport stdio
+md-youtube-mcp --transport stdio
 ```
 
 **Audio MCP tools:** `transcribe_audio_path`, `transcribe_audio_base64`.  
-**Video MCP tools:** `transcribe_video_path`, `transcribe_video_base64`.
+**Video MCP tools:** `transcribe_video_path`, `transcribe_video_base64`.  
+**YouTube MCP tool:** `youtube_url_to_markdown`.
 
-Equivalent modules: `python -m md_generator.media.audio.api.mcp_server`, `python -m md_generator.media.video.api.mcp_server`.
+Equivalent modules: `python -m md_generator.media.audio.api.mcp_server`, `python -m md_generator.media.video.api.mcp_server`, `python -m md_generator.media.youtube.api.mcp_server`.
 
 ### Thin shims (repo clone)
 
-[`audio-to-md/converter.py`](audio-to-md/converter.py) and [`video-to-md/converter.py`](video-to-md/converter.py) delegate to the same `main` as `md-audio` / `md-video`. Tests and `pytest.ini` live under `audio-to-md/tests/` and `video-to-md/tests/`.
+[`audio-to-md/converter.py`](audio-to-md/converter.py), [`video-to-md/converter.py`](video-to-md/converter.py), and [`youtube-to-md/converter.py`](youtube-to-md/converter.py) delegate to the same `main` as `md-audio` / `md-video` / `md-youtube`. Tests and `pytest.ini` live under `audio-to-md/tests/`, `video-to-md/tests/`, and `youtube-to-md/tests/`. [`db-to-md/converter.py`](db-to-md/converter.py) delegates to `md-db`; tests live under `db-to-md/tests/`. **graph-to-md** uses `md-graph` / `mdengine graph-to-md` directly (no thin `converter.py` shim); tests live under [`graph-to-md/tests/`](graph-to-md/tests/).
 
 ---
 
@@ -565,8 +635,12 @@ Install `mdengine[api]` plus the format extra(s), then run the **`app`** object
 | Text/JSON/XML | `md_generator.text.api.main:app` | `text`, `api`, `mcp` |
 | ZIP | `md_generator.archive.api.main:app` | `archive`, `api`, `mcp` (+ extras for nested office/PDF) |
 | URL / HTML | `md_generator.url.api.main:app` | `url`, `api`, `mcp` |
+| Playwright / SPA | `md_generator.playwright.api.main:app` | `playwright`, `api`, `mcp` |
+| Database metadata | `md_generator.db.api.main:app` | `db`, `api`, `mcp` |
+| Graph metadata (Neo4j / NetworkX) | `md_generator.graph.api.main:app` | `graph`, `api`, `mcp` |
 | Audio (Whisper) | `md_generator.media.audio.api.main:create_app` (use **`--factory`**) or `…main:app` | `audio`, `api`, `mcp` |
 | Video (Whisper) | `md_generator.media.video.api.main:create_app` (use **`--factory`**) or `…main:app` | `video`, `api`, `mcp` |
+| YouTube | `md_generator.media.youtube.api.main:create_app` (use **`--factory`**) or `…main:app` | `youtube`, `api`, `mcp` |
 
 Examples:
 
@@ -575,10 +649,15 @@ uvicorn md_generator.pdf.api.main:app --host 127.0.0.1 --port 8001
 uvicorn md_generator.word.api.main:app --host 127.0.0.1 --port 8002
 uvicorn md_generator.archive.api.main:app --host 127.0.0.1 --port 8010
 uvicorn md_generator.url.api.main:app --host 127.0.0.1 --port 8011
+uvicorn md_generator.playwright.api.main:app --host 127.0.0.1 --port 8014
+uvicorn md_generator.graph.api.main:app --host 127.0.0.1 --port 8012
 uvicorn md_generator.media.audio.api.main:create_app --factory --host 127.0.0.1 --port 8011
 uvicorn md_generator.media.video.api.main:create_app --factory --host 127.0.0.1 --port 8012
+uvicorn md_generator.media.youtube.api.main:create_app --factory --host 127.0.0.1 --port 8013
 ```
 
+**Port note:** **`md-graph-api`** and **`md-video-api`** both default to **8012**; set **`GRAPH_TO_MD_PORT`** or **`MD_VIDEO_API_PORT`** when you need both on one machine.
+
 ### MCP over HTTP on the same server
 
 These apps mount an MCP HTTP app at **`/mcp`** (Streamable HTTP / framework-specific). Start the API as above, then point an MCP client at `http://<host>:<port>/mcp` where supported.
@@ -596,8 +675,12 @@ Prefixes differ per service (often read from a `.env` file next to the process):
 | Text | `TXT_JSON_XML_TO_MD_` | same pattern |
 | XLSX | `XLSX_TO_MD_` | `XLSX_TO_MD_TEMP_DIR`, `XLSX_TO_MD_CORS_ORIGINS`, etc. (see `md_generator.xlsx.api.app`) |
 | URL | `URL_TO_MD_` | `URL_TO_MD_MAX_SYNC_URLS`, `URL_TO_MD_MAX_SYNC_CRAWL_PAGES`, `URL_TO_MD_MAX_JOB_URLS`, `URL_TO_MD_JOB_TTL_SECONDS`, `URL_TO_MD_TEMP_DIR`, `URL_TO_MD_CORS_ORIGINS` |
+| Playwright / SPA | `PLAYWRIGHT_TO_MD_` | `PLAYWRIGHT_TO_MD_MAX_SYNC_URLS`, `PLAYWRIGHT_TO_MD_MAX_JOB_URLS`, `PLAYWRIGHT_TO_MD_JOB_TTL_SECONDS`, `PLAYWRIGHT_TO_MD_TEMP_DIR`, `PLAYWRIGHT_TO_MD_CORS_ORIGINS`, `PLAYWRIGHT_TO_MD_API_HOST`, `PLAYWRIGHT_TO_MD_API_PORT` (default **8014**) |
+| Database metadata | `DB_TO_MD_` | `DB_TO_MD_JOB_SQLITE_PATH`, `DB_TO_MD_JOB_WORKSPACE_ROOT`, `DB_TO_MD_CORS_ORIGINS`, `DB_TO_MD_MAX_SYNC_ZIP_MB`, `DB_TO_MD_HOST`, `DB_TO_MD_PORT` (default **8010**) |
+| Graph metadata | `GRAPH_TO_MD_` | `GRAPH_TO_MD_JOB_SQLITE_PATH`, `GRAPH_TO_MD_JOB_WORKSPACE_ROOT`, `GRAPH_TO_MD_CORS_ORIGINS`, `GRAPH_TO_MD_MAX_SYNC_ZIP_MB`, `GRAPH_TO_MD_HOST`, `GRAPH_TO_MD_PORT` (default **8012**) |
 | Audio API | `MD_AUDIO_` | `MD_AUDIO_MAX_UPLOAD_MB`, `MD_AUDIO_MAX_SYNC_UPLOAD_MB`, `MD_AUDIO_JOB_TTL_SECONDS`, `MD_AUDIO_TEMP_DIR`, `MD_AUDIO_CORS_ORIGINS`, `MD_AUDIO_API_HOST`, `MD_AUDIO_API_PORT` |
 | Video API | `MD_VIDEO_` | Same pattern as audio with `MD_VIDEO_*` (defaults: larger upload/sync caps, port **8012**) |
+| YouTube API | `MD_YOUTUBE_` | `MD_YOUTUBE_JOB_TTL_SECONDS`, `MD_YOUTUBE_TEMP_DIR`, `MD_YOUTUBE_CORS_ORIGINS`, `MD_YOUTUBE_API_HOST`, `MD_YOUTUBE_API_PORT` (default **8013**); optional `MD_YOUTUBE_YTDLP` path for audio fallback |
 
 Exact variable names match the `ApiSettings` / helper functions in each `api/settings` or `api/app` module.
 
@@ -621,8 +704,12 @@ Two usage patterns:
 | PPTX | `python -m md_generator.ppt.api.mcp_server` (see module docstring for flags) |
 | Image | `python -m md_generator.image.api.mcp_server` (see module for CLI) |
 | URL / HTML | `python -m md_generator.url.api.mcp_server` / `--transport sse` / `--transport streamable-http` |
+| Playwright / SPA | `md-playwright-mcp` or `python -m md_generator.playwright.api.mcp_server` / `--transport sse` / `--transport streamable-http` |
 | Audio | `md-audio-mcp` or `python -m md_generator.media.audio.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
 | Video | `md-video-mcp` or `python -m md_generator.media.video.api.mcp_server` — same transports |
+| YouTube | `md-youtube-mcp` or `python -m md_generator.media.youtube.api.mcp_server` — same transports |
+| Database metadata | `md-db-mcp` or `python -m md_generator.db.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
+| Graph (Neo4j / NetworkX) | `md-graph-mcp` or `python -m md_generator.graph.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
 
 **Word** and **XLSX** also ship a small runner script in the repo:
 
@@ -647,7 +734,7 @@ pip install -e ".[dev,all]"   # or a smaller subset of extras
 python -m pytest
 ```
 
-Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/tests/`); `pyproject.toml` configures `pythonpath = ["src"]` so `md_generator` resolves without a separate `PYTHONPATH`.
+Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/tests/`) and **`graph-to-md/tests/`**; `pyproject.toml` configures `pythonpath = ["src"]` so `md_generator` resolves without a separate `PYTHONPATH`.
 
 ---
 
@@ -657,7 +744,7 @@ Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/test
 |------|------|
 | `LICENSE` | MIT license text |
 | `CODE_OF_CONDUCT.md` | [Contributor Covenant](https://www.contributor-covenant.org/) 2.1 |
-| `src/md_generator/` | **Library source** (all formats + `api` subpackages); **audio/video** under [`media/audio/`](src/md_generator/media/audio/) and [`media/video/`](src/md_generator/media/video/) |
+| `src/md_generator/` | **Library source** (all formats + `api` subpackages); **audio/video** under [`media/audio/`](src/md_generator/media/audio/) and [`media/video/`](src/md_generator/media/video/); **graph-to-md** under [`graph/`](src/md_generator/graph/) |
 | `pyproject.toml` | Packaging, extras, CLI entry points, pytest |
 | `*-to-md/` | **Docs, tests, fixtures**, thin `converter.py` shims, some `run.py` helpers |
 | `README.md` | This document |

{mdengine-0.3.0 → mdengine-0.5.0}/README.md

@@ -1,6 +1,6 @@
 # mdengine
 
-Single Python distribution for converting **PDF**, **Word (.docx)**, **PowerPoint (.pptx)**, **Excel (.xlsx/.xlsm)**, **images** (OCR), **plain text / JSON / XML**, **ZIP archives**, and **audio / video** (Whisper transcription → Markdown) into **Markdown** (and related assets). Install only the extras you need; everything imports under the **`md_generator`** package.
+Single Python distribution for converting **PDF**, **Word (.docx)**, **PowerPoint (.pptx)**, **Excel (.xlsx/.xlsm)**, **images** (OCR), **plain text / JSON / XML**, **ZIP archives**, **audio / video** (Whisper transcription → Markdown), **database metadata** (SQL + Mongo), and **graphs** (Neo4j / NetworkX → Markdown) into **Markdown** (and related assets). Install only the extras you need; everything imports under the **`md_generator`** package.
 
 - **PyPI name:** `mdengine` (import package: `md_generator`)
 - **Source:** [github.com/vishal7090/md-generator](https://github.com/vishal7090/md-generator)
@@ -78,6 +78,7 @@ pip install "mdengine[all]"
 | `video` | **Video → Markdown** (ffmpeg extracts mono 16 kHz WAV, then same Whisper stack as `audio`) |
 | `api` | FastAPI, uvicorn, httpx, pydantic-settings |
 | `mcp` | MCP servers (`mcp`, `fastmcp` where used) |
+| `graph` | **Graph → Markdown** (Neo4j Bolt + NetworkX GraphML/GML): `networkx`, `neo4j`, `pyyaml` |
 | `dev` | pytest + API/MCP test helpers |
 | `all` | Large superset of dependencies (use only if you need everything) |
 
@@ -92,7 +93,7 @@ All converters can be run from a terminal after you install the package (with th
 ### 1. Install (once)
 
 ```bash
-pip install "mdengine[pdf,word]"          # adjust extras: ppt, xlsx, image, archive, text, …
+pip install "mdengine[pdf,word]"          # adjust extras: ppt, xlsx, image, archive, text, db, graph, …
 # or from a clone:
 pip install -e ".[pdf,word,archive]"
 ```
@@ -120,10 +121,26 @@ If the shell reports “command not found”, ensure the Python **Scripts** dire
 | `md-url` | `md_generator.url.converter:main` | `md-url https://example.com/doc ./web-out --artifact-layout` |
 | `md-audio` | `md_generator.media.audio.converter:main` | `md-audio clip.mp3 transcript.md --model base` |
 | `md-video` | `md_generator.media.video.converter:main` | `md-video clip.mp4 transcript.md --model base` |
+| `md-youtube` | `md_generator.media.youtube.converter:main` | `md-youtube "https://youtu.be/…" out.md --transcript-lang en` |
 | `md-audio-api` | `md_generator.media.audio.api.run:main` | REST + MCP on port **8011** (see [Audio and video to Markdown](#audio-and-video-to-markdown)) |
 | `md-video-api` | `md_generator.media.video.api.run:main` | REST + MCP on port **8012** |
+| `md-youtube-api` | `md_generator.media.youtube.api.run:main` | REST + MCP on port **8013** (JSON `url` body; see same section) |
 | `md-audio-mcp` | `md_generator.media.audio.api.mcp_server:main` | Standalone MCP (`--transport stdio` \| `sse` \| `streamable-http`) |
 | `md-video-mcp` | `md_generator.media.video.api.mcp_server:main` | Same for video |
+| `md-youtube-mcp` | `md_generator.media.youtube.api.mcp_server:main` | Same for YouTube (`youtube_url_to_markdown`) |
+| `md-db` | `md_generator.db.cli.main:main` | `pip install "mdengine[db]"` then `md-db --config db.yaml` (or `mdengine db-to-md …`) |
+| `md-db-api` | `md_generator.db.api.run:main` | FastAPI on port **8010** (`DB_TO_MD_PORT`): `POST /db-to-md/run`, `/db-to-md/job`, SSE `/db-to-md/job/{id}/events` |
+| `md-db-mcp` | `md_generator.db.api.mcp_server:main` | Standalone MCP for metadata export tools |
+| `md-graph` | `md_generator.graph.cli.main:main` | `pip install "mdengine[graph]"` then `md-graph --source neo4j --uri bolt://…` (or `mdengine graph-to-md …`) |
+| `md-graph-api` | `md_generator.graph.api.run:main` | FastAPI on port **8012** (`GRAPH_TO_MD_PORT`): `POST /graph-to-md/run`, `/graph-to-md/job`, SSE `/graph-to-md/job/{id}/events` |
+| `md-graph-mcp` | `md_generator.graph.api.mcp_server:main` | Standalone MCP for graph export tools |
+| `mdengine` | `md_generator.engine_cli:main` | `mdengine db-to-md …` / `mdengine graph-to-md …` (delegates to `md-db` / `md-graph`) |
+
+**db-to-md ER diagrams:** add **`erd`** to the export feature list (YAML `features.include`, API body, or CLI `--include …,erd`). **Preferred:** **Graphviz** (`dot` on `PATH`, or **`GRAPHVIZ_DOT`**) produces `erd/*.dot`, `erd/*.png`, and `erd/*.svg`. **If Graphviz is missing,** the exporter falls back to **Mermaid** (`erDiagram`): it writes `erd/*.mermaid` plus a fenced **`erd/*.md`** for GitHub-style preview. With **`mermaid-py`** (included in `mdengine[db]`), it also requests **PNG/SVG** via mermaid.ink (requires network unless you self-host mermaid.ink and set **`MERMAID_INK_SERVER`** per [mermaid-py](https://pypi.org/project/mermaid-py/)). Tune **`erd.max_tables`** (default 100) and **`erd.scope`** (`full` \| `per_schema` \| `per_table`) under `erd:` in YAML; CLI: `--erd-max-tables`, `--erd-scope`. Async job SSE uses `progress_update` with `current` starting with `erd:`.
+
+**db-to-md split exports and README merge:** with **`output.split_files: true`**, set **`output.write_combined_feature_markdown: true`** to also write root-level combined Markdown (for example `tables.md`, `functions.md`, `indexes.md`, and feature-specific paths such as `oracle/packages.md` or `mongodb/collections.md` when those features run). Set **`output.readme_feature_merge`** to **`inline`** (append full bundle bodies into `README.md`) or **`toc`** (append a linked list to those files). If merge is not **`none`** and split files are on, combined bundle writes are turned on automatically when loading config. CLI: `--write-combined-feature-markdown`, `--readme-feature-merge none|inline|toc`.
+
+**graph-to-md (Neo4j + NetworkX):** library lives under [`md_generator/graph/`](src/md_generator/graph/). **Sources:** **`networkx`** (GraphML/GML via `graph.graph_file` or `--graph-file`) or **`neo4j`** (`graph.uri`, `graph.user`, `graph.password`, optional `graph.database` for `session(database=…)`). **Output layout:** by default **`output.combine_markdown: true`** writes **`nodes.md`**, **`relationship.md`**, and **`graph_summary.md`** (summary plus embedded nodes and relationships). Set **`combine_markdown: false`** or CLI **`--individual` / `--markdown-layout individual`** for per-entity files under **`nodes/`** and **`relationships/`**. **Diagrams:** **`viz.mermaid: true`** (default) writes **`graph/graph.mmd`** and embeds a fenced Mermaid block in the export **`README.md`** (no Graphviz required). **`viz.enabled: true`** or CLI **`--viz`** also writes **`graph/graph.dot`** and runs **`dot`** for PNG/SVG/PDF when Graphviz is on `PATH` (or **`GRAPHVIZ_DOT`**). CLI **`--no-mermaid`** disables Mermaid; **`--depth`**, **`--start-node`**, **`--max-nodes`**, **`--max-edges`** bound traversal. Packaged defaults: [`src/md_generator/graph/config/default.yaml`](src/md_generator/graph/config/default.yaml). Tests: **`graph-to-md/tests/`**; API image: [`graph-to-md/Dockerfile.api`](graph-to-md/Dockerfile.api).
 
 Every command accepts **`-h` / `--help`** for full flags (artifact layout, OCR, ZIP options, etc.).
 
@@ -143,6 +160,7 @@ md-zip archive.zip ./unzipped-md
 md-url https://example.com/page ./page-bundle --artifact-layout
 md-audio ./voice.mp3 ./voice.md --model tiny
 md-video ./screen.mp4 ./screen.md --model base
+pip install "mdengine[graph]" && md-graph --source neo4j --uri neo4j://localhost:7687 --user neo4j --password secret --database neo4j --output ./graph-out --viz
 ```
 
 **Windows PowerShell** (same commands; use backslashes for paths if you prefer)
@@ -153,6 +171,8 @@ md-zip .\archive.zip .\zip-out
 md-url https://example.com/page .\page-bundle --artifact-layout
 md-audio .\voice.mp3 .\voice.md --model tiny
 md-video .\screen.mp4 .\screen.md --model base
+pip install "mdengine[graph]"
+md-graph --source neo4j --uri neo4j://localhost:7687 --user neo4j --password secret --database neo4j --output .\graph-out --viz
 ```
 
 **Windows CMD**
@@ -337,6 +357,7 @@ Library code lives under **`md_generator.media`**: shared probing in [`document_
 ```bash
 pip install "mdengine[audio,api,mcp]"    # audio CLI + HTTP + MCP
 pip install "mdengine[video,api,mcp]"   # video CLI + HTTP + MCP (same ML stack as audio)
+pip install "mdengine[youtube,api,mcp]" # YouTube URL → Markdown (captions + metadata; optional Whisper fallback)
 ```
 
 ### Python library
@@ -365,6 +386,18 @@ md = svc.to_markdown(Path("input.mp4"), title=None)
 svc.write_markdown(Path("input.mp4"), Path("out/transcript.md"))
 ```
 
+**YouTube** — captions API + page metadata (BeautifulSoup / oEmbed); optional **yt-dlp + Whisper** when captions are missing (`mdengine[audio]` and `yt-dlp` on `PATH`, or `MD_YOUTUBE_YTDLP`):
+
+```python
+from md_generator.media.youtube import YouTubeToMarkdownService
+
+svc = YouTubeToMarkdownService(whisper_model="base")
+md = svc.to_markdown("https://www.youtube.com/watch?v=VIDEO_ID", transcript_languages=["en"])
+svc.write_markdown("https://youtu.be/VIDEO_ID", Path("out/youtube.md"))
+```
+
+For file-based pipelines, [`YouTubeConverter`](src/md_generator/media/youtube/converter.py) reads a `.url` / `.yturl` / `.youtube` file (or a `.txt` whose first non-comment line is a YouTube URL) and implements [`DocumentConverter`](src/md_generator/media/document_converter.py).
+
 Public symbols are also re-exported from [`md_generator.media`](src/md_generator/media/__init__.py) for ffprobe helpers (`ffprobe_json`, `VideoProbeResult`, …).
 
 ### REST API (FastAPI)
@@ -379,13 +412,15 @@ Each service exposes the same job pattern as other converters:
 | `GET /convert/jobs/{job_id}/download` | Markdown when `done`; workspace removed after download. |
 
 **Audio** defaults: `MD_AUDIO_MAX_UPLOAD_MB=200`, `MD_AUDIO_MAX_SYNC_UPLOAD_MB=40`, `MD_AUDIO_API_PORT=8011`.  
-**Video** defaults: `MD_VIDEO_MAX_UPLOAD_MB=500`, `MD_VIDEO_MAX_SYNC_UPLOAD_MB=80`, `MD_VIDEO_API_PORT=8012`.
+**Video** defaults: `MD_VIDEO_MAX_UPLOAD_MB=500`, `MD_VIDEO_MAX_SYNC_UPLOAD_MB=80`, `MD_VIDEO_API_PORT=8012`.  
+**YouTube** uses **JSON** (not multipart): `POST /convert/sync` and `POST /convert/jobs` accept `{"url":"https://www.youtube.com/watch?v=…","title":null,"transcript_languages":["en"],"enable_audio_fallback":true,"whisper_model":"base","language":null}`. Defaults: `MD_YOUTUBE_API_PORT=8013`, `MD_YOUTUBE_JOB_TTL_SECONDS`, `MD_YOUTUBE_CORS_ORIGINS`, `MD_YOUTUBE_TEMP_DIR`.
 
 Run with the bundled runners (each call builds the app with **`factory=True`** for a clean MCP session manager):
 
 ```bash
 md-audio-api --host 127.0.0.1 --port 8011
 md-video-api --host 127.0.0.1 --port 8012
+md-youtube-api --host 127.0.0.1 --port 8013
 ```
 
 Or with Uvicorn directly (the ASGI app is built by **`create_app()`** so each worker gets its own MCP session manager):
@@ -393,6 +428,7 @@ Or with Uvicorn directly (the ASGI app is built by **`create_app()`** so each wo
 ```bash
 uvicorn md_generator.media.audio.api.main:create_app --factory --host 127.0.0.1 --port 8011
 uvicorn md_generator.media.video.api.main:create_app --factory --host 127.0.0.1 --port 8012
+uvicorn md_generator.media.youtube.api.main:create_app --factory --host 127.0.0.1 --port 8013
 ```
 
 The module also defines **`app = create_app()`** for a single-process target: `uvicorn md_generator.media.audio.api.main:app` (no `--factory`).
@@ -401,7 +437,7 @@ Swagger is at **`/docs`** when the app is running.
 
 ### MCP (stdio, SSE, streamable HTTP)
 
-1. **With FastAPI** — start `md-audio-api` or `md-video-api`; mount Streamable HTTP MCP at **`http://<host>:<port>/mcp`** (same host as REST).
+1. **With FastAPI** — start `md-audio-api`, `md-video-api`, or `md-youtube-api`; mount Streamable HTTP MCP at **`http://<host>:<port>/mcp`** (same host as REST).
 2. **Standalone** — process speaks MCP only:
 
 ```bash
@@ -409,16 +445,18 @@ md-audio-mcp --transport stdio
 md-audio-mcp --transport sse
 md-audio-mcp --transport streamable-http
 md-video-mcp --transport stdio
+md-youtube-mcp --transport stdio
 ```
 
 **Audio MCP tools:** `transcribe_audio_path`, `transcribe_audio_base64`.  
-**Video MCP tools:** `transcribe_video_path`, `transcribe_video_base64`.
+**Video MCP tools:** `transcribe_video_path`, `transcribe_video_base64`.  
+**YouTube MCP tool:** `youtube_url_to_markdown`.
 
-Equivalent modules: `python -m md_generator.media.audio.api.mcp_server`, `python -m md_generator.media.video.api.mcp_server`.
+Equivalent modules: `python -m md_generator.media.audio.api.mcp_server`, `python -m md_generator.media.video.api.mcp_server`, `python -m md_generator.media.youtube.api.mcp_server`.
 
 ### Thin shims (repo clone)
 
-[`audio-to-md/converter.py`](audio-to-md/converter.py) and [`video-to-md/converter.py`](video-to-md/converter.py) delegate to the same `main` as `md-audio` / `md-video`. Tests and `pytest.ini` live under `audio-to-md/tests/` and `video-to-md/tests/`.
+[`audio-to-md/converter.py`](audio-to-md/converter.py), [`video-to-md/converter.py`](video-to-md/converter.py), and [`youtube-to-md/converter.py`](youtube-to-md/converter.py) delegate to the same `main` as `md-audio` / `md-video` / `md-youtube`. Tests and `pytest.ini` live under `audio-to-md/tests/`, `video-to-md/tests/`, and `youtube-to-md/tests/`. [`db-to-md/converter.py`](db-to-md/converter.py) delegates to `md-db`; tests live under `db-to-md/tests/`. **graph-to-md** uses `md-graph` / `mdengine graph-to-md` directly (no thin `converter.py` shim); tests live under [`graph-to-md/tests/`](graph-to-md/tests/).
 
 ---
 
@@ -447,8 +485,12 @@ Install `mdengine[api]` plus the format extra(s), then run the **`app`** object
 | Text/JSON/XML | `md_generator.text.api.main:app` | `text`, `api`, `mcp` |
 | ZIP | `md_generator.archive.api.main:app` | `archive`, `api`, `mcp` (+ extras for nested office/PDF) |
 | URL / HTML | `md_generator.url.api.main:app` | `url`, `api`, `mcp` |
+| Playwright / SPA | `md_generator.playwright.api.main:app` | `playwright`, `api`, `mcp` |
+| Database metadata | `md_generator.db.api.main:app` | `db`, `api`, `mcp` |
+| Graph metadata (Neo4j / NetworkX) | `md_generator.graph.api.main:app` | `graph`, `api`, `mcp` |
 | Audio (Whisper) | `md_generator.media.audio.api.main:create_app` (use **`--factory`**) or `…main:app` | `audio`, `api`, `mcp` |
 | Video (Whisper) | `md_generator.media.video.api.main:create_app` (use **`--factory`**) or `…main:app` | `video`, `api`, `mcp` |
+| YouTube | `md_generator.media.youtube.api.main:create_app` (use **`--factory`**) or `…main:app` | `youtube`, `api`, `mcp` |
 
 Examples:
 
@@ -457,10 +499,15 @@ uvicorn md_generator.pdf.api.main:app --host 127.0.0.1 --port 8001
 uvicorn md_generator.word.api.main:app --host 127.0.0.1 --port 8002
 uvicorn md_generator.archive.api.main:app --host 127.0.0.1 --port 8010
 uvicorn md_generator.url.api.main:app --host 127.0.0.1 --port 8011
+uvicorn md_generator.playwright.api.main:app --host 127.0.0.1 --port 8014
+uvicorn md_generator.graph.api.main:app --host 127.0.0.1 --port 8012
 uvicorn md_generator.media.audio.api.main:create_app --factory --host 127.0.0.1 --port 8011
 uvicorn md_generator.media.video.api.main:create_app --factory --host 127.0.0.1 --port 8012
+uvicorn md_generator.media.youtube.api.main:create_app --factory --host 127.0.0.1 --port 8013
 ```
 
+**Port note:** **`md-graph-api`** and **`md-video-api`** both default to **8012**; set **`GRAPH_TO_MD_PORT`** or **`MD_VIDEO_API_PORT`** when you need both on one machine.
+
 ### MCP over HTTP on the same server
 
 These apps mount an MCP HTTP app at **`/mcp`** (Streamable HTTP / framework-specific). Start the API as above, then point an MCP client at `http://<host>:<port>/mcp` where supported.
@@ -478,8 +525,12 @@ Prefixes differ per service (often read from a `.env` file next to the process):
 | Text | `TXT_JSON_XML_TO_MD_` | same pattern |
 | XLSX | `XLSX_TO_MD_` | `XLSX_TO_MD_TEMP_DIR`, `XLSX_TO_MD_CORS_ORIGINS`, etc. (see `md_generator.xlsx.api.app`) |
 | URL | `URL_TO_MD_` | `URL_TO_MD_MAX_SYNC_URLS`, `URL_TO_MD_MAX_SYNC_CRAWL_PAGES`, `URL_TO_MD_MAX_JOB_URLS`, `URL_TO_MD_JOB_TTL_SECONDS`, `URL_TO_MD_TEMP_DIR`, `URL_TO_MD_CORS_ORIGINS` |
+| Playwright / SPA | `PLAYWRIGHT_TO_MD_` | `PLAYWRIGHT_TO_MD_MAX_SYNC_URLS`, `PLAYWRIGHT_TO_MD_MAX_JOB_URLS`, `PLAYWRIGHT_TO_MD_JOB_TTL_SECONDS`, `PLAYWRIGHT_TO_MD_TEMP_DIR`, `PLAYWRIGHT_TO_MD_CORS_ORIGINS`, `PLAYWRIGHT_TO_MD_API_HOST`, `PLAYWRIGHT_TO_MD_API_PORT` (default **8014**) |
+| Database metadata | `DB_TO_MD_` | `DB_TO_MD_JOB_SQLITE_PATH`, `DB_TO_MD_JOB_WORKSPACE_ROOT`, `DB_TO_MD_CORS_ORIGINS`, `DB_TO_MD_MAX_SYNC_ZIP_MB`, `DB_TO_MD_HOST`, `DB_TO_MD_PORT` (default **8010**) |
+| Graph metadata | `GRAPH_TO_MD_` | `GRAPH_TO_MD_JOB_SQLITE_PATH`, `GRAPH_TO_MD_JOB_WORKSPACE_ROOT`, `GRAPH_TO_MD_CORS_ORIGINS`, `GRAPH_TO_MD_MAX_SYNC_ZIP_MB`, `GRAPH_TO_MD_HOST`, `GRAPH_TO_MD_PORT` (default **8012**) |
 | Audio API | `MD_AUDIO_` | `MD_AUDIO_MAX_UPLOAD_MB`, `MD_AUDIO_MAX_SYNC_UPLOAD_MB`, `MD_AUDIO_JOB_TTL_SECONDS`, `MD_AUDIO_TEMP_DIR`, `MD_AUDIO_CORS_ORIGINS`, `MD_AUDIO_API_HOST`, `MD_AUDIO_API_PORT` |
 | Video API | `MD_VIDEO_` | Same pattern as audio with `MD_VIDEO_*` (defaults: larger upload/sync caps, port **8012**) |
+| YouTube API | `MD_YOUTUBE_` | `MD_YOUTUBE_JOB_TTL_SECONDS`, `MD_YOUTUBE_TEMP_DIR`, `MD_YOUTUBE_CORS_ORIGINS`, `MD_YOUTUBE_API_HOST`, `MD_YOUTUBE_API_PORT` (default **8013**); optional `MD_YOUTUBE_YTDLP` path for audio fallback |
 
 Exact variable names match the `ApiSettings` / helper functions in each `api/settings` or `api/app` module.
 
@@ -503,8 +554,12 @@ Two usage patterns:
 | PPTX | `python -m md_generator.ppt.api.mcp_server` (see module docstring for flags) |
 | Image | `python -m md_generator.image.api.mcp_server` (see module for CLI) |
 | URL / HTML | `python -m md_generator.url.api.mcp_server` / `--transport sse` / `--transport streamable-http` |
+| Playwright / SPA | `md-playwright-mcp` or `python -m md_generator.playwright.api.mcp_server` / `--transport sse` / `--transport streamable-http` |
 | Audio | `md-audio-mcp` or `python -m md_generator.media.audio.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
 | Video | `md-video-mcp` or `python -m md_generator.media.video.api.mcp_server` — same transports |
+| YouTube | `md-youtube-mcp` or `python -m md_generator.media.youtube.api.mcp_server` — same transports |
+| Database metadata | `md-db-mcp` or `python -m md_generator.db.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
+| Graph (Neo4j / NetworkX) | `md-graph-mcp` or `python -m md_generator.graph.api.mcp_server` — `--transport stdio` (default), `sse`, `streamable-http` |
 
 **Word** and **XLSX** also ship a small runner script in the repo:
 
@@ -529,7 +584,7 @@ pip install -e ".[dev,all]"   # or a smaller subset of extras
 python -m pytest
 ```
 
-Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/tests/`); `pyproject.toml` configures `pythonpath = ["src"]` so `md_generator` resolves without a separate `PYTHONPATH`.
+Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/tests/`) and **`graph-to-md/tests/`**; `pyproject.toml` configures `pythonpath = ["src"]` so `md_generator` resolves without a separate `PYTHONPATH`.
 
 ---
 
@@ -539,7 +594,7 @@ Tests live under each legacy folder’s `tests/` directory (e.g. `pdf-to-md/test
 |------|------|
 | `LICENSE` | MIT license text |
 | `CODE_OF_CONDUCT.md` | [Contributor Covenant](https://www.contributor-covenant.org/) 2.1 |
-| `src/md_generator/` | **Library source** (all formats + `api` subpackages); **audio/video** under [`media/audio/`](src/md_generator/media/audio/) and [`media/video/`](src/md_generator/media/video/) |
+| `src/md_generator/` | **Library source** (all formats + `api` subpackages); **audio/video** under [`media/audio/`](src/md_generator/media/audio/) and [`media/video/`](src/md_generator/media/video/); **graph-to-md** under [`graph/`](src/md_generator/graph/) |
 | `pyproject.toml` | Packaging, extras, CLI entry points, pytest |
 | `*-to-md/` | **Docs, tests, fixtures**, thin `converter.py` shims, some `run.py` helpers |
 | `README.md` | This document |

{mdengine-0.3.0 → mdengine-0.5.0}/pyproject.toml

@@ -4,14 +4,14 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "mdengine"
-version = "0.3.0"
+version = "0.5.0"
 description = "Convert PDF, Office, images, audio, video, text/JSON/XML, ZIP archives, and web URLs to Markdown."
 readme = "README.md"
 requires-python = ">=3.10"
 license = "MIT"
 license-files = ["LICENSE"]
 authors = [{ name = "mdengine contributors" }]
-keywords = ["markdown", "pdf", "docx", "pptx", "xlsx", "ocr", "zip", "url", "html"]
+keywords = ["markdown", "pdf", "docx", "pptx", "xlsx", "ocr", "zip", "url", "html", "youtube", "playwright", "database"]
 classifiers = [
   "Programming Language :: Python :: 3",
   "Programming Language :: Python :: 3 :: Only",
@@ -76,6 +76,36 @@ url-full = [
 audio = ["openai-whisper>=20231117", "imageio-ffmpeg>=0.5.1"]
 # Same ML stack as audio; ships a bundled ``ffmpeg`` binary when the system has none.
 video = ["openai-whisper>=20231117", "imageio-ffmpeg>=0.5.1"]
+youtube = [
+  "youtube-transcript-api>=0.6.0",
+  "httpx>=0.27.0",
+  "beautifulsoup4>=4.12.0",
+  "lxml>=5.0.0",
+]
+# Playwright-rendered SPA → Markdown (install browsers: playwright install chromium).
+playwright = [
+  "playwright>=1.49.0",
+  "httpx>=0.27.0",
+  "beautifulsoup4>=4.12.0",
+  "lxml>=5.0.0",
+  "markdownify>=0.14.0",
+  "readability-lxml>=0.8.1",
+  "Pillow>=10.0.0",
+]
+db = [
+  "sqlalchemy>=2.0.0",
+  "pyyaml>=6.0.0",
+  "psycopg2-binary>=2.9.9",
+  "pymysql>=1.1.0",
+  "oracledb>=2.0.0",
+  "pymongo>=4.6.0",
+  "mermaid-py>=0.8.0",
+]
+graph = [
+  "networkx>=3.2.0",
+  "neo4j>=5.14.0",
+  "pyyaml>=6.0.0",
+]
 api = [
   "fastapi>=0.115.0",
   "uvicorn[standard]>=0.32.0",
@@ -87,9 +117,15 @@ mcp = ["mcp>=1.2.0", "fastmcp>=2.3.0"]
 dev = [
   "pytest>=8.0.0",
   "httpx>=0.27.0",
+  "beautifulsoup4>=4.12.0",
+  "lxml>=5.0.0",
+  "youtube-transcript-api>=0.6.0",
   "mdengine[api]",
   "mdengine[mcp]",
   "mdengine[url]",
+  "mdengine[playwright]",
+  "mdengine[db]",
+  "mdengine[graph]",
 ]
 all = [
   "pymupdf>=1.24.0",
@@ -116,6 +152,7 @@ all = [
   "beautifulsoup4>=4.12.0",
   "lxml_html_clean>=0.4.0",
   "readability-lxml>=0.8.1",
+  "youtube-transcript-api>=0.6.0",
 ]
 
 [project.urls]
@@ -138,10 +175,27 @@ md-audio-api = "md_generator.media.audio.api.run:main"
 md-video-api = "md_generator.media.video.api.run:main"
 md-audio-mcp = "md_generator.media.audio.api.mcp_server:main"
 md-video-mcp = "md_generator.media.video.api.mcp_server:main"
+md-youtube = "md_generator.media.youtube.converter:main"
+md-youtube-api = "md_generator.media.youtube.api.run:main"
+md-youtube-mcp = "md_generator.media.youtube.api.mcp_server:main"
+md-playwright = "md_generator.playwright.cli:main"
+md-playwright-api = "md_generator.playwright.api.run:main"
+md-playwright-mcp = "md_generator.playwright.api.mcp_server:main"
+md-db = "md_generator.db.cli.main:main"
+md-db-api = "md_generator.db.api.run:main"
+md-db-mcp = "md_generator.db.api.mcp_server:main"
+md-graph = "md_generator.graph.cli.main:main"
+md-graph-api = "md_generator.graph.api.run:main"
+md-graph-mcp = "md_generator.graph.api.mcp_server:main"
+mdengine = "md_generator.engine_cli:main"
 
 [tool.setuptools.packages.find]
 where = ["src"]
 
+[tool.setuptools.package-data]
+"md_generator.db.config" = ["*.yaml"]
+"md_generator.graph.config" = ["*.yaml"]
+
 [tool.pytest.ini_options]
 pythonpath = ["src"]
 testpaths = [
@@ -155,5 +209,9 @@ testpaths = [
   "url-to-md/tests",
   "audio-to-md/tests",
   "video-to-md/tests",
+  "youtube-to-md/tests",
+  "playwright-to-md/tests",
+  "db-to-md/tests",
+  "graph-to-md/tests",
 ]
 markers = ["integration: optional dependency or slower checks"]