epub2md 0.1.0__tar.gz

epub2md-0.1.0/.gitignore

@@ -0,0 +1,10 @@
+# Python-generated files
+__pycache__/
+*.py[oc]
+build/
+dist/
+wheels/
+*.egg-info
+
+# Virtual environments
+.venv

epub2md-0.1.0/.python-version

@@ -0,0 +1 @@
+3.13

epub2md-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2024
+
+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.

epub2md-0.1.0/PKG-INFO

@@ -0,0 +1,38 @@
+Metadata-Version: 2.4
+Name: epub2md
+Version: 0.1.0
+Summary: Convert EPUB to clean Markdown chapters
+Project-URL: Repository, https://github.com/mefengl/epub2md
+License-File: LICENSE
+Requires-Python: >=3.8
+Description-Content-Type: text/markdown
+
+# epub2md
+
+Convert EPUB to clean Markdown chapters.
+
+## Install
+
+```bash
+pip install epub2md
+```
+
+## Usage
+
+```bash
+epub2md book.epub
+epub2md book.epub my-chapters
+```
+
+Output:
+- `chapters/` - Markdown files
+- `chapters-media/` - Images
+
+## Requirements
+
+- Python 3.8+
+- [pandoc](https://pandoc.org/installing.html)
+
+## License
+
+MIT

epub2md-0.1.0/README.md

@@ -0,0 +1,29 @@
+# epub2md
+
+Convert EPUB to clean Markdown chapters.
+
+## Install
+
+```bash
+pip install epub2md
+```
+
+## Usage
+
+```bash
+epub2md book.epub
+epub2md book.epub my-chapters
+```
+
+Output:
+- `chapters/` - Markdown files
+- `chapters-media/` - Images
+
+## Requirements
+
+- Python 3.8+
+- [pandoc](https://pandoc.org/installing.html)
+
+## License
+
+MIT

epub2md-0.1.0/epub2md.py

@@ -0,0 +1,77 @@
+#!/usr/bin/env python3
+import sys, os, re, subprocess, tempfile, shutil
+import xml.etree.ElementTree as ET
+from pathlib import Path
+
+LUA = """
+function Div(el) return el.content end
+function Span(el) return el.content end
+function Para(el)
+  if el.content and #el.content==1 and el.content[1].t=='Str' and el.content[1].text=='\\\\' then return {} end
+  return el
+end
+function Plain(el)
+  if el.content and #el.content==1 and el.content[1].t=='Str' and el.content[1].text=='\\\\' then return {} end
+  return el
+end
+function Image(el) el.classes={} el.attributes={} return el end
+"""
+
+def main():
+    if len(sys.argv) < 2 or sys.argv[1] in ['-h', '--help']:
+        print("epub2md - Convert EPUB to Markdown\n\nUsage: epub2md <book.epub> [outdir]\n\nOutput:\n  <outdir>/: Markdown chapters\n  <outdir>-media/: Images")
+        sys.exit(0)
+    
+    epub = Path(sys.argv[1]).resolve()
+    out = sys.argv[2] if len(sys.argv) > 2 else 'chapters'
+    
+    if not epub.exists(): sys.exit(f"Error: {epub} not found")
+    if not shutil.which('pandoc'): sys.exit("Error: pandoc not found. Install: brew install pandoc")
+    
+    print(f"Converting {epub.name}...")
+    outdir = Path(out).resolve()
+    media = Path(f"{out}-media").resolve()
+    outdir.mkdir(exist_ok=True)
+    
+    with tempfile.TemporaryDirectory() as tmp:
+        t = Path(tmp)
+        subprocess.run(['unzip', '-q', str(epub), '-d', str(t)], check=True)
+        (t/'f.lua').write_text(LUA)
+        
+        toc = t/'toc.ncx'
+        if not toc.exists(): sys.exit("Error: toc.ncx not found")
+        
+        tree = ET.parse(toc)
+        ns = {'n': 'http://www.daisy.org/z3986/2005/ncx/'}
+        
+        n = 0
+        for nav in tree.findall('.//n:navPoint', ns):
+            te = nav.find('.//n:text', ns)
+            ce = nav.find('.//n:content', ns)
+            if te is None or ce is None: continue
+            
+            title = te.text or 'untitled'
+            src = ce.get('src', '').split('#')[0]
+            if not src.endswith(('.xhtml', '.html')): continue
+            if not (t/src).exists(): continue
+            
+            n += 1
+            safe = re.sub(r'[^a-z0-9]+', '-', title.lower()).strip('-') or 'untitled'
+            name = outdir / f"{n:02d}-{safe}.md"
+            
+            r = subprocess.run([
+                'pandoc', src, '-f', 'html', '-t', 'gfm', '--wrap=none',
+                '--lua-filter', 'f.lua', '--extract-media', str(media), '-o', str(name)
+            ], cwd=t, capture_output=True)
+            
+            if r.returncode == 0:
+                print(f"✓ {n:02d} {title}")
+            else:
+                print(f"✗ {title}")
+    
+    print(f"\nDone! {n} chapters → {out}/")
+    if media.exists() and list(media.iterdir()):
+        print(f"Images → {media.name}/")
+
+if __name__ == '__main__':
+    main()

epub2md-0.1.0/pyproject.toml

@@ -0,0 +1,17 @@
+[project]
+name = "epub2md"
+version = "0.1.0"
+description = "Convert EPUB to clean Markdown chapters"
+readme = "README.md"
+requires-python = ">=3.8"
+dependencies = []
+
+[project.scripts]
+epub2md = "epub2md:main"
+
+[project.urls]
+Repository = "https://github.com/mefengl/epub2md"
+
+[build-system]
+requires = ["hatchling"]
+build-backend = "hatchling.build"

epub2md-0.1.0/uv.lock

@@ -0,0 +1,8 @@
+version = 1
+revision = 3
+requires-python = ">=3.8"
+
+[[package]]
+name = "epub2md"
+version = "0.1.0"
+source = { editable = "." }