multi-convert 0.1.0__py3-none-any.whl

multi_convert/__init__.py

@@ -0,0 +1,5 @@
+"""Convert documents between Markdown, HTML, and PDF."""
+
+from .core import FORMATS, ConversionError, convert
+
+__all__ = ["FORMATS", "ConversionError", "convert"]

multi_convert/cli.py

@@ -0,0 +1,23 @@
+"""Command line interface for multi_convert."""
+
+import argparse
+from pathlib import Path
+
+from .core import ConversionError, convert
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        prog="multi-convert",
+        description="Convert documents between Markdown, HTML, and PDF.",
+    )
+    parser.add_argument("input", type=Path, help="File to convert")
+    parser.add_argument("output", type=Path, help="Destination file; the format is taken from its extension")
+    args = parser.parse_args()
+
+    try:
+        convert(args.input, args.output)
+    except ConversionError as error:
+        parser.exit(1, f"error: {error}\n")
+
+    print(f"Converted {args.input} -> {args.output}")

multi_convert/core.py

@@ -0,0 +1,90 @@
+"""Document conversion between Markdown, HTML, and PDF."""
+
+from pathlib import Path
+
+import html2text
+import markdown
+from markdown_pdf import MarkdownPdf, Section
+from pypdf import PdfReader
+
+FORMATS = ("md", "html", "pdf")
+
+_HTML_HEAD = """<!DOCTYPE html>
+<html>
+<head>
+<meta charset="utf-8">
+<style>
+  body { font-family: -apple-system, sans-serif; line-height: 1.6; max-width: 800px; margin: 2rem auto; padding: 0 1rem; }
+  code { background: #f4f4f4; padding: 2px 4px; border-radius: 4px; }
+  pre { background: #f4f4f4; padding: 1rem; overflow-x: auto; }
+  table { border-collapse: collapse; width: 100%; }
+  th, td { border: 1px solid #ddd; padding: 8px; text-align: left; }
+</style>
+</head>
+<body>
+"""
+
+_HTML_TAIL = """
+</body>
+</html>
+"""
+
+
+class ConversionError(Exception):
+    """Raised when a conversion cannot be performed."""
+
+
+def _format_of(path):
+    fmt = path.suffix.lower().lstrip(".")
+    if fmt not in FORMATS:
+        raise ConversionError(f"Unsupported format {path.suffix!r}; expected one of {', '.join(FORMATS)}")
+    return fmt
+
+
+def _read_md(path):
+    return path.read_text(encoding="utf-8")
+
+
+def _read_html(path):
+    handler = html2text.HTML2Text()
+    handler.ignore_links = False
+    return handler.handle(path.read_text(encoding="utf-8"))
+
+
+def _read_pdf(path):
+    pages = (page.extract_text() for page in PdfReader(path).pages)
+    return "\n\n".join(page for page in pages if page)
+
+
+def _write_md(content, path):
+    path.write_text(content, encoding="utf-8")
+
+
+def _write_html(content, path):
+    body = markdown.markdown(content, extensions=["tables", "fenced_code"])
+    path.write_text(_HTML_HEAD + body + _HTML_TAIL, encoding="utf-8")
+
+
+def _write_pdf(content, path):
+    pdf = MarkdownPdf(toc_level=2)
+    pdf.add_section(Section(content))
+    pdf.save(str(path))
+
+
+_READERS = {"md": _read_md, "html": _read_html, "pdf": _read_pdf}
+_WRITERS = {"md": _write_md, "html": _write_html, "pdf": _write_pdf}
+
+
+def convert(source, target):
+    """Convert ``source`` to ``target``, inferring both formats from file extensions.
+
+    Every conversion routes through Markdown as an intermediate representation, so
+    reading a PDF yields extracted plain text rather than structured markup.
+    """
+    source, target = Path(source), Path(target)
+    if not source.is_file():
+        raise ConversionError(f"Input file not found: {source}")
+
+    reader, writer = _READERS[_format_of(source)], _WRITERS[_format_of(target)]
+    writer(reader(source), target)
+    return target

multi_convert-0.1.0.dist-info/METADATA

@@ -0,0 +1,74 @@
+Metadata-Version: 2.4
+Name: multi_convert
+Version: 0.1.0
+Summary: A python package for converting multiple document formats
+Home-page: https://github.com/tasteslikecobrachicken/multi_convert
+Author: Cobra Chicken
+Author-email: Cobra Chicken <tasteslikecobrachicken@gmail.com>
+Project-URL: Homepage, https://github.com/tasteslikecobrachicken/multi_convert
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: markdown>=3.5
+Requires-Dist: markdown-pdf>=1.4
+Requires-Dist: html2text>=2024.2.26
+Requires-Dist: pypdf>=4.0
+Provides-Extra: test
+Requires-Dist: pytest>=8; extra == "test"
+Dynamic: author
+Dynamic: home-page
+Dynamic: license-file
+Dynamic: requires-python
+
+# multi_convert
+
+Python package for converting document formats between Markdown, HTML, and PDF.
+
+## Installation
+
+```bash
+pip install multi_convert
+```
+
+Requires Python 3.10 or newer.
+
+## Usage
+
+### Library
+
+```python
+from multi_convert import convert
+
+convert("notes.md", "notes.pdf")
+convert("page.html", "page.md")
+```
+
+Both formats are inferred from the file extensions. `convert` returns the output
+path and raises `ConversionError` if the input is missing or either extension is
+not one of `.md`, `.html`, or `.pdf`.
+
+### Command line
+
+```bash
+multi-convert notes.md notes.pdf
+```
+
+## Supported conversions
+
+| From | To |
+| --- | --- |
+| Markdown | HTML, PDF |
+| HTML | Markdown, PDF |
+| PDF | Markdown, HTML |
+
+Every conversion routes through Markdown as an intermediate representation.
+Because PDF text extraction recovers plain text only, converting *from* PDF
+loses headings, tables, and emphasis; the other five directions preserve
+structure.
+
+## License
+
+MIT

multi_convert-0.1.0.dist-info/RECORD

@@ -0,0 +1,9 @@
+multi_convert/__init__.py,sha256=nGxvTj9Tj9GQ7PtG4SIO1nVFJ0pSsc5dnqHVl432o6c,163
+multi_convert/cli.py,sha256=rMe6E8kid5uKCW1umG_g1qpWcrBMyuMp6cVeuHZtnm0,692
+multi_convert/core.py,sha256=y5Tsf-HzsjrT1A-C-5ci7hTvVh6aHvSycDboRh9Zqwc,2508
+multi_convert-0.1.0.dist-info/licenses/LICENSE,sha256=vxvQmJ-9FHlKlumoI5ptuBf6EwR6w87UkfIq_jJ5_0Y,1073
+multi_convert-0.1.0.dist-info/METADATA,sha256=hJ0FYhqiViFEvBP1KOreKPq_Vys9ci4Zg6SE30shVvI,1829
+multi_convert-0.1.0.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+multi_convert-0.1.0.dist-info/entry_points.txt,sha256=HPVT6gV0xkqPluiAnu6ut6K7hxRNXPfyH6CJ-elPT7I,57
+multi_convert-0.1.0.dist-info/top_level.txt,sha256=56Vm8Ow94pRFPkINmKgixtk0tVQr__x5EvgEJjdM-94,14
+multi_convert-0.1.0.dist-info/RECORD,,

multi_convert-0.1.0.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

multi_convert-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+multi-convert = multi_convert.cli:main

multi_convert-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) [2026] [Cobra Chicken]
+
+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.

multi_convert-0.1.0.dist-info/top_level.txt

@@ -0,0 +1 @@
+multi_convert