pdfmd 0.1.0__py3-none-any.whl

pdfmd/__init__.py

@@ -0,0 +1 @@
+__version__ = "0.1.0"

pdfmd/__main__.py

@@ -0,0 +1,4 @@
+from pdf2md.cli import main
+import sys
+
+sys.exit(main())

pdfmd/cli.py

@@ -0,0 +1,95 @@
+"""pdf2md - Convert PDF files to Markdown using pymupdf4llm."""
+
+import argparse
+import sys
+from pathlib import Path
+
+import pymupdf4llm
+
+
+def parse_pages(spec: str) -> list[int]:
+    """Parse a page spec like '1,3,5-8' into a 0-indexed list."""
+    pages = set()
+    for part in spec.split(","):
+        part = part.strip()
+        if "-" in part:
+            start, end = part.split("-", 1)
+            pages.update(range(int(start) - 1, int(end)))
+        else:
+            pages.add(int(part) - 1)
+    return sorted(pages)
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser(
+        description="Convert a PDF to Markdown.",
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter,
+    )
+    ap.add_argument("input", type=Path, help="input PDF file")
+    ap.add_argument(
+        "-o", "--output", type=Path,
+        help="output .md file (default: input with .md extension, '-' for stdout)",
+    )
+    ap.add_argument(
+        "-p", "--pages", type=str,
+        help="pages to extract, e.g. '1,3,5-8' (1-indexed). default: all",
+    )
+    ap.add_argument(
+        "--images", action="store_true",
+        help="extract embedded images alongside the markdown",
+    )
+    ap.add_argument(
+        "--image-dir", type=Path, default=Path("images"),
+        help="directory for extracted images",
+    )
+    ap.add_argument(
+        "--image-format", default="png", choices=["png", "jpg"],
+        help="image format",
+    )
+    ap.add_argument(
+        "--dpi", type=int, default=150,
+        help="DPI for rendered/extracted images",
+    )
+    ap.add_argument(
+        "--table-strategy", default="lines", choices=["lines", "lines_strict"],
+        help="table detection strategy",
+    )
+    ap.add_argument(
+        "-q", "--quiet", action="store_true",
+        help="suppress progress output",
+    )
+    args = ap.parse_args()
+
+    if not args.input.is_file():
+        sys.exit(f"error: {args.input} not found")
+
+    kwargs = {
+        "table_strategy": args.table_strategy,
+        "dpi": args.dpi,
+        "show_progress": not args.quiet,
+    }
+    if args.pages:
+        try:
+            kwargs["pages"] = parse_pages(args.pages)
+        except ValueError:
+            sys.exit(f"error: invalid page spec: {args.pages!r}")
+    if args.images:
+        args.image_dir.mkdir(parents=True, exist_ok=True)
+        kwargs["write_images"] = True
+        kwargs["image_path"] = str(args.image_dir)
+        kwargs["image_format"] = args.image_format
+
+    try:
+        md = pymupdf4llm.to_markdown(str(args.input), **kwargs)
+    except Exception as e:
+        sys.exit(f"error: conversion failed: {e}")
+
+    if args.output and str(args.output) == "-":
+        sys.stdout.write(md)
+    else:
+        out = args.output or args.input.with_suffix(".md")
+        out.write_text(md, encoding="utf-8")
+        if not args.quiet:
+            print(f"wrote {out} ({len(md):,} chars)", file=sys.stderr)
+
+    return 0

pdfmd-0.1.0.dist-info/METADATA

@@ -0,0 +1,40 @@
+Metadata-Version: 2.4
+Name: pdfmd
+Version: 0.1.0
+Summary: Convert PDF files to Markdown using pymupdf4llm
+Requires-Python: >=3.10
+Requires-Dist: pymupdf4llm
+Description-Content-Type: text/markdown
+
+# pdf2md
+
+Convert PDF files to Markdown using [pymupdf4llm](https://github.com/pymupdf/RAG).
+
+## Installation
+
+```bash
+# With uv
+uv sync
+
+# Or with pip
+pip install .
+```
+
+## Usage
+
+```bash
+pdf2md input.pdf                          # writes input.md
+pdf2md input.pdf -o output.md             # explicit output path
+pdf2md input.pdf -o -                     # stdout
+pdf2md input.pdf -p "1,3,5-8"            # specific pages (1-indexed)
+pdf2md input.pdf --images --dpi 200       # extract images
+```
+
+Run `pdf2md --help` for all options.
+
+## Build & Publish
+
+```bash
+uv build      # creates dist/*.whl and dist/*.tar.gz
+uv publish    # publish to PyPI
+```

pdfmd-0.1.0.dist-info/RECORD

@@ -0,0 +1,7 @@
+pdfmd/__init__.py,sha256=kUR5RAFc7HCeiqdlX36dZOHkUI5wI6V_43RpEcD8b-0,22
+pdfmd/__main__.py,sha256=EurL_Wa0CJy1bMx4Ha0tsqLBcnCY-Gr8p7peeKGH408,57
+pdfmd/cli.py,sha256=DnoY46QqpWUM7zejCCiyK4-MjFZJhMdRCRnIaw-f2-s,2913
+pdfmd-0.1.0.dist-info/METADATA,sha256=gnzFYsyuH6oURDtPV5I9ra4r6mHtp1zL4cLWtmU4Tck,852
+pdfmd-0.1.0.dist-info/WHEEL,sha256=QccIxa26bgl1E6uMy58deGWi-0aeIkkangHcxk2kWfw,87
+pdfmd-0.1.0.dist-info/entry_points.txt,sha256=EJ-1aBfge6N41zjl-ks12NE7H8LDd1FZhETWfhb98_Y,41
+pdfmd-0.1.0.dist-info/RECORD,,

pdfmd-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.29.0
+Root-Is-Purelib: true
+Tag: py3-none-any

pdfmd-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+pdfmd = pdfmd.cli:main