doc-to-md-cli 0.1.0__py3-none-any.whl → 0.1.1__py3-none-any.whl

doc2md/__init__.py

@@ -0,0 +1,84 @@
+"""
+doc-to-md-cli: Convert DOCX files to Markdown using Playwright
+"""
+
+from pathlib import Path
+from playwright.sync_api import sync_playwright
+
+
+__version__ = "0.1.1"
+
+
+def convert_docx_to_md(
+    input_path: str | Path,
+    output_dir: str | Path = "./md",
+    headless: bool = True,
+) -> list[Path]:
+    """
+    Convert DOCX file(s) to Markdown.
+
+    Args:
+        input_path: Path to a DOCX file or directory containing DOCX files
+        output_dir: Directory where Markdown files will be saved
+        headless: Whether to run browser in headless mode
+
+    Returns:
+        List of paths to the generated Markdown files
+
+    Raises:
+        FileNotFoundError: If input_path doesn't exist
+        ValueError: If no DOCX files found
+
+    Example:
+        >>> from doc2md import convert_docx_to_md
+        >>> convert_docx_to_md("document.docx", "output")
+        ['output/document.md']
+    """
+    input_path = Path(input_path).expanduser()
+    output_dir = Path(output_dir).expanduser()
+    output_dir.mkdir(parents=True, exist_ok=True)
+
+    if not input_path.exists():
+        raise FileNotFoundError(f"Path not found: {input_path}")
+
+    # Determine files to convert
+    if input_path.is_file():
+        if input_path.suffix.lower() != ".docx":
+            raise ValueError("Input file must be a .docx file")
+        files = [input_path]
+    else:
+        files = list(input_path.glob("*.docx"))
+        if not files:
+            raise ValueError("No .docx files found in directory")
+
+    converted_files = []
+
+    with sync_playwright() as p:
+        browser = p.chromium.launch(headless=headless)
+        context = browser.new_context(
+            permissions=["clipboard-read", "clipboard-write"]
+        )
+        page = context.new_page()
+        page.goto("https://word2md.com/")
+
+        for file_path in files:
+            with page.expect_file_chooser() as fc_info:
+                page.click('input[type="file"]')
+            file_chooser = fc_info.value
+            file_chooser.set_files(str(file_path))
+
+            page.wait_for_selector("#copy-button", state="visible")
+            page.click("#copy-button")
+
+            md_content = page.evaluate("navigator.clipboard.readText()")
+
+            out_file = output_dir / (file_path.stem + ".md")
+            out_file.write_text(md_content, encoding="utf-8")
+            converted_files.append(out_file)
+
+        browser.close()
+
+    return converted_files
+
+
+__all__ = ["convert_docx_to_md", "__version__"]

doc2md/cli.py

@@ -1,44 +1,13 @@
 #!/usr/bin/env python3
 import argparse
 from pathlib import Path
-from playwright.sync_api import sync_playwright
 
-
-def convert_files(files, output_dir: Path, headless: bool):
-    output_dir.mkdir(parents=True, exist_ok=True)
-
-    with sync_playwright() as p:
-        browser = p.chromium.launch(headless=headless)
-        context = browser.new_context(
-            permissions=["clipboard-read", "clipboard-write"]
-        )
-        page = context.new_page()
-        page.goto("https://word2md.com/")
-
-        for file_path in files:
-            print(f"⬇ Converting: {file_path.name}")
-
-            with page.expect_file_chooser() as fc_info:
-                page.click('input[type="file"]')
-            file_chooser = fc_info.value
-            file_chooser.set_files(str(file_path))
-
-            page.wait_for_selector("#copy-button", state="visible")
-            page.click("#copy-button")
-
-            md_content = page.evaluate("navigator.clipboard.readText()")
-
-            out_file = output_dir / (file_path.stem + ".md")
-            out_file.write_text(md_content, encoding="utf-8")
-
-            print(f"✔ Saved: {out_file}")
-
-        browser.close()
+from . import convert_docx_to_md
 
 
 def main():
     parser = argparse.ArgumentParser(
-        prog="doc2md",
+        prog="doc-to-md",
         description="Convert DOCX files to Markdown using word2md.com"
     )
 
@@ -56,29 +25,29 @@ def main():
     parser.add_argument(
         "--headless",
         action="store_true",
-        help="Run browser in headless mode"
+        default=True,
+        help="Run browser in headless mode (default: True)"
     )
 
-    args = parser.parse_args()
-
-    input_path = Path(args.input).expanduser()
-    output_dir = Path(args.out).expanduser()
-
-    if not input_path.exists():
-        raise SystemExit(f"❌ Path not found: {input_path}")
-
-    # 🔥 NEW LOGIC
-    if input_path.is_file():
-        if input_path.suffix.lower() != ".docx":
-            raise SystemExit("❌ Input file must be a .docx file")
-        files = [input_path]
+    parser.add_argument(
+        "--no-headless",
+        action="store_false",
+        dest="headless",
+        help="Show browser window"
+    )
 
-    else:
-        files = list(input_path.glob("*.docx"))
-        if not files:
-            raise SystemExit("❌ No .docx files found")
+    args = parser.parse_args()
 
-    convert_files(files, output_dir, args.headless)
+    try:
+        converted_files = convert_docx_to_md(
+            args.input,
+            output_dir=args.out,
+            headless=args.headless,
+        )
+        for f in converted_files:
+            print(f"✔ Saved: {f}")
+    except (FileNotFoundError, ValueError) as e:
+        raise SystemExit(f"❌ {e}")
 
 
 if __name__ == "__main__":

{doc_to_md_cli-0.1.0.dist-info → doc_to_md_cli-0.1.1.dist-info}/METADATA

@@ -1,10 +1,10 @@
 Metadata-Version: 2.4
 Name: doc-to-md-cli
-Version: 0.1.0
+Version: 0.1.1
 Summary: Convert DOCX files to Markdown using Playwright
-Project-URL: Homepage, https://github.com/YOUR_USERNAME/doc2md-cli
-Project-URL: Repository, https://github.com/YOUR_USERNAME/doc2md-cli
-Project-URL: Issues, https://github.com/YOUR_USERNAME/doc2md-cli/issues
+Project-URL: Homepage, https://github.com/ebinesh25/doc2md-cli
+Project-URL: Repository, https://github.com/ebinesh25/doc2md-cli
+Project-URL: Issues, https://github.com/ebinesh25/doc2md-cli/issues
 License: MIT
 License-File: LICENSE
 Keywords: cli,converter,docx,markdown,word
@@ -26,7 +26,7 @@ Description-Content-Type: text/markdown
 
 # doc-to-md-cli
 
-A command-line tool to convert DOCX files to Markdown using Playwright automation.
+A Python library and CLI tool to convert DOCX files to Markdown using Playwright automation.
 
 ## Features
 
@@ -34,6 +34,7 @@ A command-line tool to convert DOCX files to Markdown using Playwright automatio
 - Batch processing support
 - Headless browser mode for automation
 - Clean Markdown output powered by word2md.com
+- Use as a CLI tool or import as a Python library
 
 ## Installation
 
@@ -41,43 +42,62 @@ A command-line tool to convert DOCX files to Markdown using Playwright automatio
 pip install doc-to-md-cli
 ```
 
+Install Playwright browser (required):
+
+```bash
+playwright install chromium
+```
+
 ## Usage
 
-### Convert a single file
+### CLI
+
+Convert a single file:
 
 ```bash
 doc-to-md document.docx
 ```
 
-### Convert to a specific output directory
+Convert to a specific output directory:
 
 ```bash
 doc-to-md document.docx --out ./output
 ```
 
-### Convert all DOCX files in a directory
+Convert all DOCX files in a directory:
 
 ```bash
 doc-to-md ./my-docs --out ./converted
 ```
 
-### Run in headless mode (no visible browser)
+Show browser window (non-headless mode):
 
 ```bash
-doc-to-md document.docx --headless
+doc-to-md document.docx --no-headless
 ```
 
-## Requirements
+### Python API
 
-- Python 3.8 or higher
-- Playwright (installed automatically)
+```python
+from doc2md import convert_docx_to_md
 
-After installing, you may need to install Playwright browsers:
+# Convert a single file
+files = convert_docx_to_md("document.docx", "output")
+print(files)  # ['output/document.md']
 
-```bash
-playwright install chromium
+# Convert all files in a directory
+files = convert_docx_to_md("./my-docs", "output")
+# ['output/file1.md', 'output/file2.md', ...]
+
+# Convert with browser visible
+files = convert_docx_to_md("document.docx", headless=False)
 ```
 
+## Requirements
+
+- Python 3.8 or higher
+- Playwright (installed automatically)
+
 ## License
 
 MIT License - see LICENSE file for details.

doc_to_md_cli-0.1.1.dist-info/RECORD

@@ -0,0 +1,7 @@
+doc2md/__init__.py,sha256=ZzsCLzhzHV0fKtIVNFNHT0dFPGzXeNgLSIBnUzwc55g,2478
+doc2md/cli.py,sha256=y8PNOErH6cVm_4zOJgzlLj26Wo5Riue2u4dM735VN_I,1183
+doc_to_md_cli-0.1.1.dist-info/METADATA,sha256=3EqwwL0WYKKUwqwbMZne03PqMgMdzAnQ2PzCmfldjwI,2447
+doc_to_md_cli-0.1.1.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
+doc_to_md_cli-0.1.1.dist-info/entry_points.txt,sha256=YyynNzAcKo_GQg_JVs7gKf3JKJvjf1Tg6HPPmRhzBvc,46
+doc_to_md_cli-0.1.1.dist-info/licenses/LICENSE,sha256=iDvN_LXmDQT00XUgh0zJHPIWQqWpwd-YXOhR_7WD7uQ,1063
+doc_to_md_cli-0.1.1.dist-info/RECORD,,

{doc_to_md_cli-0.1.0.dist-info → doc_to_md_cli-0.1.1.dist-info}/licenses/LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2025 [Your Name]
+Copyright (c) 2025Ebinesh
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

doc_to_md_cli-0.1.0.dist-info/RECORD

@@ -1,7 +0,0 @@
-doc2md/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-doc2md/cli.py,sha256=GLfepA1qHLdPb1Jjl630srrDAAGL6NW86MW0S5ihp2s,2319
-doc_to_md_cli-0.1.0.dist-info/METADATA,sha256=rhWZqq_MsfmkGaWF5YNEUBuy8RLoTUF_s7VDYqLXLys,2014
-doc_to_md_cli-0.1.0.dist-info/WHEEL,sha256=WLgqFyCfm_KASv4WHyYy0P3pM_m7J5L9k2skdKLirC8,87
-doc_to_md_cli-0.1.0.dist-info/entry_points.txt,sha256=YyynNzAcKo_GQg_JVs7gKf3JKJvjf1Tg6HPPmRhzBvc,46
-doc_to_md_cli-0.1.0.dist-info/licenses/LICENSE,sha256=mnxgbhYn7K71v_xzsVUFRVeXIMYebeqdmubgALMnuIg,1068
-doc_to_md_cli-0.1.0.dist-info/RECORD,,