Clean up README.md

* feat: issue where inherited function from `markdownify.MarkdownConverter` doesn't have `current_tags` leading to error using `kwargs`, also set default value for `convert_as_inline`

README.md

@@ -87,42 +87,6 @@ print(result.text_content)
 docker build -t markitdown:latest .
 docker run --rm -i markitdown:latest < ~/your-file.pdf > output.md
 ```
-<details>
-    
-<summary>Batch Processing Multiple Files</summary>
-
-This example shows how to convert multiple files to markdown format in a single run. The script processes all supported files in a directory and creates corresponding markdown files.
-
-
-```python convert.py
-from markitdown import MarkItDown
-from openai import OpenAI
-import os
-client = OpenAI(api_key="your-api-key-here")
-md = MarkItDown(llm_client=client, llm_model="gpt-4o-2024-11-20")
-supported_extensions = ('.pptx', '.docx', '.pdf', '.jpg', '.jpeg', '.png')
-files_to_convert = [f for f in os.listdir('.') if f.lower().endswith(supported_extensions)]
-for file in files_to_convert:
-    print(f"\nConverting {file}...")
-    try:
-        md_file = os.path.splitext(file)[0] + '.md'
-        result = md.convert(file)
-        with open(md_file, 'w') as f:
-            f.write(result.text_content)
-        
-        print(f"Successfully converted {file} to {md_file}")
-    except Exception as e:
-        print(f"Error converting {file}: {str(e)}")
-
-print("\nAll conversions completed!")
-```
-2. Place the script in the same directory as your files
-3. Install required packages: like openai
-4. Run script ```bash python convert.py ```
-
-Note that original files will remain unchanged and new markdown files are created with the same base name.
-
-</details>
    
 ## Contributing
 

src/markitdown/__about__.py

@@ -1,4 +1,4 @@
 # SPDX-FileCopyrightText: 2024-present Adam Fourney <adamfo@microsoft.com>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.1a3"
+__version__ = "0.0.1"

src/markitdown/__main__.py

@@ -3,6 +3,7 @@
 # SPDX-License-Identifier: MIT
 import argparse
 import sys
+import shutil
 from textwrap import dedent
 from .__about__ import __version__
 from ._markitdown import MarkItDown, DocumentConverterResult
@@ -74,6 +75,8 @@ def main():
     parser.add_argument("filename", nargs="?")
     args = parser.parse_args()
 
+    which_exiftool = shutil.which("exiftool")
+
     if args.use_docintel:
         if args.endpoint is None:
             raise ValueError(
@@ -81,9 +84,11 @@ def main():
             )
         elif args.filename is None:
             raise ValueError("Filename is required when using Document Intelligence.")
-        markitdown = MarkItDown(docintel_endpoint=args.endpoint)
+        markitdown = MarkItDown(
+            exiftool_path=which_exiftool, docintel_endpoint=args.endpoint
+        )
     else:
-        markitdown = MarkItDown()
+        markitdown = MarkItDown(exiftool_path=which_exiftool)
 
     if args.filename is None:
         result = markitdown.convert_stream(sys.stdin.buffer)

src/markitdown/_markitdown.py

@@ -91,7 +91,14 @@ class _CustomMarkdownify(markdownify.MarkdownConverter):
         # Explicitly cast options to the expected type if necessary
         super().__init__(**options)
 
-    def convert_hn(self, n: int, el: Any, text: str, convert_as_inline: bool) -> str:
+    def convert_hn(
+        self,
+        n: int,
+        el: Any,
+        text: str,
+        convert_as_inline: Optional[bool] = False,
+        **kwargs,
+    ) -> str:
         """Same as usual, but be sure to start with a new line"""
         if not convert_as_inline:
             if not re.search(r"^\n", text):
@@ -99,7 +106,9 @@ class _CustomMarkdownify(markdownify.MarkdownConverter):
 
         return super().convert_hn(n, el, text, convert_as_inline)  # type: ignore
 
-    def convert_a(self, el: Any, text: str, convert_as_inline: bool):
+    def convert_a(
+        self, el: Any, text: str, convert_as_inline: Optional[bool] = False, **kwargs
+    ):
         """Same as usual converter, but removes Javascript links and escapes URIs."""
         prefix, suffix, text = markdownify.chomp(text)  # type: ignore
         if not text:
@@ -135,7 +144,9 @@ class _CustomMarkdownify(markdownify.MarkdownConverter):
             else text
         )
 
-    def convert_img(self, el: Any, text: str, convert_as_inline: bool) -> str:
+    def convert_img(
+        self, el: Any, text: str, convert_as_inline: Optional[bool] = False, **kwargs
+    ) -> str:
         """Same as usual converter, but removes data URIs"""
 
         alt = el.attrs.get("alt", None) or ""
@@ -1752,6 +1763,8 @@ class MarkItDown:
         ext = ext.strip()
         if ext == "":
             return
+        if ext in extensions:
+            return
         # if ext not in extensions:
         extensions.append(ext)