Added missing comma.

src/markitdown/__about__.py

@@ -1,4 +1,4 @@
 # SPDX-FileCopyrightText: 2024-present Adam Fourney <adamfo@microsoft.com>
 #
 # SPDX-License-Identifier: MIT
-__version__ = "0.0.1"
+__version__ = "0.0.2"

src/markitdown/__main__.py

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

src/markitdown/_markitdown.py

@@ -17,7 +17,7 @@ from xml.dom import minidom
 from typing import Any, Dict, List, Optional, Union
 from pathlib import Path
 from urllib.parse import parse_qs, quote, unquote, urlparse, urlunparse
-from warnings import warn, resetwarnings, catch_warnings
+from warnings import warn, filterwarnings
 
 import mammoth
 import markdownify
@@ -51,21 +51,14 @@ mimetypes.add_type("text/csv", ".csv")
 
 # Optional Transcription support
 IS_AUDIO_TRANSCRIPTION_CAPABLE = False
+filterwarnings("ignore", message=r".*Couldn\'t find ffmpeg or avconv.*", module="pydub")
 try:
-    # Using warnings' catch_warnings to catch
-    # pydub's warning of ffmpeg or avconv missing
-    with catch_warnings(record=True) as w:
-        import pydub
-
-        if w:
-            raise ModuleNotFoundError
+    import pydub
     import speech_recognition as sr
 
     IS_AUDIO_TRANSCRIPTION_CAPABLE = True
 except ModuleNotFoundError:
     pass
-finally:
-    resetwarnings()
 
 # Optional YouTube transcription support
 try:
@@ -974,18 +967,6 @@ class MediaConverter(DocumentConverter):
 
     def _get_metadata(self, local_path, exiftool_path=None):
         if not exiftool_path:
-            which_exiftool = shutil.which("exiftool")
-            if which_exiftool:
-                warn(
-                    f"""Implicit discovery of 'exiftool' is disabled. If you would like to continue to use exiftool in MarkItDown, please set the exiftool_path parameter in the MarkItDown consructor. E.g., 
-
-    md = MarkItDown(exiftool_path="{which_exiftool}")
-
-This warning will be removed in future releases.
-""",
-                    DeprecationWarning,
-                )
-
             return None
         else:
             try:
@@ -1088,6 +1069,14 @@ class Mp3Converter(WavConverter):
             handle, temp_path = tempfile.mkstemp(suffix=".wav")
             os.close(handle)
             try:
+                # Check if pydub defaulted to ffmpeg
+                if pydub.AudioSegment.converter == "ffmpeg" and not shutil.which(
+                    "ffmpeg"
+                ):
+                    warn(
+                        "pydub: Couldn't find ffmpeg or avconv - defaulting to ffmpeg, but may not work",
+                        RuntimeWarning,
+                    )
                 sound = pydub.AudioSegment.from_mp3(local_path)
                 sound.export(temp_path, format="wav")
 
@@ -1498,34 +1487,26 @@ class MarkItDown:
         if exiftool_path is None:
             exiftool_path = os.environ.get("EXIFTOOL_PATH")
 
-        # Handle deprecation notices
-        #############################
-        if mlm_client is not None:
-            if llm_client is None:
-                warn(
-                    "'mlm_client' is deprecated, and was renamed 'llm_client'.",
-                    DeprecationWarning,
-                )
-                llm_client = mlm_client
-                mlm_client = None
-            else:
-                raise ValueError(
-                    "'mlm_client' is deprecated, and was renamed 'llm_client'. Do not use both at the same time. Just use 'llm_client' instead."
-                )
-
-        if mlm_model is not None:
-            if llm_model is None:
-                warn(
-                    "'mlm_model' is deprecated, and was renamed 'llm_model'.",
-                    DeprecationWarning,
-                )
-                llm_model = mlm_model
-                mlm_model = None
-            else:
-                raise ValueError(
-                    "'mlm_model' is deprecated, and was renamed 'llm_model'. Do not use both at the same time. Just use 'llm_model' instead."
-                )
-        #############################
+        # Still none? Check well-known paths
+        if exiftool_path is None:
+            candidate = shutil.which("exiftool")
+            if candidate:
+                candidate = os.path.abspath(candidate)
+                if any(
+                    d == os.path.dirname(candidate)
+                    for d in [
+                        "/usr/bin",
+                        "/usr/local/bin",
+                        "/opt",
+                        "/opt/bin",
+                        "/opt/local/bin",
+                        "/opt/homebrew/bin",
+                        "C:\\Windows\\System32",
+                        "C:\\Program Files",
+                        "C:\\Program Files (x86)",
+                    ]
+                ):
+                    exiftool_path = candidate
 
         self._llm_client = llm_client
         self._llm_model = llm_model

tests/test_markitdown.py

@@ -6,8 +6,6 @@ import shutil
 import pytest
 import requests
 
-from warnings import catch_warnings, resetwarnings
-
 from markitdown import MarkItDown
 
 skip_remote = (
@@ -277,18 +275,6 @@ def test_markitdown_local() -> None:
     reason="do not run if exiftool is not installed",
 )
 def test_markitdown_exiftool() -> None:
-    # Test the automatic discovery of exiftool throws a warning
-    # and is disabled
-    try:
-        with catch_warnings(record=True) as w:
-            markitdown = MarkItDown()
-            result = markitdown.convert(os.path.join(TEST_FILES_DIR, "test.jpg"))
-            assert len(w) == 1
-            assert w[0].category is DeprecationWarning
-            assert result.text_content.strip() == ""
-    finally:
-        resetwarnings()
-
     # Test explicitly setting the location of exiftool
     which_exiftool = shutil.which("exiftool")
     markitdown = MarkItDown(exiftool_path=which_exiftool)
@@ -306,40 +292,6 @@ def test_markitdown_exiftool() -> None:
         assert target in result.text_content
 
 
-def test_markitdown_deprecation() -> None:
-    try:
-        with catch_warnings(record=True) as w:
-            test_client = object()
-            markitdown = MarkItDown(mlm_client=test_client)
-            assert len(w) == 1
-            assert w[0].category is DeprecationWarning
-            assert markitdown._llm_client == test_client
-    finally:
-        resetwarnings()
-
-    try:
-        with catch_warnings(record=True) as w:
-            markitdown = MarkItDown(mlm_model="gpt-4o")
-            assert len(w) == 1
-            assert w[0].category is DeprecationWarning
-            assert markitdown._llm_model == "gpt-4o"
-    finally:
-        resetwarnings()
-
-    try:
-        test_client = object()
-        markitdown = MarkItDown(mlm_client=test_client, llm_client=test_client)
-        assert False
-    except ValueError:
-        pass
-
-    try:
-        markitdown = MarkItDown(mlm_model="gpt-4o", llm_model="gpt-4o")
-        assert False
-    except ValueError:
-        pass
-
-
 @pytest.mark.skipif(
     skip_llm,
     reason="do not run llm tests without a key",
@@ -364,5 +316,4 @@ if __name__ == "__main__":
     # test_markitdown_remote()
     # test_markitdown_local()
     test_markitdown_exiftool()
-    # test_markitdown_deprecation()
     # test_markitdown_llm()