Added pdfs

packages/markitdown/pyproject.toml

@@ -28,7 +28,6 @@ dependencies = [
   "requests",
   "markdownify~=0.14.1",
   "numpy",
-  "pdfminer.six",
   "puremagic",
   "pydub",
   "olefile",
@@ -47,12 +46,14 @@ all = [
   "mammoth",
   "pandas",
   "openpyxl",
-  "xlrd"
+  "xlrd",
+  "pdfminer.six"
 ]
 pptx = ["python-pptx"]
 docx = ["mammoth"]
 xlsx = ["pandas", "openpyxl"]
 xls = ["pandas", "xlrd"]
+pdf = ["pdfminer.six"]
 
 [project.urls]
 Documentation = "https://github.com/microsoft/markitdown#readme"

packages/markitdown/src/markitdown/converters/_docx_converter.py

@@ -36,7 +36,7 @@ class DocxConverter(HtmlConverter):
         if extension.lower() != ".docx":
             return None
 
-        # Load the dependencies
+        # Check: the dependencies
         if _dependency_exc_info is not None:
             raise MissingDependencyException(
                 MISSING_DEPENDENCY_MESSAGE.format(

packages/markitdown/src/markitdown/converters/_pdf_converter.py

@@ -1,7 +1,17 @@
-import pdfminer
+import sys
-import pdfminer.high_level
 from typing import Union
 from ._base import DocumentConverter, DocumentConverterResult
+from .._exceptions import MissingDependencyException, MISSING_DEPENDENCY_MESSAGE
+
+# Try loading optional (but in this case, required) dependencies
+# Save reporting of any exceptions for later
+_dependency_exc_info = None
+try:
+    import pdfminer
+    import pdfminer.high_level
+except ImportError:
+    # Preserve the error and stack trace for later
+    _dependency_exc_info = sys.exc_info()
 
 
 class PdfConverter(DocumentConverter):
@@ -20,6 +30,18 @@ class PdfConverter(DocumentConverter):
         if extension.lower() != ".pdf":
             return None
 
+        # Check the dependencies
+        if _dependency_exc_info is not None:
+            raise MissingDependencyException(
+                MISSING_DEPENDENCY_MESSAGE.format(
+                    converter=type(self).__name__,
+                    extension=".pdf",
+                    feature="pdf",
+                )
+            ) from _dependency_exc_info[1].with_traceback(
+                _dependency_exc_info[2]
+            )  # Restore the original traceback
+
         return DocumentConverterResult(
             title=None,
             text_content=pdfminer.high_level.extract_text(local_path),

packages/markitdown/src/markitdown/converters/_pptx_converter.py

@@ -64,7 +64,7 @@ class PptxConverter(HtmlConverter):
         if extension.lower() != ".pptx":
             return None
 
-        # Load the dependencies
+        # Check the dependencies
         if _dependency_exc_info is not None:
             raise MissingDependencyException(
                 MISSING_DEPENDENCY_MESSAGE.format(

packages/markitdown/src/markitdown/converters/_xlsx_converter.py

@@ -39,7 +39,7 @@ class XlsxConverter(HtmlConverter):
         if extension.lower() != ".xlsx":
             return None
 
-        # Load the dependencies
+        # Check the dependencies
         if _xlsx_dependency_exc_info is not None:
             raise MissingDependencyException(
                 MISSING_DEPENDENCY_MESSAGE.format(