close file object after using

packages/markitdown/src/markitdown/_markitdown.py

@@ -182,7 +182,6 @@ class MarkItDown:
             - source: can be a string representing a path either as string pathlib path object or url, a requests.response object, or a file object (TextIO or BinaryIO)
             - extension: specifies the file extension to use when interpreting the file. If None, infer from source (path, uri, content-type, etc.)
         """
-
         # Local path or url
         if isinstance(source, str):
             if (
@@ -198,6 +197,9 @@ class MarkItDown:
             return self.convert_response(source, **kwargs)
         elif isinstance(source, Path):
             return self.convert_local(source, **kwargs)
+        # File object
+        elif isinstance(source, BufferedIOBase) or isinstance(source, TextIOBase):
+            return self.convert_file_object(source, **kwargs)
 
     def convert_local(
         self, path: Union[str, Path], **kwargs: Any
@@ -341,7 +343,6 @@ class MarkItDown:
         self, input: ConverterInput, extensions: List[Union[str, None]], **kwargs
     ) -> DocumentConverterResult:
         error_trace = ""
-
         # Create a copy of the page_converters list, sorted by priority.
         # We do this with each call to _convert because the priority of converters may change between calls.
         # The sort is guaranteed to be stable, so converters with the same priority will remain in the same order.
@@ -442,7 +443,7 @@ class MarkItDown:
             # Guess extensions for file objects
             elif isinstance(source, BufferedIOBase) or isinstance(source, TextIOBase):
                 guesses = puremagic.magic_stream(source)
-
+                
             extensions = list()
             for g in guesses:
                 ext = g.extension.strip()

packages/markitdown/src/markitdown/converters/_bing_serp_converter.py

@@ -39,6 +39,7 @@ class BingSerpConverter(DocumentConverter):
         soup = None
         file_obj = input.read_file(mode="rt", encoding="utf-8")
         soup = BeautifulSoup(file_obj.read(), "html.parser")
+        file_obj.close()
 
         # Clean up some formatting
         for tptt in soup.find_all(class_="tptt"):

packages/markitdown/src/markitdown/converters/_doc_intel_converter.py

@@ -63,6 +63,7 @@ class DocumentIntelligenceConverter(DocumentConverter):
         # Get the bytestring from the converter input
         file_obj = input.read_file(mode='rb')
         file_bytes = file_obj.read()
+        file_obj.close()
 
         # Certain document analysis features are not availiable for office filetypes (.xlsx, .pptx, .html, .docx)
         if extension.lower() in [".xlsx", ".pptx", ".html", ".docx"]:

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

@@ -31,6 +31,7 @@ class DocxConverter(HtmlConverter):
         style_map = kwargs.get("style_map", None)
         file_obj = input.read_file(mode="rb")
         result = mammoth.convert_to_html(file_obj, style_map=style_map)
+        file_obj.close()
         html_content = result.value
         result = self._convert(html_content)
 

packages/markitdown/src/markitdown/converters/_html_converter.py

@@ -25,6 +25,7 @@ class HtmlConverter(DocumentConverter):
         result = None
         file_obj = input.read_file(mode="rt", encoding="utf-8")
         result = self._convert(file_obj.read())
+        file_obj.close()
 
         return result
 

packages/markitdown/src/markitdown/converters/_image_converter.py

@@ -73,6 +73,7 @@ class ImageConverter(MediaConverter):
             content_type = "image/jpeg"
         image_file = input.read_file(mode="rb")
         image_base64 = base64.b64encode(image_file.read()).decode("utf-8")
+        image_file.close()
         data_uri = f"data:{content_type};base64,{image_base64}"
 
         messages = [

packages/markitdown/src/markitdown/converters/_ipynb_converter.py

@@ -30,6 +30,7 @@ class IpynbConverter(DocumentConverter):
         result = None
         file_obj = input.read_file(mode="rt", encoding="utf-8")
         notebook_content = json.load(file_obj)
+        file_obj.close()
         result = self._convert(notebook_content)
 
         return result

packages/markitdown/src/markitdown/converters/_outlook_msg_converter.py

@@ -26,8 +26,9 @@ class OutlookMsgConverter(DocumentConverter):
             return None
 
         try:
-            file_obj = input.read_file(mode="rt", encoding="utf-8")
+            file_obj = input.read_file(mode="rb")
             msg = olefile.OleFileIO(file_obj)
+
             # Extract email metadata
             md_content = "# Email Message\n\n"
 
@@ -51,6 +52,7 @@ class OutlookMsgConverter(DocumentConverter):
                 md_content += body
 
             msg.close()
+            file_obj.close()
 
             return DocumentConverterResult(
                 title=headers.get("Subject"), text_content=md_content.strip()

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

@@ -25,6 +25,8 @@ class PdfConverter(DocumentConverter):
         output = StringIO()
         file_obj = input.read_file(mode="rb")
         pdfminer.high_level.extract_text_to_fp(file_obj, output)
+        file_obj.close()
+
         return DocumentConverterResult(
             title=None,
             text_content=output.getvalue(),

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

@@ -59,6 +59,8 @@ class PptxConverter(HtmlConverter):
 
         file_obj = input.read_file(mode="rb")
         presentation = pptx.Presentation(file_obj)
+        file_obj.close()
+        
         slide_num = 0
         for slide in presentation.slides:
             slide_num += 1

packages/markitdown/src/markitdown/converters/_wikipedia_converter.py

@@ -31,6 +31,7 @@ class WikipediaConverter(DocumentConverter):
         soup = None
         file_obj = input.read_file(mode="rt", encoding="utf-8")
         soup = BeautifulSoup(file_obj.read(), "html.parser")
+        file_obj.close()
 
         # Remove javascript and style blocks
         for script in soup(["script", "style"]):

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

@@ -25,6 +25,8 @@ class XlsxConverter(HtmlConverter):
 
         file_obj = input.read_file(mode="rb")
         sheets = pd.read_excel(file_obj, sheet_name=None, engine="openpyxl")
+        file_obj.close()
+
         md_content = ""
         for s in sheets:
             md_content += f"## {s}\n"
@@ -50,6 +52,8 @@ class XlsConverter(HtmlConverter):
 
         file_obj = input.read_file(mode="rb")
         sheets = pd.read_excel(file_obj, sheet_name=None, engine="xlrd")
+        file_obj.close()
+
         md_content = ""
         for s in sheets:
             md_content += f"## {s}\n"

packages/markitdown/src/markitdown/converters/_youtube_converter.py

@@ -41,6 +41,7 @@ class YouTubeConverter(DocumentConverter):
         soup = None
         file_obj = input.read_file(mode="rt", encoding="utf-8")
         soup = BeautifulSoup(file_obj.read(), "html.parser")
+        file_obj.close()
 
         # Read the meta tags
         assert soup.title is not None and soup.title.string is not None