luciano/markitdown
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

update: changed "method" parameter fro PdfConverter to "pdf_engine" for better user instruction. Add examples for PdfConverter.convert() calling.

Browse source
This commit is contained in:
tungsten106 2024-12-24 15:11:37 +08:00
parent 797e0d4071
commit ba5df9bbc3
1 changed files with 9 additions and 4 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

13
src/markitdown/_markitdown.py
View file

@ -677,18 +677,23 @@ class BingSerpConverter(DocumentConverter):
class PdfConverter(DocumentConverter): class PdfConverter(DocumentConverter):
""" """
Converts PDFs to Markdown. Most style information is ignored, so the results are essentially plain-text. Converts PDFs to Markdown. Most style information is ignored, so the results are essentially plain-text.
""" """
def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]: def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
"""
Example:
>>> source = "https://arxiv.org/pdf/2308.08155v2.pdf"
>>> markitdown.convert(source, pdf_engine="pymupdf4llm")
"""
# Bail if not a PDF # Bail if not a PDF
extension = kwargs.get("file_extension", "") extension = kwargs.get("file_extension", "")
if extension.lower() != ".pdf": if extension.lower() != ".pdf":
return None return None
method = kwargs.get("method", "pdfminer") pdf_engine = kwargs.get("pdf_engine", "pdfminer")
if method == "pdfminer": if pdf_engine == "pdfminer":
text_content = pdfminer.high_level.extract_text(local_path) text_content = pdfminer.high_level.extract_text(local_path)
elif method == "pymupdf4llm": elif pdf_engine == "pymupdf4llm":
text_content = pymupdf4llm.to_markdown(local_path, show_progress=False) text_content = pymupdf4llm.to_markdown(local_path, show_progress=False)
else: else:
return None # unknown method return None # unknown method