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

enhanceextraimage

Browse source
This commit is contained in:
朱昊天 2025-04-30 14:27:49 +12:00
parent 4eb0107e2f
commit a0b3cf7de3
2 changed files with 2 additions and 8 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
packages/markitdown/src/markitdown/converters/_html_converter.py
View file

@ -61,6 +61,7 @@ class HtmlConverter(DocumentConverter):
webpage_text = _CustomMarkdownify(**kwargs).convert_soup(soup) webpage_text = _CustomMarkdownify(**kwargs).convert_soup(soup)
assert isinstance(webpage_text, str) assert isinstance(webpage_text, str)
# remove leading and trailing \n # remove leading and trailing \n
webpage_text = webpage_text.strip() webpage_text = webpage_text.strip()

9
packages/markitdown/src/markitdown/converters/_markdownify.py
View file

@ -104,7 +104,6 @@ class _CustomMarkdownify(markdownify.MarkdownConverter):
Supports categorized storage in subfolders by document name Supports categorized storage in subfolders by document name
""" """
alt = el.attrs.get("alt", None) or "" alt = el.attrs.get("alt", None) or ""
# src = el.attrs.get("src", None) or ""
src = el.attrs.get("src", None) or el.attrs.get("data-src", None) or "" src = el.attrs.get("src", None) or el.attrs.get("data-src", None) or ""
title = el.attrs.get("title", None) or "" title = el.attrs.get("title", None) or ""
title_part = ' "%s"' % title.replace('"', r"\"") if title else "" title_part = ' "%s"' % title.replace('"', r"\"") if title else ""
@ -142,29 +141,23 @@ class _CustomMarkdownify(markdownify.MarkdownConverter):
if hasattr(self, 'conversion_name') and self.conversion_name: if hasattr(self, 'conversion_name') and self.conversion_name:
# If conversion_name exists, create subfolder # If conversion_name exists, create subfolder
output_dir = os.path.join(self.image_output_dir, self.conversion_name) output_dir = os.path.join(self.image_output_dir, self.conversion_name)
print(f"[DEBUG] Using subfolder for image: {output_dir}")
else: else:
# Otherwise use base directory # Otherwise use base directory
output_dir = self.image_output_dir output_dir = self.image_output_dir
print(f"[DEBUG] Using base directory for image: {output_dir}")
# Ensure directory exists # Ensure directory exists
os.makedirs(output_dir, exist_ok=True) os.makedirs(output_dir, exist_ok=True)
print(f"[DEBUG] Ensuring directory exists: {output_dir}")
# Save image file # Save image file
filepath = os.path.join(output_dir, filename) filepath = os.path.join(output_dir, filename)
with open(filepath, "wb") as f: with open(filepath, "wb") as f:
f.write(image_data) f.write(image_data)
print(f"[DEBUG] Image saved to: {filepath}")
# Update src to relative path # Update src to relative path
src = os.path.join(output_dir, filename).replace("\\", "/") src = os.path.join(output_dir, filename).replace("\\", "/")
print(f"[DEBUG] Updated image path to: {src}")
except Exception as e: except Exception as e:
error_msg = f"Error saving image: {str(e)}" error_msg = f"Error saving image: {str(e)}"
print(f"[ERROR] {error_msg}", file=sys.stderr)
import traceback import traceback
traceback.print_exc(file=sys.stderr) traceback.print_exc(file=sys.stderr)
# If extraction fails, revert to original truncating behavior # If extraction fails, revert to original truncating behavior
@ -174,7 +167,7 @@ class _CustomMarkdownify(markdownify.MarkdownConverter):
# Process other data URIs that are not images (truncate them) # Process other data URIs that are not images (truncate them)
elif src.startswith("data:") and not self.options.get("keep_data_uris", False): elif src.startswith("data:") and not self.options.get("keep_data_uris", False):
src = src.split(",")[0] + "..." src = src.split(",")[0] + "..."
# Return Markdown format image reference # Return Markdown format image reference
return f"![{alt}]({src}{title_part})" return f"![{alt}]({src}{title_part})"