orhan/test
1
1
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix docx parse error(\n in alt) (#1163)

Browse Source
This commit is contained in:
Yuzhong Zhang
2025-08-27 06:20:17 +08:00
committed by GitHub
parent 459d462f29
commit 59eb60f8cb
1 changed files with 2 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
packages/markitdown/src/markitdown/converters/_markdownify.py
View File

@@ -95,6 +95,8 @@ class _CustomMarkdownify(markdownify.MarkdownConverter):
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 ""
# Remove all line breaks from alt
alt = alt.replace("\n", " ")
if ( if (
convert_as_inline convert_as_inline
and el.parent.name not in self.options["keep_inline_images_in"] and el.parent.name not in self.options["keep_inline_images_in"]