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

fix linter

Browse source
This commit is contained in:
Yuzhong Zhang 2025-03-18 20:30:44 +08:00
parent 41cd9b5e2a
commit 4899148310
5 changed files with 19 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

4
packages/markitdown/src/markitdown/converters/_bing_serp_converter.py
View file

@ -79,7 +79,9 @@ class BingSerpConverter(DocumentConverter):
slug.extract() slug.extract()
# Parse the algorithmic results # Parse the algorithmic results
_markdownify = _CustomMarkdownify(keep_data_uris=kwargs.get("keep_data_uris", False)) _markdownify = _CustomMarkdownify(
keep_data_uris=kwargs.get("keep_data_uris", False)
)
results = list() results = list()
for result in soup.find_all(class_="b_algo"): for result in soup.find_all(class_="b_algo"):
if not hasattr(result, "find_all"): if not hasattr(result, "find_all"):

2
packages/markitdown/src/markitdown/converters/_docx_converter.py
View file

@ -74,5 +74,5 @@ class DocxConverter(HtmlConverter):
style_map = kwargs.get("style_map", None) style_map = kwargs.get("style_map", None)
return self._html_converter.convert_string( return self._html_converter.convert_string(
mammoth.convert_to_html(file_stream, style_map=style_map).value, mammoth.convert_to_html(file_stream, style_map=style_map).value,
keep_data_uris=kwargs.get("keep_data_uris", False) keep_data_uris=kwargs.get("keep_data_uris", False),
) )

8
packages/markitdown/src/markitdown/converters/_html_converter.py
View file

@ -57,9 +57,13 @@ class HtmlConverter(DocumentConverter):
webpage_text = "" webpage_text = ""
keep_data_uris = kwargs.get("keep_data_uris", False) keep_data_uris = kwargs.get("keep_data_uris", False)
if body_elm: if body_elm:
webpage_text = _CustomMarkdownify(keep_data_uris=keep_data_uris).convert_soup(body_elm) webpage_text = _CustomMarkdownify(
keep_data_uris=keep_data_uris
).convert_soup(body_elm)
else: else:
webpage_text = _CustomMarkdownify(keep_data_uris=keep_data_uris).convert_soup(soup) webpage_text = _CustomMarkdownify(
keep_data_uris=keep_data_uris
).convert_soup(soup)
assert isinstance(webpage_text, str) assert isinstance(webpage_text, str)

4
packages/markitdown/src/markitdown/converters/_rss_converter.py
View file

@ -171,7 +171,9 @@ class RssConverter(DocumentConverter):
try: try:
# using bs4 because many RSS feeds have HTML-styled content # using bs4 because many RSS feeds have HTML-styled content
soup = BeautifulSoup(content, "html.parser") soup = BeautifulSoup(content, "html.parser")
return _CustomMarkdownify(keep_data_uris=self._kwargs.get("keep_data_uris", False)).convert_soup(soup) return _CustomMarkdownify(
keep_data_uris=self._kwargs.get("keep_data_uris", False)
).convert_soup(soup)
except BaseException as _: except BaseException as _:
return content return content

10
packages/markitdown/src/markitdown/converters/_wikipedia_converter.py
View file

@ -76,11 +76,13 @@ class WikipediaConverter(DocumentConverter):
main_title = title_elm.string main_title = title_elm.string
# Convert the page # Convert the page
webpage_text = f"# {main_title}\n\n" + _CustomMarkdownify(keep_data_uris=kwargs.get("keep_data_uris", False)).convert_soup( webpage_text = f"# {main_title}\n\n" + _CustomMarkdownify(
body_elm keep_data_uris=kwargs.get("keep_data_uris", False)
) ).convert_soup(body_elm)
else: else:
webpage_text = _CustomMarkdownify(keep_data_uris=kwargs.get("keep_data_uris", False)).convert_soup(soup) webpage_text = _CustomMarkdownify(
keep_data_uris=kwargs.get("keep_data_uris", False)
).convert_soup(soup)
return DocumentConverterResult( return DocumentConverterResult(
markdown=webpage_text, markdown=webpage_text,