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

add other converter para support

Browse source
This commit is contained in:
Yuzhong Zhang 2025-03-18 20:14:46 +08:00
parent 9f1bcf3b83
commit 41cd9b5e2a
4 changed files with 10 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

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

@ -79,7 +79,7 @@ class BingSerpConverter(DocumentConverter):
slug.extract() slug.extract()
# Parse the algorithmic results # Parse the algorithmic results
_markdownify = _CustomMarkdownify() _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"):

3
packages/markitdown/src/markitdown/converters/_docx_converter.py
View file

@ -72,8 +72,7 @@ class DocxConverter(HtmlConverter):
) )
style_map = kwargs.get("style_map", None) style_map = kwargs.get("style_map", None)
keep_data_uris = kwargs.get("keep_data_uris", False)
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=keep_data_uris keep_data_uris=kwargs.get("keep_data_uris", False)
) )

7
packages/markitdown/src/markitdown/converters/_rss_converter.py
View file

@ -28,6 +28,10 @@ CANDIDATE_FILE_EXTENSIONS = [
class RssConverter(DocumentConverter): class RssConverter(DocumentConverter):
"""Convert RSS / Atom type to markdown""" """Convert RSS / Atom type to markdown"""
def __init__(self):
super().__init__()
self._kwargs = {}
def accepts( def accepts(
self, self,
file_stream: BinaryIO, file_stream: BinaryIO,
@ -82,6 +86,7 @@ class RssConverter(DocumentConverter):
stream_info: StreamInfo, stream_info: StreamInfo,
**kwargs: Any, # Options to pass to the converter **kwargs: Any, # Options to pass to the converter
) -> DocumentConverterResult: ) -> DocumentConverterResult:
self._kwargs = kwargs
doc = minidom.parse(file_stream) doc = minidom.parse(file_stream)
feed_type = self._feed_type(doc) feed_type = self._feed_type(doc)
@ -166,7 +171,7 @@ 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().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

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

@ -76,11 +76,11 @@ 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().convert_soup( webpage_text = f"# {main_title}\n\n" + _CustomMarkdownify(keep_data_uris=kwargs.get("keep_data_uris", False)).convert_soup(
body_elm body_elm
) )
else: else:
webpage_text = _CustomMarkdownify().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,