WeKnora/docreader/parser/docx2_parser.py

29 lines
855 B
Python
Raw Permalink Blame History

This file contains ambiguous Unicode characters!

This file contains ambiguous Unicode characters that may be confused with others in your current locale. If your use case is intentional and legitimate, you can safely ignore this warning. Use the Escape button to highlight these characters.

import logging
from docreader.parser.chain_parser import FirstParser
from docreader.parser.docx_parser import DocxParser
from docreader.parser.markitdown_parser import MarkitdownParser
logger = logging.getLogger(__name__)
class Docx2Parser(FirstParser):
_parser_cls = (MarkitdownParser, DocxParser)
if __name__ == "__main__":
logging.basicConfig(level=logging.DEBUG)
your_file = "/path/to/your/file.docx"
parser = Docx2Parser(separators=[".", "?", "!", "。", "?", "!"])
with open(your_file, "rb") as f:
content = f.read()
document = parser.parse(content)
for cc in document.chunks:
logger.info(f"chunk: {cc}")
# document = parser.parse_into_text(content)
# logger.info(f"docx content: {document.content}")
# logger.info(f"find images {document.images.keys()}")