DESKTOP-72TV0V4\caoxiaozhu
d24b29afe4
- 添加多种文档解析器 (PDF, Word, Excel, Markdown 等) - 添加基础解析器和链式解析器 - 添加存储和注册机制 - 添加 gRPC 服务实现 Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
29 lines
855 B
Python
29 lines
855 B
Python
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()}")
|