begoniezhao
2d66abedf0
移除日志设置与冗余代码，优化导入、类型提示及OCR后端管理 统一调整各文件模块导入路径为绝对导入 调整导入路径，移除部分导入，优化日志及注释 升级文档解析器为 Docx2Parser，优化超时与图片处理逻辑
32 lines
901 B
Python
32 lines
901 B
Python
import io
|
|
import logging
|
|
|
|
from markitdown import MarkItDown
|
|
|
|
from docreader.models.document import Document
|
|
from docreader.parser.base_parser import BaseParser
|
|
from docreader.parser.chain_parser import PipelineParser
|
|
from docreader.parser.markdown_parser import MarkdownParser
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class StdMarkitdownParser(BaseParser):
|
|
"""
|
|
PDF Document Parser
|
|
|
|
This parser handles PDF documents by extracting text content.
|
|
It uses the markitdown library for simple text extraction.
|
|
"""
|
|
|
|
def __init__(self, *args, **kwargs):
|
|
self.markitdown = MarkItDown()
|
|
|
|
def parse_into_text(self, content: bytes) -> Document:
|
|
result = self.markitdown.convert(io.BytesIO(content), keep_data_uris=True)
|
|
return Document(content=result.text_content)
|
|
|
|
|
|
class MarkitdownParser(PipelineParser):
|
|
_parser_cls = (StdMarkitdownParser, MarkdownParser)
|