lanyuanxiaoyao
9daff73589
- 更新 openspec/config.yaml 中 git 任务相关说明 - 将 scripts.core.* 改为 core.*，scripts.readers.* 改为 readers.* - 优化 lyxy_document_reader.py 中 sys.path 设置方式 - 同步更新所有测试文件的导入路径
35 lines
1.2 KiB
Python
35 lines
1.2 KiB
Python
"""使用 unstructured 库解析 PDF 文件（hi_res 策略 + PaddleOCR）"""
|
||
|
||
from typing import Optional, Tuple
|
||
|
||
from readers._utils import convert_unstructured_to_markdown
|
||
|
||
|
||
def parse(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||
"""使用 unstructured 库解析 PDF 文件（hi_res 策略 + PaddleOCR）"""
|
||
try:
|
||
from unstructured.partition.pdf import partition_pdf
|
||
except ImportError:
|
||
return None, "unstructured 库未安装"
|
||
|
||
try:
|
||
from unstructured.partition.utils.constants import OCR_AGENT_PADDLE
|
||
except ImportError:
|
||
return None, "unstructured-paddleocr 库未安装"
|
||
|
||
try:
|
||
elements = partition_pdf(
|
||
filename=file_path,
|
||
infer_table_structure=True,
|
||
strategy="hi_res",
|
||
languages=["chi_sim"],
|
||
ocr_agent=OCR_AGENT_PADDLE,
|
||
table_ocr_agent=OCR_AGENT_PADDLE,
|
||
)
|
||
content = convert_unstructured_to_markdown(elements, trust_titles=True)
|
||
if not content.strip():
|
||
return None, "文档为空"
|
||
return content, None
|
||
except Exception as e:
|
||
return None, f"unstructured OCR 解析失败: {str(e)}"
|