lanyuanxiaoyao
09904aefdc
从 BaseReader 抽象基类及所有 Reader 子类中移除 supported_extensions 属性，该属性在代码库中从未被实际调用，仅作为元数据存在。
54 lines
1.4 KiB
Python
54 lines
1.4 KiB
Python
"""PDF 文件阅读器，支持多种解析方法（OCR 优先）。"""
|
||
|
||
import os
|
||
from typing import List, Optional, Tuple
|
||
|
||
from scripts.readers.base import BaseReader
|
||
from scripts.utils import is_valid_pdf
|
||
|
||
from . import docling_ocr
|
||
from . import unstructured_ocr
|
||
from . import docling
|
||
from . import unstructured
|
||
from . import markitdown
|
||
from . import pypdf
|
||
|
||
|
||
PARSERS = [
|
||
("docling OCR", docling_ocr.parse),
|
||
("unstructured OCR", unstructured_ocr.parse),
|
||
("docling", docling.parse),
|
||
("unstructured", unstructured.parse),
|
||
("MarkItDown", markitdown.parse),
|
||
("pypdf", pypdf.parse),
|
||
]
|
||
|
||
|
||
class PdfReader(BaseReader):
|
||
"""PDF 文件阅读器"""
|
||
|
||
def supports(self, file_path: str) -> bool:
|
||
return file_path.lower().endswith('.pdf')
|
||
|
||
def parse(self, file_path: str) -> Tuple[Optional[str], List[str]]:
|
||
failures = []
|
||
|
||
# 检查文件是否存在
|
||
if not os.path.exists(file_path):
|
||
return None, ["文件不存在"]
|
||
|
||
# 验证文件格式
|
||
if not is_valid_pdf(file_path):
|
||
return None, ["不是有效的 PDF 文件"]
|
||
|
||
content = None
|
||
|
||
for parser_name, parser_func in PARSERS:
|
||
content, error = parser_func(file_path)
|
||
if content is not None:
|
||
return content, failures
|
||
else:
|
||
failures.append(f"- {parser_name}: {error}")
|
||
|
||
return None, failures
|