77 lines
2.6 KiB
Python
77 lines
2.6 KiB
Python
#!/usr/bin/env python3
|
||
"""PDF 文件解析模块，提供多种解析方法。"""
|
||
|
||
from typing import Optional, Tuple
|
||
|
||
from common import _unstructured_elements_to_markdown, parse_with_docling, parse_with_markitdown
|
||
|
||
|
||
def parse_pdf_with_docling(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||
"""使用 docling 库解析 PDF 文件"""
|
||
return parse_with_docling(file_path)
|
||
|
||
|
||
def parse_pdf_with_unstructured(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||
"""使用 unstructured 库解析 PDF 文件，优先 hi_res 策略配合 PaddleOCR"""
|
||
try:
|
||
from unstructured.partition.pdf import partition_pdf
|
||
except ImportError:
|
||
return None, "unstructured 库未安装"
|
||
|
||
base_kwargs = {"filename": file_path, "infer_table_structure": True}
|
||
|
||
try:
|
||
# 优先 hi_res 策略（版面分析 + PaddleOCR），失败则回退 fast
|
||
try:
|
||
from unstructured.partition.utils.constants import OCR_AGENT_PADDLE
|
||
|
||
elements = partition_pdf(
|
||
**base_kwargs,
|
||
strategy="hi_res",
|
||
languages=["chi_sim"],
|
||
ocr_agent=OCR_AGENT_PADDLE,
|
||
table_ocr_agent=OCR_AGENT_PADDLE,
|
||
)
|
||
trust_titles = True
|
||
except Exception:
|
||
# fast 策略不做版面分析，Title 类型标注不可靠
|
||
elements = partition_pdf(**base_kwargs, strategy="fast", languages=["chi_sim"])
|
||
trust_titles = False
|
||
|
||
content = _unstructured_elements_to_markdown(elements, trust_titles)
|
||
if not content.strip():
|
||
return None, "文档为空"
|
||
return content, None
|
||
except Exception as e:
|
||
return None, f"unstructured 解析失败: {str(e)}"
|
||
|
||
|
||
def parse_pdf_with_markitdown(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||
"""使用 MarkItDown 库解析 PDF 文件"""
|
||
return parse_with_markitdown(file_path)
|
||
|
||
|
||
def parse_pdf_with_pypdf(file_path: str) -> Tuple[Optional[str], Optional[str]]:
|
||
"""使用 pypdf 库解析 PDF 文件"""
|
||
try:
|
||
from pypdf import PdfReader
|
||
except ImportError:
|
||
return None, "pypdf 库未安装"
|
||
|
||
try:
|
||
reader = PdfReader(file_path)
|
||
md_content = []
|
||
|
||
for page in reader.pages:
|
||
text = page.extract_text(extraction_mode="plain")
|
||
if text and text.strip():
|
||
md_content.append(text.strip())
|
||
md_content.append("")
|
||
|
||
content = "\n".join(md_content).strip()
|
||
if not content:
|
||
return None, "文档为空"
|
||
return content, None
|
||
except Exception as e:
|
||
return None, f"pypdf 解析失败: {str(e)}"
|