58 lines
1.7 KiB
Python
58 lines
1.7 KiB
Python
"""DOCX text extraction using python-docx.
|
|
|
|
Preserves heading structure and paragraph breaks.
|
|
"""
|
|
|
|
import logging
|
|
from pathlib import Path
|
|
|
|
from .base import ExtractionResult
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class DocxExtractor:
|
|
"""Extracts text from .docx files preserving structure."""
|
|
|
|
def can_handle(self, file_path: Path) -> bool:
|
|
"""Return True for .docx files."""
|
|
return file_path.suffix.lower() == ".docx"
|
|
|
|
def extract(self, file_path: Path) -> ExtractionResult:
|
|
"""Extract text from DOCX preserving headings and paragraphs."""
|
|
try:
|
|
from docx import Document
|
|
except ImportError:
|
|
raise ImportError(
|
|
"python-docx is required for DOCX extraction. "
|
|
"Install with: pip install python-docx"
|
|
)
|
|
|
|
doc = Document(str(file_path))
|
|
parts: list[str] = []
|
|
|
|
for paragraph in doc.paragraphs:
|
|
text = paragraph.text.strip()
|
|
if not text:
|
|
continue
|
|
|
|
# Preserve heading structure with markdown-style headers
|
|
style_name = paragraph.style.name.lower() if paragraph.style else ""
|
|
if "heading 1" in style_name:
|
|
parts.append(f"# {text}")
|
|
elif "heading 2" in style_name:
|
|
parts.append(f"## {text}")
|
|
elif "heading 3" in style_name:
|
|
parts.append(f"### {text}")
|
|
elif "heading 4" in style_name:
|
|
parts.append(f"#### {text}")
|
|
else:
|
|
parts.append(text)
|
|
|
|
return ExtractionResult(
|
|
text="\n\n".join(parts),
|
|
source_file=file_path,
|
|
extraction_method="direct",
|
|
metadata={"paragraph_count": len(parts)},
|
|
)
|