45 lines
1.3 KiB
Python
45 lines
1.3 KiB
Python
|
"""
|
||
|
|
PDF extractor using pymupdf4llm.
|
||
|
|
"""
|
||
|
|
|
||
|
|
from pathlib import Path
|
||
|
|
|
||
|
|
from markitect.proxy.extractors.base import BaseExtractor
|
||
|
|
from markitect.proxy.models import ExtractionResult
|
||
|
|
from markitect.proxy.exceptions import DependencyMissingError
|
||
|
|
|
||
|
|
|
||
|
|
class PdfExtractor(BaseExtractor):
|
||
|
|
"""Extracts markdown from PDF files via pymupdf4llm."""
|
||
|
|
|
||
|
|
name = "pdf"
|
||
|
|
version = "1.0"
|
||
|
|
extensions = (".pdf",)
|
||
|
|
|
||
|
|
def check_dependencies(self) -> bool:
|
||
|
|
try:
|
||
|
|
import pymupdf4llm # noqa: F401
|
||
|
|
return True
|
||
|
|
except ImportError:
|
||
|
|
return False
|
||
|
|
|
||
|
|
def dependency_hint(self) -> str:
|
||
|
|
return 'pip install "markitect[proxy-pdf]" (or: pip install pymupdf4llm)'
|
||
|
|
|
||
|
|
def extract(self, source_path: Path) -> ExtractionResult:
|
||
|
|
if not self.check_dependencies():
|
||
|
|
raise DependencyMissingError(
|
||
|
|
"pymupdf4llm is required to extract PDF files.",
|
||
|
|
package="pymupdf4llm",
|
||
|
|
install_hint=self.dependency_hint(),
|
||
|
|
)
|
||
|
|
|
||
|
|
import pymupdf4llm
|
||
|
|
|
||
|
|
md_text = pymupdf4llm.to_markdown(str(source_path))
|
||
|
|
return ExtractionResult(
|
||
|
|
content=md_text,
|
||
|
|
extractor=self.name,
|
||
|
|
extractor_version=self.version,
|
||
|
|
)
|