Source code for langchain_community.document_loaders.srt

from pathlib import Path
from typing import List, Union

from langchain_core.documents import Document

from langchain_community.document_loaders.base import BaseLoader



[docs]
class SRTLoader(BaseLoader):
    """Load `.srt` (subtitle) files."""


[docs]
    def __init__(self, file_path: Union[str, Path]):
        """Initialize with a file path."""
        try:
            import pysrt  # noqa:F401
        except ImportError:
            raise ImportError(
                "package `pysrt` not found, please install it with `pip install pysrt`"
            )
        self.file_path = str(file_path)



[docs]
    def load(self) -> List[Document]:
        """Load using pysrt file."""
        import pysrt

        parsed_info = pysrt.open(self.file_path)
        text = " ".join([t.text for t in parsed_info])
        metadata = {"source": self.file_path}
        return [Document(page_content=text, metadata=metadata)]