You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
langchain/libs/community/langchain_community/document_loaders/srt.py

30 lines
901 B
Python

from pathlib import Path
from typing import List, Union
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseLoader
class SRTLoader(BaseLoader):
"""Load `.srt` (subtitle) files."""
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)
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)]