mirror of
https://github.com/Mintplex-Labs/langchain-python.git
synced 2026-07-19 21:33:31 -04:00
Leonid Ganeline
c28cc0f1ac
# changed ValueError to ImportError Code cleaning. Fixed inconsistencies in ImportError handling. Sometimes it raises ImportError and sometime ValueError. I've changed all cases to the `raise ImportError` Also: - added installation instruction in the error message, where it missed; - fixed several installation instructions in the error message; - fixed several error handling in regards to the ImportError
29 lines
885 B
Python
29 lines
885 B
Python
"""Loader for .srt (subtitle) files."""
|
|
from typing import List
|
|
|
|
from langchain.docstore.document import Document
|
|
from langchain.document_loaders.base import BaseLoader
|
|
|
|
|
|
class SRTLoader(BaseLoader):
|
|
"""Loader for .srt (subtitle) files."""
|
|
|
|
def __init__(self, file_path: str):
|
|
"""Initialize with 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 = 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)]
|