forked from Archives/langchain
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.
29 lines
872 B
Python
29 lines
872 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 ValueError(
|
|
"package `pysrt` not found, please install it with `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)]
|