mirror of
https://github.com/hwchase17/langchain
synced 2024-11-08 07:10:35 +00:00
f7a1fd91b8
So this arose from the https://github.com/langchain-ai/langchain/pull/18397 problem of document loaders not supporting `pathlib.Path`. This pull request provides more uniform support for Path as an argument. The core ideas for this upgrade: - if there is a local file path used as an argument, it should be supported as `pathlib.Path` - if there are some external calls that may or may not support Pathlib, the argument is immidiately converted to `str` - if there `self.file_path` is used in a way that it allows for it to stay pathlib without conversion, is is only converted for the metadata. Twitter handle: https://twitter.com/mwmajewsk
30 lines
901 B
Python
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)]
|