mirror of
https://github.com/hwchase17/langchain
synced 2024-11-06 03:20:49 +00:00
c3f8733aef
fix spellings **seperate -> separate**: found more occurrences, see https://github.com/langchain-ai/langchain/pull/14602 **initialise -> intialize**: the latter is more common in the repo **pre-defined > predefined**: adding a comma after a prefix is a delicate matter, but this is a generally accepted word also, another word that appears in the repo is "fs" (stands for filesystem), e.g., in `libs/core/langchain_core/prompts/loading.py` ` """Unified method for loading a prompt from LangChainHub or local fs."""` Isn't "filesystem" better?
77 lines
2.5 KiB
Python
77 lines
2.5 KiB
Python
import email
|
|
import logging
|
|
from typing import Dict, List, Union
|
|
|
|
from langchain_core.documents import Document
|
|
|
|
from langchain_community.document_loaders.base import BaseLoader
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
class MHTMLLoader(BaseLoader):
|
|
"""Parse `MHTML` files with `BeautifulSoup`."""
|
|
|
|
def __init__(
|
|
self,
|
|
file_path: str,
|
|
open_encoding: Union[str, None] = None,
|
|
bs_kwargs: Union[dict, None] = None,
|
|
get_text_separator: str = "",
|
|
) -> None:
|
|
"""initialize with path, and optionally, file encoding to use, and any kwargs
|
|
to pass to the BeautifulSoup object.
|
|
|
|
Args:
|
|
file_path: Path to file to load.
|
|
open_encoding: The encoding to use when opening the file.
|
|
bs_kwargs: Any kwargs to pass to the BeautifulSoup object.
|
|
get_text_separator: The separator to use when getting the text
|
|
from the soup.
|
|
"""
|
|
try:
|
|
import bs4 # noqa:F401
|
|
except ImportError:
|
|
raise ImportError(
|
|
"beautifulsoup4 package not found, please install it with "
|
|
"`pip install beautifulsoup4`"
|
|
)
|
|
|
|
self.file_path = file_path
|
|
self.open_encoding = open_encoding
|
|
if bs_kwargs is None:
|
|
bs_kwargs = {"features": "lxml"}
|
|
self.bs_kwargs = bs_kwargs
|
|
self.get_text_separator = get_text_separator
|
|
|
|
def load(self) -> List[Document]:
|
|
from bs4 import BeautifulSoup
|
|
|
|
"""Load MHTML document into document objects."""
|
|
|
|
with open(self.file_path, "r", encoding=self.open_encoding) as f:
|
|
message = email.message_from_string(f.read())
|
|
parts = message.get_payload()
|
|
|
|
if not isinstance(parts, list):
|
|
parts = [message]
|
|
|
|
for part in parts:
|
|
if part.get_content_type() == "text/html":
|
|
html = part.get_payload(decode=True).decode()
|
|
|
|
soup = BeautifulSoup(html, **self.bs_kwargs)
|
|
text = soup.get_text(self.get_text_separator)
|
|
|
|
if soup.title:
|
|
title = str(soup.title.string)
|
|
else:
|
|
title = ""
|
|
|
|
metadata: Dict[str, Union[str, None]] = {
|
|
"source": self.file_path,
|
|
"title": title,
|
|
}
|
|
return [Document(page_content=text, metadata=metadata)]
|
|
return []
|