Archives/langchain
2
0
Fork 1
mirror of https://github.com/hwchase17/langchain synced 2024-11-08 07:10:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Harrison/rtd loader (#1513)

Browse Source 
Co-authored-by: Youssef A. Abukwaik <yousseb@users.noreply.github.com>
This commit is contained in:
Harrison Chase 2023-03-07 21:09:54 -08:00 committed by GitHub
parent 8f21605d71
commit a4a2d79087
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 29 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
langchain/document_loaders/readthedocs.py
View File

@ -1,6 +1,6 @@
"""Loader that loads ReadTheDocs documentation directory dump."""
from pathlib import Path
from typing import List
from typing import Any, List, Optional
from langchain.docstore.document import Document
from langchain.document_loaders.base import BaseLoader
@ -9,16 +9,41 @@ from langchain.document_loaders.base import BaseLoader
class ReadTheDocsLoader(BaseLoader):
"""Loader that loads ReadTheDocs documentation directory dump."""
def __init__(self, path: str):
def __init__(
self,
path: str,
encoding: Optional[str] = None,
errors: Optional[str] = None,
**kwargs: Optional[Any]
):
"""Initialize path."""
try:
from bs4 import BeautifulSoup
except ImportError:
raise ValueError(
"Could not import python packages. "
"Please install it with `pip install beautifulsoup4`. "
)
try:
_ = BeautifulSoup(
"<html><body>Parser builder library test.</body></html>", **kwargs
)
except Exception as e:
raise ValueError("Parsing kwargs do not appear valid") from e
self.file_path = path
self.encoding = encoding
self.errors = errors
self.bs_kwargs = kwargs
def load(self) -> List[Document]:
"""Load documents."""
from bs4 import BeautifulSoup
def _clean_data(data: str) -> str:
soup = BeautifulSoup(data)
soup = BeautifulSoup(data, **self.bs_kwargs)
text = soup.find_all("main", {"id": "main-content"})
if len(text) != 0:
text = text[0].get_text()
@ -30,7 +55,7 @@ class ReadTheDocsLoader(BaseLoader):
for p in Path(self.file_path).rglob("*"):
if p.is_dir():
continue
with open(p) as f:
with open(p, encoding=self.encoding, errors=self.errors) as f:
text = _clean_data(f.read())
metadata = {"source": str(p)}
docs.append(Document(page_content=text, metadata=metadata))