mirror of
https://github.com/hwchase17/langchain.git
synced 2025-06-24 23:54:14 +00:00
docs: fix broken Appearance of langchain_community/document_loaders/recursive_url_loader API Reference (#29305)
# PR mesesage ## Description Fixed a broken Appearance of RecurisveUrlLoader API Reference. ### Before <p align="center"> <img width="750" alt="image" src="https://github.com/user-attachments/assets/f39df65d-b788-411d-88af-8bfa2607c00b" /> <img width="750" alt="image" src="https://github.com/user-attachments/assets/b8a92b70-4548-4b4a-965f-026faeebd0ec" /> </p> ### After <p align="center"> <img width="750" alt="image" src="https://github.com/user-attachments/assets/8ea28146-de45-42e2-b346-3004ec4dfc55" /> <img width="750" alt="image" src="https://github.com/user-attachments/assets/914c6966-4055-45d3-baeb-2d97eab06fe7" /> </p> ## Issue: N/A ## Dependencies None ## Twitter handle N/A # Add tests and docs Not applicable; this change only affects documentation. # Lint and test Ran make format, make lint, and make test to ensure no issues.
This commit is contained in:
parent
6c52378992
commit
5d64597490
@ -53,7 +53,8 @@ def _metadata_extractor(
|
||||
class RecursiveUrlLoader(BaseLoader):
|
||||
"""Recursively load all child links from a root URL.
|
||||
|
||||
**Security Note**: This loader is a crawler that will start crawling
|
||||
**Security Note**:
|
||||
This loader is a crawler that will start crawling
|
||||
at a given URL and then expand to crawl child links recursively.
|
||||
|
||||
Web crawlers should generally NOT be deployed with network access
|
||||
@ -162,7 +163,7 @@ class RecursiveUrlLoader(BaseLoader):
|
||||
|
||||
def bs4_extractor(html: str) -> str:
|
||||
soup = BeautifulSoup(html, "lxml")
|
||||
return re.sub(r"\n\n+", "\n\n", soup.text).strip()
|
||||
return re.sub(r"\\n\\n+", "\\n\\n", soup.text).strip()
|
||||
|
||||
loader = RecursiveUrlLoader(
|
||||
"https://docs.python.org/3.9/",
|
||||
|
Loading…
Reference in New Issue
Block a user