feat: add llms.txt downloader with error handling
This commit is contained in:
43
cli/llms_txt_downloader.py
Normal file
43
cli/llms_txt_downloader.py
Normal file
@@ -0,0 +1,43 @@
|
||||
"""ABOUTME: Downloads llms.txt files from documentation URLs with error handling"""
|
||||
"""ABOUTME: Handles timeouts, retries, and validates content before returning"""
|
||||
|
||||
import requests
|
||||
from typing import Optional
|
||||
|
||||
class LlmsTxtDownloader:
|
||||
"""Download llms.txt content from URLs"""
|
||||
|
||||
def __init__(self, url: str, timeout: int = 30):
|
||||
self.url = url
|
||||
self.timeout = timeout
|
||||
|
||||
def download(self) -> Optional[str]:
|
||||
"""
|
||||
Download llms.txt content.
|
||||
|
||||
Returns:
|
||||
String content or None if download fails
|
||||
"""
|
||||
try:
|
||||
headers = {
|
||||
'User-Agent': 'Skill-Seekers-llms.txt-Reader/1.0'
|
||||
}
|
||||
|
||||
response = requests.get(
|
||||
self.url,
|
||||
headers=headers,
|
||||
timeout=self.timeout
|
||||
)
|
||||
response.raise_for_status()
|
||||
|
||||
content = response.text
|
||||
|
||||
# Validate content is not empty and looks like markdown
|
||||
if len(content) < 100:
|
||||
return None
|
||||
|
||||
return content
|
||||
|
||||
except requests.RequestException as e:
|
||||
print(f"❌ Failed to download {self.url}: {e}")
|
||||
return None
|
||||
12
tests/test_llms_txt_downloader.py
Normal file
12
tests/test_llms_txt_downloader.py
Normal file
@@ -0,0 +1,12 @@
|
||||
import pytest
|
||||
from cli.llms_txt_downloader import LlmsTxtDownloader
|
||||
|
||||
def test_download_llms_txt():
|
||||
"""Test downloading llms.txt content"""
|
||||
downloader = LlmsTxtDownloader("https://hono.dev/llms-full.txt")
|
||||
|
||||
content = downloader.download()
|
||||
|
||||
assert content is not None
|
||||
assert len(content) > 100 # Should have substantial content
|
||||
assert isinstance(content, str)
|
||||
Reference in New Issue
Block a user