mirror of
https://github.com/tiennm99/DocsGPT.git
synced 2026-10-03 20:12:55 +00:00
Alex
574f96341e
The backend import package is now docsgpt, the name it will carry on PyPI; application was far too generic to install into anyone's site-packages. git mv plus a mechanical rewrite of every import, dotted string and path reference: 734 Python files, the compose files, Dockerfile, workflows, docs, setup scripts, devcontainer, k8s manifests, vscode config, pytest and coverage config, .gitignore. Behaviour is unchanged. Kept for one release: - A top-level application package whose meta-path finder resolves application.x.y to the already-imported docsgpt.x.y object, so old imports and entry points (celery -A application.app.celery, uvicorn application.asgi:asgi_app) keep working with a FutureWarning. - Celery registers every application.* task name as an alias of its docsgpt.* task on start-up, so messages queued by the previous release still run. The redbeat key prefix moves to redbeat:docsgpt:v2: so schedule entries the previous release wrote are left unread instead of firing twice. The backend image builds from the repository root (docker build -f docsgpt/Dockerfile .) so it can ship the alias package; a root .dockerignore allow-lists docsgpt/ and application/ and keeps caches, local data, .env files, the sample index files and the Dockerfile out. Compose and the image workflows point at the new context.
58 lines
1.9 KiB
Python
58 lines
1.9 KiB
Python
import logging
|
|
|
|
from bs4 import BeautifulSoup
|
|
|
|
from docsgpt.core.url_validation import SSRFError, validate_url
|
|
from docsgpt.parser.remote.base import BaseRemote
|
|
from docsgpt.parser.schema.base import Document
|
|
from docsgpt.security.safe_url import pinned_request
|
|
|
|
headers = {
|
|
"User-Agent": "Mozilla/5.0",
|
|
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*"
|
|
";q=0.8",
|
|
"Accept-Language": "en-US,en;q=0.5",
|
|
"Referer": "https://www.google.com/",
|
|
"DNT": "1",
|
|
"Connection": "keep-alive",
|
|
"Upgrade-Insecure-Requests": "1",
|
|
}
|
|
|
|
|
|
class WebLoader(BaseRemote):
|
|
def load_data(self, inputs):
|
|
urls = inputs
|
|
if isinstance(urls, str):
|
|
urls = [urls]
|
|
documents = []
|
|
for url in urls:
|
|
try:
|
|
url = validate_url(url)
|
|
except SSRFError as e:
|
|
logging.warning(
|
|
f"Skipping URL due to SSRF validation failure: {url} - {e}"
|
|
)
|
|
continue
|
|
try:
|
|
response = pinned_request("GET", url, headers=headers, timeout=30)
|
|
response.raise_for_status()
|
|
soup = BeautifulSoup(response.text, "html.parser")
|
|
metadata = {"source": url}
|
|
if soup.title:
|
|
title = soup.title.get_text(strip=True)
|
|
if title:
|
|
metadata["title"] = title
|
|
html_tag = soup.find("html")
|
|
if html_tag and html_tag.get("lang"):
|
|
metadata["language"] = html_tag.get("lang")
|
|
documents.append(
|
|
Document(
|
|
soup.get_text(separator="\n", strip=True),
|
|
extra_info=metadata,
|
|
)
|
|
)
|
|
except Exception as e:
|
|
logging.error(f"Error processing URL {url}: {e}", exc_info=True)
|
|
continue
|
|
return documents
|