TheLovinator/discord-rss-bot
1
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Add git backup functionality

Browse source 
Fixes: https://github.com/TheLovinator1/discord-rss-bot/issues/421
Merges: https://github.com/TheLovinator1/discord-rss-bot/pull/422
This commit is contained in:
Joakim Hellsén 2026-03-07 01:01:09 +01:00
commit e8bd528def
Signed by: Joakim Hellsén
SSH key fingerprint: SHA256:/9h/CsExpFp+PRhsfA0xznFx2CGfTT5R/kpuFfUgEQk
16 changed files with 1062 additions and 89 deletions
Download patch file Download diff file Expand all files Collapse all files

138
discord_rss_bot/main.py
View file

@ -7,48 +7,62 @@ import typing
import urllib.parse
from contextlib import asynccontextmanager
from dataclasses import dataclass
from datetime import UTC, datetime
from datetime import UTC
from datetime import datetime
from functools import lru_cache
from typing import TYPE_CHECKING, Annotated, cast
from typing import TYPE_CHECKING
from typing import Annotated
from typing import Any
from typing import cast
import httpx
import sentry_sdk
import uvicorn
from apscheduler.schedulers.asyncio import AsyncIOScheduler
from fastapi import FastAPI, Form, HTTPException, Request
from fastapi import FastAPI
from fastapi import Form
from fastapi import HTTPException
from fastapi import Request
from fastapi.responses import HTMLResponse
from fastapi.staticfiles import StaticFiles
from fastapi.templating import Jinja2Templates
from httpx import Response
from markdownify import markdownify
from reader import Entry, EntryNotFoundError, Feed, FeedNotFoundError, Reader, TagNotFoundError
from reader import Entry
from reader import EntryNotFoundError
from reader import Feed
from reader import FeedNotFoundError
from reader import Reader
from reader import TagNotFoundError
from starlette.responses import RedirectResponse
from discord_rss_bot import settings
from discord_rss_bot.custom_filters import (
entry_is_blacklisted,
entry_is_whitelisted,
)
from discord_rss_bot.custom_message import (
CustomEmbed,
get_custom_message,
get_embed,
get_first_image,
replace_tags_in_text_message,
save_embed,
)
from discord_rss_bot.feeds import create_feed, extract_domain, send_entry_to_discord, send_to_discord
from discord_rss_bot.custom_filters import entry_is_blacklisted
from discord_rss_bot.custom_filters import entry_is_whitelisted
from discord_rss_bot.custom_message import CustomEmbed
from discord_rss_bot.custom_message import get_custom_message
from discord_rss_bot.custom_message import get_embed
from discord_rss_bot.custom_message import get_first_image
from discord_rss_bot.custom_message import replace_tags_in_text_message
from discord_rss_bot.custom_message import save_embed
from discord_rss_bot.feeds import create_feed
from discord_rss_bot.feeds import extract_domain
from discord_rss_bot.feeds import send_entry_to_discord
from discord_rss_bot.feeds import send_to_discord
from discord_rss_bot.git_backup import commit_state_change
from discord_rss_bot.git_backup import get_backup_path
from discord_rss_bot.missing_tags import add_missing_tags
from discord_rss_bot.search import create_search_context
from discord_rss_bot.settings import get_reader
if TYPE_CHECKING:
from collections.abc import AsyncGenerator, Iterable
from collections.abc import AsyncGenerator
from collections.abc import Iterable
from reader.types import JSONType
LOGGING_CONFIG = {
LOGGING_CONFIG: dict[str, Any] = {
"version": 1,
"disable_existing_loggers": True,
"formatters": {
@ -130,11 +144,11 @@ async def post_add_webhook(
webhook_name: The name of the webhook.
webhook_url: The url of the webhook.
Raises:
HTTPException: If the webhook already exists.
Returns:
RedirectResponse: Redirect to the index page.
Raises:
HTTPException: If the webhook already exists.
"""
# Get current webhooks from the database if they exist otherwise use an empty list.
webhooks = list(reader.get_tag((), "webhooks", []))
@ -151,6 +165,8 @@ async def post_add_webhook(
reader.set_tag((), "webhooks", webhooks) # pyright: ignore[reportArgumentType]
commit_state_change(reader, f"Add webhook {webhook_name.strip()}")
return RedirectResponse(url="/", status_code=303)
# TODO(TheLovinator): Show this error on the page.
@ -165,11 +181,12 @@ async def post_delete_webhook(webhook_url: Annotated[str, Form()]) -> RedirectRe
Args:
webhook_url: The url of the webhook.
Returns:
RedirectResponse: Redirect to the index page.
Raises:
HTTPException: If the webhook could not be deleted
Returns:
RedirectResponse: Redirect to the index page.
"""
# TODO(TheLovinator): Check if the webhook is in use by any feeds before deleting it.
# TODO(TheLovinator): Replace HTTPException with a custom exception for both of these.
@ -196,6 +213,8 @@ async def post_delete_webhook(webhook_url: Annotated[str, Form()]) -> RedirectRe
# Add our new list of webhooks to the database.
reader.set_tag((), "webhooks", webhooks) # pyright: ignore[reportArgumentType]
commit_state_change(reader, f"Delete webhook {webhook_url.strip()}")
return RedirectResponse(url="/", status_code=303)
@ -215,6 +234,7 @@ async def post_create_feed(
"""
clean_feed_url: str = feed_url.strip()
create_feed(reader, feed_url, webhook_dropdown)
commit_state_change(reader, f"Add feed {clean_feed_url}")
return RedirectResponse(url=f"/feed?feed_url={urllib.parse.quote(clean_feed_url)}", status_code=303)
@ -286,6 +306,8 @@ async def post_set_whitelist(
reader.set_tag(clean_feed_url, "regex_whitelist_content", regex_whitelist_content) # pyright: ignore[reportArgumentType][call-overload]
reader.set_tag(clean_feed_url, "regex_whitelist_author", regex_whitelist_author) # pyright: ignore[reportArgumentType][call-overload]
commit_state_change(reader, f"Update whitelist for {clean_feed_url}")
return RedirectResponse(url=f"/feed?feed_url={urllib.parse.quote(clean_feed_url)}", status_code=303)
@ -367,6 +389,7 @@ async def post_set_blacklist(
reader.set_tag(clean_feed_url, "regex_blacklist_summary", regex_blacklist_summary) # pyright: ignore[reportArgumentType][call-overload]
reader.set_tag(clean_feed_url, "regex_blacklist_content", regex_blacklist_content) # pyright: ignore[reportArgumentType][call-overload]
reader.set_tag(clean_feed_url, "regex_blacklist_author", regex_blacklist_author) # pyright: ignore[reportArgumentType][call-overload]
commit_state_change(reader, f"Update blacklist for {clean_feed_url}")
return RedirectResponse(url=f"/feed?feed_url={urllib.parse.quote(clean_feed_url)}", status_code=303)
@ -433,6 +456,7 @@ async def post_set_custom(
reader.set_tag(feed_url, "custom_message", default_custom_message)
clean_feed_url: str = feed_url.strip()
commit_state_change(reader, f"Update custom message for {clean_feed_url}")
return RedirectResponse(url=f"/feed?feed_url={urllib.parse.quote(clean_feed_url)}", status_code=303)
@ -552,6 +576,7 @@ async def post_embed(
# Save the data.
save_embed(reader, feed, custom_embed)
commit_state_change(reader, f"Update embed settings for {clean_feed_url}")
return RedirectResponse(url=f"/feed?feed_url={urllib.parse.quote(clean_feed_url)}", status_code=303)
@ -567,6 +592,7 @@ async def post_use_embed(feed_url: Annotated[str, Form()]) -> RedirectResponse:
"""
clean_feed_url: str = feed_url.strip()
reader.set_tag(clean_feed_url, "should_send_embed", True) # pyright: ignore[reportArgumentType]
commit_state_change(reader, f"Enable embed mode for {clean_feed_url}")
return RedirectResponse(url=f"/feed?feed_url={urllib.parse.quote(clean_feed_url)}", status_code=303)
@ -582,6 +608,7 @@ async def post_use_text(feed_url: Annotated[str, Form()]) -> RedirectResponse:
"""
clean_feed_url: str = feed_url.strip()
reader.set_tag(clean_feed_url, "should_send_embed", False) # pyright: ignore[reportArgumentType]
commit_state_change(reader, f"Disable embed mode for {clean_feed_url}")
return RedirectResponse(url=f"/feed?feed_url={urllib.parse.quote(clean_feed_url)}", status_code=303)
@ -611,11 +638,11 @@ async def get_feed(feed_url: str, request: Request, starting_after: str = ""):
request: The request object.
starting_after: The entry to start after. Used for pagination.
Raises:
HTTPException: If the feed is not found.
Returns:
HTMLResponse: The feed page.
Raises:
HTTPException: If the feed is not found.
"""
entries_per_page: int = 20
@ -845,23 +872,25 @@ async def get_webhooks(request: Request):
@app.get("/", response_class=HTMLResponse)
def get_index(request: Request):
def get_index(request: Request, message: str = ""):
"""This is the root of the website.
Args:
request: The request object.
message: Optional message to display to the user.
Returns:
HTMLResponse: The index page.
"""
return templates.TemplateResponse(request=request, name="index.html", context=make_context_index(request))
return templates.TemplateResponse(request=request, name="index.html", context=make_context_index(request, message))
def make_context_index(request: Request):
def make_context_index(request: Request, message: str = ""):
"""Create the needed context for the index page.
Args:
request: The request object.
message: Optional message to display to the user.
Returns:
dict: The context for the index page.
@ -894,6 +923,7 @@ def make_context_index(request: Request):
"webhooks": hooks,
"broken_feeds": broken_feeds,
"feeds_without_attached_webhook": feeds_without_attached_webhook,
"messages": message or None,
}
@ -904,17 +934,20 @@ async def remove_feed(feed_url: Annotated[str, Form()]):
Args:
feed_url: The feed to add.
Raises:
HTTPException: Feed not found
Returns:
RedirectResponse: Redirect to the index page.
Raises:
HTTPException: Feed not found
"""
try:
reader.delete_feed(urllib.parse.unquote(feed_url))
except FeedNotFoundError as e:
raise HTTPException(status_code=404, detail="Feed not found") from e
commit_state_change(reader, f"Remove feed {urllib.parse.unquote(feed_url)}")
return RedirectResponse(url="/", status_code=303)
@ -926,11 +959,12 @@ async def update_feed(request: Request, feed_url: str):
request: The request object.
feed_url: The feed URL to update.
Raises:
HTTPException: If the feed is not found.
Returns:
RedirectResponse: Redirect to the feed page.
Raises:
HTTPException: If the feed is not found.
"""
try:
reader.update_feed(urllib.parse.unquote(feed_url))
@ -941,6 +975,33 @@ async def update_feed(request: Request, feed_url: str):
return RedirectResponse(url="/feed?feed_url=" + urllib.parse.quote(feed_url), status_code=303)
@app.post("/backup")
async def manual_backup(request: Request) -> RedirectResponse:
"""Manually trigger a git backup of the current state.
Args:
request: The request object.
Returns:
RedirectResponse: Redirect to the index page with a success or error message.
"""
backup_path = get_backup_path()
if backup_path is None:
message = "Git backup is not configured. Set GIT_BACKUP_PATH environment variable to enable backups."
logger.warning("Manual git backup attempted but GIT_BACKUP_PATH is not configured")
return RedirectResponse(url=f"/?message={urllib.parse.quote(message)}", status_code=303)
try:
commit_state_change(reader, "Manual backup triggered from web UI")
message = "Successfully created git backup!"
logger.info("Manual git backup completed successfully")
except Exception as e:
message = f"Failed to create git backup: {e}"
logger.exception("Manual git backup failed")
return RedirectResponse(url=f"/?message={urllib.parse.quote(message)}", status_code=303)
@app.get("/search", response_class=HTMLResponse)
async def search(request: Request, query: str):
"""Get entries matching a full-text search query.
@ -988,11 +1049,12 @@ def modify_webhook(old_hook: Annotated[str, Form()], new_hook: Annotated[str, Fo
old_hook: The webhook to modify.
new_hook: The new webhook.
Returns:
RedirectResponse: Redirect to the webhook page.
Raises:
HTTPException: Webhook could not be modified.
Returns:
RedirectResponse: Redirect to the webhook page.
"""
# Get current webhooks from the database if they exist otherwise use an empty list.
webhooks = list(reader.get_tag((), "webhooks", []))
@ -1042,11 +1104,11 @@ def extract_youtube_video_id(url: str) -> str | None:
# Handle standard YouTube URLs (youtube.com/watch?v=VIDEO_ID)
if "youtube.com/watch" in url and "v=" in url:
return url.split("v=")[1].split("&")[0]
return url.split("v=")[1].split("&", maxsplit=1)[0]
# Handle shortened YouTube URLs (youtu.be/VIDEO_ID)
if "youtu.be/" in url:
return url.split("youtu.be/")[1].split("?")[0]
return url.split("youtu.be/")[1].split("?", maxsplit=1)[0]
return None