Files
telegram-scraper/scraper_jobs.py
T
2026-09-10 11:50:12 +02:00

146 lines
5.7 KiB
Python

import asyncio
import logging
import threading
from pathlib import Path
from typing import Any
from app_state import StateStore
logger = logging.getLogger(__name__)
BASE_DIR = Path(__file__).resolve().parent
def _run_in_new_loop(coro_factory):
"""Run an awaitable on a dedicated thread with its own event loop.
Returns the coroutine's result. This avoids ``asyncio.run()`` raising
``RuntimeError`` when the caller runs on a thread that already has a
running event loop (e.g. job threads, auth-loop threads).
"""
result = {}
error = {}
def runner():
loop = asyncio.new_event_loop()
try:
asyncio.set_event_loop(loop)
result["value"] = loop.run_until_complete(coro_factory())
except BaseException as exc: # noqa: BLE001 - relay any failure
error["value"] = exc
finally:
try:
loop.close()
finally:
asyncio.set_event_loop(None)
thread = threading.Thread(target=runner, daemon=True)
thread.start()
thread.join()
if "value" in error:
raise error["value"]
return result.get("value")
class ScraperJobService:
def __init__(self, state_store: StateStore):
self.state_store = state_store
def run(self, job_type: str, payload: dict[str, Any]) -> None:
if job_type == "set_scrape_media":
# The webui handler already persists the scrape_media setting to
# the per-account (or legacy) store before enqueueing this job.
# Multi-account mode has no single global change to make, so this
# is a passthrough that just records success to keep the
# job-status / SSE flow intact.
value = bool(payload["value"])
logger.info("Media scraping set to %s (already persisted by handler)", value)
return
# Run the async job on a fresh thread/event loop so we never hit
# "asyncio.run() cannot be called from a running event loop".
_run_in_new_loop(lambda: self._run_async(job_type, payload))
async def _run_async(self, job_type: str, payload: dict[str, Any]) -> None:
# Extract account_id from payload, default to None (legacy)
account_id: str | None = payload.get("account_id")
ScraperClass = self._import_scraper_class()
scraper = ScraperClass(account_id=account_id, base_dir=BASE_DIR)
if account_id:
from app_state import load_account
acc_state = load_account(self.state_store.path.parent, account_id)
# Load per-account state into scraper state
scraper.state = acc_state
initialized = await scraper.initialize_client(interactive=False)
if not initialized:
raise RuntimeError(
"Telegram client is not ready. Check credentials, session, and write access."
)
try:
if job_type == "scrape_channel":
await self._scrape_channels(scraper, [payload["channel_id"]])
elif job_type == "scrape_all":
await self._scrape_channels(
scraper, list(scraper.state.get("channels", {}).keys())
)
elif job_type == "scrape_selected":
await self._scrape_channels(
scraper,
[str(channel_id) for channel_id in payload.get("channels", [])],
)
elif job_type == "export_all":
await scraper.export_data()
elif job_type == "export_channel":
channel_id = payload["channel_id"]
scraper.export_to_csv(channel_id)
scraper.export_to_json(channel_id)
elif job_type == "rescrape_media":
await scraper.rescrape_media(payload["channel_id"])
elif job_type == "fix_missing_media":
await scraper.fix_missing_media(payload["channel_id"])
elif job_type == "refresh_dialogs":
await scraper.list_channels()
else:
raise RuntimeError(f"Unsupported job type: {job_type}")
finally:
scraper.close_db_connections()
if scraper.client:
await scraper.client.disconnect()
async def _scrape_channels(self, scraper, channels: list[str]) -> None:
"""Scrape all channels resiliently: a single channel failure does not
abort the rest. Each channel's offset is persisted even on failure
(see scrape_channel's finally block), so partial progress is retained.
If *every* channel fails, raise so the job is marked failed.
"""
failed: list[str] = []
for channel_id in channels:
offset = int(scraper.state.get("channels", {}).get(channel_id, 0) or 0)
try:
ok = await scraper.scrape_channel(channel_id, offset)
except Exception:
logger.exception("Scrape of channel %s raised", channel_id)
failed.append(channel_id)
continue
if not ok:
logger.warning("Scrape of channel %s reported failure", channel_id)
failed.append(channel_id)
if failed and len(failed) == len(channels):
raise RuntimeError(
"All scrape target(s) failed: " + ", ".join(failed)
)
if failed:
logger.warning(
"Partial scrape failure — %d/%d channel(s) failed: %s",
len(failed),
len(channels),
", ".join(failed),
)
def _import_scraper_class(self):
from telegram_scraper_with_forwarding import OptimizedTelegramScraper
return OptimizedTelegramScraper