summaryrefslogtreecommitdiff
path: root/data_collector.py
diff options
context:
space:
mode:
authorA Farzat <a@farzat.xyz>2025-10-05 07:24:22 +0300
committerA Farzat <a@farzat.xyz>2025-10-05 07:24:22 +0300
commit3b418daf684f01a126a56b58c83120af5914f576 (patch)
tree20b6ea9487cce5a90cff8696085b8c3f7783db75 /data_collector.py
parent66194a36af3d1f6897e8fd0e3b61388cb18f6e1f (diff)
downloadcsca5028-3b418daf684f01a126a56b58c83120af5914f576.tar.gz
csca5028-3b418daf684f01a126a56b58c83120af5914f576.zip
Remove the redundant scheduler class
This allows fetching the database every time, ensuring any updates to the database between fetches as captured.
Diffstat (limited to 'data_collector.py')
-rwxr-xr-xdata_collector.py23
1 files changed, 6 insertions, 17 deletions
diff --git a/data_collector.py b/data_collector.py
index 9da9404..485d8af 100755
--- a/data_collector.py
+++ b/data_collector.py
@@ -1,24 +1,13 @@
#!/usr/bin/env python
from time import sleep
+from datetime import datetime, timedelta, UTC
from components.database import subscriptions
-from components.subscriptions.main import Subscription, default_scheduler
-
-subs_to_fetch = ["fiwzLy-8yKzIbsmZTzxDgw", "Ef0-WZoqYFzLZtx43KPvag",
- "PF-oYb2-xN5FbCXy0167Gg", "hlgI3UHCOnwUGzWzbJ3H5w", ]
-for id in subs_to_fetch:
- sub_dict = subscriptions.find_one({"_id": "yt:channel:"+id})
- if sub_dict:
- sub = Subscription(**sub_dict)
- else:
- sub = Subscription(
- _id="yt:channel:"+id,
- link="http://www.youtube.com/feeds/videos.xml?channel_id=UC"+id,
- time_between_fetches=5,
- )
- sub.insert()
- sub.initialise_job()
+from components.subscriptions.main import Subscription
while True:
- default_scheduler.run_pending()
+ for sub_dict in subscriptions.find():
+ sub = Subscription(**sub_dict)
+ if datetime.now(tz=UTC) - sub.last_fetch > timedelta(seconds=sub.time_between_fetches):
+ sub.fetch()
sleep(60)