mirror of
https://github.com/internetarchive/brozzler.git
synced 2025-05-02 06:36:20 -04:00
disable the re-claiming of sites that are marked claimed from more than an hour ago, because sometimes pages legitimately take longer than an hour to brozzle; working on a better solution to this issue
This commit is contained in:
parent
7ae22381ef
commit
6bae53e646
3 changed files with 19 additions and 9 deletions
|
@ -723,14 +723,17 @@ def test_claim_site():
|
|||
with pytest.raises(brozzler.NothingToClaim):
|
||||
claimed_site = frontier.claim_site(worker_id='test_claim_site')
|
||||
|
||||
# site last_claimed more than 1 hour ago can be reclaimed
|
||||
### temporarily changing this behavior
|
||||
### # site last_claimed more than 1 hour ago can be reclaimed
|
||||
site = claimed_site
|
||||
claimed_site = None
|
||||
site.last_claimed = doublethink.utcnow() - datetime.timedelta(minutes=65)
|
||||
site.save()
|
||||
claimed_site = frontier.claim_site(worker_id='test_claim_site')
|
||||
assert claimed_site.id == site.id
|
||||
### claimed_site = frontier.claim_site(worker_id='test_claim_site')
|
||||
### assert claimed_site.id == site.id
|
||||
with pytest.raises(brozzler.NothingToClaim):
|
||||
claimed_site = frontier.claim_site(worker_id='test_claim_site')
|
||||
|
||||
# clean up
|
||||
rr.table('sites').get(claimed_site.id).delete().run()
|
||||
rr.table('sites').get(site.id).delete().run()
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue