mirror of
https://github.com/internetarchive/brozzler.git
synced 2025-04-20 23:56:34 -04:00
fix another oversight
This commit is contained in:
parent
1ee36c38b9
commit
8de3e21103
@ -121,6 +121,7 @@ def new_seed_page(frontier, site):
|
||||
|
||||
def new_site(frontier, site):
|
||||
logging.info("new site %s", site)
|
||||
site.id = site.id or str(uuid.uuid4())
|
||||
# insert the Page into the database before the Site, to avoid situation
|
||||
# where a brozzler worker immediately claims the site, finds no pages
|
||||
# to crawl, and decides the site is finished
|
||||
|
Loading…
x
Reference in New Issue
Block a user