mirror of
https://github.com/internetarchive/brozzler.git
synced 2025-05-15 04:52:22 -04:00
fix case where rethinkdb page already has claimed=True
This commit is contained in:
parent
ffcf26b6c9
commit
2e687b65fb
2 changed files with 6 additions and 6 deletions
|
@ -197,12 +197,12 @@ class RethinkDbFrontier:
|
|||
1).update({
|
||||
"claimed":True,
|
||||
"last_claimed_by":worker_id},
|
||||
return_changes=True).run()
|
||||
self._vet_result(result, replaced=[0,1])
|
||||
if result["replaced"] == 1:
|
||||
return brozzler.Page(**result["changes"][0]["new_val"])
|
||||
else:
|
||||
return_changes="always").run()
|
||||
self._vet_result(result, unchanged=[0,1], replaced=[0,1])
|
||||
if result["unchanged"] == 0 and result["replaced"] == 0:
|
||||
raise brozzler.NothingToClaim
|
||||
else:
|
||||
return brozzler.Page(**result["changes"][0]["new_val"])
|
||||
|
||||
def has_outstanding_pages(self, site):
|
||||
results_iter = self.r.table("pages").between(
|
||||
|
|
2
setup.py
2
setup.py
|
@ -21,7 +21,7 @@ import setuptools
|
|||
|
||||
setuptools.setup(
|
||||
name='brozzler',
|
||||
version='1.1.dev34',
|
||||
version='1.1.dev35',
|
||||
description='Distributed web crawling with browsers',
|
||||
url='https://github.com/internetarchive/brozzler',
|
||||
author='Noah Levitt',
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue