mirror of
https://github.com/internetarchive/brozzler.git
synced 2025-06-19 12:24:20 -04:00
fix bug preventing brozzler-new-site from working, add note about brozzler-new-site in readme
This commit is contained in:
parent
479713e25b
commit
7431ae0eb1
3 changed files with 11 additions and 1 deletions
|
@ -70,6 +70,14 @@ must be specified, everything else is optional.
|
||||||
scope:
|
scope:
|
||||||
surt: http://(org,example,
|
surt: http://(org,example,
|
||||||
|
|
||||||
|
Submit a Site to Crawl Without Configuring a Job
|
||||||
|
------------------------------------------------
|
||||||
|
|
||||||
|
::
|
||||||
|
|
||||||
|
brozzler-new-site --proxy=localhost:8000 --enable-warcprox-features \
|
||||||
|
--time-limit=600 http://example.com/
|
||||||
|
|
||||||
Brozzler Web Console
|
Brozzler Web Console
|
||||||
--------------------
|
--------------------
|
||||||
|
|
||||||
|
|
|
@ -233,6 +233,8 @@ class RethinkDbFrontier:
|
||||||
yield brozzler.Job(**result)
|
yield brozzler.Job(**result)
|
||||||
|
|
||||||
def job(self, id):
|
def job(self, id):
|
||||||
|
if id is None:
|
||||||
|
return None
|
||||||
result = self.r.table("jobs").get(id).run()
|
result = self.r.table("jobs").get(id).run()
|
||||||
if result:
|
if result:
|
||||||
return brozzler.Job(**result)
|
return brozzler.Job(**result)
|
||||||
|
|
2
setup.py
2
setup.py
|
@ -21,7 +21,7 @@ import setuptools
|
||||||
|
|
||||||
setuptools.setup(
|
setuptools.setup(
|
||||||
name='brozzler',
|
name='brozzler',
|
||||||
version='1.1.dev32',
|
version='1.1.dev33',
|
||||||
description='Distributed web crawling with browsers',
|
description='Distributed web crawling with browsers',
|
||||||
url='https://github.com/internetarchive/brozzler',
|
url='https://github.com/internetarchive/brozzler',
|
||||||
author='Noah Levitt',
|
author='Noah Levitt',
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue