diff --git a/job-conf.rst b/job-conf.rst index 08707b68..6a5a51ee 100644 --- a/job-conf.rst +++ b/job-conf.rst @@ -14,7 +14,6 @@ Example id: myjob time_limit: 60 # seconds - proxy: 127.0.0.1:8000 # point at warcprox for archiving ignore_robots: false max_claimed_sites: 2 warcprox_meta: @@ -186,16 +185,6 @@ enforced at the seed level. If a time limit is specified at the top level, it is inherited by each seed as described above, and enforced individually on each seed. -``proxy`` -~~~~~~~~~ -+--------+----------+---------+ -| type | required | default | -+========+==========+=========+ -| string | no | *none* | -+--------+----------+---------+ -HTTP proxy, with the format ``host:port``. Typically configured to point to -warcprox for archival crawling. - ``ignore_robots`` ~~~~~~~~~~~~~~~~~ +---------+----------+-----------+ @@ -226,8 +215,8 @@ to contact the operator if the crawl is causing problems. +============+==========+===========+ | dictionary | no | ``false`` | +------------+----------+-----------+ -Specifies the ``Warcprox-Meta`` header to send with every request, if ``proxy`` -is configured. The value of the ``Warcprox-Meta`` header is a json blob. It is +Specifies the ``Warcprox-Meta`` header to send with every request. +The value of the ``Warcprox-Meta`` header is a json blob. It is used to pass settings and information to warcprox. Warcprox does not forward the header on to the remote site. For further explanation of this field and its uses see diff --git a/vagrant/README.rst b/vagrant/README.rst index 8b54e591..5609f755 100644 --- a/vagrant/README.rst +++ b/vagrant/README.rst @@ -31,16 +31,15 @@ Then you can run brozzler-new-site: :: - (brozzler-ve3)vagrant@brzl:~$ brozzler-new-site --proxy=localhost:8000 http://example.com/ + (brozzler-ve3)vagrant@brzl:~$ brozzler-new-site http://example.com/ -Or brozzler-new-job (make sure to set the proxy to localhost:8000): +Or brozzler-new-job: :: (brozzler-ve3)vagrant@brzl:~$ cat >job1.yml < $f && ' - '/home/vagrant/brozzler-ve3/bin/python ' - '/home/vagrant/brozzler-ve3/bin/brozzler-new-job $f'], + '/opt/brozzler-ve3/bin/python ' + '/opt/brozzler-ve3/bin/brozzler-new-job $f'], stdin=f) if __name__ == '__main__': diff --git a/vagrant/vagrant-brozzler-new-site.py b/vagrant/vagrant-brozzler-new-site.py index b0a0d800..1c7193ed 100755 --- a/vagrant/vagrant-brozzler-new-site.py +++ b/vagrant/vagrant-brozzler-new-site.py @@ -71,7 +71,7 @@ def main(argv=[]): options.append('--verbose') # cd to path with Vagrantfile so "vagrant ssh" knows what to do - os.chdir(os.path.dirname(__file__)) + os.chdir(os.path.realpath(os.path.dirname(__file__))) cmd = ( '/opt/brozzler-ve3/bin/python /opt/brozzler-ve3/bin/brozzler-new-site '