Merge branch 'master' into qa

* master:
  avoid "Uncaught TypeError: Cannot read property 'querySelectorAll' of undefined" from outlinks script
  little readme fix
  for vagrant, static ansible inventory file, add brozzler-webconsole
  add info to display of jobless sites in brozzler-webconsole; fix creation of "least_hops" index on the rethinkdb table "pages"
  add arguments --webconsole-address --webconsole-port --pywb-address and change default ports
  list jobless sites on brozzler-webconsole front page
  run brozzler-webconsole inside brozzler-easy
  add section about brozzler-easy to the readme
  add --help to brozzler-webconsole

README.rst

@@ -1,4 +1,4 @@
-.. |logo| image:: https://cdn.rawgit.com/nlevitt/brozzler/d1158ab2242815b28fe7bb066042b5b5982e4627/webconsole/static/brozzler.svg
+.. |logo| image:: https://cdn.rawgit.com/internetarchive/brozzler/1.1b5/brozzler/webconsole/static/brozzler.svg
    :width: 7%
 
 brozzler |logo|
@@ -6,37 +6,76 @@ brozzler |logo|
 
 "browser" \| "crawler" = "brozzler"
 
-Brozzler is a distributed web crawler (爬虫) that uses a real browser
-(chrome or chromium) to fetch pages and embedded urls and to extract
-links. It also uses `youtube-dl <https://github.com/rg3/youtube-dl>`__
-to enhance media capture capabilities.
-
-It is forked from https://github.com/internetarchive/umbra.
+Brozzler is a distributed web crawler (爬虫) that uses a real browser (chrome
+or chromium) to fetch pages and embedded urls and to extract links. It also
+uses `youtube-dl <https://github.com/rg3/youtube-dl>`_ to enhance media
+capture capabilities.
 
 Brozzler is designed to work in conjunction with
-`warcprox <https://github.com/internetarchive/warcprox>`__ for web
+`warcprox <https://github.com/internetarchive/warcprox>`_ for web
 archiving.
 
-Installation
+Requirements
 ------------
 
-Brozzler requires python 3.4 or later.
+- Python 3.4 or later
+- RethinkDB deployment
+- Chromium or Google Chrome browser
+
+Worth noting is that the browser requires a graphical environment to run. You
+already have this on your laptop, but on a server it will probably require
+deploying some additional infrastructure (typically X11). The vagrant
+configuration in the brozzler repository (still a work in progress) has an
+example setup.
+
+Getting Started
+---------------
+
+The easiest way to get started with brozzler for web archiving is with
+``brozzler-easy``. Brozzler-easy runs brozzler-worker, warcprox,
+`pywb <https://github.com/ikreymer/pywb>`_, and brozzler-webconsole, configured
+to work with each other, in a single process.
+
+Mac instructions:
 
 ::
 
-    # set up virtualenv if desired
-    pip install brozzler
+    # install and start rethinkdb
+    brew install rethinkdb
+    rethinkdb &>>rethinkdb.log &
 
-Brozzler also requires a rethinkdb deployment.
+    # install brozzler with special dependencies pywb and warcprox
+    pip install brozzler[easy]  # in a virtualenv if desired
 
-Usage
------
+    # queue a site to crawl
+    brozzler-new-site http://example.com/
+
+    # or a job
+    brozzler-new-job job1.yml
+
+    # start brozzler-easy
+    brozzler-easy
+
+At this point brozzler-easy will start brozzling your site. Results will be
+immediately available for playback in pywb at http://localhost:8880/brozzler/.
+
+*Brozzler-easy demonstrates the full brozzler archival crawling workflow, but
+does not take advantage of brozzler's distributed nature.*
+
+Installation and Usage
+----------------------
+
+To install brozzler only:
+
+::
+
+    pip install brozzler  # in a virtualenv if desired
 
 Launch one or more workers:
 
 ::
 
-    brozzler-worker -e chromium
+    brozzler-worker
 
 Submit jobs:
 
@@ -44,6 +83,13 @@ Submit jobs:
 
     brozzler-new-job myjob.yaml
 
+Submit sites not tied to a job:
+
+::
+
+    brozzler-new-site --proxy=localhost:8000 --enable-warcprox-features \
+        --time-limit=600 http://example.com/
+
 Job Configuration
 -----------------
 
@@ -70,14 +116,6 @@ must be specified, everything else is optional.
         scope:
           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
 --------------------
 
@@ -95,19 +133,7 @@ To start the app, run
 
     brozzler-webconsole
 
-
-XXX configuration stuff
-
-Fonts (for decent screenshots)
-------------------------------
-
-On ubuntu 14.04 trusty I installed these packages:
-
-xfonts-base ttf-mscorefonts-installer fonts-arphic-bkai00mp
-fonts-arphic-bsmi00lp fonts-arphic-gbsn00lp fonts-arphic-gkai00mp
-fonts-arphic-ukai fonts-farsiweb fonts-nafees fonts-sil-abyssinica
-fonts-sil-ezra fonts-sil-padauk fonts-unfonts-extra fonts-unfonts-core
-ttf-indic-fonts fonts-thai-tlwg fonts-lklug-sinhala
+See ``brozzler-webconsole --help`` for configuration options.
 
 License
 -------

brozzler/browser.py

@@ -304,11 +304,13 @@ class Browser:
 var __brzl_framesDone = new Set();
 var __brzl_compileOutlinks = function(frame) {
     __brzl_framesDone.add(frame);
-    var outlinks = Array.prototype.slice.call(
-            frame.document.querySelectorAll('a[href]'));
-    for (var i = 0; i < frame.frames.length; i++) {
-        if (frame.frames[i] && !__brzl_framesDone.has(frame.frames[i])) {
-            outlinks = outlinks.concat(__brzl_compileOutlinks(frame.frames[i]));
+    if (frame && frame.document) {
+        var outlinks = Array.prototype.slice.call(
+                frame.document.querySelectorAll('a[href]'));
+        for (var i = 0; i < frame.frames.length; i++) {
+            if (frame.frames[i] && !__brzl_framesDone.has(frame.frames[i])) {
+                outlinks = outlinks.concat(__brzl_compileOutlinks(frame.frames[i]));
+            }
         }
     }
     return outlinks;

brozzler/easy.py

@@ -1,7 +1,7 @@
 #!/usr/bin/env python
 '''
-brozzler-easy - brozzler-worker, warcprox, and pywb all working together in a
-single process
+brozzler-easy - brozzler-worker, warcprox, pywb, and brozzler-webconsole all
+working together in a single process
 
 Copyright (C) 2016 Internet Archive
 
@@ -27,7 +27,7 @@ try:
     import brozzler.pywb
     import wsgiref.simple_server
     import wsgiref.handlers
-    import six.moves.socketserver
+    import brozzler.webconsole
 except ImportError as e:
     logging.critical(
             '%s: %s\n\nYou might need to run "pip install '
@@ -44,16 +44,17 @@ import threading
 import time
 import rethinkstuff
 import traceback
+import socketserver
 
 def _build_arg_parser(prog=os.path.basename(sys.argv[0])):
     arg_parser = argparse.ArgumentParser(
             prog=prog, formatter_class=argparse.ArgumentDefaultsHelpFormatter,
             description=(
                 'brozzler-easy - easy deployment of brozzler, with '
-                'brozzler-worker, warcprox, and pywb all running in a single '
-                'process'))
+                'brozzler-worker, warcprox, pywb, and brozzler-webconsole all '
+                'running in a single process'))
 
-    # === common args ===
+    # common args
     arg_parser.add_argument(
             '--rethinkdb-servers', dest='rethinkdb_servers',
             default='localhost', help=(
@@ -66,7 +67,7 @@ def _build_arg_parser(prog=os.path.basename(sys.argv[0])):
             '-d', '--warcs-dir', dest='warcs_dir', default='./warcs',
             help='where to write warcs')
 
-    # === warcprox args ===
+    # warcprox args
     arg_parser.add_argument(
             '-c', '--cacert', dest='cacert',
             default='./%s-warcprox-ca.pem' % socket.gethostname(),
@@ -83,24 +84,42 @@ def _build_arg_parser(prog=os.path.basename(sys.argv[0])):
                 'host:port of tor socks proxy, used only to connect to '
                 '.onion sites'))
 
-    # === brozzler-worker args ===
+    # brozzler-worker args
     arg_parser.add_argument(
             '-e', '--chrome-exe', dest='chrome_exe',
             default=brozzler.cli.suggest_default_chome_exe(),
             help='executable to use to invoke chrome')
     arg_parser.add_argument(
-            '-n', '--max-browsers', dest='max_browsers', default='1',
-            help='max number of chrome instances simultaneously browsing pages')
+            '-n', '--max-browsers', dest='max_browsers',
+            type=int, default=1, help=(
+                'max number of chrome instances simultaneously '
+                'browsing pages'))
 
-    # === pywb args ===
+    # pywb args
     arg_parser.add_argument(
-            '--pywb-port', dest='pywb_port', type=int, default=8091,
-            help='pywb wayback port')
+            '--pywb-address', dest='pywb_address',
+            default='0.0.0.0',
+            help='pywb wayback address to listen on')
+    arg_parser.add_argument(
+            '--pywb-port', dest='pywb_port', type=int,
+            default=8880, help='pywb wayback port')
 
-    # === common at the bottom args ===
+    # webconsole args
     arg_parser.add_argument(
-            '-v', '--verbose', dest='verbose', action='store_true')
-    arg_parser.add_argument('-q', '--quiet', dest='quiet', action='store_true')
+            '--webconsole-address', dest='webconsole_address',
+            default='localhost',
+            help='brozzler web console address to listen on')
+    arg_parser.add_argument(
+            '--webconsole-port', dest='webconsole_port',
+            type=int, default=8881, help='brozzler web console port')
+
+    # common at the bottom args
+    arg_parser.add_argument(
+            '-v', '--verbose', dest='verbose', action='store_true',
+            help='verbose logging')
+    arg_parser.add_argument(
+            '-q', '--quiet', dest='quiet', action='store_true',
+            help='quiet logging (warnings and errors only)')
     # arg_parser.add_argument(
     #         '-s', '--silent', dest='log_level', action='store_const',
     #         default=logging.INFO, const=logging.CRITICAL)
@@ -110,6 +129,10 @@ def _build_arg_parser(prog=os.path.basename(sys.argv[0])):
 
     return arg_parser
 
+class ThreadingWSGIServer(
+        socketserver.ThreadingMixIn, wsgiref.simple_server.WSGIServer):
+    pass
+
 class BrozzlerEasyController:
     logger = logging.getLogger(__module__ + "." + __qualname__)
 
@@ -120,6 +143,12 @@ class BrozzlerEasyController:
                 self._warcprox_args(args))
         self.brozzler_worker = self._init_brozzler_worker(args)
         self.pywb_httpd = self._init_pywb(args)
+        self.webconsole_httpd = self._init_brozzler_webconsole(args)
+
+    def _init_brozzler_webconsole(self, args):
+        return wsgiref.simple_server.make_server(
+                args.webconsole_address, args.webconsole_port,
+                brozzler.webconsole.app, ThreadingWSGIServer)
 
     def _init_brozzler_worker(self, args):
         r = rethinkstuff.Rethinker(
@@ -128,7 +157,7 @@ class BrozzlerEasyController:
         service_registry = rethinkstuff.ServiceRegistry(r)
         worker = brozzler.worker.BrozzlerWorker(
                 frontier, service_registry,
-                max_browsers=int(args.max_browsers),
+                max_browsers=args.max_browsers,
                 chrome_exe=args.chrome_exe,
                 proxy='%s:%s' % self.warcprox_controller.proxy.server_address,
                 enable_warcprox_features=True)
@@ -166,12 +195,9 @@ class BrozzlerEasyController:
 
         # disable is_hop_by_hop restrictions
         wsgiref.handlers.is_hop_by_hop = lambda x: False
-        class ThreadingWSGIServer(
-                six.moves.socketserver.ThreadingMixIn,
-                wsgiref.simple_server.WSGIServer):
-            pass
         return wsgiref.simple_server.make_server(
-                '', args.pywb_port, wsgi_app, ThreadingWSGIServer)
+                args.pywb_address, args.pywb_port, wsgi_app,
+                ThreadingWSGIServer)
 
     def start(self):
         self.logger.info('starting warcprox')
@@ -185,7 +211,15 @@ class BrozzlerEasyController:
                 'starting pywb at %s:%s', *self.pywb_httpd.server_address)
         threading.Thread(target=self.pywb_httpd.serve_forever).start()
 
+        self.logger.info(
+                'starting brozzler-webconsole at %s:%s',
+                *self.webconsole_httpd.server_address)
+        threading.Thread(target=self.webconsole_httpd.serve_forever).start()
+
     def shutdown(self):
+        self.logger.info('shutting down brozzler-webconsole')
+        self.webconsole_httpd.shutdown()
+
         self.logger.info('shutting down brozzler-worker')
         self.brozzler_worker.shutdown_now()
         # brozzler-worker is fully shut down at this point

brozzler/frontier.py

@@ -69,7 +69,7 @@ class RethinkDbFrontier:
             self.r.table("pages").index_create(
                     "least_hops", [
                         self.r.row["site_id"], self.r.row["brozzle_count"],
-                        self.r.row["hops_from_seed"]])
+                        self.r.row["hops_from_seed"]]).run()
         if not "jobs" in tables:
             self.logger.info(
                     "creating rethinkdb table 'jobs' in database %s",

brozzler/webconsole/__init__.py

@@ -27,7 +27,6 @@ except ImportError as e:
             'brozzler[webconsole]".\nSee README.rst for more information.',
             type(e).__name__, e)
     sys.exit(1)
-
 import rethinkstuff
 import json
 import os
@@ -56,11 +55,16 @@ SETTINGS = {
         'RETHINKDB_SERVERS', 'localhost').split(','),
     'RETHINKDB_DB': os.environ.get('RETHINKDB_DB', 'brozzler'),
     'WAYBACK_BASEURL': os.environ.get(
-        'WAYBACK_BASEURL', 'http://wbgrp-svc107.us.archive.org:8091'),
+        'WAYBACK_BASEURL', 'http://localhost:8091/brozzler'),
 }
 r = rethinkstuff.Rethinker(
         SETTINGS['RETHINKDB_SERVERS'], db=SETTINGS['RETHINKDB_DB'])
-service_registry = rethinkstuff.ServiceRegistry(r)
+_svc_reg = None
+def service_registry():
+    global _svc_reg
+    if not _svc_reg:
+        _svc_reg = rethinkstuff.ServiceRegistry(r)
+    return _svc_reg
 
 @app.route("/api/sites/<site_id>/queued_count")
 @app.route("/api/site/<site_id>/queued_count")
@@ -149,6 +153,16 @@ def sites(job_id):
             s["cookie_db"] = base64.b64encode(s["cookie_db"]).decode("ascii")
     return flask.jsonify(sites=sites_)
 
+@app.route("/api/jobless-sites")
+def jobless_sites():
+    # XXX inefficient (unindexed) query
+    sites_ = list(r.table("sites").filter(~r.row.has_fields("job_id")).run())
+    # TypeError: <binary, 7168 bytes, '53 51 4c 69 74 65...'> is not JSON serializable
+    for s in sites_:
+        if "cookie_db" in s:
+            s["cookie_db"] = base64.b64encode(s["cookie_db"]).decode("ascii")
+    return flask.jsonify(sites=sites_)
+
 @app.route("/api/jobs/<int:job_id>")
 @app.route("/api/job/<int:job_id>")
 def job(job_id):
@@ -165,12 +179,12 @@ def job_yaml(job_id):
 
 @app.route("/api/workers")
 def workers():
-    workers_ = service_registry.available_services("brozzler-worker")
+    workers_ = service_registry().available_services("brozzler-worker")
     return flask.jsonify(workers=list(workers_))
 
 @app.route("/api/services")
 def services():
-    services_ = service_registry.available_services()
+    services_ = service_registry().available_services()
     return flask.jsonify(services=list(services_))
 
 @app.route("/api/jobs")
@@ -221,7 +235,26 @@ except ImportError:
         logging.info('running brozzler-webconsole using simple flask app.run')
         app.run()
 
-if __name__ == "__main__":
-    # arguments?
+def main():
+    import argparse
+    arg_parser = argparse.ArgumentParser(
+            prog=os.path.basename(sys.argv[0]),
+            formatter_class=argparse.RawDescriptionHelpFormatter,
+            description=(
+                'brozzler-webconsole - web application for viewing brozzler '
+                'crawl status'),
+            epilog=(
+                'brozzler-webconsole has no command line options, but can be '
+                'configured using the following environment variables:\n\n'
+                '  RETHINKDB_SERVERS   rethinkdb servers, e.g. db0.foo.org,'
+                'db0.foo.org:38015,db1.foo.org (default: localhost)\n'
+                '  RETHINKDB_DB        rethinkdb database name (default: '
+                'brozzler)\n'
+                '  WAYBACK_BASEURL     base url for constructing wayback '
+                'links (default http://localhost:8091/brozzler)'))
+    args = arg_parser.parse_args(args=sys.argv[1:])
     run()
 
+if __name__ == "__main__":
+    main()
+

brozzler/webconsole/static/js/app.js

@@ -79,6 +79,9 @@ brozzlerControllers.controller("HomeController", ["$scope", "$http",
         $http.get("/api/services").success(function(data) {
             $scope.services = data.services;
         });
+        $http.get("/api/jobless-sites").success(function(data) {
+            $scope.joblessSites = data.sites;
+        });
    }]);
 
 brozzlerControllers.controller("WorkersListController", ["$scope", "$http",

brozzler/webconsole/static/partials/home.html

@@ -41,7 +41,6 @@
     </div>
 
     <h2>Jobs</h2>
-
     <div class="row">
         <div class="col-sm-12">
             <table class="table table-striped">
@@ -66,4 +65,29 @@
             </table>
         </div>
     </div>
+
+    <h2>Jobless Sites</h2>
+    <div class="row">
+        <div class="col-sm-12">
+            <table class="table table-striped">
+                <thead>
+                    <tr>
+                        <th>id</th>
+                        <th>status</th>
+                        <th>started</th>
+                        <th>seed url</th>
+                    </tr>
+                </thead>
+                <tbody>
+                  <tr ng-repeat="site in joblessSites">
+                      <td><a href="/sites/{{site.id}}">{{site.id}}</a></td>
+                      <td>{{site.status}}</td>
+                      <td>{{site.start_time}}</td>
+                      <td>{{site.seed}}</td>
+                  </tr>
+                </tbody>
+            </table>
+        </div>
+    </div>
+
 </div>

setup.py

@@ -32,7 +32,7 @@ def find_package_data(package):
 
 setuptools.setup(
         name='brozzler',
-        version='1.1b6.dev69',
+        version='1.1b6.dev78',
         description='Distributed web crawling with browsers',
         url='https://github.com/internetarchive/brozzler',
         author='Noah Levitt',
@@ -51,7 +51,7 @@ setuptools.setup(
                 'brozzler-new-site=brozzler.cli:brozzler_new_site',
                 'brozzler-worker=brozzler.cli:brozzler_worker',
                 'brozzler-ensure-tables=brozzler.cli:brozzler_ensure_tables',
-                'brozzler-webconsole=brozzler.webconsole:run',
+                'brozzler-webconsole=brozzler.webconsole:main',
                 'brozzler-easy=brozzler.easy:main',
             ],
         },
@@ -69,7 +69,7 @@ setuptools.setup(
         ],
         extras_require={
             'webconsole': ['flask>=0.11', 'gunicorn'],
-            'easy': ['warcprox>=2.0b1', 'pywb'],
+            'easy': ['warcprox>=2.0b1', 'pywb', 'flask>=0.11', 'gunicorn'],
         },
         zip_safe=False,
         classifiers=[

vagrant/Vagrantfile

@@ -1,16 +1,13 @@
 Vagrant.configure(2) do |config|
   config.vm.box = "ubuntu/trusty64"
-  config.vm.hostname = "brozzler-easy"
+  config.vm.define "10.9.9.9"
+  config.vm.hostname = "brzl"
+  config.vm.network :private_network, ip: "10.9.9.9"
 
   config.vm.synced_folder "..", "/brozzler"
 
   config.vm.provision "ansible" do |ansible|
+    ansible.inventory_path = "ansible/hosts"
     ansible.playbook = "ansible/playbook.yml"
-    ansible.groups = {
-      "rethinkdb" => ["default"],
-      "warcprox" => ["default"],
-      "brozzler-worker" => ["default"],
-      # "brozzler-webconsole" => ["default"],
-    }
   end
 end

vagrant/ansible/hosts

@@ -0,0 +1,16 @@
+ansible_ssh_private_key_file=.vagrant/machines/10.9.9.9/virtualbox/private_key
+
+[rethinkdb]
+10.9.9.9
+
+[warcprox]
+10.9.9.9
+
+[brozzler-worker]
+10.9.9.9
+
+[brozzler-webconsole]
+10.9.9.9
+
+[pywb]
+10.9.9.9

vagrant/ansible/playbook.yml

@@ -2,27 +2,27 @@
 - name: apply common configuration to all nodes
   hosts: all
   roles:
-    - common
+  - common
 
 - name: deploy rethinkdb
   hosts: rethinkdb
   roles:
-    - rethinkdb
+  - rethinkdb
 
 - name: deploy warcprox
   hosts: warcprox
   roles:
-    - warcprox
+  - warcprox
 
 - name: deploy brozzler-worker
   hosts: brozzler-worker
   roles:
-    - brozzler-worker
+  - brozzler-worker
 
-# - name: deploy brozzler-webconsole
-#   hosts: brozzler-webconsole
-#   roles:
-#     - brozzler-webconsole
+- name: deploy brozzler-webconsole
+  hosts: brozzler-webconsole
+  roles:
+  - brozzler-webconsole
 
 # - name: deploy pywb
 #   hosts: pywb

vagrant/ansible/roles/brozzler-webconsole/handlers/main.yml

@@ -0,0 +1,4 @@
+---
+- name: restart brozzler-webconsole
+  service: name=brozzler-webconsole state=restarted
+  become: true

vagrant/ansible/roles/brozzler-webconsole/tasks/main.yml

@@ -1,19 +1,15 @@
 ---
-- name: git clone https://github.com/internetarchive/brozzler.git
-  git: repo=https://github.com/internetarchive/brozzler.git
-       dest=/home/vagrant/brozzler
-- name: pip install -r requirements.txt in virtualenv
-  pip: requirements=/home/vagrant/brozzler/webconsole/requirements.txt
+- name: install brozzler[webconsole] in virtualenv
+  become: true
+  pip: name='-e /brozzler[webconsole]'
        virtualenv=/home/vagrant/brozzler-webconsole-ve34
        virtualenv_python=python3.4
        extra_args='--no-input --upgrade --pre'
   notify:
-    - restart brozzler-webconsole
+  - restart brozzler-webconsole
 - name: install upstart config /etc/init/brozzler-webconsole.conf
   become: true
   template: src=templates/brozzler-webconsole.conf.j2
             dest=/etc/init/brozzler-webconsole.conf
   notify:
-    - restart brozzler-webconsole
-
-
+  - restart brozzler-webconsole

vagrant/ansible/roles/brozzler-webconsole/templates/brozzler-webconsole.conf.j2

@@ -3,19 +3,16 @@ description "brozzler-webconsole"
 start on runlevel [2345]
 stop on runlevel [!2345]
 
-env PYTHONPATH=/home/vagrant/brozzler-webconsole-ve34/lib/python3.4/site-packages:/home/vagrant/brozzler/webconsole
+env PYTHONPATH=/home/vagrant/brozzler-webconsole-ve34/lib/python3.4/site-packages
 env PATH=/home/vagrant/brozzler-webconsole-ve34/bin:/usr/bin:/bin
 env LC_ALL=C.UTF-8
 
-env WAYBACK_BASEURL={{base_wayback_url}}/all
-# env RETHINKDB_SERVERS={{groups['rethinkdb'] | join(',')}}
-env RETHINKDB_SERVERS=localhost
-env RETHINKDB_DB={{rethinkdb_db}}
+env WAYBACK_BASEURL=http://{{groups['pywb'][0]}}:8880/brozzler
+env RETHINKDB_SERVERS={{groups['rethinkdb'] | join(',')}}
+env RETHINKDB_DB=brozzler
 
 setuid vagrant
 
 # console log
 
-exec gunicorn --bind=0.0.0.0:8081 brozzler-webconsole:app >&/vagrant/logs/brozzler-webconsole.log
-
-
+exec gunicorn --bind=0.0.0.0:8881 brozzler.webconsole:app >>/vagrant/logs/brozzler-webconsole.log 2>&1

vagrant/ansible/roles/brozzler-worker/templates/brozzler-worker.conf.j2

@@ -19,7 +19,5 @@ stop on stopping Xvnc
 kill timeout 60
 
 exec nice brozzler-worker \
-     --rethinkdb-servers=localhost \
-     --max-browsers=4 >>/vagrant/logs/brozzler-worker.log 2>&1
-     # --rethinkdb-servers={{groups['rethinkdb'] | join(',')}} \
-
+    --rethinkdb-servers={{groups['rethinkdb'] | join(',')}} \
+    --max-browsers=4 >>/vagrant/logs/brozzler-worker.log 2>&1

vagrant/ansible/roles/brozzler-worker/templates/vnc-websock.conf.j2

@@ -10,5 +10,6 @@ console log
 env PYTHONPATH=/home/vagrant/websockify-ve34/lib/python3.4/site-packages
 env PATH=/home/vagrant/websockify-ve34/bin:/usr/bin:/bin
 
+# port 8901 is hard-coded in brozzler/webconsole/static/partials/workers.html
 exec nice websockify 0.0.0.0:8901 localhost:5901
 

vagrant/ansible/roles/rethinkdb/templates/rethinkdb-brozzler-easy.conf.j2

@@ -1,5 +1,5 @@
 runuser=vagrant
-# bind=0.0.0.0
+bind=0.0.0.0
 # directory=/var/lib/rethinkdb
 # log-file=/var/log/rethinkdb.log
 log-file=/vagrant/logs/rethinkdb.log  # synced dir