Merge branch 'master' into adds-hop-path-support

README.rst

@@ -14,7 +14,7 @@ or Chromium) to fetch pages and embedded URLs and to extract links. It employs
 capabilities and `rethinkdb <https://github.com/rethinkdb/rethinkdb>`_ to
 manage crawl state.
 
-Brozzler is designed to work in conjuction with warcprox for web archiving.
+Brozzler is designed to work in conjunction with warcprox for web archiving.
 
 Requirements
 ------------

brozzler/chrome.py

@@ -168,7 +168,7 @@ class Chrome:
                 '--remote-debugging-port=%s' % self.port,
                 '--use-mock-keychain', # mac thing
                 '--user-data-dir=%s' % self._chrome_user_data_dir,
-                '--disable-background-networking',
+                '--disable-background-networking', '--disable-breakpad',
                 '--disable-renderer-backgrounding', '--disable-hang-monitor',
                 '--disable-background-timer-throttling', '--mute-audio',
                 '--disable-web-sockets',
@@ -176,7 +176,8 @@ class Chrome:
                 '--disable-first-run-ui', '--no-first-run',
                 '--homepage=about:blank', '--disable-direct-npapi-requests',
                 '--disable-web-security', '--disable-notifications',
-                '--disable-extensions', '--disable-save-password-bubble']
+                '--disable-extensions', '--disable-save-password-bubble',
+                '--disable-sync']
 
         extra_chrome_args = os.environ.get('BROZZLER_EXTRA_CHROME_ARGS')
         if extra_chrome_args:

brozzler/js-templates/fec_gov.js

@@ -65,7 +65,7 @@ var umbraBehavior = {
 						if (where == 0) {
 							console.log("clicking on " + clickRadioButtonTargets[k]);
 							// do mouse over event on click target
-							// since some urls are requsted only on
+							// since some urls are requested only on
 							// this event - see
 							// https://webarchive.jira.com/browse/AITFIVE-451
 							var mouseOverEvent = document.createEvent('Events');

brozzler/js-templates/psu24.js

@@ -46,7 +46,7 @@ var umbraBehavior = {
 				if (where == 0) {
 					console.log("clicking on " + clickTargets[i].outerHTML);
 					// do mouse over event on click target
-					// since some urls are requsted only on
+					// since some urls are requested only on
 					// this event - see
 					// https://webarchive.jira.com/browse/AITFIVE-451
 					var mouseOverEvent = document.createEvent('Events');

brozzler/js-templates/umbraBehavior.js.j2

@@ -168,7 +168,7 @@ class UmbraBehavior {
     doTarget(target, action) {
         // console.log("doing " + action + target.outerHTML);
         // do mouse over event on target
-        // since some urls are requsted only on
+        // since some urls are requested only on
         // this event - see
         // https://webarchive.jira.com/browse/AITFIVE-451
         var mouseOverEvent = document.createEvent("Events");

setup.py

@@ -2,7 +2,7 @@
 '''
 setup.py - brozzler setup script
 
-Copyright (C) 2014-2021 Internet Archive
+Copyright (C) 2014-2022 Internet Archive
 
 Licensed under the Apache License, Version 2.0 (the "License");
 you may not use this file except in compliance with the License.
@@ -32,7 +32,7 @@ def find_package_data(package):
 
 setuptools.setup(
         name='brozzler',
-        version='1.5.25',
+        version='1.5.26',
         description='Distributed web crawling with browsers',
         url='https://github.com/internetarchive/brozzler',
         author='Noah Levitt',

tests/test_brozzling.py

@@ -75,7 +75,7 @@ def httpd(request):
         def do_POST(self):
             if self.path == '/login-action':
                 self.send_response(200)
-                payload = b'login successfull\n'
+                payload = b'login successful\n'
                 self.send_header('Content-Type', 'text/plain;charset=utf-8')
                 self.send_header('Content-Length', len(payload))
                 self.end_headers()